Enabling Personalized Decision Support with Patient-Generated Data and Attributable Components

TL;DR

This paper introduces attributable components analysis (ACA), a novel method inspired by optimal transport theory, to analyze patient-generated data for personalized health decision support, especially in diabetes management.

Contribution

The paper presents ACA, a new analytical approach that captures non-linear relationships and provides robust, interpretable insights from patient data for health decision-making.

Findings

ACA identifies non-linear relationships in data.

ACA is more robust to outliers than linear regression.

ACA provides broader uncertainty estimates.

Abstract

Decision-making related to health is complex. Machine learning (ML) and patient generated data can identify patterns and insights at the individual level, where human cognition falls short, but not all ML-generated information is of equal utility for making health-related decisions. We develop and apply attributable components analysis (ACA), a method inspired by optimal transport theory, to type 2 diabetes self-monitoring data to identify patterns of association between nutrition and blood glucose control. In comparison with linear regression, we found that ACA offers a number of characteristics that make it promising for use in decision support applications. For example, ACA was able to identify non-linear relationships, was more robust to outliers, and offered broader and more expressive uncertainty estimates. In addition, our results highlight a tradeoff between model accuracy and interpretability, and we discuss implications for ML-driven decision support systems.