Boosting LLM-assisted diagnosis: 10-minute LLM tutorial elevates radiology residents’ performance in brain MRI interpretation

Abstract

To evaluate the impact of a structured tutorial on the use of a large language model (LLM)-based search engine on radiology residents’ performance in brain MRI differential diagnosis. In this study, nine radiology residents determined the three most likely differential diagnoses for three sets of ten brain MRI cases with a challenging yet definite diagnosis. Each set was assessed (1) with the support of conventional internet search, (2) using an LLM-based search engine (© Perplexity AI) without prior tutorial, or (3) using the LLM-based search engine after a structured 10-minute tutorial. Reader responses were rated using a binary and numeric scoring system. Reading times and confidence levels (measured on a 5-point Likert scale) were recorded for each case. Search engine logs were examined to quantify user interaction metrics, and to identify hallucinations and misinterpretations in LLM responses. Radiology residents achieved the highest accuracy when employing the LLM-based search engine following the tutorial, indicating the correct diagnosis among the top three differential diagnoses in 62.5% of cases (55/88). This was followed by the LLM-assisted workflow before the tutorial (44.8%; 39/87) and the conventional internet search workflow (32.2%; 28/87). The LLM tutorial led to significantly higher performance (binary scores: p = 0.042, numeric scores: p = 0.016) and confidence (p = 0.006) but resulted in no relevant differences in reading times. Hallucinations were found in 5.1% of LLM queries. Our findings demonstrate the considerable benefits that even low-effort educational interventions on LLMs can provide, highlighting their potential role in radiology training programs.

Ähnliche Arbeiten