ParkDetect - Early Diagnosing Parkinson's disease

Description:

Parkinson’s disease is one of the most common neurodegenerative disorders of the central nervous system that affects elderly. There are four main symptoms: tremors, rigidity, bradykinesia (slow movements) and posture instability. Nowadays any type of diagnose for this disorder is done through observation by a health care professional specialized in this area. Therefore it is necessary a method that is simple and efficient for health care professionals of general clinic to use so they can have some grounded backup to decide to forward a possible patient to a specialist. In this context a mobile application where a health care professional can insert values about possible patient’s symptoms or the patient himself can realize small test is an interesting challenge due to reach they have today.

This project can be split in three important phases: (1) development of a smartphone application, (2) use it to gather data from real patients and a control group and (3) testing and selection of a classification algorithm (selecting the relevant data and compare different algorithms) to be inserted in the same application.

The first phase was the one with the most research since it was needed to understand how the symptoms could be detected only using the smartphone components and develop/adapt the application. The second one was the most time consuming, lasting from after the application getting developed to almost the end of the available time due to delays from the medical institution and the lack of capable patients that could perform the tests. The final one was highly affected with the lack of available data, making properly grounded conclusions impossible, however it was possible to obtain some promising results from the gait analysis of the patients where the pelvic sway was a good feature to help differentiate Parkinson patients from healthy ones.

 

Author: Ricardo Graça

Type: MSc thesis

Partner: Faculdade de Engenharia da Universidade do Porto

Year: 2013