Methods to Enhance Causal Inference for Assessing Impact of Clinical Informatics Platform Implementation

Michael Gaies, Mary K. Olive, Gabe E. Owens, John R. Charpie, Wenying Zhang, Sara K. Pasquali, Darren Klugman, John M. Costello, Steven M. Schwartz, Mousumi Banerjee

Research output: Contribution to journalArticlepeer-review


Background: Hospitals are increasingly likely to implement clinical informatics tools to improve quality of care, necessitating rigorous approaches to evaluate effectiveness. We leveraged a multi-institutional data repository and applied causal inference methods to assess implementation of a commercial data visualization software in our pediatric cardiac intensive care unit. Methods: Natural experiment in the University of Michigan (UM) Cardiac Intensive Care Unit pre and postimplementation of data visualization software analyzed within the Pediatric Cardiac Critical Care Consortium clinical registry; we identified N=21 control hospitals that contributed contemporaneous registry data during the study period. We used the platform during multiple daily rounds to visualize clinical data trends. We evaluated outcomes - case-mix adjusted postoperative mortality, cardiac arrest and unplanned readmission rates, and postoperative length of stay - most likely impacted by this change. There were no quality improvement initiatives focused specifically on these outcomes nor any organizational changes at UM in either era. We performed a difference-in-differences analysis to compare changes in UM outcomes to those at control hospitals across the pre versus postimplementation eras. Results: We compared 1436 pre versus 779 postimplementation admissions at UM to 19 854 (pre) versus 14 160 (post) at controls. Admission characteristics were similar between eras. Postimplementation at UM we observed relative reductions in cardiac arrests among medical admissions, unplanned readmissions, and postoperative length of stay by -14%, -41%, and -18%, respectively. The difference-in-differences estimate for each outcome was statistically significant (P<0.05), suggesting the difference in outcomes at UM pre versus postimplementation is statistically significantly different from control hospitals during the same time. Conclusions: Clinical registries provide opportunities to thoroughly evaluate implementation of new informatics tools at single institutions. Borrowing strength from multi-institutional data and drawing ideas from causal inference, our analysis solidified greater belief in the effectiveness of this software across our institution.

Original languageEnglish (US)
Pages (from-to)E009277
JournalCirculation: Cardiovascular Quality and Outcomes
Issue number2
StatePublished - Feb 1 2023


  • causality inference
  • critical care
  • informatics
  • outcomes assessment
  • pediatric

ASJC Scopus subject areas

  • Cardiology and Cardiovascular Medicine


Dive into the research topics of 'Methods to Enhance Causal Inference for Assessing Impact of Clinical Informatics Platform Implementation'. Together they form a unique fingerprint.

Cite this