Personalized monitoring and healthcare information management using physiological basis functions
First Claim
1. A method useful in healthcare information management comprising:
- collecting at least one primary element as a snapshot present at the time of recording of health data using at least one collection method selected from one-time, periodic, quasi-periodic and continuous monitoring, and electronically comparing said at least one primary element with at least one reference value selected from physiological basis functions representing physiological and pathophysiological states, and transitions between said physiological and pathophysiological states to detect changes in said at least one primary element and thereby identify any abnormal or unstable primary element (a first-level, low-resolution analysis); and
analyzing serial changes in said at least one primary element of health data using a dynamic serial analysis and processing unit employing at least one of the following methods selected from mathematical decomposition, mathematical modeling, computer modeling, signal processing, time-series analysis, statistical analysis, and methods of artificial intelligence for assessing changes in serial data, orthogonal decomposition, non-orthogonal decomposition (independent component analysis), multidimensional scaling based on non-metric distances and mapping techniques, non-orthogonal linear mappings, nonlinear mappings and other methods, that make use of projection, re-scaling (change of variables), methods from the theories of singularities, bifurcations, catastrophes, and dynamical systems, and other statistical estimators, linear and nonlinear correlation, analysis of variance, cluster analysis, factor analysis, canonical analysis, regression and discriminant function analyses, and probabilistic methods, Bayesian probability, Bayesian network, Euclidean, Markov model, hidden Markov model, and Mahalanobis distance, pattern recognition, fuzzy logic, neural networks, expert systems, and hybrid artificial intelligence systems to provide detailed characterization of serial changes in any abnormal or unstable primary element (a second-level, higher resolution serial analysis).
0 Assignments
0 Petitions
Accused Products
Abstract
Analysis of individual'"'"'s serial changes, also referred to as the physiological, pathophysiological, medical or health dynamics, is the backbone of medical diagnosis, monitoring and patient healthcare management. However, such an analysis is complicated by enormous intra-individual and inter-individual variability. To address this problem, a novel serial-analysis method and system based on the concept of personalized basis functions (PBFs) is disclosed. Due to more accurate reference information provided by the PBFs, individual'"'"'s changes associated with specific physiological activity or a sequence, transition or combination of activities (for example, a transition from sleep to wakefulness and transition from rest to exercise) can be monitored more accurately. Hence, subtle but clinically important changes can be detected earlier than using other methods. A library of individual'"'"'s PBFs and their transition probabilities (which can be described by Hidden Markov Models) can completely describe individual'"'"'s physiological dynamics. The system can be adapted for healthcare information management, diagnosis, medical decision support, treatment and side-effect control. It can also be adapted for guiding health, fitness and wellness training, subject identification and more efficient management of clinical trials.
-
Citations
20 Claims
-
1. A method useful in healthcare information management comprising:
-
collecting at least one primary element as a snapshot present at the time of recording of health data using at least one collection method selected from one-time, periodic, quasi-periodic and continuous monitoring, and electronically comparing said at least one primary element with at least one reference value selected from physiological basis functions representing physiological and pathophysiological states, and transitions between said physiological and pathophysiological states to detect changes in said at least one primary element and thereby identify any abnormal or unstable primary element (a first-level, low-resolution analysis); and analyzing serial changes in said at least one primary element of health data using a dynamic serial analysis and processing unit employing at least one of the following methods selected from mathematical decomposition, mathematical modeling, computer modeling, signal processing, time-series analysis, statistical analysis, and methods of artificial intelligence for assessing changes in serial data, orthogonal decomposition, non-orthogonal decomposition (independent component analysis), multidimensional scaling based on non-metric distances and mapping techniques, non-orthogonal linear mappings, nonlinear mappings and other methods, that make use of projection, re-scaling (change of variables), methods from the theories of singularities, bifurcations, catastrophes, and dynamical systems, and other statistical estimators, linear and nonlinear correlation, analysis of variance, cluster analysis, factor analysis, canonical analysis, regression and discriminant function analyses, and probabilistic methods, Bayesian probability, Bayesian network, Euclidean, Markov model, hidden Markov model, and Mahalanobis distance, pattern recognition, fuzzy logic, neural networks, expert systems, and hybrid artificial intelligence systems to provide detailed characterization of serial changes in any abnormal or unstable primary element (a second-level, higher resolution serial analysis). - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. A system useful in healthcare information management comprising:
-
a first analysis and processing unit for analyzing a snapshot of at least one of a plurality of primary elements from recorded health data and processing said at least one primary element to generate data respecting said at least one primary element, and comparing at least one reference value selected from physiological basis functions representing physiological and pathophysiological states, and transitions between said physiological and pathophysiological states respecting said at least one primary element with data newly received by said first analysis and processing unit and producing at least one indicator respecting any differences between said at least one reference value and said newly received data (a low resolution analysis), a second analysis and processing unit that includes at least one computer device of higher resolution analysis for processing health data collected over time using at least one of the following methods selected from mathematical decomposition, mathematical modeling, computer modeling, signal processing, time-series analysis, statistical analysis, and methods of artificial intelligence for assessing changes in serial data, orthogonal decomposition, non-orthogonal decomposition (independent component analysis), mathematical modeling, computer modeling, signal processing, time-series analysis, statistical analysis, multidimensional scaling based on non-metric distances and mapping techniques, non-orthogonal linear mappings, nonlinear mappings and other methods, that make use of projection, re-scaling (change of variables), methods from the theories of singularities, bifurcations, catastrophes, and dynamical systems, and other statistical estimators, linear and nonlinear correlation, analysis of variance, cluster analysis, factor analysis, canonical analysis, regression and discriminant function analyses, and probabilistic methods, Bayesian probability, Bayesian network, Euclidean, Markov model, hidden Markov model, and Mahalanobis distance, pattern recognition, fuzzy logic, neural networks, expert systems, and hybrid artificial intelligence systems to detect serial changes in said at least one primary element (higher resolution analysis); and in which said at least one of first analysis and processing unit and said at least one computer device for a higher resolution analysis performs at least one analysis selected from forecasting or prediction of serial changes or trends in physiological or health data, early prediction and prevention of physiological disorders and abnormalities, assessment of short-term and long term dynamics, fitness level, disease progression, treatment, complications and side-effects control, assessment of clinical trials data, physical examination, early detection of subtle changes, timely initiation of therapy, adjustment of therapy, comparison of the values of data obtained from individual patients against values obtained from at least one of a group of patients and a population of patients to facilitate analysis of individual data and to determine the values that characterize said at least one of a group of patients and a population of patients with similar characteristics and similar disorders. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
Specification