Enhancing tremor classification: Transformer-based analysis of biomechanics patterns for Parkinson's and essential tremor.
Differentiating Essential Tremor and Parkinson's Disease is challenging due to overlapping tremor characteristics, including similar frequency ranges (4–8 Hz) and kinetic manifestations that defy conventional clinical differentiation. This study aimed to develop a multiclass differentiation system f...
| Publicado en: | Clinical Biomechanics Vol. 127 |
|---|---|
| Autores principales: | , , , , , , |
| Formato: | research Journal Article |
| Publicado: |
Elsevier B.V.
Jul2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=186499359&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 186499359 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02680033 JB1 jtl: Clinical Biomechanics issn: 02680033 maglogo: N pubinfo: dt: Jul2025 vid: 127 pid: 467 pub: Elsevier B.V. place: New York, New York artinfo: ui: 186499359 186499359 186499359 10.1016/j.clinbiomech.2025.106599 186499359 ppct: 1 formats: tig: atl: Enhancing tremor classification: Transformer-based analysis of biomechanics patterns for Parkinson's and essential tremor. aug: au: Mahali, Muhammad Izzuddin Leu, Jenq-Shiou Avian, Cries Darmawan, Jeremie Theddy Faisal, Muhamad Putro, Nur Achmad Sulistyo Prakosa, Setya Widyawan affil: Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan sug: subj: Essential Tremor Diagnosis Parkinson Disease Diagnosis Biomechanics Essential Tremor Physiopathology Parkinson Disease Physiopathology Deep Learning Movement Motor Skills Task Performance and Analysis Human Accelerometers Severity of Illness Thumb Fingers Wrist Comparative Studies Signal Processing, Computer Assisted Protocols Descriptive Statistics Decision Making, Clinical Artificial Intelligence Neurodegenerative Diseases ab: Differentiating Essential Tremor and Parkinson's Disease is challenging due to overlapping tremor characteristics, including similar frequency ranges (4–8 Hz) and kinetic manifestations that defy conventional clinical differentiation. This study aimed to develop a multiclass differentiation system for Essential Tremor, Parkinson's Disease, and Healthy Controls by employing deep learning to decode distinct biomechanical patterns from multi-sensor movement data during dynamic motor tasks. Tremor severity was assessed using accelerometers positioned on the thumb, index finger, metacarpal, and wrist during four protocols: two static (rest, postural) and two dynamic (free motion, motion with object). We employed a Transformer-based model with multi-head attention to capture spatiotemporal movement patterns. Two analytical approaches were compared: (1) feature extraction followed by Transformer processing, and (2) direct Transformer processing of raw signals. The feature-based approach achieved perfect classification accuracy (100 %) for postural holding (utilizing integrated absolute value and other derived features) and free motion (employing mean power and additional features). The raw signal approach similarly attained 100 % accuracy in classifying free motion (200-sample window) and motion with object (200- and 300-sample windows). Integration of multi-protocol dynamic tasks (free motion and motion with object) yielded 99.32 % overall accuracy. Crucially, dynamic protocols demonstrated consistent superiority over static protocols in diagnostic performance. The Transformer model with multi-head attention effectively identified disease-specific biomechanical patterns. Its high accuracy in distinguishing Essential Tremor, Parkinson's Disease, and Healthy Control participants, particularly during dynamic tasks, positions it as a promising tool for enhancing clinical decision-making and artificial intelligence-assisted monitoring of neurodegenerative disorders. • Deep Learning model with multi-head attention improves tremor classification accuracy. • Biomechanical movement protocols enhance differentiation of tremor types. • Multi-protocol approach increases diagnostic in clinical assessments. • AI-based model enables effective monitoring of neurodegenerative diseases. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|