Koneksa to study if AI smartwatch data can predict Parkinson's disease progression

There’s no standard timeline for the progression of Parkinson’s disease. Though it typically moves slowly, with symptoms gradually becoming more severe over the course of several years, some patients may see their condition worsen on a much shorter timeline.

Predicting the disease’s progression as soon as it’s diagnosed would be a major boon since it could start patients on symptom-soothing regimens much earlier—though no such predictive diagnostics currently exist.

Digital biomarker builder Koneksa is hoping to change that. Armed with funding from the Michael J. Fox Foundation for Parkinson’s Research, the startup is embarking on a study of how digitally collected data points could potentially be used to plot out how an individual’s case of Parkinson’s will advance over time.

In the study, researchers will analyze data already collected in the Parkinson’s Progression Markers Initiative, an ongoing effort launched by the Fox Foundation in 2010 to build a massive clinical database of health information and biosamples from Parkinson’s patients to support new drug development and other research work.

Those data points will include activity tracking, gait analysis and sleep cycles—all collected using Verily’s clinical smartwatch. They’ll be analyzed using Koneksa’s own algorithms, plus additional machine learning techniques.

The ultimate goal of the study is to identify which of those data points collected by a smartwatch or other digital device can be used to predict and model Parkinson’s progression, much like how the Apple Watch has been used in trials to automatically predict conditions ranging from COVID-19 to low ejection fraction.

“Algorithms for analyzing passively acquired sensor data are a substantial gap in the digital biomarker landscape,” said Koneksa founder and CEO Chris Benko. “There are no current diagnostics to detect progression in early PD or in the prodromal (pre-diagnostic) stage, and identifying any predictive digital biomarkers would be a meaningful addition for patients and physicians.”

Koneksa didn’t disclose the exact amount contributed by the Fox Foundation.

The new award comes just a few weeks after the research foundation doled out another grant to the New York City-based startup. That funding, awarded in mid-June, was put toward a separate Parkinson’s-focused study, this one conducted in partnership with Northwestern University to develop an objective measurement system linking vocal abnormalities to early progression of the disease.

That investigation will be helped along by Koneksa’s recently announced collaboration with Aural Analytics, which brings clinical-grade speech analytics to Koneksa’s digital biomarker platform.