AI Advances in Parkinson’s Disease Diagnosis

Researchers from the University of Florida have developed an AI system that effectively monitors the progression of Parkinson’s disease through patients’ hand movements.

The scientists trained the artificial intelligence to analyze rapid tapping of the thumb and index finger. The neural network can detect even subtle changes that are difficult for humans to perceive, enabling precise and efficient diagnosis.

“The beauty of this technology is that the patient can record themselves performing the test, and the software analyzes the recording and informs the doctor about their movement, allowing the specialist to make decisions,” noted Diego Guarin, the associate professor who developed the technology.

Parkinson’s disease affects the brain, causing slowed movements, tremors, body stiffness, speech changes, and difficulties with balance and coordination. Symptoms develop gradually, and doctors rely on a series of exercises to identify and assess the severity of the disorder.

The AI system determined the precise timing for finger tapping in both healthy and affected individuals.

“This is new information that is practically impossible to obtain without video and a computer. It shows that the technology can help better characterize the impact of Parkinson’s disease on movement and provide new markers to assess therapy effectiveness,” commented Guarin.

The neural network was trained using large volumes of video data. A mobile application is currently being developed based on this system, allowing individuals to self-diagnose the disease at home.

Previously, a new artificial intelligence model was able to detect 13 different types of cancer with 98.2% accuracy based on DNA data from tissue samples.

In July, an AI system was taught to predict Alzheimer’s disease with 70% accuracy seven years before diagnosis and 80% a year prior.

Back in 2022, Canadian scientists created a highly sensitive AI biosensor capable of detecting brain cancer from a drop of blood.