Dr. Agent: Clinical predictive model via mimicked second opinions

Junyi Gao, Cao Xiao, Lucas M. Glass, Jimeng Sun

Research output: Contribution to journalArticlepeer-review


Objective: Prediction of disease phenotypes and their outcomes is a difficult task. In practice, patients routinely seek second opinions from multiple clinical experts for complex disease diagnosis. Our objective is to mimic such a practice of seeking second opinions by training 2 agents with different focuses: the primary agent studies the most recent visit of the patient to learn the current health status, and then the second-opinion agent considers the entire patient history to obtain a more global view. Materials and Methods: Our approach Dr. Agent augments recurrent neural networks with 2 policy gradient agents. Moreover, Dr. Agent is customized with various patient demographics information and learns a dynamic skip connection to focus on the relevant information over time. We trained Dr. Agent to perform 4 clinical prediction tasks on the publicly available MIMIC-III (Medical Information Mart for Intensive Care) database: (1) in-hospital mortality prediction, (2) acute care phenotype classification, (3) physiologic decompensation prediction, and (4) forecasting length of stay. We compared the performance of Dr. Agent against 4 baseline clinical predictive models. Results: Dr. Agent outperforms baseline clinical prediction models across all 4 tasks in terms of all metrics. Compared with the best baseline model, Dr. Agent achieves up to 15% higher area under the precision-recall curve on different tasks. Conclusions: Dr. Agent can comprehensively model the long-term dependencies of patients' health status while considering patients' demographics using 2 agents, and therefore achieves better prediction performance on different clinical prediction tasks.

Original languageEnglish (US)
Pages (from-to)1084-1091
Number of pages8
JournalJournal of the American Medical Informatics Association
Issue number7
StatePublished - Jul 1 2020


  • clinical prediction
  • deep learning
  • electronic health records
  • intensive care
  • recurrent neural network
  • reinforcement learning

ASJC Scopus subject areas

  • Health Informatics


Dive into the research topics of 'Dr. Agent: Clinical predictive model via mimicked second opinions'. Together they form a unique fingerprint.

Cite this