Replication of Real-World Evidence in Oncology Using Electronic Health Record Data Extracted by Machine Learning
Cancers · 20.03.2023 · 15 (6) · 1853
DOI: 10.3390/cancers15061853 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cancers, online erschienen am 20.03.2023. Verfasst von Corey M Benedum und 7 weiteren Autor:innen. Beteiligte Einrichtung: Flatiron Health, Inc., 233 Spring Street, New York, NY 10003, USA. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Flatiron Health (United States), Flatiron Health, Inc..
Abstract (Originalsprache)
Meaningful real-world evidence (RWE) generation requires unstructured data found in electronic health records (EHRs) which are often missing from administrative claims; however, obtaining relevant data from unstructured EHR sources is resource-intensive. In response, researchers are using natural language processing (NLP) with machine learning (ML) techniques (i.e., ML extraction) to extract real-world data (RWD) at scale. This study assessed the quality and fitness-for-use of EHR-derived oncology data curated using NLP with ML as compared to the reference standard of expert abstraction. Using a sample of 186,313 patients with lung cancer from a nationwide EHR-derived de-identified database, we performed a series of replication analyses demonstrating some common analyses conducted in retrospective observational research with complex EHR-derived data to generate evidence. Eligible patients were selected into biomarker- and treatment-defined cohorts, first with expert-abstracted then with ML-extracted data. We utilized the biomarker- and treatment-defined cohorts to perform analyses related to biomarker-associated survival and treatment comparative effectiveness, respectively. Across all analyses, the results differed by less than 8% between the data curation methods, and similar conclusions were reached. These results highlight that high-performance ML-extracted variables trained on expert-abstracted data can achieve similar results as when using abstracted data, unlocking the ability to perform oncology research at scale.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Flatiron Health, Inc., 233 Spring Street, New York, NY 10003, USA.
- Department of Medicine, NYU Grossman School of Medicine, New York, NY 10016, USA.
- Comparative Health Outcomes, Policy and Economics (CHOICE) Institute, University of Washington, Seattle, WA 98195, USA.
ORCID-Profile: Corey M Benedum, Blythe Adamson, Melissa Estévez, Selen Bozkurt
Förderung
- Flatiron Health (United States)
- Flatiron Health, Inc.
Zitieren
APA
Benedum, C. M., Sondhi, A., Fidyk, E., Cohen, A. B., Nemeth, S., Adamson, B., Estévez, M., & Bozkurt, S. (2023). Replication of Real-World Evidence in Oncology Using Electronic Health Record Data Extracted by Machine Learning. Cancers, 15(6), 1853. https://doi.org/10.3390/cancers15061853
Vancouver
Benedum CM, Sondhi A, Fidyk E, Cohen AB, Nemeth S, Adamson B, et al. Replication of Real-World Evidence in Oncology Using Electronic Health Record Data Extracted by Machine Learning. Cancers. 2023;15(6):1853. doi:10.3390/cancers15061853
BibTeX
@article{Benedum2023,
author = {Benedum, Corey M and Sondhi, Arjun and Fidyk, Erin and Cohen, Aaron B and Nemeth, Sheila and Adamson, Blythe and Estévez, Melissa and Bozkurt, Selen},
title = {Replication of Real-World Evidence in Oncology Using Electronic Health Record Data Extracted by Machine Learning},
journal = {Cancers},
year = {2023},
volume = {15},
number = {6},
pages = {1853},
doi = {10.3390/cancers15061853}
}
EUVIMED