Clinical And Translational Informatics

Medical decision making is complex and data-driven and is increasingly outstripping the cognitive abilities of physicians. DBMI is focused on developing, implementing and evaluating high performance clinical decision support tools that are powered by artificial intelligence.  

Faculty in DBMI are active in a wide range of clinical informatics research projects with clinical collaborators across the Pitt School of Medicine. Examples of projects include: (1) a clinical decision support system that uses electronic medical records and machine-learning to identify medical errors; (2) image processing tools for pediatric heart disease detection and brain tumor monitoring; (3) an intelligent electronic medical record system that adapts to display the right data at the right time; (4) a monitoring system for real-time identification of brain ischemia during surgery; (5) a Twitter surveillance system to analyze vaping-related tweets; (6) clinician-focused explanations of predictive models of pediatric deterioration and mortality; and (7) knowledge-representation, management, and use for predicted drug-drug interactions. 

Sample of Related Publications:

Yan Q, Kim J, Hall DE, Shinall MC Jr, Reitz KM, Stitzenberg KB, Kao LS, George EL, Youk A, Wang CP, Silverstein JC, Bernstam EV, Shireman PK. Association of Frailty and the Expanded Operative Stress Score with Preoperative Acute Serious Conditions, Complications and Mortality in Males Compared to Females: A Retrospective Observational Study. Ann Surg. 2021 Jun 25:10.1097/SLA.0000000000005027. doi: 10.1097/SLA.0000000000005027. Epub ahead of print. PMID: 34183515; PMCID: PMC8709872. 

Walker LW, Nowalk AJ, Visweswaran S. Predicting outcomes in central venous catheter salvage in pediatric central line-associated bloodstream infection. J Am Med Inform Assoc. 2021 Mar 18;28(4):862-867. doi: 10.1093/jamia/ocaa328. PMID: 33463685; PMCID: PMC7973452. 

King AJ, Cooper GF, Clermont G, Hochheiser H, Hauskrecht M, Sittig DF, Visweswaran S. Leveraging Eye Tracking to Prioritize Relevant Medical Record Data: Comparative Machine Learning Study. J Med Internet Res. 2020 Apr 2;22(4):e15876. doi: 10.2196/15876. PMID: 32238342; PMCID: PMC7163414. 

Boyce RD, Jao J, Miller T, Kane-Gill SL. Automated Screening of Emergency Department Notes for Drug-Associated Bleeding Adverse Events Occurring in Older Adults. Appl Clin Inform. 2017 Oct;8(4):1022-1030. doi: 10.4338/ACI-2017-02-RA-0036. Epub 2017 Dec 14. PMID: 29241242; PMCID: PMC5802315. 

Barda, A.J., Horvat, C.M. & Hochheiser, H. A qualitative research framework for the design of user-centered displays of explanations for machine learning model predictions in healthcare. BMC Med Inform Decis Mak 20, 257 (2020). https://doi.org/10.1186/s12911-020-01276-x