KU RESEARCHERS INTEGRATE DEEP LEARNING WITH SMARTPHONES TO DETECT PARKINSON’S
EARLY DETECTION OF PARKINSON’S DISEASE IS CRUCIAL TO MANAGING SYMPTOMS AND SLOWING THE DISEASE’S PROGRESSION, BUT ITS EARLY SIGNS ARE OFTEN MISSED
A team of researchers at Khalifa University (KU) has developed a new tool that can help detect early symptoms of Parkinson’s disease using sensors from the average smartphone. Parkinson’s disease is the fastestgrowing neurological disorder, affecting more than 10 million people worldwide. Early detection of the disease is crucial for managing symptoms and slowing the disease’s progression. However, the finemotor impairment (FMI) associated with its early stages, such as barely noticeable hand tremors, are often missed. In collaboration with researchers from Greece, Germany, and the United Kingdom, the KU team led by Dr. Leontios Hadjileontiadis, Professor of Biomedical Engineering, introduced a deep learning framework that analyzes data captured by the phone’s sensors. The system uses deep learning algorithms to detect and monitor subtle
motor skill degradation. In addition to monitoring tremors, it looks for patterns in keystroke dynamics, such as “hold time,” the time interval between the press and release of a key. The rate at which a person presses down and then releases a finger on a key indicates how quickly the brain can control the muscles. Using these techniques, the team achieved 92.8% sensitivity and 86.2% specificity in disease detection. An article on the research was published in the journal Scientific Reports. “Using a smartphone provides an unobtrusive way of capturing data,” explained Dr. Hadjileontiadis. “This is a solid first step towards a highperforming remote Parkinson’s disease detection system that can be used to discreetly monitor subjects and urge them to visit a doctor if signs of the disease are detected.”
Source: Jade Sterling, Science Writer, Khalifa University https://www.ku.ac.ae/detecting-parkinsons-disease-using-deep-learning-techniquesfrom-smart-phone-data