Posts Tagged ‘Machine Learning (ML)’

Al is on the way to lead critical ED decisions on CT

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

Artificial intelligence (AI) has infiltrated many organizational processes, raising concerns that robotic systems will eventually replace many humans in decision-making. The advent of AI as a tool for improving health care provides new prospects to improve patient and clinical team’s performance, reduce costs, and impact public health. Examples include, but are not limited to, automation; information synthesis for patients, “fRamily” (friends and family unpaid caregivers), and health care professionals; and suggestions and visualization of information for collaborative decision making.

In the emergency department (ED), patients with Crohn’s disease (CD) are routinely subjected to Abdomino-Pelvic Computed Tomography (APCT). It is necessary to diagnose clinically actionable findings (CAF) since they may require immediate intervention, which is typically surgical. Repeated APCTs, on the other hand, results in higher ionizing radiation exposure. The majority of APCT performance guidance is clinical and empiric. Emergency surgeons struggle to identify Crohn’s disease patients who actually require a CT scan to determine the source of acute abdominal distress.

Image Courtesy: Jim Coote via Pixabay https://www.aiin.healthcare/media/49446

Aid seems to be on the way. Researchers employed machine learning to accurately distinguish these sufferers from Crohn’s patients who appear with the same complaint but may safely avoid the recurrent exposure to contrast materials and ionizing radiation that CT would otherwise wreak on them.

The study entitled “Machine learning for selecting patients with Crohn’s disease for abdominopelvic computed tomography in the emergency department” was published on July 9 in Digestive and Liver Disease by gastroenterologists and radiologists at Tel Aviv University in Israel.

Retrospectively, Jacob Ollech and his fellow researcher have analyzed 101 emergency treatments of patients with Crohn’s who underwent abdominopelvic CT.

They were looking for examples where a scan revealed clinically actionable results. These were classified as intestinal blockage, perforation, intra-abdominal abscess, or complex fistula by the researchers.

On CT, 44 (43.5 %) of the 101 cases reviewed had such findings.

Ollech and colleagues utilized a machine-learning technique to design a decision-support tool that required only four basic clinical factors to test an AI approach for making the call.

The approach was successful in categorizing patients into low- and high-risk groupings. The researchers were able to risk-stratify patients based on the likelihood of clinically actionable findings on abdominopelvic CT as a result of their success.

Ollech and co-authors admit that their limited sample size, retrospective strategy, and lack of external validation are shortcomings.

Moreover, several patients fell into an intermediate risk category, implying that a standard workup would have been required to guide CT decision-making in a real-world situation anyhow.

Consequently, they generate the following conclusion:

We believe this study shows that a machine learning-based tool is a sound approach for better-selecting patients with Crohn’s disease admitted to the ED with acute gastrointestinal complaints about abdominopelvic CT: reducing the number of CTs performed while ensuring that patients with high risk for clinically actionable findings undergo abdominopelvic CT appropriately.

Main Source:

Konikoff, Tom, Idan Goren, Marianna Yalon, Shlomit Tamir, Irit Avni-Biron, Henit Yanai, Iris Dotan, and Jacob E. Ollech. “Machine learning for selecting patients with Crohn’s disease for abdominopelvic computed tomography in the emergency department.” Digestive and Liver Disease (2021). https://www.sciencedirect.com/science/article/abs/pii/S1590865821003340

Other Related Articles published in this Open Access Online Scientific Journal include the following:

Al App for People with Digestive Disorders

Reporter: Irina Robu, Ph.D.


Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc


Al System Used to Detect Lung Cancer

Reporter: Irina Robu, Ph.D.


Artificial Intelligence: Genomics & Cancer


Yet another Success Story: Machine Learning to predict immunotherapy response

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc


Systemic Inflammatory Diseases as Crohn’s disease, Rheumatoid Arthritis and Longer Psoriasis Duration May Mean Higher CVD Risk

Reporter: Aviva Lev-Ari, PhD, RN


Autoimmune Inflammatory Bowel Diseases: Crohn’s Disease & Ulcerative Colitis: Potential Roles for Modulation of Interleukins 17 and 23 Signaling for Therapeutics

Curators: Larry H Bernstein, MD FCAP and Aviva Lev-Ari, PhD, RN https://pharmaceuticalintelligence.com/2016/01/23/autoimmune-inflammtory-bowl-diseases-crohns-disease-ulcerative-colitis-potential-roles-for-modulation-of-interleukins-17-and-23-signaling-for-therapeutics/

Inflammatory Disorders: Inflammatory Bowel Diseases (IBD) – Crohn’s and Ulcerative Colitis (UC) and Others

Curators: Larry H. Bernstein, MD, FCAP and Aviva Lev-Ari, PhD, RN


Read Full Post »

