Approach to Machine Learning for Extraction of Real-World Data Variables from Electronic Health Records
Authors:
- Blythe AdamsonBABlythe Adamson
- Michael WaskomMWMichael Waskom
- Auriane BlarreABAuriane Blarre
- Jonathan KellyJKJonathan Kelly
- Konstantin KrismerKKKonstantin Krismer
- Sheila NemethSNSheila Nemeth
- James GippettiJGJames Gippetti
- John RittenJRJohn Ritten
- Katherine HarrisonKHKatherine Harrison
- George HoGHGeorge Ho
- Robin LinzmayerRLRobin Linzmayer
- Tarun BansalTBTarun Bansal
Preprint
Abstract
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 (eg, 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 (ie, 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. Conclusions 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.Keywords
This publication has 29 references indexed in Scilit:
- Competing biomedical HIV prevention strategies: potential cost‐effectiveness of HIV vaccines and PrEP in Seattle, WAJournal of the International AIDS Society, 2019
- Artificial intelligence in digital pathology — new tools for diagnosis and precision oncologyNature Reviews Clinical Oncology, 2019
- Artificial intelligence and machine learning in clinical development: a translational perspectivenpj Digital Medicine, 2019
- PPM8 A MACHINE LEARNING MODEL FOR CANCER BIOMARKER IDENTIFICATION IN ELECTRONIC HEALTH RECORDSValue in Health, 2019
- PCN166 OPTIMIZATION OF NATURAL LANGUAGE PROCESSING-SUPPORTED COMORBIDITY CLASSIFICATION ALGORITHMS IN ELECTRONIC HEALTH RECORDSValue in Health, 2019
- Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic reviewJournal of the American Medical Informatics Association, 2019
- Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) AnalysisIEEE Journal of Biomedical and Health Informatics, 2017
- A Study of Machine Learning in Healthcare2017
- Optimal Thresholding of Classifiers to Maximize F1 Measure2014
- Long Short-Term MemoryNeural Computation, 1997