Clinical and biomedical modeling
Research agenda
My work is organized around one evidentiary problem: how to make model-based conclusions that remain reliable under patient heterogeneity, uncertainty, incomplete measurement, and differences across datasets or biological systems.
The work spans medical images, electronic health records, physiological measurements, and biomolecular data. Across these settings, I use causal reasoning, calibrated uncertainty, mechanistic structure, and reproducible computation to determine whether a model supports the decision at hand and where its interpretation should stop.
Three connected research directions
Patient-level clinical AI reliability
Identify where failures concentrate, whether they persist across modalities and encounters, and how calibration and uncertainty change interpretation.
Causal and statistical reasoning under uncertainty
Estimate clinically or biologically meaningful structure while reporting sensitivity, instability, and the assumptions required for interpretation.
Mechanism-informed biomedical modeling
Combine mechanistic simulation, scientific machine learning, and cross-system alignment while preserving biological constraints and unsupported ambiguity.
Future research direction
The next stage of this program is to connect these directions into a common framework for trustworthy clinical and biomedical modeling: patient-level reliability for prediction, explicit uncertainty for causal and statistical structure, and mechanistic constraints for translation across systems and populations.
Project portfolio
Selected projects in order of current research priority.
The project pages distinguish ongoing methodological development from completed analyses and published work.
Trustworthy multimodal clinical AI
Identify where errors concentrate, not only how often they occur.
At MIT Critical Data, I evaluate diagnostic-imaging models and link image-level errors to high-acuity clinical context. The unit of analysis is the examination, encounter, or patient, because cohort averages can conceal repeated failure in smaller groups.
- Calibration and uncertainty quantification
- Consensus-based harm scoring across model ensembles
- Subgroup, fairness, and instance-level error auditing
- Encounter-level linkage of MIMIC-CXR and MIMIC-IV
- Threshold and severity-sensitivity analysis
Causal inference & patient-specific decisions
Estimate structure, then quantify how stable the estimate is.
My causal-inference work combines ensemble Bayesian network learning, conditional-independence testing, MCMC exploration of graph structures, and bootstrap assessment of edge stability. BaMANI developed from my doctoral research on heterocellular networks in cancer.
The same evidentiary discipline guides my work on epilepsy-surgery outcomes. I interpret diagnostic performance alongside subgroup patterns, structural missingness, sensitivity analyses, and the clinical meaning of proposed thresholds.
- Bayesian and ensemble causal-network inference
- Bootstrap edge stability and multiple-testing control
- Penalized regression and prespecified sensitivity analysis
- Failure analysis for patient selection and treatment counseling
Mechanistic & multiscale scientific ML
Use biological structure to constrain prediction and simulation.
At Duke, I connect agent-based and differential-equation models with machine learning. Gradient-boosted trees, Gaussian-process surrogates, and physics-informed neural networks reduce the computational cost of exploring mechanistic systems while retaining explicit attention to uncertainty.
In the NIH-supported Duke and Weill Cornell congenital CMV project, these methods support maternal-fetal immune modeling, vaccine-efficacy analysis, and cross-species immune-cell alignment.
- Mechanistic simulators, ODEs, and agent-based models
- Gaussian-process and machine-learning surrogates
- Physics-informed neural networks
- Optimal transport with relaxed marginals
- Docker and SLURM/HPC reproducibility
Methodological backbone