Temple University
Temple University
College of Public Health
Our work

Projects

Federally and foundation-funded research applying AI, informatics, and analytics to some of the most pressing challenges in health and health equity.

Dream-KG project logo

Proto-OKN Theme 1: Dream-KG

Develop Dynamic, REsponsive, Adaptive, and Multifaceted Knowledge Graphs to address homelessness with Explainable AI

Dream-KG is building a knowledge graph to support homelessness triage, service coordination, and data integration across sectors — co-designed with a Community Advisory Board.

Principal Investigator: Huanmei Wu, PhD

Co-Investigators: Chiu Tan, PhD; Yuzhou Chen, PhD; Ying Ding, PhD; Philip McCallion, PhD; Omar Martinez, JD, MPH, MS

Sponsor: National Science Foundation

Timeline: 10/01/2023 – 09/30/2026

SaTC:EDU project logo

SaTC:EDU: Cybersecurity Training for Next-Generation Healthcare Professionals

Developing, deploying, and evaluating comprehensive cybersecurity-training materials for graduate students in health informatics, nursing, social work, and public health.

Principal Investigator: Chiu Tan, PhD

Co-Investigators: Huanmei Wu, PhD; Bari Dzomba, MS, PhD; Kesa Bond, PhD, MHA, MA, RHIA, PMP

Sponsor: National Science Foundation

Timeline: 08/01/2023 – 07/31/2026

DETERMINE: Diabetes prEdicTion and Equity through Responsible MachINe lEarning

Building an AI-powered, equitable, interpretable, and generalizable diabetes-risk prediction model.

Principal Investigator: Feifan Lu, PhD

Co-Investigators: Huanmei Wu, PhD

Sponsor: NIH, AIM-AHEAD Program, UMass Chan Medical School

Timeline: 09/17/2023 – 03/16/2026

Targeting Interventions for Peripheral Artery Disease & Chronic Limb-Threatening Ischemia

Piloting a multi-state leg-amputation analysis to reduce preventable amputations

Identifying ZIP codes with high amputation rates to target outreach in at-risk communities, reduce preventable amputations, and inform scalable prevention strategies.

Principal Investigator: Ron Renzi, DPM

Co-Investigators: Paul J. DiMuzio, MD, FACS; Neva White, DNP, CRNP, CDCES; Huanmei Wu, PhD; Susan VonNessen-Scanlin, DNP, MBA, MSN, CRNP-AC; Olamide Alabi, MD, RPVI, MS; Carl Yang, PhD; Julia Glaser, MD, FACS

Sponsor: The Foundation to Advance Vascular Cures (Collaborative Patient-Centric Research Award)

Timeline: 07/01/2025 – 09/30/2026

Never Again: Advancing the Prevention of Recurrent Child Sexual Abuse

Identifying drivers of recurrent childhood sexual abuse to inform innovative, targeted, systems-level prevention strategies.

Principal Investigator: Julia Kobulsky, PhD

Co-Investigators: Chang Su, PhD; Huanmei Wu, PhD; Krista Schroeder, PhD; Kevin Henry, PhD; Jingwei Wu, PhD

Sponsor / Award: NIH / NICHD (Eunice Kennedy Shriver National Institute of Child Health and Human Development) · Weill Cornell Medical College

Timeline: 09/20/2024 – 08/19/2028

AI2Equity: Advancing Health Equity in Cardiovascular Risk Prediction

Integrating SDoH data to advance health equity in cardiovascular-disease risk prediction

An AI-driven initiative integrating clinical and social-determinants-of-health data to improve cardiovascular-disease risk prediction across diverse populations.

Principal Investigator: Feifan Lu, PhD

Co-Investigators: Ben Gerber, MD, MPH; Huanmei Wu, PhD; Omar Martinez, JD, MPH, MS

Sponsor: NIH / NHLBI

Timeline: 04/20/2024 – 03/31/2028

Enhancing Trial Capacity at Temple University ALS Center of Hope

Expanding clinical-trial capacity while reducing participation burden and advancing equitable enrollment of individuals with ALS from racial and ethnic minority populations.

Principal Investigator: Terry Heiman-Patterson, MD

Co-Investigators: Huanmei Wu, PhD

Sponsor: The ALS Association

Timeline: 01/01/2023 – 12/31/2026

Improving Preventive Care Through Data-Driven Insights for Chronic Disease Management

Ensuring that patients with chronic conditions like hypertension and type-2 diabetes receive consistent preventive care — using AI and health-information-exchange data to identify who is at risk of falling out of care.

Funder: Robert Wood Johnson Foundation (RWJF) Health Data for Action Initiative

Grant Number: 78961

Other Projects

Systematic Review of Diabetes-Prevention Interventions

Project Author: Syeda Maryam Abidi

Synthesizing evidence from randomized controlled trials of pharmacological, lifestyle, and digital-health interventions to prevent progression from prediabetes to type-2 diabetes — examining incidence and key metabolic outcomes across diverse populations to identify effective, scalable prevention strategies.

Cost-Effectiveness of GLP-1 Therapy for Prediabetes

Project Author: Syeda Maryam Abidi

Evaluating the cost-effectiveness of GLP-1 receptor-agonist therapy for high-risk individuals with prediabetes. Using a health-system perspective, the analysis compares long-term costs and outcomes versus standard care to inform payer coverage and diabetes-prevention policy.

Medicaid Gatekeeping & Access to Continuous Glucose Monitoring

Project Author: Syeda Maryam Abidi

Examining how state Medicaid programs govern access to continuous glucose monitoring through coverage rules. Using policy surveillance and legal-epidemiology methods, the study builds a typology of CGM gatekeeping and tests whether policy design is associated with diabetes outcomes.

Multi-Source Data Pipeline for Longitudinal Analysis

Project Author: Junchao Fei

Developing a multi-source data pipeline that links person-level administrative records into analyzable episodes, uses a rule-guided, LLM-assisted workflow to extract information from unstructured interview text, and assembles tract-level neighborhood measures for consistent linkage between individual records and community context.

Clinical & SDoH Data Integration for Equity Monitoring

Project Author: Junchao Fei

Building a practical framework that integrates clinical data and social determinants of health into a consistent, analysis-ready structure, then applying statistical analyses to track temporal trends, compare patterns across communities, and support equity-focused monitoring.