EUVIMEDEUVIMED entdecken
Crossref

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

Lucas Alessandro, Nicolas Bianciotti, Luciana Salama, Santiago Volmaro, Veronica Navarrine, Lucia Ameghino iD, Julieta Arena, Santiago Bestoso, Veronica Bruno, Sergio Castillo Torres iD, Mauricio Chamorro, Blas Couto iD und 19 weitere

Movement Disorders · 2025

DOI: 10.1002/mds.30168 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Movement Disorders, 2025. Verfasst von Lucas Alessandro und 30 weiteren Autor:innen. Beteiligte Einrichtung: Departmento de Neurologia, Fleni, Buenos Aires, Argentina. Hauptthemen laut MEDLINE: Artificial Intelligence, Ataxia. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 62 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceAtaxiaHumansMaleAdultMiddle AgedFemaleChronic DiseaseAgedAlgorithms

Stichwörter der Autor:innen

artificial intelligenceataxiadiagnostic approachgenetic diseasesmovement disordersrare diseases

Autor:innen und Institutionen

  • Departmento de Neurologia, Fleni, Buenos Aires, Argentina.
  • Entelai, Buenos Aires, Argentina.
  • Facultad de Medicina, Universidad de Buenos Aires, Buenos Aires, Argentina.
  • Sección de Movimientos Anormales, Departamento de Neurología, Fleni, Buenos Aires, Argentina.
  • Sección Parkinson y Trastornos del Movimiento del Hospital Italiano Buenos Aires (HIBA).
  • Department of Clinical Neurosciences, University of Calgary Hotchkiss Brain Institute, Calgary, Alberta, Canada.

ORCID-Profile: Lucia Ameghino, Sergio Castillo Torres, Blas Couto, Viviana Martinez Villota, Mauricio Paez Maggio, Malco Rossi

Zitieren

APA

Alessandro, L., Bianciotti, N., Salama, L., Volmaro, S., Navarrine, V., Ameghino, L., Arena, J., Bestoso, S., Bruno, V., Castillo Torres, S., Chamorro, M., Couto, B., De La Riestra, T., Echeverria, F., Genco, J., Gonzalez Del Boca, F., Guarnaschelli, M., Giugni, J. C., Laffue, A., …, & Rossi, M. (2025). Artificial Intelligence‐Based Virtual Assistant for the Diagnostic Approach of Chronic Ataxias. Movement Disorders. https://doi.org/10.1002/mds.30168

Vancouver

Alessandro L, Bianciotti N, Salama L, Volmaro S, Navarrine V, Ameghino L, et al. Artificial Intelligence‐Based Virtual Assistant for the Diagnostic Approach of Chronic Ataxias. Movement Disorders. 2025. doi:10.1002/mds.30168

BibTeX
@article{Alessandro2025,
  author = {Alessandro, Lucas and Bianciotti, Nicolas and Salama, Luciana and Volmaro, Santiago and Navarrine, Veronica and Ameghino, Lucia and Arena, Julieta and Bestoso, Santiago and Bruno, Veronica and Castillo Torres, Sergio and Chamorro, Mauricio and Couto, Blas and De La Riestra, Tomas and Echeverria, Florencia and Genco, Juan and Gonzalez Del Boca, Federico and Guarnaschelli, Marlene and Giugni, Juan Carlos and Laffue, Alfredo and Martinez Villota, Viviana and Medina Escobar, Alex and Paez Maggio, Mauricio and Rauek, Sebastian and Rodriguez Quiroga, Sergio and Tela, Marcela and Villa, Carolina and Sanguinetti, Olivia and Kauffman, Marcelo and Fernandez Slezak, Diego and Farez, Mauricio F and Rossi, Malco},
  title = {Artificial Intelligence‐Based Virtual Assistant for the Diagnostic Approach of Chronic Ataxias},
  journal = {Movement Disorders},
  year = {2025},
  doi = {10.1002/mds.30168}
}
Kostenlos starten →