Campus Life

Competition highlights generative AI’s power, pitfalls for medical diagnoses

Center for Socially Responsible AI announces winners of ‘Diagnose-a-thon'

Winners of the first "Diagnose-a-thon" challenge received cash prizes, with the first place earning $1,000.  Credit: woravut/Adobe Stock. All Rights Reserved.

UNIVERSITY PARK, Pa. — Penn State’s Center for Socially Responsible Artificial Intelligence (CSRAI) announced the winners of its first-ever “Diagnose-a-thon.” The virtual competition, held Nov. 11-17, invited Penn Staters to identify the power and pitfalls of using generative AI tools like ChatGPT for medical inquiries. 

Acting as patients and medical providers, participants prompted large language models (LLMs) to generate accurate or potentially harmful diagnoses. A panel of nine Penn State physicians reviewed each submission and assigned points to each response on its validity, quality of information and logical reasoning. Awards were given to participants who earned the most points, regardless of whether their submissions were accurate or misleading.

The winners were: 

  • First place, $1,000: Asa Reynolds, integrated undergraduate/graduate student, College of Information Sciences and Technology (IST) 

  • Second place, $500: Bryan Shabroski, undergraduate student, College of Engineering 

  • Third place, $250: Wahid Uz Zaman, doctoral student, College of Engineering 

Five participants received $50 consolation prizes: 

  • Adelaide Klutse, doctoral student, College of Health and Human Development 

  • Saiber Shaikh, doctoral student, College of Education 

  • Meruyert Aristombayeva, visiting scholar, College of IST 

  • Ajay Narayanan Sridhar, doctoral student, College of Engineering 

  • Rosemary Aviste, doctoral student, College of the Liberal Arts 

A $1,000 prize was also awarded to Shaoqing Zhang, doctoral student in the Eberly College of Science, for creating a prompt that produced the diagnoses that would be most harmful if acted upon. 

“A total of 200 diagnoses were submitted to the competition, with 138 in the patient track, 74 in the medical professional track and eight in the out-of-the-box track,” said Bonam Mingole, a doctoral student in the College of IST and CSRAI student affiliate, who organized the event. “The variety in prompt styles and level of details demonstrates the diverse ways users engage with LLMs for medical assistance.” 

More than 85% of responses were determined to provide accurate diagnoses by the participant and panel. However, several entries identified where LLMs missed making connections between symptoms and potential causes — such as how leg pain can be associated with an untreated strep throat infection — or overlooked basic details when providing guidance — such as omitting the step for a surgeon to confirm the site of the operation before proceeding. 

Other entries noted that while many tools responded with disclaimers that they were not qualified health care professionals, some did not explicitly urge the user to seek professional medical attention for pressing or potentially serious conditions. 

“The Diagnose-a-thon was a unique opportunity to understand both the incredible potential and the associated risks of using generative AI to answer health queries by general internet users,” said Amulya Yadav, associate professor in the College of IST and CSRAI associate director of programs. “This competition highlights the need to raise awareness for responsible development and integration of AI tools, particularly in fields like health care where errors can have serious consequences.” 

For example, one entry prompted the LLM to respond to a patient’s mental health crisis and thoughts of self-harm. According to the user, multiple generative AI tools attempted “to engage in therapeutic-style responses rather than immediate redirection to professional help, a dangerous development that could lead users to mistake AI interaction for actual mental health support and delay seeking crucial human intervention.” 

The competition organizers had anticipated that mostly medical students would be interested and able to determine the problems of using generative AI for diagnosing health conditions, according to S. Shyam Sundar, CSRAI director and James P. Jimirro Professor of Media Effects in the Donald P. Bellisario College of Communications, but the response was much broader. 

“We had robust participation from all corners of the University, with winners coming from a wide spectrum of colleges, from science to liberal arts, from education to engineering,” he said. “The use of generative AI for health issues is clearly universal, creating an urgent need to promote more literacy about its strengths and pitfalls.” 

About the Center for Socially Responsible Artificial Intelligence

The Center for Socially Responsible Artificial Intelligence, which launched in 2020, promotes high-impact, transformative AI research and development, while encouraging the consideration of social and ethical implications in all such efforts. It supports a broad range of activities from foundational research to the application of AI to all areas of human endeavor. 

Last Updated January 15, 2025

Contact