Biomedical Informatics and Data Science

Program affiliation
Biomedical Informatics and Data Science

Research summary

Key words

Program affiliation
Biomedical Informatics and Data Science

Research summary
Our lab develops and applies informatics methods to support clinical research and learning health systems across a range of neurological and chronic disease domains. Core research areas include **computational phenotyping**, where we focus on developing, evaluating, and critically appraising algorithms that identify patient populations from large-scale EHR data; **real-world evidence generation**, where we build automated pipelines and predictive models that translate clinical data into actionable insights for care and research; and **research infrastructure for learning health systems**, where we design and evaluate the data harmonization pipelines, classification tools, and integration methods that make large-scale clinical research possible. Across all of these areas, we maintain a strong emphasis on algorithmic equity, examining how methods perform across demographic subgroups and surfacing structural disparities in access and care. These methods are applied to a broad set of clinically significant conditions—including diabetes, stroke, Alzheimer's disease, ALS, movement disorders, and epilepsy—that share common informatics challenges such as diagnostic uncertainty, heterogeneous data, and underrepresented populations. Trainees gain hands-on experience in EHR-based cohort construction, multimodal data integration, algorithm development and validation, and the translation of informatics tools into practice, with opportunities to collaborate with clinical experts across these domains.

Key words
precision medicine, ehr, data science, phenotyping, informatics

Program affiliation
Biomedical Informatics and Data Science
Human and Statistical Genetics

Research summary
My research is focused on investigating the genetic determinants of under-studied musculoskeletal phenotypes, determining the impact of occupational burdens on musculoskeletal disease, and understanding interactions between genetic and non-genetic risk factors for musculoskeletal disease.

Key words

Program affiliation
Biomedical Informatics and Data Science

Research summary
Focused on applied clinical informatics research to support clinicians adapting to health information technology

Key words

Program affiliation
Computational and Systems Biology
Biomedical Informatics and Data Science
Developmental Regenerative and Stem Cell Biology

Research summary

Key words
Bioinformatics, epigenetics

Program affiliation
Biomedical Informatics and Data Science
Cancer Biology
Computational and Systems Biology

Research summary
Deep learning; AI; Multi-omics; Translational cancer research; Cancer; Genomics; Imaging

Key words
RNA-seq, WGS, genomics, sequencing, deep learning, machine learning, artificial intelligence, AI, bioinformatics, computational biology, algorithm, multi-omics, cancer, HPV, radiation, PET, MRI, image

Program affiliation
Biomedical Informatics and Data Science
Computational and Systems Biology

Research summary
My research integrates causal modeling and machine learning to improve the reliability of real-world evidence generation and to improve the trustworthiness of AI-based clinical algorithms.

Key words
causal inference, machine learning, artificial intelligence, electronic health records, clinical informatics