AI steps up in healthcare: GPT-3.5 and 4 excel in clinical reasoning

In a recent study published in npj Digital Medicine, researchers developed diagnostic reasoning prompts to investigate whether large language models (LLMs) could simulate diagnostic clinical reasons.

Doctor sits at laptop with futuristic projection representing artificial intelligence
Study: Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. Image Credit: chayanuphol/Shutterstock.com

LLMs, artificial intelligence-based systems trained using enormous amounts of text data, are known for human-simulating performances in tasks like writing clinical notes and passing medical exams. However, understanding their clinical diagnostic reasoning abilities is crucial for their integration into clinical care.

Recent studies have concentrated on open-ended-type clinical questions, indicating that innovative large-language models, like GPT-4, have the potential to identify complex patients. Prompt engineering has begun to overcome this issue, as LLM performance varies based on the type of prompts and questions.

About the study

In the present study, researchers assessed diagnostic reasoning by GPT-3.5 and GPT-4 for open-ended-type clinical questions, hypothesizing that GPT models could outperform conventional chain-of-thought (CoT) prompting with diagnostic reasoning prompts.

The team used the revised MedQA United States Medical Licensing Exam (USMLE) dataset and the New England Journal of Medicine (NEJM) case series to compare conventional chain-of-thought prompting with various diagnostic logic prompts modeled after the cognitive procedures of forming differential diagnosis, analytical reasoning, Bayesian inferences, and intuitive reasoning.

They investigated whether large-language models can mimic clinical reasoning skills using specialized prompts, combining clinical expertise with advanced prompting techniques.

The team used prompt engineering to generate prompts for diagnostic reasoning, converting questions into free responses by eliminating multiple-choice selections. They included only step II and step III questions from the USMLE dataset and those evaluating patient diagnosis.

Each round of prompt engineering involved GPT-3.5 accuracy evaluation using the MEDQA training set. The training and testing sets, which contained 95 and 518 questions, respectively, were reserved for assessment.

The researchers also evaluated GPT-4 performance on 310 cases recently published in the NEJM journal. They excluded 10 that did not have definitive final diagnoses or surpassed the maximum context length for GPT-4. They compared conventional CoT prompting with the best-performing clinical diagnostic reasoning CoT prompts (reasoning for differential diagnosis) on the MedQA dataset.

Every prompt consisted of two exemplifying questions with rationales using target reasoning techniques or few-shot learning. The study evaluation used free-response questions from the USMLE and NEJM case report series to facilitate rigorous comparison between prompting strategies.

Physician authors, attending physicians, and an internal medicine resident evaluated language model responses, with each question assessed by two blinded physicians. A third researcher resolved the disagreements. Physicians verified the accuracy of answers using software when needed.

Results

The study reveals that GPT-4 prompts could mimic the clinical reasoning of clinicians without compromising diagnostic accuracy, which is crucial to assessing the accuracy of LLM responses, thereby enhancing their trustworthiness for patient care. The approach can help overcome the black box limitations of LLMs, bringing them closer to safe and effective use in medicine.

GPT-3.5 accurately responded to 46% of assessment questions by standard CoT prompting and 31% by zero-shot-type non-chain-of-thought prompting. Of prompts associated with clinical diagnostic reasoning, GPT-3.5 performed the best with intuitive-type reasonings (48% versus 46%).

Compared to classic chain-of-thought, GPT-3.5 performed significantly inferiorly with analytical reasoning prompts (40%) and those for developing differential diagnoses (38%), while Bayesian inferences fell short of significance (42%). The team observed an inter-rater consensus of 97% for MedQA data GPT-3.5 evaluations.

The GPT-4 API returned errors for 20 test questions, limiting the size of the test dataset to 498. GPT-4 displayed more accuracy than GPT-3.5. GPT-4 showed 76%, 77%, 78%, 78%, and 72% accuracies with classical chain-of-thought, intuitive-type reasoning, differential diagnostic reasoning, analytical reasoning prompts, and Bayesian inferences, respectively. The inter-rater consensus was 99% for GPT-4 MedQA evaluations.

Regarding the NEJM dataset, GPT-4 scored 38% accuracy with conventional CoT versus 34% with that for formulating differential diagnosis (a 4.2% difference). The inter-rater consensus for the GPT-4 NEJM assessment was 97%. GPT-4 responses and rationales for the complete NEJM dataset. Prompts promoting step-by-step reasoning and focusing on a single diagnostic reasoning strategy performed better than those combining multiple strategies.

Overall, the study findings showed that GPT-3.5 and GPT-4 have improved reasoning abilities but not accuracy. GPT-4 performed similarly with conventional and intuitive-type reasoning chain-of-thought prompts but worse with analytical and differential diagnosis prompts. Bayesian inferences and chain-of-thought prompting also showed worse performance compared to classical CoT.

The authors propose three explanations for the difference: the reasoning mechanisms of GPT-4 could be integrally different from those of human providers; it could explain post-hoc diagnostic evaluations in desired reasoning formats; or it could attain maximum precision with the provided vignette data.

Journal reference:
Pooja Toshniwal Paharia

Written by

Pooja Toshniwal Paharia

Dr. based clinical-radiological diagnosis and management of oral lesions and conditions and associated maxillofacial disorders.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Toshniwal Paharia, Pooja Toshniwal Paharia. (2024, January 28). AI steps up in healthcare: GPT-3.5 and 4 excel in clinical reasoning. News-Medical. Retrieved on February 26, 2024 from https://www.news-medical.net/news/20240128/AI-steps-up-in-healthcare-GPT-35-and-4-excel-in-clinical-reasoning.aspx.

  • MLA

    Toshniwal Paharia, Pooja Toshniwal Paharia. "AI steps up in healthcare: GPT-3.5 and 4 excel in clinical reasoning". News-Medical. 26 February 2024. <https://www.news-medical.net/news/20240128/AI-steps-up-in-healthcare-GPT-35-and-4-excel-in-clinical-reasoning.aspx>.

  • Chicago

    Toshniwal Paharia, Pooja Toshniwal Paharia. "AI steps up in healthcare: GPT-3.5 and 4 excel in clinical reasoning". News-Medical. https://www.news-medical.net/news/20240128/AI-steps-up-in-healthcare-GPT-35-and-4-excel-in-clinical-reasoning.aspx. (accessed February 26, 2024).

  • Harvard

    Toshniwal Paharia, Pooja Toshniwal Paharia. 2024. AI steps up in healthcare: GPT-3.5 and 4 excel in clinical reasoning. News-Medical, viewed 26 February 2024, https://www.news-medical.net/news/20240128/AI-steps-up-in-healthcare-GPT-35-and-4-excel-in-clinical-reasoning.aspx.

Comments

The opinions expressed here are the views of the writer and do not necessarily reflect the views and opinions of News Medical.
Post a new comment
Post
You might also like...
Study uncovers unique genetic diversity in Australian Indigenous populations