MASKED is a transdisciplinary research project that applies biosemiotic methods to develop non‑invasive, quantitative tools for assessing facial masking and motor symptoms in Parkinson’s disease. By combining standardized facial action coding (FACS), neuropsychological gesture coding (NEUROGES), high‑resolution video/sensor data, and advanced statistical and machine‑learning analysis, MASKED creates validated diagnostic indices for early detection, monitoring, and therapeutic decision‑making. The open‑science platform provides clinicians, caregivers, and researchers with reproducible data, visualizations, and integration pathways across diagnostic, prognostic, and treatment workflows.
Funding
Funding not disclosed
Founders
Product
Problem
Parkinson’s disease often causes hypomimia, or “facial masking,” which reduces patients’ facial expressivity and makes it difficult to assess disease severity and progression using standard clinical observation alone.
Solution
MASKED applies biosemiotic methods to create non‑invasive, quantitative assessment tools for Parkinson’s facial masking and related motor symptoms. The project trains researchers in facial action coding (FACS) and neuropsychological gesture coding (NEUROGES) and combines these annotations with advanced computational statistics to generate diagnostic indices. These indices provide objective measures that can be used for early detection, longitudinal monitoring, and therapeutic decision‑making across all disease stages. The approach is designed to be open‑science, with data, analysis pipelines, and visualizations made findable, accessible, interoperable, and reusable for clinicians, caregivers, and researchers. By delivering faster and more accurate symptom quantification, MASKED aims to improve patient outcomes and reduce the socioeconomic burden of neurodegenerative disorders.
Target Audience
Primary users are neurologists, movement‑disorder specialists, and clinical researchers who need objective measures of facial masking, as well as caregivers and patients participating in longitudinal monitoring programs.
Features
- Standardized facial action coding (FACS) and gesture coding (NEUROGES) protocols for consistent data capture
- High‑resolution video and sensor data acquisition pipelines for non‑invasive monitoring
- Computational statistics and machine‑learning models that convert coded behaviors into validated diagnostic indices
- Open‑source data export, visualization dashboards, and reproducible analysis scripts
- Integration pathways for clinical, caregiver, and research workflows, supporting diagnostic, prognostic, and therapeutic use cases