Advertisements
Feeds:
Posts
Comments

Archive for the ‘Artificial intelligence applications for cardiology’ Category


Prediction of Cardiovascular Risk by Machine Learning (ML) Algorithm: Best performing algorithm by predictive capacity had area under the ROC curve (AUC) scores: 1st, quadratic discriminant analysis; 2nd, NaiveBayes and 3rd, neural networks, far exceeding the conventional risk-scaling methods in Clinical Use

Reporter: Aviva Lev-Ari, PhD, RN

Best three machine-learning methods with the best predictive capacity had area under the ROC curve (AUC) scores of

  • 0.7086 (quadratic discriminant analysis),
  • 0.7084 (NaiveBayes) and
  • 0.7042 (neural networks)
  • the conventional risk-scaling methods—which are widely used in clinical practice in Spain—fell in at 11th and 12th places, with AUCs below 0.64.

 

Machine learning to predict cardiovascular risk

First published: 01 July 2019

This article has been accepted for publication and undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as doi:10.1111/ijcp.13389

Abstract

Aims

To analyze the predictive capacity of 15 machine learning methods for estimating cardiovascular risk in a cohort and to compare them with other risk scales.

Methods

We calculated cardiovascular risk by means of 15 machine‐learning methods and using the SCORE and REGICOR scales and in 38,527 patients in the Spanish ESCARVAL RISK cohort, with five‐year follow‐up. We considered patients to be at high risk when the risk of a cardiovascular event was over 5% (according to SCORE and machine learning methods) or over 10% (using REGICOR). The area under the receiver operating curve (AUC) and the C‐index were calculated, as well as the diagnostic accuracy rate, error rate, sensitivity, specificity, positive and negative predictive values, positive likelihood ratio, and number of needed to treat to prevent a harmful outcome.

Results

The method with the greatest predictive capacity was quadratic discriminant analysis, with an AUC of 0.7086, followed by NaiveBayes and neural networks, with AUCs of 0.7084 and 0.7042, respectively. REGICOR and SCORE ranked 11th and 12th, respectively, in predictive capacity, with AUCs of 0.63. Seven machine learning methods showed a 7% higher predictive capacity (AUC) as well as higher sensitivity and specificity than the REGICOR and SCORE scales.

Conclusions

Ten of the 15 machine learning methods tested have a better predictive capacity for cardiovascular events and better classification indicators than the SCORE and REGICOR risk assessment scales commonly used in clinical practice in Spain. Machine learning methods should be considered in the development of future cardiovascular risk scales.

This article is protected by copyright. All rights reserved.

SOURCE

https://onlinelibrary.wiley.com/doi/abs/10.1111/ijcp.13389

Advertisements

Read Full Post »


Real Time Coverage @BIOConvention #BIO2019: Machine Learning and Artificial Intelligence: Realizing Precision Medicine One Patient at a Time

Reporter: Stephen J Williams, PhD @StephenJWillia2

The impact of Machine Learning (ML) and Artificial Intelligence (AI) during the last decade has been tremendous. With the rise of infobesity, ML/AI is evolving to an essential capability to help mine the sheer volume of patient genomics, omics, sensor/wearables and real-world data, and unravel the knot of healthcare’s most complex questions.

Despite the advancements in technology, organizations struggle to prioritize and implement ML/AI to achieve the anticipated value, whilst managing the disruption that comes with it. In this session, panelists will discuss ML/AI implementation and adoption strategies that work. Panelists will draw upon their experiences as they share their success stories, discuss how to implement digital diagnostics, track disease progression and treatment, and increase commercial value and ROI compared against traditional approaches.

  • most of trials which are done are still in training AI/ML algorithms with training data sets.  The best results however have been about 80% accuracy in training sets.  Needs to improve
  • All data sets can be biased.  For example a professor was looking at heartrate using a IR detector on a wearable but it wound up that different types of skin would generate a different signal to the detector so training sets maybe population biases (you are getting data from one group)
  • clinical grade equipment actually haven’t been trained on a large set like commercial versions of wearables, Commercial grade is tested on a larger study population.  This can affect the AI/ML algorithms.
  • Regulations:  The regulatory bodies responsible is up to debate.  Whether FDA or FTC is responsible for AI/ML in healtcare and healthcare tech and IT is not fully decided yet.  We don’t have the guidances for these new technologies
  • some rules: never use your own encryption always use industry standards especially when getting personal data from wearables.  One hospital corrupted their system because their computer system was not up to date and could not protect against a virus transmitted by a wearable.
  • pharma companies understand they need to increase value of their products so very interested in how AI/ML can be used.

Please follow LIVE on TWITTER using the following @ handles and # hashtags:

@Handles

@pharma_BI

@AVIVA1950

@BIOConvention

# Hashtags

#BIO2019 (official meeting hashtag)

Read Full Post »


Applying AI to Improve Interpretation of Medical Imaging

Author and Curator: Dror Nir, PhD

 

 

images

The idea that we can use machines’ intelligence to help us perform daily tasks is not an alien any more. As consequence, applying AI to improve the assessment of patients’ clinical condition is booming. What used to be the field of daring start-ups became now a playground for the tech-giants; Google, Amazon, Microsoft and IBM.

Interpretation of medical-Imaging involves standardised workflows and requires analysis of many data-items. Also, it is well established that human-subjectivity is a barrier to reproducibility and transferability of medical imaging results (evident by the reports on high intraoperative variability in  imaging-interpretation).Accepting the fact that computers are better suited that humans to perform routine, repeated tasks involving “big-data” analysis makes AI a very good candidate to improve on this situation.Google’s vision in that respect: “Machine learning has dozens of possible application areas, but healthcare stands out as a remarkable opportunity to benefit people — and working closely with clinicians and medical providers, we’re developing tools that we hope will dramatically improve the availability and accuracy of medical services.”

Google’s commitment to their vision is evident by their TensorFlow initiative. “TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.” Two recent papers describe in length the use of TensorFlow in retrospective studies (supported by Google AI) in which medical-images (from publicly accessed databases) where used:

Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning, Nature Biomedical Engineering, Authors: Ryan Poplin, Avinash V. Varadarajan, Katy Blumer, Yun Liu, Michael V. McConnell, Greg S. Corrado, Lily Peng, and Dale R. Webster

As a demonstrator to the expected benefits the use of AI in interpretation of medical-imaging entails this is a very interesting paper. The authors show how they could extract information that is relevant for the assessment of the risk for having an adverse cardiac event from retinal fundus images collected while managing a totally different medical condition.  “Using deep-learning models trained on data from 284,335 patients and validated on two independent datasets of 12,026 and 999 patients, we predicted cardiovascular risk factors not previously thought to be present or quantifiable in retinal images, such as age (mean absolute error within 3.26 years), gender (area under the receiver operating characteristic curve (AUC) = 0.97), smoking status (AUC = 0.71), systolic

blood pressure (mean absolute error within 11.23 mmHg) and major adverse cardiac events (AUC = 0.70).”

 

Screenshot 2019-05-28 at 10.07.21Screenshot 2019-05-28 at 10.09.40

Clearly, if such algorithm would be implemented as a generalised and transferrable medical-device that can be used in routine practice, it will contribute to the cost-effectiveness of screening programs.

 

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography, Nature Medicine, Authors: Diego Ardila, Atilla P. Kiraly, Sujeeth Bharadwaj, Bokyung Choi, Joshua J. Reicher, Lily Peng, Daniel Tse , Mozziyar Etemadi, Wenxing Ye, Greg Corrado, David P. Naidich and Shravya Shetty.

This paper is in line of many previously published works demonstrating how AI can increase the accuracy of cancer diagnosis in comparison to current state of the art: “Existing challenges include inter-grader variability and high false-positive and false-negative rates. We propose a deep learning algorithm that uses a patient’s current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases.”

Screenshot 2019-05-28 at 10.22.06Screenshot 2019-05-28 at 10.23.48

The benefit of using an AI based application for lung cancer screening (If and when such algorithm is implemented as a generalised and transferable medical device) is well summarised by the authors: “The strong performance of the model at the case level has important potential clinical relevance. The observed increase in specificity could translate to fewer unnecessary follow up procedures. Increased sensitivity in cases without priors could translate to fewer missed cancers in clinical practice, especially as more patients begin screening. For patients with prior imaging exams, the performance of the deep learning model could enable gains in workflow efficiency and consistency as assessment of prior imaging is already a key component of a specialist’s workflow. Given that LDCT screening is in the relatively early phases of adoption, the potential for considerable improvement in patient care in the coming years is substantial. The model’s localization directs follow-up for specific lesion(s) of greatest concern. These predictions are critical for patients proceeding for further work-up and treatment, including diagnostic CT, positron emission tomography (PET)/CT or biopsy. Malignancy risk prediction allows for the possibility of augmenting existing, manually created interpretation guidelines such as Lung-RADS, which are limited to subjective clustering and assessment to approximate cancer risk.

BTW: The methods section in these two papers is detailed enough to allow any interested party to reproduce the study.

For the sake of balance-of-information, I would like to note that:

  • Amazon is encouraging access to its AI platform Amazon SageMaker “Amazon SageMaker provides every developer and data scientist with the ability to build, train, and deploy machine learning models quickly. Amazon SageMaker is a fully-managed service that covers the entire machine learning workflow to label and prepare your data, choose an algorithm, train the model, tune and optimize it for deployment, make predictions, and take action. Your models get to production faster with much less effort and lower cost.” Amazon is offering training courses to help programmers get proficiency in Machine-Learning using its AWS platform: “We offer 30+ digital ML courses totaling 45+ hours, plus hands-on labs and documentation, originally developed for Amazon’s internal use. Developers, data scientists, data platform engineers, and business decision makers can use this training to learn how to apply ML, artificial intelligence (AI), and deep learning (DL) to their businesses unlocking new insights and value. Validate your learning and your years of experience in machine learning on AWS with a new certification.”
  • IBM is offering a general-purpose AI platform named Watson. Watson is also promoted as a platform to develop AI applications in the “health” sector with the following positioning: “IBM Watson Health applies data-driven analytics, advisory services and advanced technologies such as AI, to deliver actionable insights that can help you free up time to care, identify efficiencies, and improve population health.”
  • Microsoft is offering its AI platform as a tool to accelerate development of AI solutions. They are also offering an AI school : “Dive in and learn how to start building intelligence into your solutions with the Microsoft AI platform, including pre-trained AI services like Cognitive Services and Bot Framework, as well as deep learning tools like Azure Machine Learning, Visual Studio Code Tools for AI and Cognitive Toolkit. Our platform enables any developer to code in any language and infuse AI into your apps. Whether your solutions are existing or new, this is the intelligence platform to build on.”

