Prediction models of that identify and forecast changes in the pain experiences among users of the Manage My Pain app were used in a study published recently in Journal of Medical Internet Research (JMIR) that aimed to define pain volatility.
Data from the analysis came from users of Manage My Pain, an app designed by Toronto-based ManagingLife to help patients and clinics measure, monitor, and manage chronic pain. In total, data from 782 users who collectively recorded more than 329,000 data points.
In the study, researchers used data mining techniques to define pain volatility, a measure used to describe how the severity of pain changes over time. Machine learning techniques were then used to predict users’ pain volatility levels 6 months in the future, based on the information entered into the app in the first month, according to a media release from the company.
Researchers report that its model can predict whether users experience low or high levels of pain volatility 6 months in the future, with approximately 70% accuracy.
They believe this innovative, data-driven approach to analysis could help shape future treatments of pain, the release continues.
“With the significant increase in data available and by applying machine learning methods, we can better understand how pain experiences change and better understand how that might evolve in the future,” says Professor Joel Katz, Canada Research Chair in Health Psychology at York U and one of the lead authors of the study, in the release.
“This study may help to identify risk factors for heightened volatility and, therefore, to potentially prevent the development of high pain volatility through effective interventions,” he adds.
[Source(s): ManagingLife, PR Newswire]