Leaders in Pharmaceutical Business Intelligence Group, LLC, Doing Business As LPBI Group, Newton, MA

• Chair, Department of Radiology, BH; Philip H. Cook Professor of Radiology, HMS

• 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

• Interim President and CEO, Chief Academic Officer, PHS; Laurie Carrol Guthart Professor of Medicine, HMS; 2019 Forum Co-Chair

• 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

• 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

• 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

• 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

• 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

• 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

• 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