Read Full Post »


LIVE Day Three – World Medical Innovation Forum ARTIFICIAL INTELLIGENCE, Boston, MA USA, Monday, April 10, 2019

 

www.worldmedicalinnovation.org

 

The Forum will focus on patient interactions across care settings, and the role technology and data can play in advancing knowledge discovery and care delivery. The agenda can be found here.

https://worldmedicalinnovation.org/agenda/

Leaders in Pharmaceutical Business Intelligence (LPBI) Group

represented by Founder & Director, Aviva Lev-Ari, PhD, RN will cover this event in REAL TIME using Social Media

@pharma_BI

@AVIVA1950

@PHSInnovation

#WMIF19 

Wednesday, April 10, 2019

7:00 am – 12:00 pm
7:30 am – 9:30 am
Bayer Ballroom

Innovation Discovery Grant Awardee Presentations

Eleven clinical teams selected to receive highly competitive Innovation Discovery Grants present their work illustrating how AI can be used to improve patient health and health care delivery. This session is designed for investors, entrepreneurs, investigators, and others who are interested in commercializing AI opportunities that are currently in development with support from the Innovation Office.

To view speakers and topics, click here.

Where AI Meets Clinical Care

Twelve clinical AI teams culled through the Innovation Discovery Grant program present their work illustrating how AI can be used to improve patient health and healthcare delivery. This session is designed for investors, entrepreneurs, investigators, and others who are interested in commercializing AI opportunities that are currently in development with support from the Innovation Office.

IDG logo

Peter Dunn, MD

Vice President, Perioperative Services and Healthcare System Engineering, MGH; Assistant Professor, Anesthesia, HMS

Using Deep Learning to Optimize Hospital Capacity Management

  • collaboration with @MIT @MGH
  • deploy mobile app across all Partners institutions

 

Kevin Elias, MD

Director, Gynecologic Oncology Research Laboratory, BH; Assistant Professor, HMS

Screening for Cancer Using Serum miRNA Neural Networks

  • cancer screening fragmented process – tests not efficient No screening for many common cancer type
  • Cervical, Breast, Colon, Ovarian Uterus Cancer
  • Serum miRNA multiple cancer types

 

Alexandra Golby, MD

Director, Image-Guided Neurosurgery, BH; Professor, Neurosurgery and Radiology, HMS

Using Machine Learning to Optimize Optical Image Guidance for Brain Tumor Surgery

  • optical visualization in Neurosurgery – to improve Brain Cancer surgery Tumor removal complete resection could cause neurological deficits
  • BWH original research on Neuronavigations, intraops MRI
  • New Tool Real Time: Color code tumors using light diagnostics with machine learning
  • GUIDING Brain surgery, applicable for Breast Cancer
  • iP filling prototype creation, testing, pre-clinical testing, clinical protocol established academic-industrial partnerships
  • AI based – World 1st guided neurosurgery

 

Jayashree Kalpathy-Cramer, PhD

Director, QTIM Lab, MGH; Associate Professor, Radiology, HMS

DeepROP: Point-of-Care System for Diagnosis of Plus Disease in Retinopathy of Prematurity

  • Prematurity 1250 gr <31 weeks f gestation
  • ROP – Retinopathy of prematurity (ROP)
  • Images annotated Plus/not plus – algorithm for rating images “normal” or “plus”
  • DeepROP Applicationsinto Camera for data acquisition, iPhone

 

Jochen Lennerz, MD, PhD

Associate Director, Center for Integrated Diagnostics, MGH; Assistant Professor, HMS

Predicting Unnecessary Surgeries in High-Risk Breast Lesions

  • 10% reduction of high risk lesion equivalent to $1.4Billion in cost savings
  • Funding for Production line

Bruno Madore, PhD

Associate Professor, Radiology, BH, HMS

Sensor Technology for Enhanced Medical Imaging

  • ML Ultrasound – Organ configuration Motion (OCM) sensor
  • Hybrid MRI-ultrasound acquisitions
  • Long term vision – collaboration with Duke for a wireless device

 

Jinsong Ouyang, PhD

Physicist, MGH; Associate Professor, HMS

Training a Neural Network to Detect Lesions

  • Approach – train a NN using artificially inserted lesions

APPLICATIONS:

  • Build unlimitted number of training sets using small 15-50 human data sets generated
  • bone lession detection using SPECT
  • cardiac detect myocardial perfusion SPECT
  • Tumor detection PET
  • Volume detection/locatization of artificial Spinal Lesions (L1-L5)

 

David Papke, MD, PhD

Resident, Surgical Pathology, BH; Clinical Fellow, HMS

Augmented Digital Microscopy for Diagnosis of Endometrial Neoplasia

See tweet

 

Martin Teicher, MD, PhD

Director, Developmental Biopsychiatry Research Program, McLean; Associate Professor, Psychiatry, HMS

Poly-Exposure Risk Scores for Psychiatric Disorders

  • MACE Scale – psychopathology development – collinearity
  • Identifying sensitivity period predictors of major depression
  • predicting risk in adolescence – dataset with high collinearity
  • Onset of depression age 10-15
  • 50% assessment exposure to adversity – based on neuroimaging
  • Analytics and AI longitudinal studies

 

 

Christian Webb, PhD

Director, Treatment and Etiology of Depression, Youth Lab, McLean; Assistant Professor, Psychiatry, HMS

Leveraging Machine Learning to Match Depressed Patients to the Optimal Treatment

  • 4-8 wks of treatment till psychotropic drugs work
  • Data driven approaches: ML can match better patients to antidepressant treatments (Zoloft vs Placebo responder /non responder)?
  • Large number of variables prediction, prognosis calculator, good vs poor outcome
  • Better on Zoloft vs Placebo

 

Brandon Westover, MD, PhD

Executive Director, Clinical Data Animation Center, MGH; Associate Professor, Neurology, HMS
  • seizure, prediction of next attack
  • EEG readings – accurate diagnosis on epilepsy
  • 50 million World wide
  • automated epilepsy detection
  • @MGH – 1,063 EEGs 88,000 spikes 7 experts scored – not all agreed
  • How well can experts identify spikes?
  • Super spike detector is better than Experts – False positive 60% 87% Sensitivity vs 10% and 87% by AI
Moderator: David Louis, MD
  • Pathologist-in-Chief, MGH; Benjamin Castleman Professor of Pathology, HMS
Moderator: Clare Tempany, MD
  • Vice-Chair, Radiology Research, BH; Ferenc Jolesz MD Professor of Radiology, HMS
9:30 am – 10:00 am
10:00 am – 10:30 am
Bayer Ballroom

1:1 Fireside Chat: Stefan Oelrich, Member of the Board of Management; President, Pharmaceutical, Bayer AG

Introduction by: John Fish
  • CEO, Suffolk; Chairman of Board Trustees, Brigham Health
Moderator: Betsy Nabel, MD
  • President, Brigham Health; Professor of Medicine, HMS
  • Member of the Board of Management, Bayer AG; President, Pharmaceutical, Bayer AG

Chief Digital Officers

  • Leaders at the top needs to understand AI
  • Millennials needs to fill Baby boomer retiring
  • Boston – funding Research by NIH by private investment technology transfer to commercialization
  • Career advice: Academia is the first step for credibility move to Big Pharma, create own company
  • America economic strength built on innovation in Healthcare to invest
  • Leadership at Bayer: “Culture eat strategy for Breakfast”
  • AI overcoming barriers – AI improving what we know Medical imaging human vs machine – AI is the new norm – platforms Imaging AI device to detect Hypertension more accurately development of Bayer and Merck – Bayer leader in Radiology
  • Clinical research End point to reach compare
  • Future billion end point which therapeutic pathway is best for which patient
  • Incentives for risky strategy
  • Motivation to collaborate in Boston: Cardiology with broad Institute
  • BWH data and algorithms to increase knowledge
  • Pricing medicine around the World
  • US system in-transparent – patients do not understand Price of meds Rebates to Payers
  • Medical Part B – no pass to Rebates price tied to value
  • As industry – innovations in Pharma reduce healthcare costs Germany 15% of HealthCare on Drugs, generics, “Patented medicine 4%” of all Best in Europe
  • beak silos
  • In US training physicians to lead innovations
10:30 am – 11:00 am
Bayer Ballroom

1:1 Fireside Chat: Deepak Chopra, MD, Founder, The Chopra Foundation

Moderator: Rudolph Tanzi, PhD
  • Vice-Chair, Neurology, Director, Genetics and Aging Research Unit, MGH; Joseph P. and Rose F. Kennedy Professor of Neurology, HMS
  • IMAGING of Brains of Women in Meditation – enlongate telemeres
  • inflammation decrease – Sleep health interactions exsercise learning new things diet
  • flashing from brain wastes – amaloydosis AD – 35 genes variance leading to disease
  • Founder, The Chopra Foundation – Body-Mind Connection
  • AI – re-invest our bodies Telemeres, transferdomics,
  • Nutrition, sleep, excercise, BP, HR, sympathetic vs non sympatheric nervous system breathing pattern, – microbiome subjective experience with Vitals emotional well being
  • emersive augmented
  • longer Telemerese – anti aging correlation
  • biomarkers vs states of energy
  • wisdom best knowledge for self awareness – highest intelligence – NOT artificial
  • Thoughts on being aware
11:00 am – 11:50 am
Bayer Ballroom

Using AI to Predict and Monitor Human Performance and Neurological Disease

In the quest for effective treatments aimed at devastating neurological diseases like Alzheimer’s and ALS, there is a critical need for robust methods to predict and monitor disease progression. AI-based approaches offer promise in this important area. Panelists will discuss efforts to map movement-related disorders and use machine learning to predict the path of disease with imaging and biomarkers.

  • Chief of Neurology, Co-Director, Neurological Clinical Research Institute, MGH; Julieanne Dorn Professor of Neurology, HMS
  • Chief Scientist, Dolby Laboratories Stanford & Adobe – measuring experience
  • convergence of skills
  • internal wellness measured in the ear, motions
  • Stimulate Vagal nerve through the ear for depression treatment
  • Legislation in CA contribution to spaces
  • Global Therapeutic Head, Neuroscience Janssen Research & Development
  • Disease starts earlier Biogen contributions in the field
  • measurement surrogate indicators for outcome given interventions
  • Autism-spectrum not one disease
  • AI will enhance the human competence for measurement
  • UK based efforts to share dat and launch programs for Dementia
  • Conditions of Brain & Mind – declining cognitive
  • Democratization of discovery
  • AI benefit iterative process in changing and improving Algorithms — FDA approved algorithm needs several versions in the future
  • Complexity of CNS Polygenic gene scores
  • Dynamics of AI
  • EVP and CMO, Biogen
  • MS – follow patients, patient reporting in 10 centers , vision cognitions –
  • Obtain measurement even on normal people for early detection – FDA introduced Stage 1,2,3 Biomarker based
  • Newborn Kit of screening teat early helps
  • Home monitoring at Home for onset of AD

Dr. Isaac Galatzer-Levy – NYU & AiCure

  • All CNS diseases are heterogeneous
  • ML requires collaboration
  • AiCure – Medication adherence monitoring from Voice of patients
  • Sampling populations – cell phone
  • Re-investigate studies that have failed with new AI tools
11:50 am – 12:50 pm
Bayer Ballroom

Disruptive Dozen: 12 Technologies that will reinvent AI in the Next 12 Months

The Disruptive Dozen identifies and ranks the AI technologies that Partners faculty feel will break through over the next year to significantly improve health care.

