Chad A. Dorn, PSM, has worked in healthcare, with a focus on data analysis and database development, for over fifteen years. His work within the biomedical informatics Center for Improving the Public's Health through Informatics (CIPHI) research group includes contributions to projects focused on cardiac care, acute kidney injury, rural health, prescribing feedback, and computable phenotypes. His prior work includes activities related to healthcare quality improvement and patient safety. He has earned a master’s degree in Computer Science and Quantitative Methods and a bachelor’s degree in Mathematics.

Chad has contributed to the following publications:

• Development of Electronic Health Record–Based Prediction Models for 30-Day Readmission Risk Among Patients Hospitalized for Acute Myocardial Infarction | Acute Coronary Syndromes | JAMA Network Open | JAMA Network
• Identifying Potential Therapeutic Applications and Diagnostic Harms of Increased Bilirubin Concentrations: A Clinical and Genetic Approach - Zanussi - 2022 - Clinical Pharmacology & Therapeutics - Wiley Online Library
• Information Extraction From Electronic Health Records to Predict Readmission Following Acute Myocardial Infarction: Does Natural Language Processing Using Clinical Notes Improve Prediction of Readmission? | Journal of the American Heart Association (ahajournals.org)
• Validating a Computable Phenotype for Nephrotic Syndrome in Children and Adults Using PCORnet Data | American Society of Nephrology (asnjournals.org)
• Proton-pump inhibitor use is not associated with severe COVID-19-related outcomes: a propensity score-weighted analysis of a national veteran cohort | Gut (bmj.com)

Dr. Zhijun Yin has a broad background in Computer Science and Biostatistics, with a particular focus on data-intensive computing system, natural language processing (NLP), machine learning, statistical inference, and their applications in health domain. Dr. Yin’s current work centers on utilizing electronic health records (EHRs) and non-clinical data source, such as social media, to model and predict health-related behaviors and outcomes. As the recipient of a prestigious NCI R37 MERIT award (an R01 with two additional years of support), he investigates the prediction of anti-cancer medication discontinuation through patient portal messages and structured EHRs. He is now co-leading an ARPA-H funded project that focusing on detecting hallucinations in medical chatbots. He also leads an AHA-supported project focusing on using conversational LLMs to process and understand heart failure outcomes from millions of patient records. He contributes as a co-investigator on several NIH-funded projects, including AIM-AHEAD and Bridge2AI, where he focuses on developing prediction models and addressing issues of bias and fairness in AI within healthcare. Dr. Yin’s other recent research areas include but are not limited to velopharyngeal dysfunction prediction, multi-modal AI in breast cancer prediction, LLM-based text-to-SQL system, and deep genomics.

In addition to his research, Dr. Yin designed and teaches a course titled “Machine Learning and Natural Language Processing for Healthcare” for senior undergraduates and graduate students in Computer Science, Data Science, and Biomedical Informatics at Vanderbilt University. Dr. Yin currently serves as an associate editor for the Journal of Medical Internet Research (JMIR) and JMIR AI and a senior program committee member for multiple peer-reviewed conferences in Computer Science and Biomedical Informatics. Dr. Yin also serves as a reviewer in NIH study sections and PCORI review panels. Dr. Yin has been honored as a fellow of the American Medical Informatics Association (FAMIA) since November 2023.