Approach to machine learning for extraction of real-world data variables from electronic health records

Frontiers in Pharmacology

Pharmacology

Erin Fidyk¹  Tarun Bansal¹  Konstantin Krismer¹  Corey M. Benedum¹  Evan Estola¹  Jonathan Kelly¹  Will Shapiro¹  Sheila Nemeth¹  James Gippetti¹  Robin Linzmayer¹  John Ritten¹  Melissa Estévez¹  Katherine Harrison¹  Michael Waskom¹  George Ho¹  Samuel Wilkinson¹  Guy Amster¹  Auriane Blarre¹  Aaron B. Cohen²  Blythe Adamson³ 

[1] Flatiron Health, Inc., New York, NY, United States;Flatiron Health, Inc., New York, NY, United States;Department of Medicine, NYU Grossman School of Medicine, New York, NY, United States;Flatiron Health, Inc., New York, NY, United States;The Comparative Health Outcomes, Policy, and Economics (CHOICE) Institute, Department of Pharmacy, University of Washington, Seattle, WA, United States;

关键词: electronic health records;    cancer;    oncology;    real-world data;    machine learning;    natural language processing;    artificial intelligence;   

DOI  :  10.3389/fphar.2023.1180962

 received in 2023-03-06, accepted in 2023-08-25,  发布年份 2023

来源: Frontiers

【 摘 要 】

Background: As artificial intelligence (AI) continues to advance with breakthroughs in natural language processing (NLP) and machine learning (ML), such as the development of models like OpenAI’s ChatGPT, new opportunities are emerging for efficient curation of electronic health records (EHR) into real-world data (RWD) for evidence generation in oncology. Our objective is to describe the research and development of industry methods to promote transparency and explainability.Methods: We applied NLP with ML techniques to train, validate, and test the extraction of information from unstructured documents (e.g., clinician notes, radiology reports, lab reports, etc.) to output a set of structured variables required for RWD analysis. This research used a nationwide electronic health record (EHR)-derived database. Models were selected based on performance. Variables curated with an approach using ML extraction are those where the value is determined solely based on an ML model (i.e. not confirmed by abstraction), which identifies key information from visit notes and documents. These models do not predict future events or infer missing information.Results: We developed an approach using NLP and ML for extraction of clinically meaningful information from unstructured EHR documents and found high performance of output variables compared with variables curated by manually abstracted data. These extraction methods resulted in research-ready variables including initial cancer diagnosis with date, advanced/metastatic diagnosis with date, disease stage, histology, smoking status, surgery status with date, biomarker test results with dates, and oral treatments with dates.Conclusion: NLP and ML enable the extraction of retrospective clinical data in EHR with speed and scalability to help researchers learn from the experience of every person with cancer.

【 授权许可】

Unknown   
Copyright © 2023 Adamson, Waskom, Blarre, Kelly, Krismer, Nemeth, Gippetti, Ritten, Harrison, Ho, Linzmayer, Bansal, Wilkinson, Amster, Estola, Benedum, Fidyk, Estévez, Shapiro and Cohen.