Enabling personalized decision support with patient-generated data and attributable components

Elliot G. Mitchell, Esteban G. Tabak, Matthew E. Levine, Lena Mamykina, David J. Albers

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Article number103639
JournalJournal of Biomedical Informatics
Volume113
DOIs
StatePublished - Jan 2021

Keywords

  • Machine learning
  • Patient decision support
  • Patient-generated health data
  • Type 2 diabetes

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Fingerprint Dive into the research topics of 'Enabling personalized decision support with patient-generated data and attributable components'. Together they form a unique fingerprint.

Cite this