EE Seminar: Artificial Intelligence Tools for Measurement of Symptoms Severity of Huntington’s Disease

25 במאי 2026, 15:00 
אולם 011, בניין כיתות-חשמל 
EE Seminar: Artificial Intelligence Tools for Measurement of Symptoms Severity of Huntington’s Disease

Electrical Engineering Systems Seminar

 

Speaker: Neta Biran

M.Sc. student under the supervision of Prof. Ran Gilad-Bachrach

 

Monday, 25th May 2026, at 15:00

Room 011, Kitot Building, Faculty of Engineering

 

 

Artificial Intelligence Tools for Measurement of Symptoms Severity of Huntington’s Disease

 

Abstract

Huntington’s disease (HD) is a progressive neurodegenerative disorder characterized by involuntary movements, including chorea, which significantly affect patients’ daily functioning and quality of life. Clinical assessment of chorea severity is limited scalability for continuous monitoring in daily living environments. The development of automated and objective methods for chorea assessment may improve monitoring accuracy and support personalized disease management and treatment.

This work investigates the use of deep learning methods for automatic chorea severity assessment from wrist-worn accelerometer data collected from individuals with HD during gait. A modified J-Net architecture, originally developed for gait detection, was adapted for chorea severity classification. The proposed framework combines a pre-trained self-supervised learning foundation model with a classification module designed for ordinal severity prediction.

The results demonstrate that the proposed learning framework and the integration of handcrafted temporal and spectral features improved classification performance and enabled more accurate differentiation between chorea severity levels.

Overall, the thesis demonstrates the feasibility of objectively assessing chorea severity in Huntington’s disease using deep learning methods, despite the inherent challenges associated with subjective labeling, inter-patient variability, and the complex nature of involuntary movements. The findings suggest that meaningful severity estimation can be achieved from wrist-worn accelerometer data and provide a foundation for future research in this area.

 

  -סמינר זה ייחשב כסמינר שמיעה לתלמידי תואר שני ושלישי-

This Seminar Is Considered A Hearing Seminar For Msc/Phd Students-

 

הרישום לסמינר יבוצע בתחילת הסמינר באמצעות סריקת הברקוד למודל (יש להיכנס לפני כן למודל,  לא באמצעות האפליקציה)

Registration to the seminar is done at the beginning of the seminar by scanning the barcode for the Moodle (Please enter ahead to the Moodle, NOT by application)

 

 

 

אוניברסיטת תל אביב עושה כל מאמץ לכבד זכויות יוצרים. אם בבעלותך זכויות יוצרים בתכנים שנמצאים פה ו/או השימוש שנעשה בתכנים אלה לדעתך מפר זכויות
שנעשה בתכנים אלה לדעתך מפר זכויות נא לפנות בהקדם לכתובת שכאן >>