Defining and Predicting Pain Volatility in Users of the Manage My Pain App: Analysis Using Data Mining and Machine Learning Methods

Conclusions: We propose a novel method for measuring pain volatility. Cluster analysis was applied to divide users into subsets of low and high volatility classes. These classes were then predicted at the sixth month of app use with an acceptable degree of accuracy using machine learning methods based on the features extracted from demographic, clinical, and app use information from the first month.

Source: Journal of Medical Internet Research - November 15, 2018 Category: General Medicine Authors: Quazi Abidur Rahman Tahir Janmohamed Meysam Pirbaglou Hance Clarke Paul Ritvo Jane M Heffernan Joel Katz Source Type: research