  • innovations, technologies close to make to market

#12 David Ahern – Mental Health in US closing the Gap

#11 David Ting – Voice first

#10 Bharti Khurana – Partners Violence

#9 Gilberto Gonzales – Acute Stroke care

#8 James Hefferman – Burden og Health care ADM

#7 Samuel Aronson – FHIR Health information exchange

#6 Joan Miller – AI for eye health

#5 Brsndon Westover – A window to the Brain

#4 Rochelle Walensky – Automated detection of Malaria

#3 Annette Kim – Streamlining Diagnosis 

  #2 Thomas McCoy – Better Prediction of Suicide risk

  #1 Alexandra Golby – Reimagining Medical Imaging 

 

Moderator: Jeffrey Golden, MD
  • Chair, Department of Pathology, BH; Ramzi S. Cotran Professor of Pathology, HMS
  • Associate Chief, Infection Control Unit, MGH; Assistant Professor, Medicine, HMS
1:00 pm – 1:10 pm
Bayer Ballroom

Read Full Post »


LIVE Day Two – World Medical Innovation Forum ARTIFICIAL INTELLIGENCE, Boston, MA USA, Monday, April 9, 2019

 

www.worldmedicalinnovation.org

 

The Forum will focus on patient interactions across care settings, and the role technology and data can play in advancing knowledge discovery and care delivery. The agenda can be found here.

https://worldmedicalinnovation.org/agenda/

Leaders in Pharmaceutical Business Intelligence (LPBI) Group

represented by Founder & Director, Aviva Lev-Ari, PhD, RN will cover this event in REAL TIME using Social Media

@pharma_BI

@AVIVA1950

@PHSInnovation

#WMIF19 

Tuesday, April 9, 2019

7:00 am – 8:00 am
7:00 am – 5:00 pm
7:40 am – 7:50 am
Bayer Ballroom

Opening Remarks

  • Chief Innovation Officer, PHS; President, Partners HealthCare International
7:50 am – 8:40 am
Bayer Ballroom

Implementing AI in Cancer Care

With AI-enabled care strategies and digital technologies, clinicians and patients are embracing new approaches to improve the lives of cancer patients through enhanced diagnosis and treatment. These include AI-guided tools for more precise methods of predicting risk, more effective screening strategies, patient data driven insights  and more personalized treatments. Panelists will engage on how these and other innovations are enabling a new era of cancer care.

  • Chief, Breast Imaging Division, MGH; Professor of Radiology, HMS
  • FDA
  • President and Co-Founder, LunaDNA
  • Patients contribute personal data get share in the company
  • democratization by AI use
  • unrepresented population in research
  • education on technology
  • Retrospective and longitudinal studies
  • Bid Trust engaging responsively
  • Delta Electronics Professor, Electrical Engineering and Computer Science Department, MIT
  • developper of AI based applications @MGH Cancer Center
  • Training AI on 3% of population vs randomized that has its bias of patient selection
  • no standards of publishing AI in medicine
  • AI to help women
  • Integration of systems to help patients
  • Director, Cancer Genome Analysis, Broad Institute; Professor, Pathology, HMS
  • AI for early detection
  • big data analysis – noise vs point of signals
  • drug resistance using genomics
  • AI – regulate the type information reviewed by doctors
  • data acquisition and monitoring along the life of the product not only till FDA approve it
  • Reporting adverse events
  • Data cost of sequencing is dropping, biomarkers,
  • regulatory needed to adopt AI and reimbursement starts at academic center followed by the entire country
  • CEO, insitro
  • AI for drug discovery
  • epigenetic effect on lesions
  • Physician are over promised on Genomics, asking them to use complex data from multiple source need be curated before it gets to Physicians
  • Reversed clinical trial vs randomized 30 years follow up
  • Data is anonymized used in research contributors get back own diagnosis genomics understanding

 

8:40 am – 9:30 am
Bayer Ballroom

Imagining Medicine in the Year 2054

In 1984 Isaac Asimov was asked to predict what life in 2019 would be like. Using the same aperture, we as what will constitute health care 35 years from now? Current trends suggest that there will be significant gains in immunotherapy, gene therapy, and breakthrough treatments for neurologic, cardiovascular and oncologic diseases. Panelists will draw on their visionary perspective and will reflect on what to expect and why.

Moderator: Keith Flaherty, MD
  • Director, Clinical Research, Cancer Center, MGH; Professor of Medicine, HMS
  • CEO, Flagship Pioneering
  • Vice Chair for Scientific Innovation, Department of Medicine, BH; Associate Professor of Medicine, HMS
  • Director, Cellular Immunotherapy Program, Cancer Center, MGH; Assistant Professor, Medicine, HMS
  • Vice-Chair, Neurology, Director, Genetics and Aging Research Unit, MGH; Joseph P. and Rose F. Kennedy Professor of Neurology, HMS
9:30 am – 9:50 am
9:50 am – 10:15 am
Bayer Ballroom

1:1 Fireside Chat: Ash Carter, U.S. Secretary of Defense (2015 – 2017)

Moderator: Gregg Meyer, MD
  • Chief Clinical Officer, PHS; Professor of Medicine, HMS; 2019 Forum Co-Chair
  • U.S. Secretary of Defense (2015–2017)
10:15 am – 10:40 am
Bayer Ballroom

1:1 Fireside Chat: Honorable Alex Azar II, Secretary of Health and Human Services

Moderator: Gregg Meyer, MD
  • Chief Clinical Officer, PHS; Professor of Medicine, HMS; 2019 Forum Co-Chair
  • 24th Secretary of Health and Human Services
  • quality cate means outcomes
  • Pricing Transparency by HMOs and Hospitals
  • Plan D – instant electronic to Drug Pricing information
  • Medicare moves away from Procedure based payment
  • Data on services, drugs and procedures in a Patient-centered system
  • Big data, pricing information, CMS
  • AI inspector General – Claims – AI – do get yield
  • AI in procurement
  • AI for services to Medicare – prescription Tools for advising Patients on best drug to use based on medcial information
  • Patient HC information is owned by Pations and is portable
  • Blue Data 2.0 – access record by patients @CMS
10:40 am – 11:30 am
Bayer Ballroom

CEO Roundtable

Chief executives share perspectives on the impact of AI on their respective companies and industry segments. Panelists will discuss their views of AI, how AI figures into their organizations’ current product and investment strategies, and how they are measuring return on existing AI investments. The panel will also address opportunities and challenges surrounding AI, ranging from workforce needs to managing bias in AI development.

Moderator: Anne Klibanski, MD
  • Interim President and CEO, Chief Academic Officer, PHS; Laurie Carrol Guthart Professor of Medicine, HMS; 2019 Forum Co-Chair
  • Partnerships between companies like : GE, Phillips, Siemens
  • CEO, Philips
  • efficiencies and outcomes
  • adaptive intelligence to be integrated AI 1.8Billion Euro invested 600 scientists
  • collaboration with Dana Farber
  • Design thinking – work with clinicians to get insights on experience with technologies
  • system change for delivery of care
  • Open API – federated data architecture EMR companies will also need to adapt
  • Phillips builds centers in Pittsburgh, Cambridge, Amsterdam, Paris
  • EVP, Head, Pharmaceuticals Research and Development, Bayer AG
  • AI – R&D efficiency
  • Disruptive approaches optimization of synthesis of chemical reactions productivity and selection of molecules
  • In house data science expertise vs image pattern recognition of HTN collaboration with Merck
  • Collaboration with MIT on clinical Trials
  • changing provides vs longitudinal care
  • Access to talent – Data scientists Amazon is a competitor on talent for AI SKILLS DOMAIN EXPRET TOPIC
  • R&D AT BAYER – DATA SCIENCE IN each division
  • CEO, Siemens Healthineers
  • 400 research collaborations
  • “analog” way innovations generations
  • CEO, GE Healthcare
  • HC – Clinical command center in Hospitals collaboration with Partners
  • Investment is in platforms vs applications – Edison platform tool kits – Radiologist will develop their own on top of PLATFORMS from GE
  • Clinicians productivity will change with AI
  • Data scientist new identity – bigger developers of systems
11:30 am – 11:35 am
Bayer Ballroom
11:35 am – 11:45 am
11:45 am – 1:00 pm

Discovery Cafe Sessions

Lunch with Experts: Intensive sessions addressing cutting-edge artificial intelligence topics.

Provider Back Office of the Future

The application of AI-based technologies to the business side of health care — including functions such as billing, payment, and insurance claims management — could lead to significant improvements in health care operations and efficiency, with billions of dollars in savings each year. Panelists will discuss emerging tools and technologies as well as the opportunities and pitfalls of using AI to innovate and automate back office functions.

Moderator: Peter Markell, EVP, Administration and Finance, CFO and Treasurer, PHS

Inge Harrison, CNO/VP of Strategic Advisory Services, Verge Health

Kent Ivanoff, CEO, VisitPay

Mary Beth Remorenko, VP, Revenue Cycle Operations, PHS

Brian Robertson, CEO, VisiQuate

 

Chief Digital Strategy Officer Roundtable

With the advent of AI-enabled technologies, this session brings together leading chief digital health officers. The discussion will address tradeoffs in sequencing technology across academic medical centers; what technologies are being prioritized; and consumer expectations.

Moderator: Alistair Erskine, MD, Chief Digital Health Officer, PHS

Michael Anderes, Chief Innovation and Digital Health Officer, Froedtert Health; President, Inception Health

Adam Landman, MD, VP and CIO, BH; Associate Professor of Emergency Medicine, HMS

Aimee Quirk, CEO, innovationOchsner

Richard Zane, MD, Chief Innovation Officer, UCHealth; Professor and Chair,Department of Emergency Medicine, University of Colorado School of Medicine

 

Innovation Fellows: A New Model of Collaboration

The Innovation Fellows Program provides experiential career development opportunities for future leaders in health care. It facilitates personnel exchanges between Harvard Medical School staff from Partners’ hospitals and participating biopharmaceutical, device, venture capital, digital health, payor and consulting firms. Fellows and Hosts learn from each other as they collaborate on projects ranging from clinical development to digital health and artificial intelligence. Learn how this new model of collaboration can deliver value and lead to broader relationships between industry and academia.

