Polygon Health Analytics to Present AI-driven chart review capabilities at ISPOR 2024
2 min read

Polygon Health Analytics is proud to announce the development of a groundbreaking capability – a Large Language Model (LLM)-facilitated chart review solution. This application of advanced AI technology has demonstrated its potential to significantly enhance the efficiency of chart reviews, while maintaining a high degree of accuracy in identifying and characterizing Systemic Lupus Erythematosus (SLE) flares. This holds true even in instances where flare diagnoses may have been missed. Our innovative work has been recognized as a Top 5% Finalist for the ISPOR 2024 Research Presentation Awards.

LLMs, which operate tirelessly around the clock, hold the promising tool for future clinical research. Our Founder and CEO, Dr. Lixia Yao, will be presenting this project, a result of our collaboration with Temple University, at the ISPOR Annual Conference in Atlanta, GA. The presentation is scheduled from 9:00 to 11:30 AM on Wednesday, May 8.

For any further inquiries or feedback, please contact us at info@polygonhealthanalytics.com. We look forward to meeting you at Atlanta. 


Abstract

OBJECTIVES

Systemic lupus erythematosus (SLE) is a chronic autoimmune disease affecting multiple organs and systems. Accurately determining the frequency and pattern of disease flares, as measured by SLE Disease Activity Index (SLEDAI), is crucial for SLE care and research. However, flare reports often reside in free-text clinical notes, lacking standardized coding and necessitating manual review. To overcome this, we utilized an advanced AI model to identify SLE flares from clinical notes.

METHODS

We obtained de-identified medical records between 1/1/2012 and 05/31/2022 from Temple University Health System’s Epic electronic health record system. The dataset included patients aged 18 years or above, with at least one rheumatology visit, one ICD-10-CM code of M32.*, and SLE mentioned in a clinical note. We developed a multi-step automated pipeline using GPT-4 and prompt engineering to accurately identify flares based on (1) SLEDAI score changes (A >3 change in SLEDAI mentioned in the physician notes is considered a mild-moderate flare while a >10 change in SLEDA is considered a severe flare), (2) physician’s reports in the notes, or (3) our automated calculation of SLEDAI changes according to new symptoms and lab results documented in physician notes.

RESULTS

From 2,085 rheumatology notes of 408 unique patients, GPT-4 identified 606 flare events. Of these, 7 were based on SLEDAI score changes, 71 on physician’s reports, and 533 on our SLEDAI calculations. A review of 200 randomly selected notes by trained medical professionals showed a 97.5% agreement with GPT-4 results. 

CONCLUSION

Our findings affirm that advanced AI technology can significantly enhance chart review efficiency while maintaining high accuracy in identifying and characterizing SLE flares, even in cases of missed flare diagnosis. Large language models, represented by GPT-4.0 show promise in accelerating SLE research using electronic health records data. 

Other Posts You Might Like
Calling for Lupus Patients and Caregivers to Shape the Future of Lupus Care
Mar 11, 2025
Sponsored by the National Institute of Minority Health and Health Disparities (NIMHD), Polygon Health Analytics is iSMILE (Individualized Social Risk Management in Systemic Lupus Erythematosus Care)...
Read more
Is Life Science Ready for AI?
Jan 02, 2025
A few days ago, Dr. Geoffrey Hinton, often referred to as the “Godfather of AI,” made a chilling statement: “There is a 10-20 percent probability that...
Read more
Polygon Health Analytics Receives Competitive SBIR Grant from NIMHD to Address Health Disparities in Lupus Care
Nov 20, 2024
Philadelphia, PA — Nov 19, 2024 — Polygon Health Analytics LLC is proud to announce its award of a $295,924 Small Business Innovation Research (SBIR) Phase I...
Read more
Polygon Health Analytics Launches First Cohort of Launchpad Program
Nov 11, 2024
Polygon Health Analytics is excited to announce the successful graduation of the first cohort of its Launchpad Program, a 3-to-6-month train-to-hire initiative designed to prepare emerging...
Read more
Introducing Vaccine Vibes – A Weekly Newsletter for Vaccine R&D
Sep 13, 2024
Staying informed about the latest developments is critical for professionals in the biopharmaceutical industry, especially in the complex world of vaccine research and development (R&...
Read more
Polygon Health Analytics LLC Awarded $400,000 National Cancer Institute Contract
Sep 06, 2024
Philadelphia, PA – September 6, 2024 – Polygon Health Analytics LLC (PHA) is thrilled to announce that it has been awarded a prestigious $399,985 contract by the...
Read more
To My Fellow Data Scientists: Transform a Useful Idea into a Real Business
Jun 24, 2024
I have been building my own startup company for the past 1.5 years. Throughout this journey, I’ve been fortunate to connect with many brilliant...
Read more
Bridging the Gap: Real-World Data Enhancing Clinical Trials
Mar 13, 2024
Randomized clinical trials (RCTs) have long been recognized as the gold standard for testing the safety and efficacy of pharmaceutical interventions. Despite their rigorous methodology, RCTs...
Read more
Navigating the Future: Your Launchpad to Success in Data Analytics
Mar 13, 2024
In today’s ever-evolving job market, the challenge of securing employment is a topic that resonates widely. Through news media and personal stories from friends and...
Read more
A Symphony of Innovation in 2023: Navigating the AI Revolution
Jan 27, 2024
Prelude to Power: OpenAI’s ChatGPT takes the lead In the waning months of 2022, OpenAI unveiled ChatGPT, marking a pivotal moment in the AI landscape....
Read more
View all