Zhang’s NSF CAREER Award will advance AI for healthcare
Ping Zhang, assistant professor of computer science and engineering and biomedical informatics, has earned a $556,828 Faculty Early Career Development (CAREER) award from the National Science Foundation for his research related to improving artificial intelligence (AI) for healthcare.
The CAREER award is the National Science Foundation’s (NSF) most prestigious award in support of junior faculty who exemplify the role of teacher-scholars through outstanding research, excellent education and the integration of both. Zhang’s project is funded by the NSF program, Information Integration and Informatics.
His project, “Developing Actionable Methods for Observational Health Data” will integrate deep learning algorithms and causal inference techniques to advance precision medicine.
Observational health data such as electronic health records and health insurance claims contain large amounts of clinical information about diverse patients and their responses to treatments in real-world settings.
“Many existing machine learning methods focus on making predictions on observational data, such as the chance of death or risk of heart attack, instead of providing actionable suggestions to physicians,” explained Zhang. “This project will help physicians propose the right treatment for the right patient at the right time.”
Researchers will develop an AI system to identify optimal treatment regimens for critically ill patients to improve their chances of survival. Based on the patient’s health status, the AI system will suggest if and when to initiate and adjust treatment such as antibiotics, vasopressors, mechanical ventilation, and surgical procedures to physicians, and each choice affects the patient's survival at the end of the hospital stay.
From a computer science perspective, combining causal inference with deep learning for modeling observational health data—which involves complex, confounding factors that can conceal true causal relationships and even lead to fake associations—will make theoretical contributions to machine learning and data mining, said Zhang.
“We will make all materials, such as source code, documentations and scientific findings available for public access,” he added. “From an application perspective, the project will develop a series of AI tools for clinical decision support.”
“We will also closely collaborate with medical researchers and physicians for model validation on various clinical problems, and will actively seek technology transfer opportunities,” said Zhang, noting that his team will work with the Department of Emergency Medicine at The Ohio State University Wexner Medical Center for sepsis treatment planning, and with the Center for Pediatric Trauma Research at Nationwide Children’s Hospital for pediatric trauma care.
Because the project is interdisciplinary, it is ideal for teaching machine learning for healthcare applications, and will provide graduate and undergraduate students with new programs, courses, research, and internship opportunities. Zhang is co-developing a new master’s program, “AI in Digital Health,” a joint effort of the Computer Science and Engineering and Biomedical Informatics departments. The program will prepare students with a core curriculum in machine learning (ML) and AI, and enhance this core by its applications to digital health. Students will be able to interact with ML/AI technologies to create novel innovations in biomedical, clinical, and healthcare research.
This project will also actively include underrepresented students and outreach to local high schools and the general public.
Zhang holds joint appointments in the Departments of Computer Science and Engineering, and Biomedical Informatics in the College of Medicine. He also leads the Artificial Intelligence in Medicine (AIMed) Lab at Ohio State and is a core faculty member in the Translational Data Analytics Institute (TDAI). Prior to joining Ohio State in 2019, he was a research staff member and master inventor at the IBM T.J. Watson Research Center. His research has contributed to multiple AI products, including Watson for Drug Discovery, and Watson for Patient Safety.
by Meggie Biss, College of Engineering Communications | firstname.lastname@example.org