IBM Fingernail Sensor for Parkinson’s

1.What is it?

  • This fingernail sensor is a wearable, wireless device being developed by the IBM research team that monitors changes in the degree of bend in the fingernail, offering surprising information on health status
  • In particular the sensor measures grip strength, which has been associated with the effectiveness of medication in Parkinson’s disease, the degree of cognitive function in schizophrenics, state of cardiovascular health and all-cause mortality

2.Why is it important?

Scans of a brain
  • Parkinson’s disease is a neurodegenerative condition affecting 1 in every 350 people and 145,000 in total in the UK. (1)
  • Monitoring the progression of the disease can be used to help design the best-personalised treatments for patients
  • One method of monitoring disease progression is a skin-based sensor to capture relevant factors to disease states such as movement or muscle and nerve health
  • However, most Parkinsonian patients are elderly so suffer from brittle and fragile skin so such sensors may cause damage or injury, including infection
  • Here, the importance of a fingernail sensor becomes apparent, research shows that minute changes in the bending of fingernails, can give important information on the health status of the patient without the drawbacks seen in the skin-based sensors

3.How does it work?

  1. We interact with objects daily using our hands and fingers, gripping, grasping, flexing and extending our fingers to do so. In such actions, a microscopic deformation of the nail can be seen and these can be detected by strain gauge sensors
  2. These strain gauges can pick up subtle information on the movements of the hands or fingers, in actions like pronation or supination in turning a lock and even the slight unique differences in writing of the different letters of the alphabet
  3. A small computer that compares these strain values, collects accelerometer data and communicates with a smartwatch
  4. This smartwatch also runs machine learning techniques to rate and measure bradykinesia, tremor and dyskinesia – all symptoms of Parkinson’s disease
  5. AI and machine learning models collate this information and analyse it to provide insights into the varied stages of disease progression for the specific individual as well as medication state and effectiveness by looking at these factors, according to the latest research.

This technology has huge potential and scope to be applied elsewhere also. In particular, the research team on the project have highlighted the potential application of this technology towards helping quadriplegic patients communicate. This could be by picking up on small discriminatory factors and translating this information into language that can be understood. Although this is still under research, we look forward to its application in the clinical field in the near future.






Shahmeer Noori – Medical Student

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.