The work I keep coming back to
Research on representation learning, foundation models, language models, and survival analysis for oncology. Work spans health records, pathology reports and slides, radiology, and omics, with software for data integration, patient embeddings, information extraction, and outcome modeling.
14 publications, 11 conference abstracts, and 8 talks and presentations. Authorship order follows each publication, with co-first and corresponding authorship noted where the publication record establishes it. Also on Google Scholar and ORCID.
Manuscripts
CT-Derived Radiomic Signature of MUC6 Expression Improves Guideline-Based Risk Stratification in Intraductal Papillary Mucinous Neoplasms
Robust Transcription Factor Binding Site Prediction and Explainability Using a Heterogeneous Mixture of Experts Architecture
Using Consensus-Based Reasoning and Large Language Models to Extract Structured Data From Surgical Pathology Reports
HONeYBEE: enabling scalable multimodal AI in oncology through foundation model-driven embeddings
Robust Multimodal Fusion for Survival Prediction in Cancer Patients
Self-Normalizing Multi-Omics Neural Network for Pan-Cancer Prognostication
Multimodal data integration for oncology in the era of deep neural networks: a review
Building Flexible, Scalable, and Machine Learning-Ready Multimodal Oncology Datasets
Transformers in time-series analysis: A tutorial
A Comparison of Feature Selection Techniques for First-day Mortality Prediction in the ICU
Role of Datasets in Precision Pathology
Talks & Presentations
Multimodal AI for Precision Oncology: From Data Integration to CDS
Clinically Integrated Multi-Agent Artificial Intelligence System for Automated Extraction of Neuro-Oncology Biomarkers from Pathology Reports
CLeVER Multi-Agent AI Orchestration for Temporal-Aware Clinical Variable Extraction from Unstructured Medical Records
AI-Driven Extraction of Key Clinical Data from Pathology Reports to Enhance Cancer Registries
Accelerate Cancer Research With AI-Driven Multimodal Data Integration
Extraction of Discrete Information from Pathology Reports Using Local and Private LLMs
Advancing Cancer Research Through Integrated Multimodal Data Analysis: A Comprehensive Framework for Precision Oncology
Pan-cancer Learning for Survival Prediction
Preprints & Dissertation
EAGLE: Efficient Alignment of Generalized Latent Embeddings for Multimodal Survival Prediction with Interpretable Attribution Analysis
Embedding-based Multimodal Learning on Pan-Squamous Cell Carcinomas for Improved Survival Outcomes
Embedding-Based Deep Learning Frameworks for Multimodal Oncology Data Integration
Conference Abstracts
Real-world evaluation of multimodal AI: Foundation model-driven multimodal AI for GBM, NSCLC, and PDAC
Multi-agent AI orchestration for temporal-aware extraction of social determinants of health from unstructured clinical records in cancer populations
Multi-Agent System for Automated Extraction of Neuro-Oncology Biomarkers from Pathology Reports
Using Patient Embeddings From Foundation Models for Enhanced Survival Analysis in Lung Squamous Cell Carcinoma
Predicting treatment outcomes using cross-modality correlations in multimodal oncology data
PARADIGM: an embeddings-based multimodal learning framework with foundation models and graph neural networks
AI-Driven Extraction of Key Clinical Data from Pathology Reports to Enhance Cancer Registries
BIO24-031: Hierarchical Multimodal Learning on Pan-Squamous Cell Carcinomas for Improved Survival Outcomes
BIO24-030: Unifying Multimodal Data, Time Series Analytics, and Contextual Medical Memory: Introducing MINDS as an Oncology-Centric Cloud-Based Platform
Multimodal transformer model improves survival prediction in lung cancer compared to unimodal approaches
SeNMo: A self-normalizing deep learning model for enhanced multi-omics data analysis in oncology