Moderator: Seema Basu, PhD, Market Sector Leader, Innovation, PHS

Nathalie Agar, PhD, Research Scientist, Neurosurgery, BH; Associate Professor, Neurosurgery, Radiology, HMS

Paul Anderson, MD, PhD, Chief Academic Officer, BH; SVP, Research, BH; K. Frank Austen Professor of Medicine, HMS

Laurie Braun, MD, Partners Innovation Fellow, MGH and Boston Pharmaceuticals; Instructor in Pediatrics, HMS

David Chiang, MD, PhD, Research Fellow, BH; Innovation Fellow, Boston Scientific

David Feygin, PhD, Chief Digital Health Officer, Boston Scientific

Peter Ho, MD, PhD, CMO, Boston Pharmaceuticals

Harry Orf, PhD, SVP, Research, MGH; Principal Associate, HMS

 

Last Mile: Fully Implementing AI in Healthcare

This session will focus on how radiology and pathology specialties are currently applying AI in the clinic. Where will it be built out first? What are the barriers and how will these challenges be overcome?

Moderator: Keith Dreyer, DO, PhD, Chief Data Science Officer, PHS; Vice Chairman, Radiology, MGH; Associate Professor, Radiology, HMS

Katherine Andriole, PhD, Director of Research Strategy and Operations, MGH & BWH CCDS; Associate Professor, Radiology, HMS

Samuel Aronson, Executive Director, IT, Personalized Medicine, PHS

Peter Durlach, SVP, Healthcare Strategy & New Business Development, Nuance

Seth Hain, VP of R&D, Epic

Jonathan Teich, MD, PhD, Chief Medical Information Officer, InterSystems; Emergency Medicine, BH

 

Reimagining Disease Management

The management of disease has become vastly more challenging, both for patients and providers. AI-based technologies promise to improve and streamline patient care through a variety of approaches. This session will feature a discussion of these new tools and how they can enhance patient engagement and optimize care management.

Moderator: Sree Chaguturu, MD, Chief Population Health Officer, PHS; Assistant Professor, Medicine, HMS

Murray Brozinsky, Chief Strategy Officer, Conversa

Jean Drouin, MD, CEO, Clarify Health Solutions

Julian Harris, MD, President, CareAllies

Erika Pabo, MD, Chief Health Officer, Humana Edge; Associate Faculty, Ariadne Labs; Associate Physician, BH; Instructor, HMS

 

Standards and Regulation: The Emerging AI Framework

As the health care industry faces an explosion of AI-based tools, the FDA’s approach to these technologies is evolving. This session will focus on the agency’s approach to AI-based products, how to calculate the risk profile of these new technologies, and the challenges of securing adequate data rights.

Moderator: Brent Henry, Member, Mintz Levin

Bethany Hills, Member/ Chair, FDA Practice, Mintz Levin

Michelle McMurry-Heath, MD, PhD, VP, Global Regulatory Affairs and International Clinical Evidence, Johnson & Johnson Medical Devices

Bakul Patel, Associate Director, Digital Health, FDA

Michael Spadafore, Managing Director, Sandbox Industries

 

From Startup to Impact (Provider Solutions)

This session will introduce you to five leading startup companies who will each share their respective impact in delivery provider solutions in ten-minute pitches.

Moderator: Meredith Fisher, PhD, Partner, Partners Innovation Fund, PHS

Moderator: James Stanford, Managing Director, Fitzroy Health

William Grambley, COO, AllazoHealth

Gal Salomon, CEO, CLEW

Siddarth Satish, CEO, Gauss Surgical

Pelu Tran, CEO, Ferrum Health

Ed Zecchini, CIO, Remedy Partners

1:00 pm – 1:10 pm
1:10 pm – 2:00 pm
Bayer Ballroom

China: AI Enabled Healthcare Leadership

China’s health care system faces major challenges — and its population is aging more rapidly than nearly every other country. To help address these problems, the Chinese health technology sector is strongly embracing AI. What are the most exciting applications? What lessons does China’s early forays into AI-enabled patient care hold for other health care systems?

Moderator: James Bradner, MD
  • President, Novartis Institutes for BioMedical Research
  • Chief Innovation Officer, GE Healthcare
  • Analytics allowing higher throughput in China in Rural areas
  • Sepsis – detection is too late
  • data exhaust for facial recognition – anticipatory diagnosis
  • oncology tumor algorithm
  • CEO, Infervision
  • Medical imaging – four years to mature nodule detection
  • AI – no resale of data
  • Chairman and Co-Founder, Yidu Cloud
  • Medical records
  • Data privacy is personal consent if identification Passport level:
  • Doctor looking on Medical record need consent
  • Administration – clearance for access
  • Managing Partner, Qiming Venture Partners
  • AI HC companies execution to build companies
  • Valuation of all AI not only HC, dropped 30%
  • Real Doctor – 14 licensing for Internet medicine 90,000 patients a day are seen
  • Consumer EMR – Alibaba invested in
  • Investment in CRISPR
  • Invest in drug discovery in China
  • In China 150 programs of drug development of PD-1
  • Government  – 90% of patients go to Public Hospital which guard the data
  • Challenges AI in China — US – China Trade issue
  • CEO, Real Doctor Corporation Limited
  • Medical imaging 12 disease found from pictures build models to other 100 hospitals
  • small nodules detection
  • China-FDA no regulation established yet Learn from US FDA
2:00 pm – 2:30 pm
Bayer Ballroom

1:1 Fireside Chat: Mark Benjamin, CEO, Nuance

Moderator: Peter Slavin, MD
  • President, MGH; Professor, Health Care Policy, HMS
  • CEO, Nuance Communications
  • System produce NOTES from conversation, clinical language, notes read interactively by looking at other chart – LIVE EXAM more that an invoicing tool
  • patient case management made efficient
  • Documentation and Clinical notes embedded into the EHR enhance intelligence at Point-of-Care

 

2:30 pm – 3:00 pm
3:00 pm – 3:50 pm
Bayer Ballroom

Getting to the AI Investment Decision

The billions invested worldwide in AI-based health care technologies underscore the enthusiasm of global investors. But where are the greatest opportunities and what is the timeline to meaningful impact? In this panel, venture, private equity investors, and buy side analysts will discuss investment priorities, timelines, and key areas of interest

  • Partner, Partners Innovation Fund, PHS
  • When is the time right and when there is only a promise
  • VP, Venture and Managing Partner, Partners Innovation Fund, PHS
  • Looks like therapeutics but it is AI
  • Managing Director, Bain Capital Life Sciences
  • companies leveraging competencies
  •  Capital put to work what is it coming to do – specific value creation
  • Is the problem HC or an Academic Medical Center, i.e., MGH problem to solve
  • If no one at PHS willing to pay — let’s think again
  • Managing Partner, Polaris Partners
  • Data in Pharma companies are ready for AI application
  • algorithms and analytics
  • Value proposition
  • Language processing & ML – recognize patterns in consistant datasets – improve decision made in patient care
  • SVP, Strategy, Commercialization and Innovation, Amgen
  • Real data using AI for speeding drug discovery commercial application
  • predictive models for second MI with partner
  • Pilot study vs scaling up
  • Managing Director, Healthcare Group, Goldman Sachs
  • As AI algorithm mature, labor intensity curbed by AI
  • IPO
  • consolidation of big pharma
  • Partner, Google Ventures – started in 2008/9; Instructor in Medicine, BH
  • data quality needed for AI to avoid bias
  • Pharma is interested in Drugs not in Targets
  • Translator between technology and healthcare
  • Teach computer the rules to go then beating its creator unanticipated modes
  • IT is different in various industries more than West Coast vs East Coast
3:50 pm – 4:20 pm
Bayer Ballroom

1:1 Fireside Chat: Robert Bradway, CEO, Amgen

  • Partner, Atlas Venture
  • CEO, Amgen
  • DeCode Genetics acquired by Amgen
  • AI is in the beginning Rapata and Evenity (romosozumab) risk of fractures – review large images archives
  • Migraine only digital health  – this is not a big area for Amgen
  • Transparency
  • Encouraged to role back the Rebate Program the sickest pay to high – policy changes
  • Part 4
  • Rapata – lower LDL reduce risk for stroke MI 600Billion fighting Heart disease – price lowered 60% patients are directed to the more expensive product
  • Investment in Biosimilars and biologics made available free resources
  • risk is Washington, generics may become the rule for biologics
  • no favor innovating products vs Biosimilars
  • ObamaCare create 12 years of data exclusivity for biologics
  • 90% of prescription is generic products
  • cost of CVD in 2019 is a fraction of the cost 15 years ago
  • CURE – is used for Cancer at what price HEP C – is a cure very expansive
  • Meaning of innovations create frameworks for saving live
4:20 pm – 5:10 pm
Bayer Ballroom

Consumer Healthcare and New Models of Care Delivery

Al is powering a revolution in consumer health care, giving patients a deeper role in monitoring their own health and spawning new models of care delivery. Many health care organizations are increasingly focused on creating a digital “front door” for patients – a single gateway to mobile apps and other online services. Panelists will also discuss the role of remote monitoring and virtual care programs as well as the role of Al in care redesign and workflow.

Moderator: Diana Nole
  • CEO, Wolters Kluwer Health
  • President, Global Strategy Group, Samsung; Founder, CareVisor
  • Real time sensing to deliver realtime care plan: Human Avatar
  • AI is hidden
  • communication varies by generations phone vs SMS
  • VP and Global CTO, Sales, Dell EMC
  • IOT – scale
  • social media – peer pressure
  • President, Health Platforms, Verily Life Sciences
  • AI applied in diet management with images of snacks
  • Co-production of Health 50s-60s concept Co-Production health by patients give patients information and they will co-produce their healthier life style
  • VP and Chief Health Officer, IBM Corporation
  • AI continues to improve – actionable insights
  • AI augmented humanity
  • In China a Team of oncologist meet with entire families to discuss plan of care Cancer patients for GrandMa,
  • SVP, Head of Innovation and Health Equity, Microsoft Healthcare
  • AI – sequence T cells
5:15 pm – 5:25 pm
Bayer Ballroom

BioBank Award Announcement

  • Third place MGH – Computational Pathology
  • First Prize – $12,000 UPittsburg – Dept Biomedical Informatics – principal components
  • First Prize – IBM Center for Computational Health – supervised algorithm
5:30 pm – 6:30 pm

 

Read Full Post »


LIVE Day One – World Medical Innovation Forum ARTIFICIAL INTELLIGENCE, Boston, MA USA, Monday, April 8, 2019

 

www.worldmedicalinnovation.org

 

The Forum will focus on patient interactions across care settings, and the role technology and data can play in advancing knowledge discovery and care delivery. The agenda can be found here.

https://worldmedicalinnovation.org/agenda/

Leaders in Pharmaceutical Business Intelligence (LPBI) Group

represented by Founder & Director, Aviva Lev-Ari, PhD, RN will cover this event in REAL TIME using Social Media

@pharma_BI

@AVIVA1950

@PHSInnovation

#WMIF19 

@evanKristel 

Monday, April 8, 2019

7:00 am – 8:00 am
7:00 am – 5:00 pm
8:00 am – 9:40 am
Bayer Ballroom

First Look: Round 1

Nine rapid fire presentations on the applications of AI in Clinical Care

To view speakers and topics, click here.

