Early and accurate detection of Parkinson’s Disease (PD) is one of the most important, yet difficult, challenges for effective treatment. Traditional diagnosis of PD is based on clinical examinations which require several doctor visits by the patient, therefore consuming both time and resources. Remote screening systems using artificial intelligence to analyze skeletal joint data captured by non-wearable sensors in a non-hospital setting can facilitate the diagnosis of PD at an early stage. 

 Sensor-data-collection

Such technology can serve as the basis for a telehealth system that allows remote public screening and provides decision support for early-stage PD diagnosis. The proposed telehealth intervention is the integration of two tools: public health screening and decision support. Other main elements in the system are patient, nurse, electronic health records (EHR), and specialist. To date, however, widespread adoption of such telehealth systems is limited due to implementation challenges such as inadequate risk analysis and system design. 

 PD-remote-detection-system

This project evaluates the risks in the implementation of sensor-based remote screening systems by an integrated Quality Function Deployment (QFD) and Failure Mode and Effect Analysis (FMEA) method. While QFD is centered in controlling the development process from concept to completion, FMEA identifies possible failures along the way.