IBM recently revealed a fingerprint sensor prototype to measure how your fingernails bend throughout the day. This sensor is used for measuring grip strength, which can help determine medical conditions.
Grip strength is a metric used for detecting a broad set of health issues. And it has been associated with the effectiveness of medication in individuals with Parkinson’s disease, the degree of cognitive function in schizophrenics, cardiovascular health, and all-cause mortality in geriatrics.
IBM Research is determined to use artificial intelligence to help clinicians to monitor individuals in their natural environments and point to indicators and clues into the progression of a patient’s conditions.
And IBM said that this project started out as an attempt to capture the medication state of people with Parkinson’s disease. This is important because getting new therapies approved requires quantifying how people on the therapy are doing based on the controls. And the majority of people with Parkinson’s are older with brittle skin. So attaching skin-based sensors can capture things such as motion, muscle and nerve cell health, and changes in sweat glands.
Skin-based sensors often cause problems such as infections with older patients. That is another reason why IBM decided to go with a fingernail sensor.
“Since nails are so tough, we decided to glue a sensor system to a fingernail without worrying about any of the issues associated with attaching to skin. Our dynamometer experiments demonstrated we could extract a consistent enough signal from the nail to give good grip force prediction in a variety of grip types,” wrote IBM researchers Stephen Heisig and Katsuyuki Sakuma in a blog post. “We also found it is possible to deconvolve subtle finger movements from nail deformation. We were able to differentiate typical daily activities which all involve pronation and supination such as turning a key, opening a doorknob or using a screwdriver. An even more subtle activity is finger writing, and we trained a neural network to produce a very good accuracy (.94) at detecting digits written by a finger wearing the sensor.”
After the fingernail sensor is attached, it sends data to a smartwatch. And then the watch runs machine learning models to rate bradykinesia, tremor, and dyskinesia — which are symptoms of Parkinson’s disease.
The researchers also pointed out that this work served as the inspiration for a new device modeled on the fingertip structure that could help one day help quadriplegics communicate. Even though this fingernail sensor is not commercially available, the learnings from the research could be implemented in devices sometime in the near future.