Machine learning analytics in real time for health services

A method for detecting a random state change in a physical subject, the method comprising:

• receiving, using one or more electronic processors, a plurality of multivariate signals via a respective plurality of physical channels, wherein the plurality of multivariate signals comprise information about the state change in the physical subject, wherein the plurality of multivariate signals are sampled at a specified sampling rate;
• monitoring, using the one or more electronic processors, values of statistical characteristics of the plurality of multivariate signals;
• detecting, using the one or more electronic processors, a potential change of state in the physical subject when the monitored statistical characteristics values of at least one of the plurality of multivariate signals exceed a threshold;
• low-pass filtering, using the one or more electronic processors, a time interval of the plurality of multivariate signals that precedes the detected potential change of state in the physical subject to generate a respective plurality of state change artifact signals;
• simultaneously decomposing, using the one or more electronic processors, the plurality of state change artifact signals by multivariate empirical mode decomposition and generating a plurality of intrinsic mode functions;
• extracting, using the one or more electronic processors, features from one or more of the plurality of intrinsic mode functions;
• providing, using the one or more electronic processors, the extracted features to a logistic regression classifier;
• repeating the steps of monitoring, detecting, low-pass filtering, decomposing, extracting, and providing the extracted features to the logistic regression classifier;
• and
• predicting, using the one or more electronic processors, a state of the physical subject using the logistic regression classifier.