June 8, 2023
2 mins read

ChatGPT performs poorly at US’ urologists exam

The explanations provided by ChatGPT were longer than those provided by SASP, but “frequently redundant and cyclical in nature”, according to the authors…reports Asian Lite News

The much-acclaimed OpenAI’s ChatGPT chatbot has failed a urologist exam in the US, according to a study.

This comes at a time of growing interest in the potential role of artificial intelligence (AI) technology in medicine and healthcare.

The study, reported in the journal Urology Practice, showed that ChatGPT achieved less than a 30 per cent rate of correct answers on the American Urologist Association’s widely used Self-Assessment Study Program for Urology (SASP).

“ChatGPT not only has a low rate of correct answers regarding clinical questions in urologic practice, but also makes certain types of errors that pose a risk of spreading medical misinformation,” said Christopher M. Deibert, from University of Nebraska Medical Center.

The AUA’s Self-Assessment Study Program (SASP) is a 150-question practice examination addressing the core curriculum of medical knowledge in urology.

The study excluded 15 questions containing visual information such as pictures or graphs.

Overall, ChatGPT gave correct answers to less than 30 per cent of SASP questions, 28.2 per cent of multiple-choice questions and 26.7 per cent of open-ended questions.

The chatbot provided “indeterminate” responses to several questions. On these questions, accuracy was decreased when the LLM model was asked to regenerate its answers.

For most open-ended questions, ChatGPT provided an explanation for the selected answer.

The explanations provided by ChatGPT were longer than those provided by SASP, but “frequently redundant and cyclical in nature”, according to the authors.

“Overall, ChatGPT often gave vague justifications with broad statements and rarely commented on specifics,” Dr. Deibert said.

Even when given feedback, “ChatGPT continuously reiterated the original explanation despite it being inaccurate”.

The researchers suggest that while ChatGPT may do well on tests requiring recall of facts, it seems to fall short on questions pertaining to clinical medicine, which require “simultaneous weighing of multiple overlapping facts, situations and outcomes”.

“Given that LLMs are limited by their human training, further research is needed to understand their limitations and capabilities across multiple disciplines before it is made available for general use,” Dr. Deibert said.

“As is, utilisation of ChatGPT in urology has a high likelihood of facilitating medical misinformation for the untrained user.”

ALSO READ-US judge orders lawyers not to use ChatGPT-drafted content  

Previous Story

Here are the most expensive cities for expats

Next Story

Erdogan dials Putin, offers mediation in Ukraine conflict

Latest from -Top News

Grave Horror in Lanka

Suspicions are mounting that the body remains may belong to civilians who disappeared during the brutal civil war between government forces and Tamil Tiger rebels, which raged from 1983 until its bloody

US General Axed Over Trump Clash

Lt Gen. Kruse is the latest high-ranking official to be removed under the second Trump administration and the second senior military intelligence leader to be ousted….reports Asian Lite News The Pentagon has

London Puts Beijing on Hold

The proposed embassy, earmarked for the site of a historic two-century-old building near the Tower of London, has been bogged down in dispute for more than three years…reports Asian Lite News The

Hands Off City Cash, Judge Tells Trump

The court’s latest order underscores a growing judicial pushback against efforts by the Trump administration to penalize sanctuary communities….reports Asian Lite News A federal judge in San Francisco has ruled that the

Pentagon restricts Ukraine’s use of US missiles

The disclosure comes as President Donald Trump grows increasingly frustrated at his failure to deliver a breakthrough in the three-year-old conflict…reports Asian Lite News The United States is quietly preventing Ukraine from
Go toTop

Don't Miss

‘ChatGPT can perform analysis at fraction of human cost’

In some cases, the AI model managed to surpass the

Apple nod to ChatGPT-driven app amid concerns

Apple approved the app called aBlueMail’ following assurances from its