EUVIMEDEUVIMED entdecken
Open Access

Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing

Sharon Jiang iD, Barbara D Lam iD, Monica Agrawal, Shannon Shen, Nicholas Kurtzman, Steven Horng iD, David R Karger, David Sontag

Journal of the American Medical Informatics Association · 2024

DOI: 10.1093/jamia/ocae092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2024. Verfasst von Sharon Jiang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States. Hauptthemen laut MEDLINE: Machine Learning, Electronic Health Records, Medical Oncology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: MIT Abdul Latif Jameel Clinic, National Science Foundation, Machine Learning Core.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Leverage electronic health record (EHR) audit logs to develop a machine learning (ML) model that predicts which notes a clinician wants to review when seeing oncology patients. Materials and Methods We trained logistic regression models using note metadata and a Term Frequency Inverse Document Frequency (TF-IDF) text representation. We evaluated performance with precision, recall, F1, AUC, and a clinical qualitative assessment.

Results

The metadata only model achieved an AUC 0.930 and the metadata and TF-IDF model an AUC 0.937. Qualitative assessment revealed a need for better text representation and to further customize predictions for the user.

Discussion

Our model effectively surfaces the top 10 notes a clinician wants to review when seeing an oncology patient. Further studies can characterize different types of clinician users and better tailor the task for different care settings.

Conclusion

EHR audit logs can provide important relevance data for training ML models that assist with note-writing in the oncology setting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningElectronic Health RecordsMedical OncologyHumansLogistic ModelsMetadataMedical AuditProof of Concept Study

Stichwörter der Autor:innen

electronic health recordmachine learningnatural language processingnote writing

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States.
  • Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139, United States.
  • Division of Hematology and Oncology, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, United States.
  • Division of Clinical Informatics, Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, United States.
  • Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02215, United States.

ORCID-Profile: Sharon Jiang, Barbara D Lam, Steven Horng

Förderung

  • MIT Abdul Latif Jameel Clinic
  • National Science Foundation
  • Machine Learning Core
  • Beth Israel Deaconess Medical Center
  • MIT Deshpande Center
  • MIT Abdul Latif Jameel Clinic for Machine Learning in Health
  • MachineLearningApplications@CSAIL initiative

Zitieren

APA

Jiang, S., Lam, B. D., Agrawal, M., Shen, S., Kurtzman, N., Horng, S., Karger, D. R., & Sontag, D. (2024). Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocae092

Vancouver

Jiang S, Lam BD, Agrawal M, Shen S, Kurtzman N, Horng S, et al. Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing. Journal of the American Medical Informatics Association. 2024. doi:10.1093/jamia/ocae092

BibTeX
@article{Jiang2024,
  author = {Jiang, Sharon and Lam, Barbara D and Agrawal, Monica and Shen, Shannon and Kurtzman, Nicholas and Horng, Steven and Karger, David R and Sontag, David},
  title = {Machine learning to predict notes for chart review in the oncology setting: a proof of concept strategy for improving clinician note-writing},
  journal = {Journal of the American Medical Informatics Association},
  year = {2024},
  doi = {10.1093/jamia/ocae092}
}
Kostenlos starten →