A photo of Judith Dexheimer.

Judith W. Dexheimer, PhD

  • Associate Professor, UC Department of Pediatrics



The ultimate goal of my research is to harness technology to improve healthcare delivery and the quality of care for children. My research interests include machine learning (ML), decision support, personal health records and multi-center informatics implementations. During my National Library of Medicine (NLM) informatics training, I studied artificial intelligence and implemented reminder systems directly into clinical care in the adult and pediatric emergency departments. My goals are to improve disease detection, especially earlier disease detection, for patients with a long history of illness. I also want to provide technology and healthcare information to underserved populations, improve care delivery and help providers use the computer as a tool that incorporates ML directly into clinical care.

I see myself accomplishing this goal by designing ways to use ML to enhance the patient-clinician experience at the point of care and by improving patient interactions with health technology in and outside of the healthcare encounter.

I was drawn to this field of research after seeing well-designed ML algorithms created but not integrated into clinical care. I also noticed that patients frequently did not have access to their own healthcare data.

Working with a collaborative team, we want to improve the use of informatics. I have experience in designing, implementing and evaluating clinical information systems, including clinical decision support systems, computerized applications for emergency medicine, organizational and workflow aspects of informatics applications.

A few of my accomplishments include:

  • Collaborating with the Pestian lab to develop one of the first real-time integrations of machine learning (epilepsy classifier) into clinical care
  • Working with Dr. Yizhao Ni at Cincinnati Children’s to integrate an automated ML patient screening system into the pediatric emergency department
  • Collaborating with Mary Greiner (Mayerson Center for Safe and Healthy Children) and Sarah Beal (Behavioral Medicine and Clinical Psychology) to develop the IDENTITY platform to share data more efficiently between the hospital and Hamilton county job and family services caseworkers, including automated matching of patients in custody

I was nominated for the Presidential Early Career Awards for Scientists and Engineers (PECASE) in 2017 and invited as a presenter at the Amazon Web Services (AWS) Machine Learning Summit in 2019. I have been a researcher for over nine years and began my work at Cincinnati Children’s in 2011.

MBA: University of Cincinnati, Cincinnati, OH, 2020. 

PhD: Biomedical Informatics, Vanderbilt University, Nashville, TN, 2011.

MS: Biomedical Informatics, Vanderbilt University, Nashville, TN, 2006.

Research Areas

Biomedical Informatics, Emergency Medicine


Automated, machine learning-based alerts increase epilepsy surgery referrals: A randomized controlled trial. Wissel, BD; Greiner, HM; Glauser, TA; Mangano, FT; Holland-Bouley, KD; Zhang, N; Szczesniak, RD; Santel, D; Pestian, JP; Dexheimer, JW. Epilepsia. 2023; 64:1791-1799.

Built environment factors predictive of early rapid lung function decline in cystic fibrosis. Gecili, E; Brokamp, C; Rasnick, E; Afonso, PM; Andrinopoulou, ER; Dexheimer, JW; Clancy, JP; Keogh, RH; Ni, Y; Palipana, A; et al. Pediatric Pulmonology. 2023; 58:1501-1513.

115. Automated Identification of Transgender and Gender Non-conforming patients from Electronic Health Record Data. Su, EC; Dexheimer, JW; Kronk, CA; Snedecor, R; Popler, E; Thomas, A; Szczesniak, R; Gecili, E; Conard, L. Journal of Adolescent Health. 2023; 72:s66.

Standardizing electronic health record ventilation data in the pediatric long-term mechanical ventilator-dependent population. Kanbar, LJ; Dexheimer, JW; Zahner, J; Burrows, EK; Chatburn, R; Messinger, A; Baker, CD; Schuler, CL; Benscoter, D; Amin, R; et al. Pediatric Pulmonology. 2023; 58:433-440.

Implementation of Machine Learning Pipelines for Clinical Practice: Development and Validation Study. Kanbar, LJ; Wissel, B; Ni, Y; Pajor, N; Glauser, T; Pestian, J; Dexheimer, JW. JMIR Medical Informatics. 2022; 10:e37833.

2.7 Automated Detection of School Violence Using Linguistic Features. Kanbar, L; Barzman, DH; Dexheimer, J; Osborn, A; Combs, JS; Diler, RS; Sorter, MT; Zhang, B; Hemphill, R; Decker, RM; et al. Journal of the American Academy of Child and Adolescent Psychiatry. 2022; 61:s184-s185.

The Risk of Coding Racism into Pediatric Sepsis Care: The Necessity of Antiracism in Machine Learning. Sveen, W; Dewan, M; Dexheimer, JW. The Journal of Pediatrics. 2022; 247:129-132.

Diversity in Machine Learning: A Systematic Review of Text-Based Diagnostic Applications. Fitzsimmons, L; Dewan, M; Dexheimer, JW. Applied Clinical Informatics - ACI. 2022; 13:569-582.

Aligning Provider Prescribing With Guidelines for Soft Tissue Infections. Kovaleski, C; Courter, JD; Ghulam, E; Hagedorn, PA; Haslam, DB; Kurowski, EM; Rudloff, J; Szczesniak, R; Dexheimer, JW. Pediatric Emergency Care. 2022; 38:e1063-e1068.

An ontology-based review of transgender literature: Revealing a history of medicalization and pathologization. Kronk, CA; Dexheimer, JW. International Journal of Medical Informatics. 2021; 156:104601.