ChatGPT in the diagnosis and management of complex polyneuropathies: comparative analysis with neurologists using real-world cases
De Lorenzo, Alberto Moretti, Giulia Sofia Bertini, Alessandro De Lorenzo, Alice Pisciotta, Chiara Collet-Vidiella, Roger Eftimov, Filip Falzone, Yuri Matteo Fasolino, Alessandra Fortanier, Etienne
De Lorenzo, Alberto
Moretti, Giulia Sofia
Bertini, Alessandro
De Lorenzo, Alice
Pisciotta, Chiara
Collet-Vidiella, Roger
Eftimov, Filip
Falzone, Yuri Matteo
Fasolino, Alessandra
Fortanier, Etienne
Abstract
Polyneuropathies are common and often require specialist expertise for accurate diagnosis. This study evaluated the diagnostic performance of ChatGPT-4o on real-world polyneuropathy cases, comparing it to peripheral neuropathy specialists and non-specialist neurologists. One hundred cases were selected from two tertiary centers in Milan, Italy. Standardized summaries included clinical, laboratory, and electrophysiological data. ChatGPT-4o was prompted to provide a leading diagnosis, two differentials, and a confirmatory test. Neurologists reviewed the same cases and generated comparable outputs, then could revise their responses after viewing ChatGPT-4o's suggestions. ChatGPT-4o achieved 65.5% leading diagnosis accuracy, comparable to non-specialists (63.0%) but lower than specialists (74.0%, p = 0.002). For differential diagnoses, it outperformed non-specialists (82.0% vs. 77.5%, p = 0.043) and recommended more appropriate tests (68.0% vs. 53.0%, p < 0.001). After reviewing ChatGPT-4o outputs, non-specialists revised their assessments in 21.8% of cases, improving accuracy. ChatGPT-4o shows potential as a diagnostic aid, particularly in non-specialist or resource-limited settings.
MIDER Authors
Affiliations
IRCCS Humanitas Research Hospital; University of Milan; Fondazione IRCCS Istituto Neurologico Carlo Besta; Hospital de la Santa Creu i Sant Pau; Amsterdam University Medical Centre; University of Amsterdam; San Raffaele Scientific Institute; AORN Cardarelli; Aix-Marseille University; Assistance Publique des Hopitaux de Marseille; Assistance Publique des Hopitaux de Paris; IRCCS San Raffaele Scientific Institute; King's College Hospital NHS Foundation Trust; King's College London; KPJ Specialized Hospital; The Cyprus Institute of Neurology and Genetics; Hospital Británico de Buenos Aires; Sant'Andrea Hospital; University of Belgrade; Aston University; Hospital Universitari i Politècnic La Fe; Centro de Investigación Biomédica en Red de Enfermedades Raras; Universitat de València; University of São Paulo; University Federico II of Naples; Hospital Clínico Universitario de Valencia; Sorbonne University; Hospital Británico de Buenos Aires; University Hospitals Birmingham NHS Foundation Trust; IRCCS Istituto Auxologico Italiano; Ospedale dei Castelli; University Hospital of the Ribeirão Preto Medical School; Universitat Autonoma de Barcelona; University Hospital of Sassari; Università degli Studi di Milano; Santobono-Pausilipon Children's Hospital; Istituto Di Ricerche Farmacologiche Mario Negri IRCCS; Milan University; Humanitas University
Date
2026-06-05
Type
Article
Collections
Citation
De Lorenzo A, Moretti GS, Bertini A, De Lorenzo A, Pisciotta C, Collet-Vidiella R, Eftimov F, Falzone YM, Fasolino A, Fortanier E, Gendre T, Gentile F, Hadden RD, Islam B, Kleopa K, Cejas LL, Leonardi L, Mandia D, Masingue M, Mira V, Peric S, Querol L, Rajabally YA, Sevilla T, Tomaselli PJ, Tozza S, Bosca M, Brouwer M, Cocco A, Cousyn L, De Santis T, Gonzalez F, Lukic MJ, Mistry N, Maranzano A, Morena E, Nakano FN, Olmedo-Saura G, Sechi E, Ticozzi N, Troisi S, Tsokkos T, Wittwer A, Bianchi E, Nobile-Orazio E, Pareyson D, Doneddu PE. ChatGPT in the diagnosis and management of complex polyneuropathies: comparative analysis with neurologists using real-world cases. NPJ Digit Med. 2026 Jun 5. doi: 10.1038/s41746-026-02815-y. Epub ahead of print.