Multivariate Residual-Based Health Index for Human Health Monitoring

Abstract

Ambulatory or in-hospital monitoring of patients is provided with early warning and prioritization, enabling proactive intervention and amelioration of both costs and risks of health care. Multivariate physiological parameters are estimated by empirical model to remove normal variation. Residuals are tested using a multivariate probability density function to provide a multivariate health index for prioritizing medical effort.

What is claimed is: 
     
         1 . A system for monitoring the health of a human, comprising:
 a device disposed to receive multiple physiological signals from a plurality of sensors arranged to capture physiological signals from a monitored human, having microprocessor hardware programmed to derive multiple physiological features from said signals;   a computer configured to receive monitored observations of said multiple physiological features from said device, to generate estimates of said features in the monitored observations using a model embodying behavior of said multiple physiological features under normal health conditions, and to generate residuals of said features by differencing the monitored observations with the estimates thereof; and   a computer-accessible memory for storing a set of exemplary observations of residuals of said multiple physiological features characteristic of a known health state, generated using said model;   said computer being specially configured to determine a likelihood that said residuals are representative of a pattern of residuals for said known health state, using a Gaussian mixture model based on said set of exemplary observations of residuals.   
     
     
         2 . A system according to  claim 1 , wherein said model is a kernel regression estimator. 
     
     
         3 . A system according to  claim 2 , wherein said the monitored observation of features is used to localize said model. 
     
     
         4 . A system according to  claim 1 , wherein said model is a similarity-based model. 
     
     
         5 . A system according to  claim 4 , wherein said the monitored observation of features is used to localize said model. 
     
     
         6 . A system according to  claim 1 , wherein said computer is further specially configured to test said likelihood to render a decision whether the monitored observation of said multiple features is characteristic of said known health state. 
     
     
         7 . A system according to  claim 6 , wherein said computer is further specially configured to test a series of said rendered decisions for persistence of like decisions regarding whether the features are characteristic of said known health state or not. 
     
     
         8 . A system according to  claim 1 , wherein said computer is further specially configured to generate an index of said likelihood as a logarithm of the inverse of said likelihood, and compare the index to a threshold. 
     
     
         9 . A system according to  claim 1 , wherein said device is a cell phone. 
     
     
         10 . A system according to  claim 1 , wherein said device is a hospital bedside vital signs monitor. 
     
     
         11 . A system according to  claim 1 , wherein said known health state is the state of normal health for the monitored human.