Towards Trustworthy Cross-patient Model Development

TL;DR

This paper explores how combining patient demographics with physiological data can improve the trustworthiness of machine learning models in medical settings, especially for ICU patient data, by enhancing performance and explainability.

Contribution

It demonstrates that incorporating patient demographics significantly impacts model performance and explainability, advancing cross-patient ML development in healthcare.

Findings

Demographics greatly influence model performance.

Model explainability varies with patient demographics.

Careful patient and model selection enhances trustworthiness.

Abstract

Machine learning is used in medicine to support physicians in examination, diagnosis, and predicting outcomes. One of the most dynamic area is the usage of patient generated health data from intensive care units. The goal of this paper is to demonstrate how we advance cross-patient ML model development by combining the patient's demographics data with their physiological data. We used a population of patients undergoing Carotid Enderarterectomy (CEA), where we studied differences in model performance and explainability when trained for all patients and one patient at a time. The results show that patients' demographics has a large impact on the performance and explainability and thus trustworthiness. We conclude that we can increase trust in ML models in a cross-patient context, by careful selection of models and patients based on their demographics and the surgical procedure.