Artificial intelligence and pain medicine education: Benefits and pitfalls for the medical trainee.

Abstract

Objectives: Artificial intelligence (AI) represents an exciting and evolving technology that is increasingly being utilized across pain medicine. Large language models (LLMs) are one type of AI that has become particularly popular. Currently, there is a paucity of literature analyzing the impact that AI may have on trainee education. As such, we sought to assess the benefits and pitfalls that AI may have on pain medicine trainee education. Given the rapidly increasing popularity of LLMs, we particularly assessed how these LLMs may promote and hinder trainee education through a pilot quality improvement project.

Materials and methods: A comprehensive search of the existing literature regarding AI within medicine was performed to identify its potential benefits and pitfalls within pain medicine. The pilot project was approved by UPMC Quality Improvement Review Committee (#4547). Three of the most commonly utilized LLMs at the initiation of this pilot study - ChatGPT Plus, Google Bard, and Bing AI - were asked a series of multiple choice questions to evaluate their ability to assist in learner education within pain medicine.

Results: Potential benefits of AI within pain medicine trainee education include ease of use, imaging interpretation, procedural/surgical skills training, learner assessment, personalized learning experiences, ability to summarize vast amounts of knowledge, and preparation for the future of pain medicine. Potential pitfalls include discrepancies between AI devices and associated cost-differences, correlating radiographic findings to clinical significance, interpersonal/communication skills, educational disparities, bias/plagiarism/cheating concerns, lack of incorporation of private domain literature, and absence of training specifically for pain medicine education. Regarding the quality improvement project, ChatGPT Plus answered the highest percentage of all questions correctly (16/17). Lowest correctness scores by LLMs were in answering first-order questions, with Google Bard and Bing AI answering 4/9 and 3/9 first-order questions correctly, respectively. Qualitative evaluation of these LLM-provided explanations in answering second- and third-order questions revealed some reasoning inconsistencies (e.g., providing flawed information in selecting the correct answer).

Conclusions: AI represents a continually evolving and promising modality to assist trainees pursuing a career in pain medicine. Still, limitations currently exist that may hinder their independent use in this setting. Future research exploring how AI may overcome these challenges is thus required. Until then, AI should be utilized as supplementary tool within pain medicine trainee education and with caution.