EHR & clinical data science University of California San Diego Department of Surgery · 2024–present

Performance, generalizability, and fairness of a peripheral artery disease detection model

Tested the model across five University of California Health systems, including performance by patient phenotype and demographic group.

LightGBM OMOP SQL Python Databricks Fairness Social determinants of health Performance drift UC data platform
ManuscriptView details ↗

Peripheral artery disease detection using structured EHR data

Developed the model in the American Family Cohort and tested it on independent UC San Diego Health data.

Open-source External validation OMOP SQL Feature explainability Subgroup performance Claude Code
ManuscriptView details ↗
In development

Diabetic foot ulcer and amputation risk: prediction and causal inference

Early-stage project combining diabetic foot complication risk prediction with causal analysis of foot exams and amputation outcomes.

XGBoost Python Causal inference Epic Caboodle AWS SageMaker SQL Claude Code
Research GrantView details ↗
In development

Representation learning for longitudinal cardiovascular risk prediction

Learning patient representations from longitudinal EHR sequences for later prediction of stroke, amputation, myocardial infarction, and related events.

Deep learning Natural language processing Word2Vec Python Claude Code
ManuscriptView details ↗

Variation in peripheral artery disease care across University of California Health systems

Compared patient populations, provider involvement, guideline-directed therapy, and limb outcomes across five health systems.

OMOP Provider involvement & care pathways Databricks SQL Python Statistical analysis
Observational studyView details ↗
Medical imaging & MRI biomarkers University of California San Diego Department of Radiology · 2022–2024

Calibrating the RSI restriction score across echo times

Developed and validated a calibration method for the Restriction Spectrum Imaging restriction score in 197 prostate MRI cases.

Quantitative MRI Restriction-score biomarker Echo-time calibration MATLAB
ManuscriptView details ↗

Validating synthetic high b-value diffusion-weighted imaging for prostate cancer detection

Compared synthetic and acquired diffusion-weighted images in 151 prostate MRI cases, finding signal underestimation and pelvic artifacts that limit quantitative use.

Diffusion MRI Synthetic DWI MATLAB ROC analysis
ManuscriptView details ↗

ReIGNITE: Clinical validation of diffusion MRI-guided prostate tumor targeting

Prospective international reader study showing that quantitative restriction maps improved tumor contour accuracy, reduced complete misses, and made focal-boost targeting more consistent.

RSI restriction score MIM Software/Cloud Clinical validation Multi-reader analytics MATLAB
ManuscriptView details ↗

ReIGNITE: Clinical impact of prostate tumor contour variability

Converted multi-reader prostate tumor contours into focal boost plans to quantify how contour variability changes dose coverage and predicted biochemical-failure risk.

RapidPlan Contour variability DVH analysis Outcome modeling MIM Software MATLAB
ManuscriptView details ↗

Validating MRI-derived synthetic computed tomography for radiotherapy planning

Compared synthetic and clinical planning images across 43 brain radiotherapy plans, including registration, dose recalculation, and failure-mode review.

Synthetic CT Radiotherapy planning MIM Software Dosimetric QA
Research grantView details ↗
Radiation oncology & treatment planning automation University of California San Diego Department of Radiation Medicine & Applied Sciences · 2019–2022

Knowledge-based OAR dose prediction for cervical brachytherapy

Co-developed and validated a MATLAB model that used patient anatomy to predict achievable bladder, rectum, and sigmoid doses for plan-quality assessment.

Knowledge-based dose prediction MATLAB Model validation
ManuscriptView details ↗

Knowledge-based brachytherapy dose prediction for ORBIT-RT

Translated a MATLAB model into a one-click MIM Software extension that displayed predicted bladder, rectum, and sigmoid doses from patient contours.

Java MIM Java API Knowledge-based dose prediction ORBIT-RT preparation
ManuscriptView details ↗

Predicting dose differences between cervical brachytherapy applicators

Applied separate tandem-and-ring and tandem-and-ovoid dose models across cohorts and checked the predicted organ-at-risk differences against clinical plans.

Knowledge-based dose prediction Cross-applicator analysis MIM Software MATLAB analysis
ManuscriptView details ↗

Predicting the need for interstitial needles in cervical brachytherapy

Developed and validated models that predicted whether OAR constraints could be met without needles, using standardized no-needle replans as the reference.

Knowledge-based dose prediction MIM Software Needle classification BrachyVision replanning
ManuscriptView details ↗

Automated ARIA batch export

Developed and deployed a Java application that retrieved patient data from the ARIA oncology information system using a supplied medical record number list.

Java ARIA automation IT integration MIM / local export
Clinical deploymentView details ↗
Brachytherapy QA & electromagnetic tracking University Hospital Erlangen, Department of Radiation Oncology · 2016–2019

EMT-based patient study of catheter stability in breast brachytherapy

Designed the clinical workflow, performed 355 tracking measurements across 41 patients, analyzed the data, and presented the findings to clinical physicists.

MATLAB EM tracking Patient study Flexitron workflow
ManuscriptView details ↗

Decision framework for selective adaptive planning in breast brachytherapy

Used Plastimatch for deformable registration and contour propagation, reconstructed catheters and reapplied plans in OncentraBrachy, and analyzed the results in MATLAB to design a physician-informed adaptive-replanning cascade.

MATLAB Plastimatch OncentraBrachy DICOM RTStruct DIR
ManuscriptView details ↗

Quantifying observer variability in brachytherapy catheter reconstruction

Designed a 13-patient, 426-catheter study and performed breast brachytherapy treatment planning to determine how reconstruction variability translates into dwell-position variations and dosimetric changes.

MATLAB Treatment planning OncentraBrachy DICOM RT Plan
ManuscriptView details ↗

EMT-based automatic catheter reconstruction for brachytherapy planning

Built a C# workflow that registered EMT measurements to CT, exported catheter reconstructions as DICOM, and transferred them into OncentraBrachy.

C# 3D point-cloud registration OncentraBrachy integration
Clinical deploymentView details ↗