Interests:
Electronic Health Records (EHR), multi-modal health data integration, common data models, biomedical ontology, EHR-based deep phenotyping and data mining, machine-learning-based clinical predictive models to be used for augmenting Clinical Decision Support Systems, diagnostics, screening, comorbidity reasoning, prognosis prediction, and evidence-based intervention.
Background:
Dr. Liang was intrigued by artificial intelligence and human cognition when he was majoring in Electrical and Information Engineering and continued the Master’s program in Psychology at Soochow University. He then obtained a PhD in Biomedical Informatics from the University of Texas McWilliams School of Biomedical Informatics. Since then, he has been committed to augmenting artificial intelligence to support clinical care and translational medicine. Dr. Liang is a Fellow of the American Medical Informatics Association. Nationally, he was recognized as the Data and Technology Advancement (DATA) Scholar at NIH/NIDDK. Emerging as a prominent junior researcher, he was the Principal Investigator to lead two NIH/NIAID funded R21 grants and Co-Investigator on numerous extramural grants.
Research:
Dr. Liang’s research has centered on multi-modal health data integration, common data models, biomedical ontology, EHR-based deep phenotyping and data mining, and machine-learning-based clinical predictive models to be used for augmenting Clinical Decision Support Systems, diagnostics, screening, comorbidity reasoning, prognosis prediction, and evidence-based intervention. He has applied these informatics methods in infectious and immune-mediated diseases (e.g., COVID-19, HIV/AIDS), obstetrics and genecology, precision medicine in nephrology, cardio-cerebrovascular diseases, oral dental and craniofacial medicine, and substance use disorders.
Current projects:
- Developing hybrid knowledge-graph-driven machine learning algorithms for identifying and characterizing Long COVID
- Examining co-infection of HIV/SARS-CoV-2 using machine learning models and nation-wide EHR
Currently accepting new students.
Representative publications:
Lyu T, Liang C. Computational Phenotyping of OMOP CDM Normalized EHR for Prenatal and Postpartum Episodes: An Informatics Framework and Clinical Implementation on All of Us. In AMIA Annual Symposium Proceedings 2023 (Vol. 2023, p. 1096). American Medical Informatics Association. https://pubmed.ncbi.nlm.nih.gov/38222375/
Lyu T, Liang C, Liu J, Hung P, Zhang J, Campbell B, Ghumman N, Olatosi B, Hikmet N, Zhang M, Yi H. Risk for Stillbirth among Pregnant Individuals with SARS-CoV-2 Infection Varied by Gestational Age. American Journal of Obstetrics and Gynecology. 2023 Feb 28. https://pubmed.ncbi.nlm.nih.gov/36858096/
Lyu T, Liang C, Liu J, Campbell B, Hung P, Shih YW, Ghumman N, Li X, National COVID Cohort Collaborative Consortium. Temporal events detector for pregnancy care (TED-PC): a rule-based algorithm to infer gestational age and delivery date from electronic health records of pregnant women with and without COVID-19. Plos one. 2022 Oct 31;17(10):e0276923. https://pubmed.ncbi.nlm.nih.gov/36315520/
Liang C, Zhou S, Yao B, Hood D, Gong Y. Toward systems-centered analysis of patient safety events: Improving root cause analysis by optimized incident classification and information presentation. International Journal of Medical Informatics. 2020 Mar 1;135:104054. https://pubmed.ncbi.nlm.nih.gov/31864129/
Liang C, Gong Y. Automated classification of multi-labeled patient safety reports: a shift from quantity to quality measure. In MEDINFO 2017: Precision Healthcare through Informatics 2017 (pp. 1070-1074). IOS Press. https://pubmed.ncbi.nlm.nih.gov/29295266/
Liang C, Sun J, Tao C. Semantic web ontology and data integration: a case study in aiding psychiatric drug repurposing. In MEDINFO 2015: eHealth-enabled Health 2015 (pp. 1051-1051). IOS Press. https://pubmed.ncbi.nlm.nih.gov/27570661/
Liang C, Gong Y. On Building an Ontological Knowledge Base for Managing Patient Safety Events. In MedInfo 2015 Jan 1 (pp. 202-206). https://pubmed.ncbi.nlm.nih.gov/26262039/