Henry Chueh, MD

Director, MGH Lab of Computer Science, MGH; Assistant Professor, Medicine, HMS

Dxplain: Expanding diagnostic horizons

 

Synho Do, MD

Director, Laboratory of Medical Imaging and Computation (LMIC), MGH; Assistant Professor, HMS

Leveraging a Deep-Learning Algorithm for the Detection of Acute Intracranial Hemorrhage

 

Laura Germine, PhD

Director, Laboratory for Brain and Cognitive Health Technology, McLean; Assistant Professor, Psychiatry, HMS

The Next Generation of Cognitive and Behavioral Assessment

 

Satrajit Ghosh, PhD

Research Associate, MEE; Principal Research Scientist, MIT; Assistant Professor, Otolaryngology, HMS

Assistive Intelligent Technologies for Brain Health

 

Chris Sidey-Gibbons, PhD

Co-Director, PROVE Center, BH; Member of Faculty, HMS

Three Computational Techniques and One Tool to Bring the Patient Voice into Care

 

Xudong Huang, PhD

Co-Director, Neurochemistry Laboratory; MGH; Associate Professor, Psychiatry, HMS

Leveraging Artificial Intelligence for Brain Drug Discovery

 

Tina Kapur, PhD

Executive Director, Image-Guided Therapy, BH; Assistant Professor, Radiology, HMS

Using AI to Better Visualize Needles in Ultrasound-Guided Liver Biopsies

 

Bharti Khurana, MD

Director, Emergency Musculoskeletal Radiology, BH; Assistant Professor, HMS

 

 

Vesela Kovacheva, MD, PhD

Attending Anesthesiologist, BH; Instructor, Anesthesiology, HMS

Harnessing the Power of Machine Learning to Automate Drug Infusions in the OR and ICU

Constance Lehman, MD, PhD

Chief, Breast Imaging Division, MGH; Professor of Radiology, HMS

AI-Based Care Delivery: A New Paradigm for Curing Cancer

 

Lisa Nickerson, PhD

Director, Applied Neuroimaging Statistics Lab, McLean; Assistant Professor, HMS

Using Digital Phenotyping and Machine Learning to Forecast, Detect, and Prevent Drug Overdose Deaths

 

Federico Parisi, PhD

Research Fellow, Wyss Institute for Biologically Inspired Engineering, SRN

Mobile Health Technologies for Monitoring Motor Fluctuations in Patients with Parkinson’s Disease

 

Stuart Pomerantz, MD

Director, Neuro-CT, Neuroradiology, MGH; Instructor, HMS

AI-Powered Diagnostic Reporting for Spinal MRI of Degenerative Disease

 

Sandro Santagata, MD, PhD

Assistant Professor, Pathology, BH, HMS

 

Joseph Schwab, MD

Chief, Orthopaedic Spine Surgery, MGH; Associate Professor, HMS

Artificial Intelligence for Diagnosis and Management in Spine Surgery

 

Hiroyuki Yoshida, PhD

Director, 3D Imaging Research, MGH; Associate Professor, Radiology, HMS

 

Nazlee Zebardast, MD

Instructor, Ophthalmology, MEE, HMS

 

Li Zhou, MD, PhD

Associate Professor/Lead Investigator, BH; Associate Professor, HMS

 

Machine Learning and NLP to Track Disease Progression and Predict Health Outcomes

Moderator: Giles Boland, MD
  • Chair, Department of Radiology, BH; Philip H. Cook Professor of Radiology, HMS
Moderator: Trung Do
  • VP, Business Development, Innovation, PHS

Henry Chueh, MD

  • wrong diagnosis, leading malpractice claims
  • 1 out of 6 new diagnosis are wrong
  • help clinicians to make 1st diagnosis and every time correct — what need be considered
  • fever, rash, arthrisis (painful swallen joint) – no correct diagnosis
  • Adult Still disease – symptoms trigger condition –
  • DXplain Knowledge base + algorithms curated over 25 yr
  • >1 Million relationships
  • probabilistic inference algorithms
  • Amazon Web Services – micro services on Amazon Web
  • UI widgets for Web apps – mobile prototype
  • 20million hits per month
  • DXplain consumer, clinician, hospitals, payer, malpractice insurer

 

Synho Do, PhD

  • AI and DL for Stroke Patient management detection of acute intracranial haemorrhage from small dat sets
  • 1 of every 10 death is a Stroke caused, 5.8 million people die of Stroke Stroke is a medical emergency, CT Scan
  • Spotting brain bleeding after
  • Deep Learning algorithms – explainable AI  – human mimiking algorithm developed @MGH
  • Explainable AI – Multi-window mixing & multi-slice mixing is in PACS @MGH
  • commercial opportunity: Near stroke detection
  • @MGH Stroke with AI algorithms Patent IP @PartnerInnovation seeking funding for Stroke management

Laura Germine, PhD

  • Next generation of behavior assessment
  • in Psychiatry – neuropsychiatry
  • Problem of measurement of innovation with validity needed – Tools to measure and have outcomes
  • Unreasonable effectiveness of Good Data : Math achievement – visual-spatial attention
  • Looking for partners

Satrajit Ghosh, PhD

  • Mental health 1 in 4 adults 18% of adolescence 13% of children
  • first treatment effective only in 25% of cases
  • Brain structure and Function – using MR – observed behaviors – using Voice, speaking is a very complex activity
  • Talk intent emotions – window into the mind
  • Speech

Xudong Huang, PhD

  • Brain Drug Discovery – leveraging AI
  • Major depressive DIsorder ( MDD) – 16 million in US 210 Billion a year treatment burden
  • Alzheimer’s DIsease  – 5.8 million AS in US – $290 in 2019 a year treatment burden
  • Potential druggable for MDD and AD
  • Tryptophan-Kynurenina pathway
  • Secreted Protein Acidic and Cysteine rich
  • AI-Powered Drug Discovery Platform – AtomNet
  • Preclinical drug discovery and development
  • Screened 10MIllion compounds – 48 inhibitors for tryptophan-catabolizing enzymes in
  • Tryptophan-Kynurenina pathway

Tina Kapur, PhD

  • AI to visualize needles in UltraSound-guided (US) liver biopsy – safer to patient and easier for the physicina
  • mass in liver suspected to be from a metastasis in the pancreas
  • AI to enable the MD to see the needle completely independent of the US technician
  • Benefits if available to all performers of liver biopsy
  • Patients: Benefit from location of tissue biopsy sampling
  • prostate needle in MRI
  • Button labelled Needle, MD turn on/of button
  • navigation systems not in use
  • 95% proceedures done free hand
  • 1 Million US guided liver biopsy/yr, growing @4%
  • manufacturing of US equipment to be interested to embed

Bharti Khurana, MD

  • Home is the most dangerous place for women killing of women hit by husband. ages 25 to 38 – fracture of bone IPV – Intimate Partner Violence – 1 in 4 women and 1 in 9 men IPV is preventable under reporting
  • Tybanny of the Urgent
  • clinical decision support to predict risk probability automate alerts 95% 50% 15% – Probability of IPV – insivible to visible
  • empower healthcare providers
  • reduce ER volume will reduce cost

Vesela Kovacheva, MD, PhD

  • Titrating drug infusions – Personalized for patient safety reduce med error
  • Titrating drug infusions – automation system from anestesia – function automonically
  • local anestatic for Cesearian section – BP drog when spinal administration of anestatic agent
  • calculate every minure – 20 minutes are critical from drug infusion
  • decision to administer vasopressors is taken evey minute on the bP
  • Rural areas one anestosiolog suverviser three OR at the same time
  • 1.25 million C-section
  • 75% develop low BP
  • complications in babies decreased BP – tachepnis in neonatal – NICU 100Million $ per year.
  • develop same algorithms for propofol in sedetion and insulin in ICU
  • other surgeries – knee, hip, spinal

Constance Lehman, Md, PhD

  • Breast Cancer Out of 2 Billion women 2million will be diagnosed with breast cancer
  • screening will prevent development
  • current tools of mamography – no single interpretation and shortage
  • memograph vs Future risk of BC development
  • Deep Learning model; Training model consequitive memograms Risk model developed – AI technology on memograpm 0.71 when other factors added
  • DIverse races – RAce blind AI model
  • AI model of diagnosis in one year after the memogram taken
  • breast density – imager certified, 6% are dense, 85% and every number in between
  • Expertise: MGH, MIT, Prior failure of CAD
  • Patents for commercialization beyond MGH

Lisa Nickerson, PhD

  • 70,000 drug overdose, 50,000 opioids related
  • Death from prescription opioids is on the increase after 2013 – fentanyl – causing overdose
  • prescription opioids overdose Prevention strategies:
  • Targeted Naloxone distribution
  • Medication assisted treatment
  • Fentanyl screening in Tox tests
  • 911 good Samaritan laws
  • Syringe services programs

Federico Parisi, PhD

  • Mobile Health Applications – Monitoring motor fluctuation in Parkinson’s Disease (PD)
  • 7 – 10Million WOrldwide, 1 Million in the US,
  • dopamine-producing neuron
  • main medication in early stage – Levodopa
  • Need an objective and continuous monitoring toool for tacking the symptoms’ dynamics
  • mHealth for monitoring PD – mimiking clinical evaluations mail limitations: Deendency on standardized motor tasks in sufficient time resolution in symptoms severity during ADLs

Stuart Pomerantz, MD

  • DeepSPINE – Challenges of Lumbar Spine Imaging: Lumbar stenosis MR interpretation Suboptimal radiology
  • DeepSPINE – end-to-end processing pipeline for clinical deployment
  • AI-Powered Diagnosis & Reporting Solutions
  • DeepSPINE: Slice Angle Optimization
  • Predict disease severity/interpretation time
  • Route of optimal staffing
  • DeepSpine Data Layer Multi-Format Reporting: Traditional Text vs Tabular Image-Enhanced
  • Portfolio of applicationsWho benefits from MRI
  • Avoid unneccesary imaging – Clinical Decision-aking
  • Better predict who needs surgery

