Skip to Main content Skip to Navigation
New interface
Conference papers

Local Explanation-Based Method for Healthcare Risk Stratification

Abstract : Decision support tools in healthcare require a strong confidence in the developed Machine Learning (ML) models both in terms of performances and in their ability to provide users a deeper understanding of the underlying situation. This study presents a novel method to construct a risk stratification based on ML and local explanations. An open-source dataset was used to demonstrate the efficiency of this method that well identified the main subgroups of patients. Therefore, this method could help practitioners adjust and build protocols to improve care deliveries that would better reflect patient's risk level and profile.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03687549
Contributor : Julien Aligon Connect in order to contact the contributor
Submitted on : Friday, June 3, 2022 - 1:48:42 PM
Last modification on : Monday, July 4, 2022 - 10:27:27 AM
Long-term archiving on: : Sunday, September 4, 2022 - 7:13:28 PM

File

SHTI-294-SHTI220520.pdf
Publisher files allowed on an open archive

Licence


Distributed under a Creative Commons Attribution - NonCommercial 4.0 International License

Identifiers

Citation

Jean-Baptiste Excoffier, Elodie Escriva, Julien Aligon, Matthieu Ortala. Local Explanation-Based Method for Healthcare Risk Stratification. Medical Informatics Europe 2022, May 2022, Nice, France. ⟨10.3233/shti220520⟩. ⟨hal-03687549⟩

Share

Metrics

Record views

62

Files downloads

8