Towards Trustworthy Cross-patient Model Development
This work addresses trust issues in ML models for physicians using patient data, but it is incremental as it builds on existing methods for model selection.
The paper tackled the problem of improving trustworthiness in cross-patient machine learning models for medical applications by combining patient demographics with physiological data, showing that demographics significantly impact performance and explainability.
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.