Sandro Santagata, MD, PhD

  • Tissue imaging quant pathology
  • DL for Mass spectrometry – full spectral resolution
  • interoperative paradigm – patient, biopsy, frozen tissue Tissue cyclic immunoflorescence hi Dimensional pathology
  • Human Tumor Atlas Network (HTAN) – phenotype cancers

Joseph Schwab, MD

  • Orthopedic Spin surgery – 1/2 million lumber fusion surgery, 5% complications $1.8 Billion
  • Data science in Spine today – algorithms based on 35,000 patients cases annotated
  • ML algorithm which Pations will need opioids after fusion
  • Predicted Probability – cost-benefit ration – Benefit to patient
  • Cervical stenosis C5-C6 – patient list of current medication – Prediction of a patient probability to need opioids after spinal surgery
  • Spinal metastasis – Survival prediction – is surgery needed if survival is few months?
  • Complications of hip replacement Perspective: Provider or Insurer
  • SORG-AI.com

Chris Sidey-Gibbons, PhD

  • Patient-reported data
  • identification of treatment satisfaction with care, quality of life, mental health,
  • ONE Questionnaire – filled by Patient – used by psychiatry since 1950
  • Clinical meaning, ML, Computer Adaptive Diagnosis (CAT algorithm) , NLP, response burden
  • ML – improve clinical meaning of Patient reported data, train algorithm – likely outcomes
  • Reconstructive surgery following mastectomy – survey of women
  • Plastic surgery Report – to improve CAT algorithm
  • imPROVE
  • InSpire

Hiroyuki Yoshida, PhD

  • Colon screening 150,000 new cases in the US, 55,000 death, 14B spent in the US
  • CT colonography (CTC)  & Colonoscopy
  • @MGH Laxative-free CT colonography: Oral oral contrast  followed by GI CT Scanning
  • GAN – generative adversarial networks: AI virtual bowel cleansing + AI small polyp detection
  • algorithms remove fecal material
  • Sensitivity: AI-latex-free – 96% sensitivity vs. CTC 46% and Laxative 67%

Nazlee Zebardast, MD

  • Deep learning for glaucoma detection – prevent
  • optic nerve disease, irriversible blindness
  • 76 Million 11 Million bilateral blind
  • +50% glacauma not diagnosed in the US – delay progression by screening
  • No reliable out reach programs – USPSTF recommended against screening
  • Deep learning used for Glaucoma detection _ Larger inter-reader interpretation variation
  • Improve reference standard
  • genetic risk of glaucoma
  • intaocular pressure – modifiable factor
  • Diabetic or non diabetic retinopathy
  • Age, gender, smokin SBP, refractive error
  • What the machine pays attention
  • high IOP and high genetic risk
  • commercialize DL based screening tool for glaucoma – 140 Million in the US
  • The market: 120 million age 30 to 40
  • Cost saving S5.8 Billion

Li, Zhou, MD, PhD

  • Palliative care ML and improve value of care
  • end of life care for Dementias: Latent topic modeling and trend analysis using clinical notes
  • reduce anxiety and depression patient more likely to have wishes known
  • Who are the patients that will benefit the most from palliative care
  • determine the right time for this intervention
  • free-text EHR data
  • Physical function status: Nutrition, feeding, swallowing
  • Commercialization – MTERMS Lab – pharmacovigilance, speech recognition, information extraction and decoding data mining

 

9:40 am – 9:55 am
9:55 am – 11:35 am
Bayer Ballroom

First Look: Round 2

Nine rapid fire presentations on the applications of AI in Clinical Care

To view speakers and topics, click here.

11:30 am – 11:45 am
11:45 am – 1:00 pm

Discovery Café Sessions

Lunch with Experts: Intensive sessions addressing cutting-edge artificial intelligence topics.

Applying AI to Save Lives During the Opioid Crisis

The U.S. is in the throes of a devastating epidemic of opioid addiction and overdose — some 130 people die nationally every day from opioids, says the National Institute on Drug Abuse. With a total economic cost of more than $78 billion a year, AI is being harnessed to develop new tools that can help alleviate this national crisis. This session will discuss AI-based strategies that academic and industry teams are leveraging to help clinical and public health officials better predict, identify, and treat opioid addiction, and also data privacy concerns.

Moderator: Thomas Sequist, MD, Chief Quality & Safety Officer, PHS

Bob Burgin, CEO, Amplifire Healthcare Alliance

Carm Huntress, CEO, RxRevu Inc

Sarah Wakeman, MD, Medical Director, Substance Use Disorder Initiative, MGH; Assistant Professor, Medicine, HMS

Scott Weiner, MD, Director, Brigham Comprehensive Opioid Response and Education (B-CORE) Program, BH; Assistant Professor, HMS

 

Community Hospitals: Key Component in Healthcare Transformation

Community hospitals are the largest sources of patient care in the U.S. As such, they represent a frontier in the transformation of health care. How are these organizations using AI and digital technologies to drive transformation? What are the distinctions from academic medical centers? This session will address these and other topics that impact community hospitals.

Moderator: Michael Jaff, DO, President, NWH, PHS, Professor of Medicine, HMS

Fabien Beckers, PhD, CEO, Arterys

Joanna Geisinger, CEO, TORq Interface

John Miller, MD, Director, Retinal Imaging, MEE; Assistant Professor, Ophthalmology, HMS

Lee Schwamm, MD, Director, Center for TeleHealth and Exec Vice Chair, Neurology, MGH; Professor, Neurology, HMS

Tal Wenderow, CEO, Beyond Verbal

 

Digital Management of Diabetes

Across the spectrum of patient care, the management of diabetes has been flooded with new technology and treatment options for both type 1 and type 2 diabetes – there is a range of new devices and software, including automatic insulin infusion systems, glucose sensors, AI-based algorithms and decision support tools, with an artificial pancreas on the horizon. This session will focus on these areas and clinical use cases that highlight the value of AI.

Moderator: Deborah Wexler, MD, Clinical Director, Diabetes Center, MGH; Associate Professor, HMS

Marie McDonnell, MD, Section Chief and Director, Diabetes Program, BH; Lecturer, HMS

Michael Meissner, PhD, CTO and VP, MED, Sanofi

Joshua Riff, MD, CEO, Onduo

Marie Schiller, VP, Connected Care and Insulins Product Development and Site Head, Cambridge Innovation Center, Eli Lilly

 

AI and Its Impact on the Future of Emergency Care

There are over 136 million Emergency Department visits annually in the U.S. providing 24/7 unscheduled treatment for problems from minor illness to life threatening traumatic injuries.  Emergency department care teams provide high quality, safe care in an efficient fashion.  In this session, we consider the future of AI in emergency care from the initial decision to seek emergency care, to diagnostic processes within the ED and final disposition decision..  From chat bots for patient triage, telehealth for patient visits to machine learning outcome prediction, we will consider how these novel technologies will impact emergency care delivery.

Moderator: Adam Landman, MD, VP and CIO, BH; Associate Professor of Emergency Medicine, HMS

Peter Chai, MD, Assistant Professor, Emergency Medicine, BH, HMS

Emily Hayden, MD, Attending Physician, Emergency Medicine, MGH; Instructor, Surgery, HMS

Kohei Hasegawa, MD, Attending Physician, Emergency Medicine, MGH; Associate Professor, Emergency Medicine, HMS

Sean Kelly, MD, CMO, Imprivata; Assistant Professor, Emergency Medicine, HMS

Bijoy Sagar, VP, Chief Digital Technology Officer, Stryker

 

Mental Health, Smartphone Apps and the Promise of AI

Patients can face significant barriers when it comes to accessing high-quality, evidence-based treatment for mental illness. AI-enabled technologies, including smartphone-based tools, that may help close this treatment gap for patients worldwide. This session will focus on efforts to develop smartphone apps and other tools, including those designed to help predict patients’ moods and provide cognitive behavioral therapy.

Moderator: Sabine Wilhelm, PhD, Chief of Psychology; Director, OCD and Related Disorders Program, MGH; Professor, Psychology, HMS

Jennifer Gentile, PsyD, SVP, US Clinical Operations, Ieso Digital Health

Thomas McCoy, MD, Director of Research, Center for Quantitative Health, MGH; Assistant Professor, Psychiatry and Medicine, HMS

Christopher Molaro, CEO, Neuroflow

David Silbersweig, MD, Chairman, Department of Psychiatry, BH; Stanley Cobb Professor of Psychiatry, HMS

Jeremy Sohn, VP, Global Head of Digital Business Development and Licensing , Novartis

 

From Startup to Impact (Pharma and Diagnostics)

This session will introduce you to five leading start-up companies who will each share their respective impact in the pharmaceutical and diagnostic realms in 10-minute pitches.

Moderator: James Brink, MD, Radiologist-in-Chief, MGH; Juan M. Taveras Professor of Radiology, HMS

Moderator: James Nicholls, Managing Director, Fitzroy Health

Sarah Beeby, EVP, GM Lifesciences, Clinithink

Charles Cadieu, PhD, CEO, Bay Labs

JB Michel, PhD, SVP Data Science & GM USA, BenevolentAI

Art Papier, MD, CEO, VisualDx

Alex Zhavoronkov, PhD, CEO, Insilico Medicine, Inc

1:00 pm – 1:15 pm
1:15 pm – 1:30 pm
Bayer Ballroom

Opening Remarks

  • Interim President and CEO, Chief Academic Officer, PHS; Laurie Carrol Guthart Professor of Medicine, HMS; 2019 Forum Co-Chair
1:30 pm – 2:00 pm
Bayer Ballroom

AI Strategy: AI from the Top

As the potential of AI comes into clearer view, many academic medical centers are taking notice and crafting institutional strategies for incorporating AI into clinical practice. But where are the most meaningful opportunities? What are the biggest challenges? And, importantly, will patient care be noticeably different — better, more available, and/or less costly?

