Blab AI
West Virginia University Professor Wins NSF CAREER Award to Study Trust in AI-Assisted Clinical Decision-Making
On June 15 2026, West Virginia University (WVU) announced that assistant professor Avishek Choudhury of the Department of Industrial and Management Systems Engineering has been selected as a recipient of the National Science Foundation’s (NSF) Faculty Early Career Development, or CAREER, award. The CAREER grant—NSF’s most prestigious honor for junior faculty—will fund Choudhury’s investigation into how clinicians develop and adjust trust in artificial intelligence (AI) tools that aid clinical decision‑making.
Choudhury’s research sits at the intersection of patient safety, AI, and clinical decision‑making. He plans to construct a machine‑learning framework that can detect shifts in clinicians’ trust as they use AI recommendations in time‑sensitive settings such as emergency departments and intensive care units. “Artificial intelligence is increasingly used to support decision‑making in health care, especially in time‑sensitive settings such as emergency care and intensive care units, but people do not always rely on these systems appropriately,” Choudhury said.
The study will employ simulation‑based experiments in which clinicians interact with AI‑assisted decision tools. During these trials, the team will gather behavioral data—eye‑gaze patterns, heart‑rate variability, brain activity, and skin electrical changes that signal physiological arousal—alongside survey responses and interaction logs. Machine‑learning methods will then identify early indicators of trust, overreliance, and insufficient reliance.
Trust, Choudhury explained, is dynamic. “It can change from one decision to the next, based on factors such as the accuracy of previous AI recommendations, the user’s workload and the complexity of the clinical situation. If we can identify those changes early, we can design AI systems that respond more effectively to users’ needs,” he added.
A key barrier to trust, the researcher notes, is liability. “If an AI system provides a recommendation and something goes wrong, the clinician remains accountable for the decision,” Choudhury said. “That is why trustworthy AI must do more than produce an answer. It must support clinicians in evaluating the recommendation and deciding whether it is appropriate for a particular patient and situation.”
The CAREER award spans five years and is granted to faculty who demonstrate a strong integration of research and education. Since 1997, 53 WVU faculty have received the award, bringing nearly $25 million in federal support to the university. Interim Vice President for WVU Research Ming Lei praised the award, noting that it “will not only propel Dr. Choudhury’s career, but also help improve health care for people.”
Choudhury’s work is part of a broader effort to make AI tools in health care more transparent and trustworthy. By focusing on the human‑technology interaction and the dynamic nature of trust, the project aims to produce AI systems clinicians can use confidently while preserving their professional judgment. The NSF CAREER award will fund the development of the machine‑learning framework, the design of simulation experiments, and the analysis of physiological and behavioral data.
The award underscores WVU’s standing as an R1 research institution and its commitment to advancing AI research with direct implications for patient safety and clinical practice. The results of Choudhury’s study are expected to inform the design of future AI‑assisted clinical decision‑support systems and could influence guidelines for safe AI deployment in hospitals. The NSF grant will support the project’s next five years of research and education activities.
Choudhury’s research sits at the intersection of patient safety, AI, and clinical decision‑making. He plans to construct a machine‑learning framework that can detect shifts in clinicians’ trust as they use AI recommendations in time‑sensitive settings such as emergency departments and intensive care units. “Artificial intelligence is increasingly used to support decision‑making in health care, especially in time‑sensitive settings such as emergency care and intensive care units, but people do not always rely on these systems appropriately,” Choudhury said.
The study will employ simulation‑based experiments in which clinicians interact with AI‑assisted decision tools. During these trials, the team will gather behavioral data—eye‑gaze patterns, heart‑rate variability, brain activity, and skin electrical changes that signal physiological arousal—alongside survey responses and interaction logs. Machine‑learning methods will then identify early indicators of trust, overreliance, and insufficient reliance.
Trust, Choudhury explained, is dynamic. “It can change from one decision to the next, based on factors such as the accuracy of previous AI recommendations, the user’s workload and the complexity of the clinical situation. If we can identify those changes early, we can design AI systems that respond more effectively to users’ needs,” he added.
A key barrier to trust, the researcher notes, is liability. “If an AI system provides a recommendation and something goes wrong, the clinician remains accountable for the decision,” Choudhury said. “That is why trustworthy AI must do more than produce an answer. It must support clinicians in evaluating the recommendation and deciding whether it is appropriate for a particular patient and situation.”
The CAREER award spans five years and is granted to faculty who demonstrate a strong integration of research and education. Since 1997, 53 WVU faculty have received the award, bringing nearly $25 million in federal support to the university. Interim Vice President for WVU Research Ming Lei praised the award, noting that it “will not only propel Dr. Choudhury’s career, but also help improve health care for people.”
Choudhury’s work is part of a broader effort to make AI tools in health care more transparent and trustworthy. By focusing on the human‑technology interaction and the dynamic nature of trust, the project aims to produce AI systems clinicians can use confidently while preserving their professional judgment. The NSF CAREER award will fund the development of the machine‑learning framework, the design of simulation experiments, and the analysis of physiological and behavioral data.
The award underscores WVU’s standing as an R1 research institution and its commitment to advancing AI research with direct implications for patient safety and clinical practice. The results of Choudhury’s study are expected to inform the design of future AI‑assisted clinical decision‑support systems and could influence guidelines for safe AI deployment in hospitals. The NSF grant will support the project’s next five years of research and education activities.
