Parkinson’s disease is the fastest growing neurological disease in the world. However, currently there is no single test or biomarker that can diagnose Parkinson’s or monitor disease progression. Now, a new study utilising Artificial Intelligence (AI)
may change the way we track Parkinson’s.

A lot like a warning system, a biomarker (short for biological marker) is used to help measure what is going on in the body. For example, the A1C blood test can help detect prediabetes. Early detection, treatment and expert care is vital to maintaining quality of life.

The challenge, so far, has been the lack of biomarkers for early Parkinson’s diagnosis. Usually, Parkinson’s is only diagnosed years after early signs appear –   when movement symptoms (such as tremor, rigidity, and difficulty walking) are present. However, a new study may have found an early biomarker for PD.

In a ground-breaking study published in the journal Nature Medicine, ‘Artificial Intelligence (AI) enabled detection and assessment of Parkinson’s disease using nocturnal breathing signals’ (Yang et al., 2022), the authors developed an Artificial Intelligence-enabled system that could reliably:

• Wirelessly identify people who have Parkinson’s from their breathing patterns during sleep
• Accurately assess people’s Parkinson’s disease severity
• Track Parkinson’s progression over time

Study authors point out that the relationship between Parkinson’s disease and breathing is documented in various studies. Further, the authors note that this breathing link has been reinforced by more recent Parkinson’s studies that go a step further – reporting that degeneration in the brainstem helps control breathing, issues of respiratory muscle weakness, and sleep breathing disorders.

According to the study, “Since breathing and sleep are impacted early in the development of Parkinson’s, we anticipate that our AI model can potentially recognise individuals with Parkinson’s before their actual diagnosis”

Artificial Intelligence is a highly sophisticated technological tool that mimics human-like thinking to analyse enormous amounts of data, find patterns, and make predictions and recommendations.

Researchers designed an AI-based system for detecting Parkinson’s, predicting its severity, and tracking disease progression over time using nocturnal breathing. The system can take the breathing input signals in two different ways:

• Using a breathing belt placed in the person’s chest or abdomen, or
• Using a Wi-Fi-like router that sends a low radio signal placed somewhere in the room. The signals transmitted are reflected off the person’s body and further analysed.

Regardless of the signal source (belt or radio waves), once collected, the AI-based model processes the signals using a neural network. This network uses a series of instructions, called algorithms, that tells a computer how to transform the enormous amounts of data into useful information.

Importantly, the person’s breathing patterns are automatically fed to the neural network to assess their Parkinson’s status and its severity. No state-of-the-art equipment is required, and no special training is needed for the person with Parkinson’s or caregiver.

To test their AI technology, researchers used a large and diverse data set that included data from 11,964 nights of sleep with more than 120,000 hours of night-time breathing among 757 people with Parkinson’s and 6,914 control subjects (people without Parkinson’s).

They sought to determine whether the AI diagnostic findings (from both belt and radio wave users) could compare to standard Parkinson’s tests, such as the Movement Disorder Society Unified Parkinson’s Disease Rating Scale (MDS-UPDRS). Parkinson’s diagnosis was evaluated using:

1) diagnosis made by a clinician using the MDS-UPDRS PD rating scale, and

2) the AI model developed by the authors.

Results

The AI system can:

• Predict the presence or development of Parkinson’s with 90% accuracy
• Track Parkinson’s progression and estimate its severity as well as the MDS-UPDRS (PD rating scale used by doctors)
• Provide an objective, non-invasive, at-home assessment of Parkinson’s while a person is asleep, without touching the body
• Combine measurements from multiple nights to achieve optimal test accuracy
• Provide nightly and weekly measurements in a person’s home, that tests such as the MDS-UPDRS would not be able to capture
• Eventually be deployed in the homes of individuals at high risk for Parkinson’s (e.g. those with the LRKK2 gene mutation) to passively monitor their status and provide feedback to their provider

What does this mean?

With impressive accuracy, this AI system was able to successfully detect, assess and track disease severity of Parkinson’s in a home setting by extracting breathing from either a wearable belt or from radio waves that bounce off a person’s body while they sleep.

This Artificial Intelligence model also provided initial evidence that a touchless, non-invasive system may be a useful biomarker for early detection or risk of Parkinson’s. Further, according to the study authors, this method is low-cost, and would bring accessibility to Parkinson’s care to people who live in rural areas that are not near medical centres that specialise in Parkinson’s care. The system could be mailed to the person’s home, used for a few nights, and returned for evaluation.

Sources

Parkinson’s Foundation

Nature Medicine