  • Board Member, PHS; President Emerita and Professor of Neuroscience, MIT
  • Cross institutional cooperation is advocated
  • AI – what it will deliver in 2 years
  • what is the role of the Top management
  • how we mwasure how we do
  • Ethics and bias  in AI vs non-AI World
  • Chief Data Science Officer, PHS; Vice Chairman, Radiology, MGH; Associate Professor, Radiology, HMS
  • scaling Machine learning focused areas high accuracy, training ground truth, today the humans establish it in the future with AI ground truth will be created by AI
  • how to handle and move the intelligence and discoveries across units
  • Chief Digital Health Officer, PHS
  • Digitization of documentation – recording the session, Nauance – AI does the borden of communication translation
  • Easy button comparison of f patients wwith same ocndition what was the treatment
  • Chief Clinical Officer, PHS; Professor of Medicine, HMS; 2019 Forum Co-Chair
  • Future 5-10 years EHR is dehumanizing at present but with AI EHR will humanize again the relations of Physician and Patients

 

2:00 pm – 2:30 pm
Bayer Ballroom

1:1 Fireside Chat: Jensen Huang, CEO, NVIDIA

Introduction by: Cathy Minehan
  • Managing Director, Arlington Advisory Partners; Chairman, Board of Trustees, MGH
  • Chief Data Science Officer, PHS; Vice Chairman, Radiology, MGH; Associate Professor, Radiology, HMS
  • CEO, NVIDIA, established in 1993 graphics, Genomics analysis
  • storage data validation and
  • AI is reinventing computer graphics taught a NN to produce animation by virtual reality in robotics
  • in next three year: Crypo-currency was not foreseen
  • Data Science ingesting data , processing doing analytics
  • RAPIDS – open source data centers clouds and the edge working together
  • AI needs to be at the edge computing to be create at the edge not in the Cloud
  • self driving cars computation odne at the edge
  • Redundence and diversity – approach is diverse
  • In Radiology – democratization of AI announced today with NVIDIA & Partners
  • Driver intervene, Radiologist will intervene
  • Concept of “Beta” – Cloud application is in Beta
  • SW: data driven algorithm written by AI and know to learn amazing results
  • Conditions for NVIDIA to succeed: Speed, SW defined, pipeline flow data curated validated
  • expertise in the company
  • In 5 years: breakthrough NLP – summarize what was said
  • Curations done by AI
  • One shot learning – AI contextual aware Knowing who goes where, when and what acronyms are
  • AI: is software – yes SW that writes SW AI is automation of Automation

 

2:30 pm – 2:45 pm
Bayer Ballroom

Remarks: The Honorable Charlie Baker

Introduction by: Scott Sperling
  • Co-President, Thomas H. Lee Partners; Chairman of the Board of Directors, PHS
  • Governor of the Commonwealth of Massachusetts
  • AI to assist practitioners in their decisions
  • Information explotions to clinician
  • medical infrastructure needs AI
  • Healthcare is held to a higher standard, people believe in Practitioners – Healthcare is held in very high esteem

 

2:45 pm – 3:35 pm
Bayer Ballroom

Real World Evidence and Trial Optimization in the AI Era

AI is a tool for conducting faster, more efficient clinical trials. Panelists will discuss how AI-enabled methods can further adaptive trial capabilities, trial design and trial management.

Moderator: Thomas Lynch, MD
  • EVP and CSO, R&D, Bristol-Myers Squibb
  • why sharing data is so hard?
  • IBM Watson – PDF can be read by Watson and come out with a Diagnosis
  • Deputy Commissioner, FDA
  • AI assists in recruitment
  • Modernization of clinical trial is acknowledged
  • Data standards for EHR oncology context
  • EVP MA&PV and Bayer CMO, Bayer AG
  • control arms in rare diseases
  • diagnostics in hypertension
  • drug safety – #AI works
  • Chief Architect, Microsoft Healthcare
  • sharing data semantic interoperability is available
  • No clinical data model
  • Which symptoms actual were experienced?
  • Blockchain
  • CEO, My Own Med Inc.
  • Wearable Pharma is adding this dimens
  • Executive Director, Clinical Trials Office, PHS; Associate Professor of Medicine, HMS
  • computation, pattern recognitions to make CT more efficient
  • competitive model among sponsors hinders data sharing
3:35 pm – 4:25 pm
Bayer Ballroom

AI Driven Value-Based Care

As providers embrace value-based approaches, the demands of clinical data collection, assessment, and information-sharing loom large. In this data-driven environment, clinicians must sift through ever-growing pools of information that can exceed the limits of human capability. An assortment of AI-based solutions is now emerging that may offer some relief. Panelists will discuss how these approaches are helping to support better, more personalized care, and the challenges faced by clinicians and managers for effective adoption.

Moderator: Timothy Ferris, MD
  • CEO, MGPO; Professor of Medicine, HMS
  • CEO, American Heart Association
  • guideline on HTN, 1/2 million wake up with HTN a day after guidelines were enacted
  • AI will not be able to replace a clinician encouraging a patient
  • AI to free time of HC professional
  • EVP, President, Network Solutions, Change Healthcare
  • 1 trillion $ is wasted Healthcare is not consumer friendly #AI has opportunities to innovate home-based solutions
  • consumer focus technologies hand held devices
  • Levers
  • CEO, NHS England
  • AI can free time for health professionals
  • diagnostics
  • productivity in Healthcare has impact of the entire econommy US – 3 trillions size of HC sector
  • 2 1/2 million literature new to clinician evry year – AI will assist
  • Clinician explainability is very important
  • AI to benefit Healthcare for all
4:25 pm – 5:15 pm
Bayer Ballroom

Cardiovascular Care: Reinvented Through AI

Cardiovascular diseases remain the leading cause of death worldwide and an expense, making this area ripe for AI-enabled innovations. Teams are pursuing a range of AI-based tools in cardiovascular medicine: including AI-powered drug discovery and diagnostics to automated cardiac image analyses and AI-guided care delivery pathways. Panelists will discuss where AI is having a sizeable impact. The discussion will also include the perspectives of a patient who benefited from AI-enabled cardiovascular care.

  • Vice Chair for Scientific Innovation, Department of Medicine, BH; Associate Professor of Medicine, HMS
  • SVP, Global Head of Digital and Analytics, Sanofi
  • COTY in Copenhagen – AI augment capability of EMTs dispatcher is prompted with questions to decide if this call is Heart arrest caving few minutes for EMT response
  • Patient
  • Independent Recording Engineer Burke Recording
  • President, Bayer Pharma Americas Region, Bayer
  • In-silicon modeling is AI based and shorten cycle of drug discovery
  • Bridge clinical care and with clinical trials
  • Challenge island of dat are disconnected,
  • Chief Cardiovascular Imaging, MGH; Professor, Radiology, HMS

 

  • To see a neurologist you need to have an MRI done already
  • Chest CT, Abdominal CT Chest X-ray — done
  • CVD CT report five pages long, prognostics — AI will tell MD what medication to suggest
  • clinical care more standardized
  • AI in clinical trial is a big premise
  • No more trials if perpatient the cost id more than $5,000
  • AI is a tool to enable lower cost clinical trials
  • imaging data sharing in what ever form
  • ML and AI at all Radiology conferences
  • QA criteria – what is quality data, to inform care
  • EVP/GM, Healthcare and Life Sciences, Persistent Systems
  • How to use AI clinical work flow goal – to be sw driven AI is a component
  • large systems sw automation data and platform dat acapture is very importnat
5:15 pm – 5:45 pm
Bayer Ballroom

1:1 Fireside Chat: Seema Verma, Administrator, Centers for Medicare & Medicaid Services

Moderator: Sree Chaguturu, MD
  • Chief Population Health Officer, PHS; Assistant Professor, Medicine, HMS
  • Administrator, Centers for Medicare and Medicaid Services
  • 2020 20% of all expenses spent will be on Healthcare in the US
  • Gov’t was a barrier to innovations
  • initiative of cutting regulations
  • innovation – how we pay providers for value produced vs regulation that stay in the way
  • gov’t slow to respond: FDA approval and CMS access to treatment and reimbursement
  • Analysis of drug a patient takes, CMS – quality, medical record given to patient across all providers they use and be able to give to a new provides all historical data
  • Data privacy and security
  • Innovators in Colorado – health care cost need be lowered in a major way
5:45 pm – 6:45 pm

Read Full Post »


The Regulatory challenge in adopting AI

Author and Curator: Dror Nir, PhD

In the last couple of years we are witnessing a surge of AI applications in healthcare. It is clear now, that AI and its wide range of health-applications are about to revolutionize diseases’ pathways and the way the variety of stakeholders in this market interact.

Not surprisingly, the developing surge has waken the regulatory watchdogs who are now debating ways to manage the introduction of such applications to healthcare. Attributing measures to known regulatory checkboxes like safety, and efficacy is proving to be a complex exercise. How to align claims made by manufacturers, use cases, users’ expectations and public expectations is unclear. A recent demonstration of that is the so called “failure” of AI in social-network applications like FaceBook and Twitter in handling harmful materials.

‘Advancing AI in the NHS’ – is a report covering the challenges and opportunities of AI in the NHS. It is a modest contribution to the debate in such a timely and fast-moving field!  I bring here the report’s preface and executive summary hoping that whoever is interested in reading the whole 50 pages of it will follow this link: f53ce9_e4e9c4de7f3c446fb1a089615492ba8c

Screenshot 2019-04-07 at 17.18.18

 

Acknowledgements

We and Polygeia as a whole are grateful to Dr Dror Nir, Director, RadBee, whose insights

were valuable throughout the research, conceptualisation, and writing phases of this work; and to Dr Giorgio Quer, Senior Research Scientist, Scripps Research Institute; Dr Matt Willis, Oxford Internet Institute, University of Oxford; Professor Eric T. Meyer, Oxford Internet Institute, University of Oxford; Alexander Hitchcock, Senior Researcher, Reform; Windi Hari, Vice President Clinical, Quality & Regulatory, HeartFlow; Jon Holmes, co-founder and Chief Technology Officer, Vivosight; and Claudia Hartman, School of Anthropology & Museum Ethnography, University of Oxford for their advice and support.

Author affiliations

Lev Tankelevitch, University of Oxford

Alice Ahn, University of Oxford

Rachel Paterson, University of Oxford

Matthew Reid, University of Oxford

Emily Hilbourne, University of Oxford

Bryan Adriaanse, University of Oxford

Giorgio Quer, Scripps Research Institute

Dror Nir, RadBee

Parth Patel, University of Cambridge

All affiliations are at the time of writing.

Polygeia

Polygeia is an independent, non-party, and non-profit think-tank focusing on health and its intersection with technology, politics, and economics. Our aim is to produce high-quality research on global health issues and policies. With branches in Oxford, Cambridge, London and New York, our work has led to policy reports, peer-reviewed publications, and presentations at the House of Commons and the European Parliament. http://www.polygeia.com @Polygeia © Polygeia 2018. All rights reserved.

Foreword

Almost every day, as MP for Cambridge, I am told of new innovations and developments that show that we are on the cusp of a technological revolution across the sectors. This technology is capable of revolutionising the way we work; incredible innovations which could increase our accuracy, productivity and efficiency and improve our capacity for creativity and innovation.

But huge change, particularly through adoption of new technology, can be difficult to  communicate to the public, and if we do not make sure that we explain carefully the real benefits of such technologies we easily risk a backlash. Despite good intentions, the care.data programme failed to win public trust, with widespread worries that the appropriate safeguards weren’t in place, and a failure to properly explain potential benefits to patients. It is vital that the checks and balances we put in place are robust enough to sooth public anxiety, and prevent problems which could lead to steps back, rather than forwards.

