Probabilistic Machine Learning for Healthcare

Irene Y. Chen, Shalmali Joshi, Marzyeh Ghassemi, Rajesh Ranganath

Research output: Contribution to journalReview articlepeer-review

Abstract

Machine learning can be used to make sense of healthcare data. Probabilistic machine learning models help provide a complete picture of observed data in healthcare. In this review, we examine how probabilistic machine learning can advance healthcare. We consider challenges in the predictive model building pipeline where probabilistic models can be beneficial, including calibration and missing data. Beyond predictive models, we also investigate the utility of probabilistic machine learning models in phenotyping, in generative models for clinical use cases, and in reinforcement learning.

Original languageEnglish (US)
Pages (from-to)393-415
Number of pages23
JournalAnnual review of biomedical data science
Volume4
DOIs
StatePublished - Jun 1 2021

Keywords

  • artificial intelligence
  • electronic health records
  • health
  • machine learning
  • probabilistic modeling

ASJC Scopus subject areas

  • Genetics
  • Biochemistry, Genetics and Molecular Biology (miscellaneous)
  • Cancer Research
  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Probabilistic Machine Learning for Healthcare'. Together they form a unique fingerprint.

Cite this