WORKFLOW for a Eight-Steps Medical Text Analysis Operation using NLP on LPBI Medical and Life Sciences Content

Author: Aviva Lev-Ari, PhD, RN with inputs related to Wolfram NLP Code by Madison Davis and Yash Choudhary

  • All INTERNS will work 50% on NLP and 50% on Synthetic Biology
  • Training will be offered
  • Protocol will be developed 
  • Software applications will be selected.
  • Mid September we will have an Internal Meeting on Mission #2, LPBI India before the Meeting with Dr. Nir
  • All Interns need to complete at least ½ an e-Book Eight-Step Workflow Protocol for NLP before starting the Synthetic Biology SW Training
  • This is the Eight-Step WORKFLOW Protocol for Medical Text Analysis using NLP at LPBI:
  • https://pharmaceuticalintelligence.com/2021/07/15/workflow-for-a-ten-steps-medical-text-analysis-operation-using-nlp-on-lpbi-medical-and-life-sciences-content/
  • Each INTERN Completing the 50% assignment on NLP will need to submit this table for his/hers NLP Book Assignment with a Check off mark for each article in each Chapter in the Book the intern was assigned for
  • This Table filled in serves as INPUT for QA of the work of the INTERN. Verification is needed for Internship completion for Certification purposes
NLPStep 1Step 2Step 3Step 4Step 5Step 6Step 7Step 8
Chapter 1, Article 1          
Chapter 1, Article n          
Chapter 2 Article 1          
Chapter 2, Article n          
Chapter 3, Article 1          
Chapter 3, Article n          
Chapter 4 Article 1          
Chapter 4, Article n          
Chapter 5, Article 1          
Chapter 5, Article n          
Chapter n Article 1          
Chapter n Article n          

Table Source :

Author: Aviva Lev-Ari, PhD, RN, 7/23/2021

This Table is the supporting evidence for:

LPBI’s WORKFLOW for Medical Text Analysis Operation using NLP on

LPBI Medical and Life Sciences Content


STEP 1: Create Merged .TXT File of Data for Semantic Analysis

  1. Go to Wolfram Cloud and login (use old or make free account)
  2. Make a new folder: click “New” then “Folder” in the corner of your dashboard
  3. Name your folder. This is where you’ll put your text files
  4. Make a new text file: click “New” then “Text” in the corner of your dashboard
  5. Name your text file.
  6. Put this text file in the folder you made.
  7. Copy and paste the text you want to analyze in the text file. The text can be from one article or multiple articles.
  8. Verify that the text has been saved by reopening the file. Sometimes you may need to repeat the process of copying and pasting text so it works.

STEP 2: Create Presentation Slides to Copy and Paste Data, Image Graphs Into

  1. Google Slides Example: Link
  2. Google Slides Template: Link

STEP 3: View this Document for a Guide on How to Make Semantics Graphs:

  1. Link
  2. Add graphs to presentation slides
  3. The link covers the following algorithms:
    1. 25 KeyWord Extraction
    2. Hypergraphs (make one hypergraph per article collection)
    3. Tree Diagrams (make one tree diagram per article collection)
    4. Bar Diagrams

STEP 4:  Use WordItOut.com and .TXT file per article to generated One WordCloud per article

  1. Go to WorditOut.com, as seen here: https://worditout.com/
  2. Click “Create Your Own”
  3. Copy and Paste the text of the article you want into the text box
  4. Click “Generate”
  5. Change the font to “serif”, disable “random on regenerate”
  6. Change the colors based on the following guidelines, although this is just a suggestion.
  7. Change the number of colors to 2, color blending method “Direct”
  8. Save the image
  9. Upload WordClouds to the Media Gallery and record Article title as Legend and Source for the graph, add your name as image producer and date
  10. Insert World Cloud in the Article following the Author/Curator’s name
  11. Place WordCloud in a one PowerPoint Presentation for the entire Article Collection

STEP 5: Transfer Powerpoint to DropBox

STEP 6: Create a .DOCX Interpretation File of Results

  1. Domain Knowledge Expert generates a .DOCX file with his expert interpretation of all the Insights drawn from the visualization artifacts generated by NLP, ML, AI when all the insights are put together for analysis and synthesis. Store the Expert interpretation into the Interpretation Folder.
  2. What are the clinical implications for patient treatment
  3. What are the clinical insights for drug discovery for Big Pharma?
  4. Are there clues for risk adjustment and policy writing tips for health care insurers?

STEP 7:  Transfer copy of Interpretations files for Translation into Foreign Languages: Spanish, Japanese, Russian into Folders with Language Name

STEP 8: Under Construction: Enrichment of the original content with External Repositories

Read Full Post »

%d bloggers like this: