Development and Validation of a Deep Learning‐Based Facial Weakness Score for Objective Assessment in Facioscapulohumeral Muscular Dystrophy

Key Points

• To develop and validate a deep learning tool for objectively measuring facial weakness in FSHD patients.
• Developed a facial weakness scoring system using deep learning techniques.
• Validated the scoring system against clinical assessments.
• Assessed reliability and consistency of the tool in various settings.
• The deep learning facial weakness score (DLFWS) demonstrated high reliability.
• Scores matched well with traditional clinical assessments.
• The tool can be applied in both clinical practice and research settings.