MIT-developed device uses neural network to discern the presence and severity of Parkinson’s disease.

Parkinson’s disease is well known for causing tremors, stiffness and slowness, but the reality is that these are symptoms which appear long after it has taken hold. However, thanks to new research by MIT and developments in neural networks, early diagnosis may be on the horizon.

New research done published this week in https://www.nature.com/articles/s41591-022-01932-xNature Medicine shows how Dina Katabi and Nicole Pham and her team have developed an artificial intelligence model that can detect Parkinson’s just from reading a person’s breathing patterns.

The development is thanks to a neural network, which essentially is a series of connected algorithms that mimic the way a human brain works. This particular network is capable of assessing whether someone has Parkinson’s from their nocturnal breathing — i.e., breathing patterns that occur while sleeping ­— is able to track the progression of their disease over time.

The disease itself has a long history of being tied to breathing, as Katabi says: “A relationship between Parkinson’s and breathing was noted as early as 1817, in the work of Dr. James Parkinson. This motivated us to consider the potential of detecting the disease from one’s breathing without looking at movements,” Katabi says. “Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, meaning that breathing attributes could be promising for risk assessment prior to Parkinson’s diagnosis.”

Parkinson’s is the fastest-growing neurological disease in the world and is currently the second-most common neurological disorder after Alzheimer's disease. In the United States alone, it afflicts over 1 million people and has an annual economic burden of $51.9 billion. The research team’s algorithm was tested on 7,687 individuals, including 757 Parkinson’s patients.

Katabi notes that the study has important implications for Parkinson’s drug development and clinical care. “In terms of drug development, the results can enable clinical trials with a significantly shorter duration and fewer participants, ultimately accelerating the development of new therapies. In terms of clinical care, the approach can help in the assessment of Parkinson’s patients in traditionally underserved communities, including those who live in rural areas and those with difficulty leaving home due to limited mobility or cognitive impairment,” she says.

This research was performed in collaboration with the University of Rochester, Mayo Clinic, and Massachusetts General Hospital, and is sponsored by the National Institutes of Health, with partial support by the National Science Foundation and the Michael J. Fox Foundation.

Read our case study to learn about Mayo Clinic’s AI factory.