RETRACTED: New Artificial Intelligence ChatGPT Performs Poorly on the 2022 Self-assessment Study Program for Urology

Abstract

Introduction:Large language models have demonstrated impressive capabilities, but application to medicine remains unclear. We seek to evaluate the use of ChatGPT on the American Urological Association Self-assessment Study Program as an educational adjunct for urology trainees and practicing physicians.Methods:One hundred fifty questions from the 2022 Self-assessment Study Program exam were screened, and those containing visual assets (n=15) were removed. The remaining items were encoded as open ended or multiple choice. ChatGPT’s output was coded as correct, incorrect, or indeterminate; if indeterminate, responses were regenerated up to 2 times. Concordance, quality, and accuracy were ascertained by 3 independent researchers and reviewed by 2 physician adjudicators. A new session was started for each entry to avoid crossover learning.Results:ChatGPT was correct on 36/135 (26.7%) open-ended and 38/135 (28.2%) multiple-choice questions. Indeterminate responses were generated in 40 (29.6%) and 4 (3.0%), respectively. Of the correct responses, 24/36 (66.7%) and 36/38 (94.7%) were on initial output, 8 (22.2%) and 1 (2.6%) on second output, and 4 (11.1%) and 1 (2.6%) on final output, respectively. Although regeneration decreased indeterminate responses, proportion of correct responses did not increase. For open-ended and multiple-choice questions, ChatGPT provided consistent justifications for incorrect answers and remained concordant between correct and incorrect answers.Conclusions:ChatGPT previously demonstrated promise on medical licensing exams; however, application to the 2022 Self-assessment Study Program was not demonstrated. Performance improved with multiple-choice over open-ended questions. More importantly were the persistent justifications for incorrect responses—left unchecked, utilization of ChatGPT in medicine may facilitate medical misinformation.

RETRACTED: Google Bard Artificial Intelligence vs the 2022 Self-Assessment Study Program for Urology

“…Overall, the results of this study align well with our previous exploration 3 of ChatGPT: not only did Google Bard perform poorly on the 2022 SASP for urology, but Bard’s responses also revealed concerning flaws. Although Bard is claimed to gather research and cite sources with real-time web searches, it still “hallucinates” facts (like ChatGPT).…”

“…Unlike ChatGPT, Bard boasts the ability to cite sources, interpret images, and perform real-time web searches for up-to-date information. Given our previous exploration 3 of AI performance on the 2022 AUA Self-Assessment Study Program (SASP), 4 we sought to evaluate Bard’s performance and assess its utility as an educational tool for urology trainees and physicians.…”

Conformity of ChatGPT recommendations with the AUA/SUFU guideline on postprostatectomy urinary incontinence

“…6 Other studies have used more complex questions and clinical scenarios and reported accuracy rates ranging from 26.7% to 81.5% for the chatbot, depending on the specific methods employed or the version that was tested. 7,15,16 In common, the studies that compared the two versions of the chatbot have consistently shown superior performance for version 4. 7,15 In our study, open questions, with different levels of complexity, were posed to ChatGPT.…”

Comparison of ChatGPT and Traditional Patient Education Materials for Men’s Health

“…The current ChatGPT version is not specialized in medical information and was trained using the entire Internet without controls for validity. 12,31 Moreover, it was only trained using data through 2021, although some studies suggest the model is self-learning from newer 2022 to 2023 data. 5 This creates risks of inaccuracy and limited ability to incorporate emerging research.…”

“…Misinformation on ChatGPT is apparently minimal but real. 5,6,12-14 Particularly worrisome is AI hallucination, where misinformation may arise from subjective, emotion-laden questioning. 3,4…”