Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals
Movement Disorders · 2025
DOI: 10.1002/mds.30176 ↗Kurz gefasst
Fachartikel in der Zeitschrift Movement Disorders, 2025. Verfasst von Reghu Anandapadmanabhan und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, All India Institute of Medical Sciences (AIIMS), New Delhi, India. Hauptthemen laut MEDLINE: Deep Learning, Tremor, Essential Tremor, Parkinson Disease. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Department of Biotechnology, Ministry of Science and Technology, India.
Abstract (Originalsprache)
Background
No objective biomarkers exist for diagnosing and classifying tremor syndromes.
Objective
The aim was to develop and validate a deep learning (DL) algorithm for classifying tremors from hand‐drawn pen‐on‐paper spirals.
Methods
We recruited participants with dystonic tremor (DT), essential tremor (ET), essential tremor plus (ETP), Parkinson's disease (PD), cerebellar ataxia (AT), and healthy volunteers (HV). Participants drew free‐hand spirals on paper, which were used to train a DL algorithm based on transfer learning using InceptionResNetV2 and Keras sequential model. We validated the model externally in two independent tremor cohorts, evaluating accuracy and F1 scores, and compared its performance to expert raters.
Results
We recruited 521 participants and obtained 2078 spirals (365 DT, 215 ET, 208 ETP, 212 PD, 78 AT, and 525 HV). Mean age of the participants was 46.1 ± 12.4 years, duration of illness was 8.9 ± 8.3 years, and the mean Fahn–Tolosa–Marin Tremor Rating Scale score in patients was 32.4 ± 14.7. The DL classifier demonstrated an overall accuracy of 81% [95% confidence interval, CI: 0.77–0.85] in distinguishing among tremor syndromes. To mitigate the potential risks of data leakage and digital fingerprinting, the algorithm was redeveloped and reanalyzed, yielding an adjusted accuracy of 70% [95% CI: 0.66–0.74]. External validation on an independent cohort of 1535 spiral drawings resulted in an accuracy of 61% [95% CI: 0.59–0.63], with the adjusted algorithm achieving 59% [95% CI: 0.58–0.60], outperforming human raters (accuracy: 46%).
Conclusion
Supervised DL algorithms can effectively detect tremor syndromes from hand‐drawn spirals, offering unbiased, feature‐independent classification with higher accuracy than human raters. © 2025 International Parkinson and Movement Disorder Society.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology, All India Institute of Medical Sciences (AIIMS), New Delhi, India.
- Comprehensive Care Centre for Movement Disorders, Sree Chitra Tirunal Institute for Medical Sciences and Technology, Thiruvananthapuram, India.
- Department of Neurology, National Institute of Mental Health and Neuro Sciences, Bengaluru, India.
- Centre for Biomedical Engineering, Indian Institute of Technology, New Delhi, India.
- Center for Data Driven Discovery, California Institute of Technology, Pasadena, California, USA.
ORCID-Profile: Reghu Anandapadmanabhan, Aayushi Vishnoi, Venugopalan Yamuna Vishnu, Nitish Kamble, Vikram Holla, Achal Srivastava, Syam Krishnan, Roopa Rajan
Förderung
- Department of Biotechnology, Ministry of Science and Technology, India
Zitieren
APA
Anandapadmanabhan, R., Vishnoi, A., Raman, G., Thachan, J., Gangaraju, B. A., Radhakrishnan, D., Vishnu, V. Y., Kamble, N., Holla, V., James, P., Srivastava, A., Joshi, D., Mahabal, A., Krishnan, S., Kumar Pal, P., & Rajan, R. (2025). Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals. Movement Disorders. https://doi.org/10.1002/mds.30176
Vancouver
Anandapadmanabhan R, Vishnoi A, Raman G, Thachan J, Gangaraju BA, Radhakrishnan D, et al. Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals. Movement Disorders. 2025. doi:10.1002/mds.30176
BibTeX
@article{Anandapadmanabhan2025,
author = {Anandapadmanabhan, Reghu and Vishnoi, Aayushi and Raman, Geetha and Thachan, Jeena and Gangaraju, Beulah Amulyavathi and Radhakrishnan, Divya and Vishnu, Venugopalan Yamuna and Kamble, Nitish and Holla, Vikram and James, Praveen and Srivastava, Achal and Joshi, Deepak and Mahabal, Ashish and Krishnan, Syam and Kumar Pal, Pramod and Rajan, Roopa},
title = {Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals},
journal = {Movement Disorders},
year = {2025},
doi = {10.1002/mds.30176}
}
EUVIMED