Aayushi Vishnoi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Aayushi Vishnoi has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Achal Kumar Srivastava
Department of Neurology, Neuroscience Centre, All India Institute of Medical Sciences, New Delhi, India
2 shared publications - Reghu Anandapadmanabhan
Department of Neurology All India Institute of Medical Sciences New Delhi India
2 shared publications Alish Dipani
National Brain Research Centre (NBRC) Manesar India
1 shared publication- Anna Latorre
Department of Clinical and Movement Neurosciences, UCL Queen Square Institute of Neurology, 33 Queen Square, London WC1N 3BG, UK
1 shared publication Ashish Mahabal
Center for Data Driven Discovery California Institute of Technology Pasadena California USA
1 shared publicationBeulah Amulyavathi Gangaraju
Department of Neurology National Institute of Mental Health and Neuro Sciences Bengaluru India
1 shared publication
Latest Publications
- 17 March 2025
- Published by Wiley in Movement Disorders
- Vol. 40 (6) , 1172-1181
Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals
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.
- 17 March 2025
- Published by Wiley in Movement Disorders
- Vol. 40 (6) , 1172-1181
Deep Learning–Based Artificial Intelligence Algorithm to Classify Tremors from Hand‐Drawn Spirals
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.
- 14 December 2023
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 11 (2) , 136-142
Essential Tremor and Essential Tremor Plus Are Essentially Similar Electrophysiologically
Background: The merits of classifying the heterogeneous group of essential tremors into essential tremor (ET) and essential tremor plus (ETP) are debated.Objectives: We studied the electrophysiological and spiral characteristics of tremor in ET and ETP.Methods: We reviewed standardized videos from a tremor database and clinically classified patients into ET, ETP, or dystonic tremor (DT). The following variables were derived from combined tri‐axial accelerometry–surface electromyography (EMG)—peak frequency, total power, peak power, full width half maximum, tremor stability index and EMG‐coherence. We analyzed hand‐drawn spirals to derive mean deviation, tremor variability, inter‐, and intra‐loop widths. We compared these variables among the groups.Results: We recruited 72 participants (81.9% male) with mean age 47.7 ± 16.1 years and Fahn‐Tolosa‐Marin Tremor Rating Scale total score 31.1 ± 14.1. Patients with ET were younger (P = 0.014) and had less severe tremor (P = 0.020) compared to ETP and DT. In ETP group, 48.6% had subtle dystonia. Peak frequency was greater in ETP (7.3 ± 0.3 Hz) compared to DT (6.1 ± 0.4 Hz; P = 0.024). Peak power was greater in ETP and DT for postural tremor. Rest tremor was recordable on accelerometry in 26.7% of ET. Other variables were similar among the groups.Conclusion: Electrophysiological evaluation revealed postural tremor of frequency 6 to 7 Hz in ET, ETP, and DT with subtle differences more severe tremor in ETP and DT, and higher frequency in ETP compared to DT. Our findings suggest a similar tremor oscillator in these conditions, supporting the view that these entities are part of a spectrum of tremor disorders, rather than distinct etiological entities.
- 14 December 2023
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 11 (2) , 136-142
Essential Tremor and Essential Tremor Plus Are Essentially Similar Electrophysiologically
Background: The merits of classifying the heterogeneous group of essential tremors into essential tremor (ET) and essential tremor plus (ETP) are debated.Objectives: We studied the electrophysiological and spiral characteristics of tremor in ET and ETP.Methods: We reviewed standardized videos from a tremor database and clinically classified patients into ET, ETP, or dystonic tremor (DT). The following variables were derived from combined tri‐axial accelerometry–surface electromyography (EMG)—peak frequency, total power, peak power, full width half maximum, tremor stability index and EMG‐coherence. We analyzed hand‐drawn spirals to derive mean deviation, tremor variability, inter‐, and intra‐loop widths. We compared these variables among the groups.Results: We recruited 72 participants (81.9% male) with mean age 47.7 ± 16.1 years and Fahn‐Tolosa‐Marin Tremor Rating Scale total score 31.1 ± 14.1. Patients with ET were younger (P = 0.014) and had less severe tremor (P = 0.020) compared to ETP and DT. In ETP group, 48.6% had subtle dystonia. Peak frequency was greater in ETP (7.3 ± 0.3 Hz) compared to DT (6.1 ± 0.4 Hz; P = 0.024). Peak power was greater in ETP and DT for postural tremor. Rest tremor was recordable on accelerometry in 26.7% of ET. Other variables were similar among the groups.Conclusion: Electrophysiological evaluation revealed postural tremor of frequency 6 to 7 Hz in ET, ETP, and DT with subtle differences more severe tremor in ETP and DT, and higher frequency in ETP compared to DT. Our findings suggest a similar tremor oscillator in these conditions, supporting the view that these entities are part of a spectrum of tremor disorders, rather than distinct etiological entities.