Skip to main content

Center for AI-Driven Translational Informatics (CATI)

Accelerating trustworthy and deployable AI solutions that integrate multi-modal biomedical data into clinical practice.

Research

CATI’s research focuses on developing and validating AI models that integrate multi-omics data and clinical information for real-world application.

Research

Key Research Areas

Translational Machine Learning

Designing clinically deployable models that integrate EHR data, genomics, and proteomics.

Multi-Modal Data Integration

Combining genetic, proteomic, metabolic, immune, imaging, and lifestyle data into AI pipelines.

Precision Risk Stratification

Building tools for predicting disease onset, progression, and treatment response.

Trustworthy AI

Ensuring model explainability, fairness, and clinician interpretability.

Featured Publications

Abramowitz S A, Boulier K, Keat K, Cardone K M, Shivakumar M, DePaolo J, Judy R, Kim D, Ritchie M D, Voight B F, Pasaniuc B, Levin M G, Damrauer S M; Penn Medicine BioBank. Evaluating Performance and Agreement of Coronary Heart Disease Polygenic Risk Scores. JAMA. 2025 Jan;333(1):60–70. doi:10.1001/jama.2024.23784.

Jung, S.-H., Kim, H., Jung, Y. M., Shivakumar, M., Xiao, B., Kim, J., Jang, B., Yun, J.-S., Won, H.-H., Park, C.-W., Park, J. S., Jun, J. K., Penn Medicine Biobank, Kim, D., & Lee, S. M. Healthy lifestyle reduces cardiovascular risk in women with genetic predisposition to hypertensive disorders of pregnancy. Nature Communications. 2025 Feb 8;16(1):1463. doi:10.1038/s41467-025-56107-2.

Keat, K., Venkatesh, R., Huang, Y., Kumar, R., Tuteja, S., Sangkuhl, K., Li, B., Gong, L., Whirl‑Carrillo, M., Klein, T. E., Ritchie, M. D., & Kim, D. PGxQA: A Resource for Evaluating LLM Performance for Pharmacogenomic QA Tasks. Pacific Symposium on Biocomputing. 2025 Jan;30:229–246. doi:10.1142/9789819807024_0017.

Nateghi Haredasht F, Kim D, Romano JD, Tison G, Daneshjou R, Chen JH. Session Introduction: AI and Machine Learning in Clinical Medicine: Generative and Interactive Systems at the Human‑Machine Interface. Pacific Symposium on Biocomputing. 2025 Jan;30:33–39. doi:10.1142/9789819807024_0003.

Shivakumar, M., Kim, Y., Jung, S.-H., Woerner, J., & Kim, D. Frequency of adding salt is a stronger predictor of chronic kidney disease in individuals with genetic risk. Pacific Symposium on Biocomputing. 2025 Jan;30:551–564. doi:10.1142/9789819807024_0039.

Sriram, V., Conard, A. M., Rosenberg, I., Kim, D., & Hall, A. K. Addressing biomedical data challenges and opportunities to inform a large‑scale data lifecycle for enhanced data sharing, interoperability, analysis, and collaboration across stakeholders. Scientific Reports. 2025 Feb;15(1):6291. doi:10.1038/s41598-025-90453-x.

Sriram, V., Woerner, J., Ahn, Y.-Y., & Kim, D. The interplay of sex and genotype in disease associations: a comprehensive network analysis in the UK Biobank. Human Genomics. 2025 Jan;19(1):4. doi:10.1186/s40246-024-00710-9.

Woerner, J., Westbrook, T., Jeong, S., Shivakumar, M., Greenplate, A. R., Apostolidis, S. A., Lee, S., Nam, Y., & Kim, D. Plasma protein-based and polygenic risk scores serve complementary roles in predicting inflammatory bowel disease. Pacific Symposium on Biocomputing. 2025 Jan;30:522–534. doi:10.1142/9789819807024_0037.