ChatGPT fails at heart risk assessment

Despite ChatGPT's reported ability to pass medical exams, new research indicates it would be unwise to rely on it for some health assessments, such as whether a patient with chest pain needs to be hospitalized.

In a study involving thousands of simulated cases of patients with chest pain, ChatGPT provided inconsistent conclusions, returning different heart risk assessment levels for the exact same patient data. The generative AI system also failed to match the traditional methods physicians use to judge a patient’s cardiac risk. The findings were published in the journal PLOS ONE.

"ChatGPT was not acting in a consistent manner," said lead author Dr. Thomas Heston, a researcher with Washington State University's Elson S. Floyd College of Medicine. "Given the exact same data, ChatGPT would give a score of low risk, then next time an intermediate risk, and occasionally, it would go as far as giving a high risk."

The authors believe the problem is likely due to the level of randomness built into the current version of the software, ChatGPT4, which helps it vary its responses to simulate natural language. This same randomness, however, does not work well for healthcare uses that require a single, consistent answer, Heston said.

"We found there was a lot of variation, and that variation in approach can be dangerous," he said. "It can be a useful tool, but I think the technology is going a lot faster than our understanding of it, so it's critically important that we do a lot of research, especially in these high-stakes clinical situations."

Chest pains are common complaints in emergency rooms, requiring doctors to rapidly assess the urgency of a patient's condition. Some very serious cases are easy to identify by their symptoms, but lower risk ones can be trickier, Heston said, especially when determining whether someone should be hospitalized for observation or sent home and receive outpatient care.

Currently medical professionals often use one of two measures that go by the acronyms TIMI and HEART to assess heart risk. Heston likened these scales to calculators with each using a handful of variables including symptoms, health history and age. In contrast, an AI neural network like ChatGPT can assess billions of variables quickly, meaning it could potentially analyze a complex situation faster and more thoroughly.

For this study, Heston and colleague Dr. Lawrence Lewis of Washington University in St. Louis first generated three datasets of 10,000 randomized, simulated cases each. One dataset had the seven variables of the TIMI scale, the second set included the five HEART scale variables and a third had 44 randomized health variables. On the first two datasets, ChatGPT gave a different risk assessment 45% to 48% of the time on individual cases than a fixed TIMI or HEART score. For the last data set, the researchers ran the cases four times and found ChatGPT often did not agree with itself, returning different assessment levels for the same cases 44% of the time.

Despite the negative findings of this study, Heston sees great potential for generative AI in health care - with further development. For instance, assuming privacy standards could be met, entire medical records could be loaded into the program, and an in an emergency setting, a doctor could ask ChatGPT to give the most pertinent facts about a patient quickly. Also, for difficult, complex cases, doctors could ask the program to generate several possible diagnoses.

"ChatGPT could be excellent at creating a differential diagnosis and that's probably one of its greatest strengths," said Heston. "If you don’t quite know what's going on with a patient, you could ask it to give the top five diagnoses and the reasoning behind each one. So it could be good at helping you think through a problem, but it’s not good at giving the answer."

Heston TF, Lewis LM.
ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain.
PLoS One. 2024 Apr 16;19(4):e0301854. doi: 10.1371/journal.pone.0301854

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Patients say "Yes..ish" to the…

As artificial intelligence (AI) continues to be integrated in healthcare, a new multinational study involving Aarhus University sheds light on how dental patients really feel about its growing role in...

Brains vs. Bytes: Study Compares Diagnos…

A University of Maine study compared how well artificial intelligence (AI) models and human clinicians handled complex or sensitive medical cases. The study published in the Journal of Health Organization...

'AI Scientist' Suggests Combin…

An 'AI scientist', working in collaboration with human scientists, has found that combinations of cheap and safe drugs - used to treat conditions such as high cholesterol and alcohol dependence...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...