Research Output

Publications

33+ peer-reviewed publications across clinical AI, ICU monitoring, surgical risk prediction, EHR data systems, and federated learning. 300+ citations.

school Google Scholar Profile

33+

Publications

300+

Citations

NIH Grants

calendar_today 2025

MANDARIN: Mixture-of-Experts for Dynamic Delirium and Coma Prediction in the ICU

Contreras et al. arXiv:2503.06059

Federated Learning for Predicting Major Postoperative Complications

Ren et al. Annals of Surgery Open, 6(2), e573

Unlocking Health Insights with Social Determinants of Health (SDoH) Data

Hu et al. arXiv:2503.19928

MELON: Multimodal Mixture-of-Experts for Long-Term Mobility Estimation in the ICU

Zhang et al. arXiv:2503.11695

calendar_today 2024

Risk-specific training cohorts to address class imbalance in surgical risk prediction

Balch et al. JAMA Surgery, 159(12), 1424–1431

Electronic Health Record Data Quality and Performance Assessments

Penev et al. JMIR Medical Informatics, 12(1), e58130

DeLLiriuM: A large language model for delirium prediction in the ICU using structured EHR

Contreras et al. arXiv:2410.17363

Acute kidney injury prediction for non-critical care patients

Adiyeke et al. arXiv:2402.04209

Federated learning model for predicting major postoperative complications

Park et al. arXiv:2404.06641

Global Contrastive Training for Multimodal Electronic Health Records with Language Supervision

Ma et al. arXiv:2404.06723

Temporal Cross-Attention for Dynamic Embedding of Multimodal EHR Data

Ma et al. arXiv:2403.04012

Promoting AI Competencies for Medical Students: A Framework for Clinical AI Education

Ma et al. arXiv:2407.18939

Transparent AI: Explainable Interface for Predicting Postoperative Complications

Ren et al. arXiv:2404.16064

Identifying acute illness phenotypes via deep temporal interpolation and clustering

Ren et al. Scientific Reports, 14(1), 8442

Risk-Specific Training Cohorts Improve Performance of a Deep Learning Surgical Risk Prediction Model

Balch et al. 239(5), S170–S171

A multi-cohort study on prediction of acute brain dysfunction states using multimodal physiological data

Silva et al. arXiv:2403.07201

APRICOT-Mamba: Acuity Prediction in Intensive Care Unit (ICU) — Extended

Contreras et al. / Rashidi et al. Research Square, rs-3

MANGO: Multimodal Acuity traNsformer for intelliGent ICU Outcomes Prediction

Zhang et al. arXiv:2412.17832

calendar_today 2023

Clinical courses of acute kidney injury in hospitalized patients: A multistate analysis

Adiyeke et al. Scientific Reports, 13(1), 17781

Machine learning–enabled clinical information systems using FHIR data standards and AI algorithms

Balch et al. JMIR Medical Informatics, 11, e48297

Predicting risk of delirium from ambient noise and light in the ICU using deep learning

Bandyopadhyay et al. arXiv:2303.06253

Dynamic Delirium Prediction in the ICU using Machine Learning on Electronic Health Records

Contreras et al. Proceedings, 1–5

APRICOT: Acuity Prediction in Intensive Care Unit (ICU)

Contreras et al. CoRR

Detecting Visual Cues in the ICU and Association with Patient Clinical Status

Nerella, Guan et al. arXiv:2311.00565

AI-enhanced intensive care unit: Revolutionizing patient care with pervasive sensing and AI

Nerella, Guan et al. arXiv:2303.06252

Computable phenotypes for brain dysfunction in the ICU

Ren, Loftus, Guan et al. arXiv:2303.05504

Diurnal pain classification in critically ill patients using physiologic time series

Sena et al. Proceedings, 2207–2212

calendar_today 2022

Performance of a machine learning algorithm using electronic health record data to predict postoperative complications

Ren et al. JAMA Network Open, 5(5), e2211973

Physiologic signatures within six hours of hospitalization identify acute illness phenotypes with distinct 30-day outcomes

Ren et al. PLOS Digital Health, 1(10), e0000110

Multi-dimensional patient acuity estimation with longitudinal EHR tokenization and flexible clinical notes

Shickel et al. Frontiers in Digital Health, 4, 1029191

calendar_today 2020 & Earlier

Application of deep interpolation network for clustering of physiologic time series

Li et al. · 2020 arXiv:2004.13066

calendar_today Preprints & Other

Network PPM — Network-based Patient Phenotyping Model

Ren et al. Preprint