Enabling scalable clinical interpretation of ML-based phenotypes using real world data

TL;DR

This paper presents tools and methods to improve the scalability, interpretability, and clinical relevance of ML-based patient stratification using large EHR datasets, enabling more meaningful insights in healthcare research.

Contribution

It introduces novel tools for clinical evaluation and interpretation of unsupervised patient stratification, reducing complexity and analysis time in large EHR datasets.

Findings

Meta clustering reduced 72 patient clusters to 3

Surrogate models identified key features like blood sodium in heart failure stratification

Curation improved clinical relevance of stratification results

Abstract

The availability of large and deep electronic healthcare records (EHR) datasets has the potential to enable a better understanding of real-world patient journeys, and to identify novel subgroups of patients. ML-based aggregation of EHR data is mostly tool-driven, i.e., building on available or newly developed methods. However, these methods, their input requirements, and, importantly, resulting output are frequently difficult to interpret, especially without in-depth data science or statistical training. This endangers the final step of analysis where an actionable and clinically meaningful interpretation is needed.This study investigates approaches to perform patient stratification analysis at scale using large EHR datasets and multiple clustering methods for clinical research. We have developed several tools to facilitate the clinical evaluation and interpretation of unsupervised patient stratification results, namely pattern screening, meta clustering, surrogate modeling, and curation. These tools can be used at different stages within the analysis. As compared to a standard analysis approach, we demonstrate the ability to condense results and optimize analysis time. In the case of meta clustering, we demonstrate that the number of patient clusters can be reduced from 72 to 3 in one example. In another stratification result, by using surrogate models, we could quickly identify that heart failure patients were stratified if blood sodium measurements were available. As this is a routine measurement performed for all patients with heart failure, this indicated a data bias. By using further cohort and feature curation, these patients and other irrelevant features could be removed to increase the clinical meaningfulness. These examples show the effectiveness of the proposed methods and we hope to encourage further research in this field.