Billions of sensors, of connected things, in what experts call the Internet of All Things or IoAT, await us around the corner. Sensors and connected things that monitor, process, and store large volumes of data in the cloud at high speeds in order to predict or establish patterns thanks to artificial intelligence (AI), machine learning or machine learning, or deep learning or learning deep thanks to neural networks.
If just a few days ago we were wondering why health was not the area of knowledge where different AI solutions are being applied the most, today we bring to this blog one of the most attractive initiatives in this field, thanks to IBM Research, which has developed a prototype of a nail sensor that takes advantage of the capabilities of artificial intelligence and machine learning . The sensor could change the way doctors use data, such as changes in a patient’s grip strength, to monitor and track diseases like Parkinson’s.
Parkinson’s disease is a chronic degenerative neurological disorder that affects one in 100 people over the age of 60. It is estimated that more than five million people have it worldwide, and the number is increasing with the aging of the current population. While it is primarily characterized by motor disorders, including involuntary tremors and impaired movement, it is not uncommon for patients with this disease to also experience cognitive decline, behavioral problems, and sleep disturbances.
Towards a personalized treatment
The sensor developed by IBM Research measures how the nails bend and move throughout the day, which is an indication of the strength of an individual’s grip, a key biomarker in health. Thanks to the continuous collection of data, which is added to AI algorithms, in the future the sensor could help doctors have a more accurate image of a patient’s grip power and its movement over time. This could allow doctors to offer more personalized treatment for different conditions, such as Parkinson’s or cardiovascular problems.
IBM has also announced a new initiative with the Michael J. Fox Foundation with the goal of better understanding Parkinson’s disease and paving the way for more effective treatments. Through this partnership, the Michael J. Fox Foundation makes its data available from the Parkinson’s Progression Markers Initiative (PPMI), an observational study that has collected a large amount of anonymous longitudinal data on Parkinson’s patient cohorts.
“The collaboration with the Michael J. Fox Foundation,” they say at IBM Research, “aims to provide a comprehensive view of the disease through longitudinal, clinical, behavioral and imaging assessments observed in patients in clinical settings, as well as genomic and biological samples, such as genetic and epigenome data ”. The Michael J. Fox Foundation has been instrumental in collecting and making this data available in a responsible manner, and the broad nature of this information provides an unprecedented opportunity to gain insight into this disease and its progression.
The challenges
Although the potential of applying AI and machine learning techniques to learn from this data is huge, challenges still exist. Specifically, the heterogeneity of disease progression in patients, the multifaceted nature of their symptoms – motor, cognitive, and behavioral – and the confounders of symptom-relieving medications make this a major challenge. “To overcome these obstacles, we plan to design machine learning methods that explicitly explain the effects of medication and other confounders by drawing on our previous work in modeling disease progression,” they say at IBM.
Ultimately, all the work that IBM will do with the Michael Foundation data will escalate to the “hope and promise” of the possibility that one day the onset and progression of Parkinson’s can be accurately predicted , which It would make it possible to help with early detection and, with timely interventions, to also better control the disease.