Previous attempts to introduce digital innovation into the NHS also teach us that cross-disciplinary and cross-sector collaboration is essential. Realising this technological revolution in healthcare will require industry, academia and the NHS to work together and share their expertise to ensure that technical innovations are developed and adopted in ways that prioritise patient health, rather than innovation for its own sake. Alongside this, we must make sure that the NHS workforce whose practice will be altered by AI are on side. Consultation and education are key, and this report details well the skills that will be vital to NHS adoption of AI. Technology is only as good as those who use it, and for this, we must listen to the medical and healthcare professionals who will rightly know best the concerns both of patients and their colleagues. The new Centre for Data Ethics and Innovation, the ICO and the National Data Guardian will be key in working alongside the NHS to create both a regulatory framework and the communications which win society’s trust. With this, and with real leadership from the sector and from politicians, focused on the rights and concerns of individuals, AI can be advanced in the NHS to help keep us all healthy.

Daniel Zeichner

MP for Cambridge

Chair, All-Party Parliamentary Group on Data Analytics

 

Executive summary

Artificial intelligence (AI) has the potential to transform how the NHS delivers care. From enabling patients to self-care and manage long-term conditions, to advancing triage, diagnostics, treatment, research, and resource management, AI can improve patient outcomes and increase efficiency. Achieving this potential, however, requires addressing a number of ethical, social, legal, and technical challenges. This report describes these challenges within the context of healthcare and offers directions forward.

Data governance

AI-assisted healthcare will demand better collection and sharing of health data between NHS, industry and academic stakeholders. This requires a data governance system that ensures ethical management of health data and enables its use for the improvement of healthcare delivery. Data sharing must be supported by patients. The recently launched NHS data opt-out programme is an important starting point, and will require monitoring to ensure that it has the transparency and clarity to avoid exploiting the public’s lack of awareness and understanding. Data sharing must also be streamlined and mutually beneficial. Current NHS data sharing practices are disjointed and difficult to negotiate from both industry and NHS perspectives. This issue is complicated by the increasing integration of ’traditional’ health data with that from commercial apps and wearables. Finding approaches to valuate data, and considering how patients, the NHS and its partners can benefit from data sharing is key to developing a data sharing framework. Finally, data sharing should be underpinned by digital infrastructure that enables cybersecurity and accountability.

Digital infrastructure

Developing and deploying AI-assisted healthcare requires high quantity and quality digital data. This demands effective digitisation of the NHS, especially within secondary care, involving not only the transformation of paper-based records into digital data, but also improvement of quality assurance practices and increased data linkage. Beyond data digitisation, broader IT infrastructure also needs upgrading, including the use of innovations such as wearable technology and interoperability between NHS sectors and institutions. This would not only increase data availability for AI development, but also provide patients with seamless healthcare delivery, putting the NHS at the vanguard of healthcare innovation.

Standards

The recent advances in AI and the surrounding hype has meant that the development of AI-assisted healthcare remains haphazard across the industry, with quality being difficult to determine or varying widely. Without adequate product validation, including in

real-world settings, there is a risk of unexpected or unintended performance, such as sociodemographic biases or errors arising from inappropriate human-AI interaction. There is a need to develop standardised ways to probe training data, to agree upon clinically-relevant performance benchmarks, and to design approaches to enable and evaluate algorithm interpretability for productive human-AI interaction. In all of these areas, standardised does not necessarily mean one-size-fits-all. These issues require addressing the specifics of AI within a healthcare context, with consideration of users’ expertise, their environment, and products’ intended use. This calls for a fundamentally interdisciplinary approach, including experts in AI, medicine, ethics, cognitive science, usability design, and ethnography.

Regulations

Despite the recognition of AI-assisted healthcare products as medical devices, current regulatory efforts by the UK Medicines and Healthcare Products Regulatory Agency and the European Commission have yet to be accompanied by detailed guidelines which address questions concerning AI product classification, validation, and monitoring. This is compounded by the uncertainty surrounding Brexit and the UK’s future relationship with the European Medicines Agency. The absence of regulatory clarity risks compromising patient safety and stalling the development of AI-assisted healthcare. Close working partnerships involving regulators, industry members, healthcare institutions, and independent AI-related bodies (for example, as part of regulatory sandboxes) will be needed to enable innovation while ensuring patient safety.

The workforce

AI will be a tool for the healthcare workforce. Harnessing its utility to improve care requires an expanded workforce with the digital skills necessary for both developing AI capability and for working productively with the technology as it becomes commonplace.

Developing capability for AI will involve finding ways to increase the number of clinician-informaticians who can lead the development, procurement and adoption of AI technology while ensuring that innovation remains tied to the human aspect of healthcare delivery. More broadly, healthcare professionals will need to complement their socio-emotional and cognitive skills with training to appropriately interpret information provided by AI products and communicate it effectively to co-workers and patients.

Although much effort has gone into predicting how many jobs will be affected by AI-driven automation, understanding the impact on the healthcare workforce will require examining how jobs will change, not simply how many will change.

Legal liability

AI-assisted healthcare has implications for the legal liability framework: who should be held responsible in the case of a medical error involving AI? Addressing the question of liability will involve understanding how healthcare professionals’ duty of care will be impacted by use of the technology. This is tied to the lack of training standards for healthcare professionals to safely and effectively work with AI, and to the challenges of algorithm interpretability, with ”black-box” systems forcing healthcare professionals to blindly trust or distrust their output. More broadly, it will be important to examine the legal liability of healthcare professionals, NHS trusts and industry partners, raising questions

Recommendations

  1. The NHS, the Centre for Data Ethics and Innovation, and industry and academic partners should conduct a review to understand the obstacles that the NHS and external organisations face around data sharing. They should also develop health data valuation protocols which consider the perspectives of patients, the NHS, commercial organisations, and academia. This work should inform the development of a data sharing framework.
  2. The National Data Guardian and the Department of Health should monitor the NHS data opt-out programme and its approach to transparency and communication, evaluating how the public understands commercial and non-commercial data use and the handling of data at different levels of anonymisation.
  3. The NHS, patient advocacy groups, and commercial organisations should expand public engagement strategies around data governance, including discussions about the value of health data for improving healthcare; public and private sector interactions in the development of AI-assisted healthcare; and the NHS’s strategies around data anonymisation, accountability, and commercial partnerships. Findings from this work should inform the development of a data sharing framework.
  4. The NHS Digital Security Operations Centre should ensure that all NHS organisations comply with cybersecurity standards, including having up-to-date technology.
  5. NHS Digital, the Centre for Data Ethics and Innovation, and the Alan Turing Institute should develop technological approaches to data privacy, auditing, and accountability that could be implemented in the NHS. This should include learning from Global Digital Exemplar trusts in the UK and from international examples such as Estonia.
  6. The NHS should continue to increase the quantity, quality, and diversity of digital health data across trusts. It should consider targeted projects, in partnership with professional medical bodies, that quality-assure and curate datasets for more deployment-ready AI technology. It should also continue to develop its broader IT infrastructure, focusing on interoperability between sectors, institutions, and technologies, and including the end users as central stakeholders.
  7. The Alan Turing Institute, the Ada Lovelace Institute, and academic and industry partners in medicine and AI should develop ethical frameworks and technological approaches for the validation of training data in the healthcare sector, including methods to minimise performance biases and validate continuously-learning algorithms.
  8. The Alan Turing Institute, the Ada Lovelace Institute, and academic and industry partners in medicine and AI should develop standardised approaches for evaluating product performance in the healthcare sector, with consideration for existing human performance standards and products’ intended use.
  9. The Alan Turing Institute, the Ada Lovelace Institute, and academic and industry partners in medicine and AI should develop methods of enabling and evaluating algorithm interpretability in the healthcare sector. This work should involve experts in AI, medicine, ethics, usability design, cognitive science, and ethnography, among others.
  10. Developers of AI products and NHS Commissioners should ensure that usability design remains a top priority in their respective development and procurement of AI-assisted healthcare products.
  11. The Medicines and Healthcare Products Regulatory Agency should establish a digital health unit with expertise in AI and digital products that will work together with manufacturers, healthcare bodies, notified bodies, AI-related organisations, and international forums to advance clear regulatory approaches and guidelines around AI product classification, validation, and monitoring. This should address issues including training data and biases, performance evaluation, algorithm interpretability, and usability.
  12. The Medicines and Healthcare Products Regulatory Agency, the Centre for Data Ethics and Innovation, and industry partners should evaluate regulatory approaches, such as regulatory sandboxing, that can foster innovation in AI-assisted healthcare, ensure patient safety, and inform on-going regulatory development.
  13. The NHS should expand innovation acceleration programmes that bridge healthcare and industry partners, with a focus on increasing validation of AI products in real-world contexts and informing the development of a regulatory framework.
  14. The Medicines and Healthcare Products Regulatory Agency and other Government bodies should arrange a post-Brexit agreement ensuring that UK regulations of medical devices, including AI-assisted healthcare, are aligned as closely as possible to the European framework and that the UK can continue to help shape Europe-wide regulations around this technology.
  15. The General Medical Council, the Medical Royal Colleges, Health Education England, and AI-related bodies should partner with industry and academia on comprehensive examinations of the healthcare sector to assess which, when, and how jobs will be impacted by AI, including analyses of the current strengths, limitations, and workflows of healthcare professionals and broader NHS staff. They should also examine how AI-driven workforce changes will impact patient outcomes.
  16. The Federation of Informatics Professionals and the Faculty of Clinical Informatics should continue to lead and expand standards for health informatics competencies, integrating the relevant aspects of AI into their training, accreditation, and professional development programmes for clinician-informaticians and related professions.
  17. Health Education England should expand training programmes to advance digital and AI-related skills among healthcare professionals. Competency standards for working with AI should be identified for each role and established in accordance with professional registration bodies such as the General Medical Council. Training programmes should ensure that ”un-automatable” socio-emotional and cognitive skills remain an important focus.
  18. The NHS Digital Academy should expand recruitment and training efforts to increase the number of Chief Clinical Information Officers across the NHS, and ensure that the latest AI ethics, standards, and innovations are embedded in their training programme.
  19. Legal experts, ethicists, AI-related bodies, professional medical bodies, and industry should review the implications of AI-assisted healthcare for legal liability. This includes understanding how healthcare professionals’ duty of care will be affected, the role of workforce training and product validation standards, and the potential role of NHS Indemnity and no-fault compensation systems.
  20. AI-related bodies such as the Ada Lovelace Institute, patient advocacy groups and other healthcare stakeholders should lead a public engagement and dialogue strategy to understand the public’s views on liability for AI-assisted healthcare.

Read Full Post »

Older Posts »