Artificial intelligence to detect Parkinson’s through breathing patterns

Similar in appearance to a Wi-Fi router, the device you can see in the attached image uses a neural network to discern the presence and severity of one of the fastest growing neurological diseases in the world.

Through this invention by MIT researchers, an alternative mechanism is proposed to contribute to the detection of Parkinson’s disease, which is particularly difficult to diagnose.

AI as an alternative for the early detection of Parkinson’s disease

Although this condition is recognizable through the symptoms that affect the body’s motor apparatus, such as tremors, slow and/or rigid movements, these manifest during a late stage of the disease, several years after its actual appearance.

A team of MIT scientists has developed an artificial intelligence model that can detect Parkinson’s simply by reading a person’s breathing patterns.

The tool in question is a neural network, a series of connected algorithms that mimic the functioning of the human brain, capable of assessing whether someone has Parkinson’s from their nocturnal breathing, that is, the breathing patterns that occur while sleeping. This AI system is also capable of discerning the severity of someone’s Parkinson’s disease and tracking the progression of their disease over time.

Through the device described above, which unlike other predecessor solutions is neither invasive nor expensive, the MIT researchers demonstrated that the artificial intelligence evaluation of Parkinson’s can be done every night at home, while the person sleeps and intervene in the body. with some physical contact.

The instrument developed for this study emits radio signals, analyzes their reflections in the surrounding environment, and extracts the subject’s breathing patterns without any physical contact. The breathing signal is then sent to the neural network to assess Parkinson’s passively, requiring no effort from the patient or caregiver.

“As early as 1817, in the work of Dr. James Parkinson, a relationship between Parkinson’s and breathing was noted. This prompted us to consider the potential of detecting disease from breathing without looking at movement.” says Dina Katabi, principal investigator of this project. “Some medical studies have shown that respiratory symptoms manifest years before motor symptoms, which means that respiratory attributes could hold promise for risk assessment prior to Parkinson’s diagnosis.”he added.

Katabi adds that the study has important implications for drug development and clinical care for Parkinson’s. “In terms of drug development, the results may enable clinical trials with significantly shorter durations and fewer participants, ultimately speeding up the development of new therapies. In terms of clinical care, the approach can help in the evaluation of Parkinson’s patients in traditionally underserved communities, including those living in rural areas and those with difficulty leaving home due to limited mobility or cognitive impairment.”He says.

If this solution is validated as an acceptable way to work in the elaboration of diagnoses, a very valuable advance would be marked. “We have not had therapeutic advances this century, which suggests that our current approaches to evaluating new treatments are not optimal”says Ray Dorsey, a professor of neurology at the University of Rochester and a Parkinson’s specialist and co-author of the paper documenting this research. Dorsey adds that the study is probably one of the largest sleep studies ever conducted on Parkinson’s. “We have very limited information about the manifestations of the disease in its natural environment and the device [de Katabi] allows you to get objective, real-world assessments of how people are doing at home. The analogy I like to draw [de las evaluaciones actuales de Parkinson] it is a street light at night, and what we see from the street light is a very small segment… The completely non-contact sensor [de Katabi] helps us illuminate the darkness»noted the expert.

Some aspects of Parkinson’s disease remain enigmatic for the scientific and clinical community. However, efforts like these seek to clarify the path to an accurate and timely diagnosis.