Shareable artificial intelligence to extract cancer outcomes from electronic health records for precision oncology research

Kenneth L. Kehl (), Justin Jee, Karl Pichotta, Morgan A. Paul, Pavel Trukhanov, Christopher Fong, Michele Waters, Ziad Bakouny, Wenxin Xu, Toni K. Choueiri, Chelsea Nichols, Deborah Schrag and Nikolaus Schultz
Additional contact information
Kenneth L. Kehl: Dana-Farber Cancer Institute
Justin Jee: Memorial Sloan Kettering Cancer Center
Karl Pichotta: Memorial Sloan Kettering Cancer Center
Morgan A. Paul: Dana-Farber Cancer Institute
Pavel Trukhanov: Dana-Farber Cancer Institute
Christopher Fong: Memorial Sloan Kettering Cancer Center
Michele Waters: Memorial Sloan Kettering Cancer Center
Ziad Bakouny: Memorial Sloan Kettering Cancer Center
Wenxin Xu: Dana-Farber Cancer Institute
Toni K. Choueiri: Dana-Farber Cancer Institute
Chelsea Nichols: Memorial Sloan Kettering Cancer Center
Deborah Schrag: Memorial Sloan Kettering Cancer Center
Nikolaus Schultz: Memorial Sloan Kettering Cancer Center

Nature Communications, 2024, vol. 15, issue 1, 1-11

Abstract: Abstract Databases that link molecular data to clinical outcomes can inform precision cancer research into novel prognostic and predictive biomarkers. However, outside of clinical trials, cancer outcomes are typically recorded only in text form within electronic health records (EHRs). Artificial intelligence (AI) models have been trained to extract outcomes from individual EHRs. However, patient privacy restrictions have historically precluded dissemination of these models beyond the centers at which they were trained. In this study, the vulnerability of text classification models trained directly on protected health information to membership inference attacks is confirmed. A teacher-student distillation approach is applied to develop shareable models for annotating outcomes from imaging reports and medical oncologist notes. ‘Teacher’ models trained on EHR data from Dana-Farber Cancer Institute (DFCI) are used to label imaging reports and discharge summaries from the Medical Information Mart for Intensive Care (MIMIC)-IV dataset. ‘Student’ models are trained to use these MIMIC documents to predict the labels assigned by teacher models and sent to Memorial Sloan Kettering (MSK) for evaluation. The student models exhibit high discrimination across outcomes in both the DFCI and MSK test sets. Leveraging private labeling of public datasets to distill publishable clinical AI models from academic centers could facilitate deployment of machine learning to accelerate precision oncology research.

Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-024-54071-x Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-54071-x

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-024-54071-x

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().