BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Poster Flash Talks Group B: Polymyography markers for Tremor Class
 ification: A Novel Approach for Differentiating Parkinsonian vs Essential 
 Tremor - Kevin Reynolds (CNRS - Ecole Normale Superieure Paris)
DTSTART:20251203T140000Z
DTEND:20251203T140500Z
UID:TALK241090@talks.cam.ac.uk
DESCRIPTION:Tremor\, a prevalent movement disorder encountered in 2&ndash\
 ;6% of neurological consultations\, presents significant diagnostic challe
 nges\, particularly in differentiating Parkinsonian tremor (PD) from essen
 tial tremor (ET) due to overlapping clinical features. Existing methods\, 
 including clinical observation and neuroimaging\, are limited by subjectiv
 ity\, cost\, and accessibility.\nThis study introduces a novel\, objective
 \, and efficient electrophysiological framework based on electromyographic
  (EMG) signal analysis to enhance the differentiation between PD and ET. E
 MG signals were retrospectively collected from two cohorts (France and Tai
 wan)\, comprising 285 recordings across 77 patients.\nA custom signal proc
 essing pipeline was developed\, involving empirical mode decomposition (EM
 D)\, signal rectification\, envelope extraction\, and a quantile-based seg
 mentation algorithm to identify tremor bursts and interburst intervals. Te
 mporal and amplitude-based features&mdash\;such as burst duration\, interb
 urst duration\, and burst amplitude variability&mdash\;were extracted and 
 statistically analyzed using linear mixed models to account for repeated m
 easures and class imbalance.\nPD patients exhibited longer interburst inte
 rvals and higher variability in burst duration\, whereas ET signals were c
 haracterized by shorter\, more consistent bursts. Frequency-based analyses
  (2&ndash\;15 Hz) did not significantly distinguish the groups.\nA neural 
 network classifier trained on the French dataset was evaluated by predicti
 ng on the independent Taiwan cohort\, achieving 80% accuracy and an AUC of
  0.89. These results demonstrate the generalizability and clinical relevan
 ce of this approach across populations.\nThe proposed EMG-based method off
 ers a robust\, non-invasive\, and time-efficient alternative to current di
 agnostic tools\, reducing misclassification and improving early-stage trem
 or assessment.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR