Mitigation of outcome conflation in predicting patient outcomes using electronic health records
Journal of the American Medical Informatics Association · 01.05.2025 · 32 (5) · 920-927
DOI: 10.1093/jamia/ocaf033 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 08.03.2025. Verfasst von S Momsen Reincke und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States. Hauptthemen laut MEDLINE: Electronic Health Records, Pancreatic Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Gates Foundation, NIH HHS, Alfred E. Mann Foundation.
Abstract (Originalsprache)
Objectives
Artificial intelligence (AI) models utilizing electronic health record data for disease prediction can enhance risk stratification but may lack specificity, which is crucial for reducing the economic and psychological burdens associated with false positives. This study aims to evaluate the impact of confounders on the specificity of single-outcome prediction models and assess the effectiveness of a multi-class architecture in mitigating outcome conflation. Materials and Methods We evaluated a state-of-the-art model predicting pancreatic cancer from disease code sequences in an independent cohort of 2.3 million patients and compared this single-outcome model with a multi-class model designed to predict multiple cancer types simultaneously. Additionally, we conducted a clinical simulation experiment to investigate the impact of confounders on the specificity of single-outcome prediction models.
Results
While we were able to independently validate the pancreatic cancer prediction model, we found that its prediction scores were also correlated with ovarian cancer, suggesting conflation of outcomes due to underlying confounders. Building on this observation, we demonstrate that the specificity of single-outcome prediction models is impaired by confounders using a clinical simulation experiment. Introducing a multi-class architecture improves specificity in predicting cancer types compared to the single-outcome model while preserving performance, mitigating the conflation of outcomes in both the real-world and simulated contexts.
Discussion
Our results highlight the risk of outcome conflation in single-outcome AI prediction models and demonstrate the effectiveness of a multi-class approach in mitigating this issue.
Conclusion
The number of predicted outcomes needs to be carefully considered when employing AI disease risk prediction models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University, Stanford, CA 94305, United States.
- Department of Pediatrics, Stanford University School of Medicine, Stanford, CA 94305, United States.
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, United States.
- Department of Pathology, Stanford University, Stanford, CA 94305, United States.
ORCID-Profile: S Momsen Reincke, Camilo Espinosa, Philip Chung, Tomin James, Eloïse Berson, Nima Aghaeepour
Förderung
- Gates Foundation
- NIH HHS
- Alfred E. Mann Foundation
- NIA NIH HHS
- Burroughs Wellcome Fund
- NIGMS NIH HHS
- Robertson Foundation
- Bill & Melinda Gates Foundation
Zitieren
APA
Reincke, S. M., Espinosa, C., Chung, P., James, T., Berson, E., & Aghaeepour, N. (2025). Mitigation of outcome conflation in predicting patient outcomes using electronic health records. Journal of the American Medical Informatics Association, 32(5), 920-927. https://doi.org/10.1093/jamia/ocaf033
Vancouver
Reincke SM, Espinosa C, Chung P, James T, Berson E, Aghaeepour N. Mitigation of outcome conflation in predicting patient outcomes using electronic health records. Journal of the American Medical Informatics Association. 2025;32(5):920-927. doi:10.1093/jamia/ocaf033
BibTeX
@article{Reincke2025,
author = {Reincke, S Momsen and Espinosa, Camilo and Chung, Philip and James, Tomin and Berson, Eloïse and Aghaeepour, Nima},
title = {Mitigation of outcome conflation in predicting patient outcomes using electronic health records},
journal = {Journal of the American Medical Informatics Association},
year = {2025},
volume = {32},
number = {5},
pages = {920--927},
doi = {10.1093/jamia/ocaf033}
}
EUVIMED