Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May;40(5):906-916.
doi: 10.1002/mds.30168. Epub 2025 Mar 22.

Artificial Intelligence-Based Virtual Assistant for the Diagnostic Approach of Chronic Ataxias

Lucas Alessandro  1   2 , Nicolas Bianciotti  3 , Luciana Salama  3 , Santiago Volmaro  3 , Veronica Navarrine  3 , Lucia Ameghino  4 , Julieta Arena  4 , Santiago Bestoso  5 , Veronica Bruno  6 , Sergio Castillo Torres  7 , Mauricio Chamorro  8 , Blas Couto  9 , Tomas De La Riestra  10 , Florencia Echeverria  11 , Juan Genco  12 , Federico Gonzalez Del Boca  13 , Marlene Guarnaschelli  14 , Juan Carlos Giugni  15 , Alfredo Laffue  1 , Viviana Martinez Villota  16 , Alex Medina Escobar  17 , Mauricio Paez Maggio  18 , Sebastian Rauek  19 , Sergio Rodriguez Quiroga  20 , Marcela Tela  4 , Carolina Villa  21 , Olivia Sanguinetti  22 , Marcelo Kauffman  23   24 , Diego Fernandez Slezak  2   25   26 , Mauricio F Farez  2   27 , Malco Rossi  4   28
Affiliations

Artificial Intelligence-Based Virtual Assistant for the Diagnostic Approach of Chronic Ataxias

Lucas Alessandro et al. Mov Disord. 2025 May.

Abstract

Background: Chronic ataxias, a complex group of over 300 diseases, pose significant diagnostic challenges because of their clinical and genetic heterogeneity. Here, we propose that artificial intelligence (AI) can aid in the identification and understanding of these disorders through the utilization of a smart virtual assistant.

Objectives: The aim is to develop and validate an AI-powered virtual assistant for diagnosing chronic ataxias.

Methods: A non-commercial virtual assistant was developed using advanced algorithms, decision trees, and large language models. In the validation process, 453 clinical cases from the literature were selected from 151 causes of chronic ataxia. The diagnostic accuracy was compared with that of 21 neurologists specializing in movement disorders and GPT-4. Usability regarding time and number of questions needed were also evaluated.

Results: The virtual assistant accuracy was 90.9%, higher than neurologists (18.3%), and GPT-4 (19.4%). It also significantly outperformed in causes of ataxia distributed by age, inheritance, frequency, associated clinical manifestations, and treatment availability. Neurologists and GPT-4 mentioned 110 incorrect diagnoses, 83.6% of which were made by GPT-4, which also generated seven data hallucinations. The virtual assistant required an average of 14 questions and 1.5 minutes to generate a list of differential diagnoses, significantly faster than the neurologists (mean, 19.4 minutes).

Conclusions: The virtual assistant proved to be accurate and easy fast-use for the diagnosis of chronic ataxias, potentially serving as a support tool in neurological consultation. This diagnostic approach could also be expanded to other neurological and non-neurological diseases. © 2025 International Parkinson and Movement Disorder Society.

Keywords: artificial intelligence; ataxia; diagnostic approach; genetic diseases; movement disorders; rare diseases.

PubMed Disclaimer

References

    1. Rossi M, Anheim M, Durr A, et al. The genetic nomenclature of recessive cerebellar ataxias. Mov Disord 2018;33(7):1056–1076. https://doi.org/10.1002/mds.27415
    1. Lange LM, Gonzalez‐Latapi P, Rajalingam R, et al. Nomenclature of genetic movement disorders: recommendations of the International Parkinson and Movement Disorder Society task force ‐ an update. Mov Disord 2022;37(5):905–935. https://doi.org/10.1002/mds.28982
    1. Beaudin M, Matilla‐Dueñas A, Soong BW, et al. The classification of autosomal recessive cerebellar ataxias: a consensus statement from the Society for Research on the cerebellum and ataxias task force. Cerebellum 2019;18(6):1098–1125. https://doi.org/10.1007/s12311-019-01052-2
    1. Beaudin M, Klein CJ, Rouleau GA, Dupré N. Systematic review of autosomal recessive ataxias and proposal for a classification. Cerebellum Ataxias 2017;4:3.
    1. Németh AH, Kwasniewska AC, Lise S, Parolin Schnekenberg R, Becker EBE, Bera KD, et al. Next generation sequencing for molecular diagnosis of neurological disorders using ataxias as a model. Brain 2013;136(10):3106–3118.

LinkOut - more resources