Christine Ik, MPH

PhD Student and HCI Researcher, Drexel University

Hi, I'm Christine,

I am a PhD student at the College of Computing & Informatics
at Drexel University, and advised by Dr. Sarcevic in the Interactive Systems for Healthcare Research Lab. Our research focuses on designing intelligent systems to support decison making and infection control in dynamic, fast-paced clinical settings, such as ICUs and EDs.

My current project explores ways to monitor and improve personal protective equipment (PPE) compliance among healthcare providers through the design of context-aware reminders and alert systems. My overall research involves participatory design methods and qualitative analysis to create interactive technologies that respond to the challenges of real clinical environments, and ultimately improve patient outcomes.

Prior to starting my PhD, I worked in public health research as an epidemiologist and project manager, leading interdisciplinary teams and managing projects in neonatal research, including neonatal studies on prematurity and infant mortality.

AI assisted alerts to Improve PPE Compliance

This project explores how AI can support healthcare workers in improving PPE compliance. Through interviews and on-site observations, we aim to identify common barriers to PPE use. Co-design workshops with frontline staff will then enable us develop effective, context-aware reminder and alert systems that fit seamlessly into existing workflows.

Manuscripts

  1. Abu Jawdeh EG, Hunt CE, Eichenwald E, Corwin MJ, McEntire B, Heeren T, Crowell LM, Ikponmwonba C, Saroufim A, Kerr S; ICAF Study Group. Adverse effects of COVID-19 pandemic on a multicenter randomized controlled trial. J Perinatol. 2022 Dec 29:1–6. doi: 10.1038/s41372-022-01592-2. E pub ahead of print. PMID: 36581761; PMCID: PMC9798371. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9798371

Abstracts

Oral and Poster Presentations

    1. Ikponmwonba, C., Zellner, K., Sarcevic, A., 2025. Adapting Hand Hygiene Monitoring Technologies to PPE Compliance: An Initial Exploratory Literature Review; 2025 April 4; Denver, CO. Presented at the Computing Research Association, Grad Cohort 2025

    2. Ikponmwonba, C., McEntire, B., SUID Tissue Consortium: Advancing Medical Research through Postmortem Tissue Donation, American SIDS Institute. National Association of Medical Examiner 2021
      3. Annual Meeting. https://www.thename.org/assets/docs/NAME_Complete%20Program.pdf (Poster)

    COMPLETE LIST

A Retrospective Analysis of COVID-19 Outbreaks in
Nursing Homes

During the first wave of COVID-19 infections in the US, Nursing homes across the country became ground zero for the transmission and death from the disease. Multiple factors can be linked to why nursing homes were hot spots in the pandemic, such as congregate living, underlying health conditions in the elderly population, amongst others.

This project utilizes Nursing Home COVID-19 Public surveillance data to investigate the extent of the infections, recoveries, mortality, and vaccination rates across various nursing centers in the US. While the long-term clinical and social implications of the pandemic are still being uncovered, the results from this project can serve as a decision-making guide on how to effectively allocate resources and mitigate excessive risks for long-term care facility preparedness in the event of a pandemic.

Cervical Cancer Risk Prediction
Using XGBoost

Cervical cancer kills about 4,000 women in the U.S. and about 300,000 women worldwide. Studies have shown that high sexual activity Human Papillloma Virus (HPV) is one of the key factors that increases the risk of having cervical cancer.

This project aims to build and train an XGBoost model to predict cervical cancer in 859 patients.

Binary Classification of CVD and Cancer Cells Using AWS AutoGluon

Cardiovascular disease (CVD) remains as the leading cause of death in the United States, accounting for 928,741 deaths in the year 2020.

This project aims to train several machine learning classifiers to detect and classify cardiovascular disease and cancer on autopilot using the AutoGluon Machine Learning library.

Contact Form