[미국특허]
Residual-based monitoring of human health
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06N-003/063
G06N-003/02
출원번호
US-0017239
(2011-01-31)
등록번호
US-8597185
(2013-12-03)
발명자
/ 주소
Pipke, Robert Matthew
출원인 / 주소
Ventura Gain LLC
인용정보
피인용 횟수 :
4인용 특허 :
60
초록▼
Improved human health monitoring is provided in the context of sensor measurements of typical vital signs and other biological parameters, by a system and method using an empirical model of the parameters and disposed to estimate values of the parameters in response to actual measurements. Residuals
Improved human health monitoring is provided in the context of sensor measurements of typical vital signs and other biological parameters, by a system and method using an empirical model of the parameters and disposed to estimate values of the parameters in response to actual measurements. Residuals resulting from the difference between the estimates and actual measurements are analyzed for robust indications of incipient health issues. Residual analysis is both more robust and more sensitive than conventional univariate range checking on vital signs.
대표청구항▼
1. A system for monitoring the health status of a human, comprising: an ambulatory device disposed to receive multiple biological parameters from a plurality of sensors configured to be attached to a monitored human;a computer disposed to obtain monitored observations of multiple biological paramete
1. A system for monitoring the health status of a human, comprising: an ambulatory device disposed to receive multiple biological parameters from a plurality of sensors configured to be attached to a monitored human;a computer disposed to obtain monitored observations of multiple biological parameters from said ambulatory device; anda computer-accessible memory for storing a set of exemplary observations of said multiple biological parameters characteristic of the interrelationships between said multiple biological parameters under normal health conditions for the monitored human;said computer being configured to generate an estimate of at least one of said multiple biological parameters in a monitored observation obtained from said ambulatory device, as a linear combination of at least some of said set of exemplary observations, determined from a kernel-based comparison of the monitored observation and at least some exemplary observations; andsaid computer being further configured to compare said estimate to the corresponding value of the at least one of said multiple biological parameters in said monitored observation, to generate a residual, and make a determination of the health status of the human there from. 2. The system according to claim 1, wherein said ambulatory device communicates with said sensors by means of local wireless communications. 3. The system according to claim 2, wherein said local wireless communications is IEEE 802.15.1. 4. The system according to claim 1, wherein said plurality of sensors includes an oximeter. 5. The system according to claim 1, wherein said plurality of sensors includes an optical blood glucose meter. 6. The system according to claim 1, wherein said plurality of sensors includes an accelerometer. 7. The system according to claim 1, wherein said plurality of sensors includes at least a pair of temperature sensors disposed to measure ambient temperature and a temperature of the monitored human. 8. The system according to claim 1, wherein said ambulatory device comprises a cell radio and said observations of multiple biological parameters are communicated to said computer at least in part over a cellular communications network. 9. The system according to claim 1, wherein said ambulatory device records said multiple biological parameters and transfers them periodically upon being attached by a cable to an internet-connected appliance, and said appliance is configured to upload said multiple biological parameters to said computer over an internet connection. 10. The system according to claim 1, wherein said set of exemplary observations of said multiple biological parameters comprises at least some observations previously obtained from the monitored human under normal health conditions using such an ambulatory device. 11. The system according to claim 1, wherein said computer is further configured to use said monitored observation for localization so that a subset of said exemplary observations is used to generate said estimate. 12. The system according to claim 11, wherein said computer is further configured to determine said localized subset by performing a kernel-based comparison of said monitored observation with said exemplary observations. 13. The system according to claim 11, wherein said computer is further configured to determine said localized subset by comparing said monitored observation with predetermined clusters of said exemplary observations. 14. The system according to claim 1, wherein said computer is further configured with the capability to adapt said stored set of exemplary observations of said multiple biological parameters to include a monitored observation. 15. The system according to claim 14, wherein said computer is further configured to test residuals and provide notifications based thereon to a web page interface that enables a user of the system to identify any notification as corresponding to data from which at least one monitored observation should be used to adapt said stored set of exemplary observations. 16. The system according to claim 1, wherein said computer is further configured to test residuals with at least one threshold and generate notifications of health status based thereon. 17. The system according to claim 1, wherein said computer is further configured to test sequences of residuals to determine if a threshold is exceeded by a residual at least a selected number of times over said sequence and generate notifications of health status based thereon. 18. The system according to claim 1, wherein said computer is further configured to test sequences of residuals with a sequential probability ratio test and generate notifications of health status based thereon. 19. The system according to claim 1, wherein said computer is further configured to test for patterns of residuals with thresholds and generate notifications of health status based thereon. 20. The system according to claim 1, wherein said computer is further configured to test residuals and provide notifications based thereon to a web page interface that enables a user of the system to annotate any notification as corresponding to one of the set of statuses selected from the group consisting of (a) the notification is being monitored and investigated; (b) the notification is overruled; and (c) the notification is confirmed. 21. The system according to claim 1, wherein said monitored observation is first tested for being characteristic of at least one activity state before an estimate is generated. 22. The system according to claim 21, wherein the at least one activity state includes a state of resting. 23. The system according to claim 21, wherein the at least one activity state includes a state of sleeping. 24. The system according to claim 1, wherein said monitored observation is excluded from use in monitoring the health status of the human if the observation coincides with an interval which exhibits a disrupted respiratory pattern. 25. The system according to claim 1, wherein said kernel-based comparison of the monitored observation and at least some exemplary observations uses a kernel that determines its output value as a function of a norm of the vector difference between its multivariate input observations treated as vectors. 26. The system according to claim 1, wherein said kernel-based comparison of the monitored observation and at least some exemplary observations uses a kernel that determines its output value as a function of respective differences between like elements of its multivariate input observations. 27. The system according to claim 1, wherein said multiple biological parameters include a measure of heart rate variability. 28. The system according to claim 1, wherein said multiple biological parameters include a measure of a time lag between a respiratory activity and resulting oxygenation changes in the blood. 29. The system according to claim 1, wherein said multiple biological parameters include a measure of a time lag between a QRS event and a subsequent blood pressure event. 30. The system according to claim 1, wherein said multiple biological parameters include a measure of the difference between the ambient air temperature and the temperature of a location of the body. 31. The system according to claim 1, wherein said multiple biological parameters include to measure of breathing depth. 32. The system according to claim 1, wherein said observations of multiple biological parameters are made every 1 minute, and the multiple biological parameters comprise at least a measure of average heart rate, a measure of average respiration rate, and a measure of average blood pressure.
Wegerich, Stephan W.; Wolosewicz, Andre; Xu, Xiao; Herzog, James P.; Pipke, Robert Matthew, Automated model configuration and deployment system for equipment health monitoring.
Hsiung, Chang-Meng B.; Munoz, Bethsabeth; Roy, Ajoy Kumar; Steinthal, Michael Gregory; Sunshine, Steven A.; Vicic, Michael Allen; Zhang, Shou-Hua, Control for an industrial process using one or more multidimensional variables.
Cusumano, Joseph; Chelidze, David; Chatterjee, Anindya, General method for tracking the evolution of hidden damage or other unwanted changes in machinery components and predicting remaining useful life.
Haimowitz Ira Joseph ; Murren Brian Terence ; Lander Henry ; Pierce Barbara Ann ; Phillips Mary Clarkeson, Matching new customer records to existing customer records in a large business database using hash key.
Glier Michael T. (Chepachet RI) Nunez Linda I. Mensinger (North Kingstown RI) Scofield Christopher L. (Providence RI), Method and apparatus for adaptive classification.
Farringdon,Jonathan; Stivoric,John M.; Teller,Eric; Andre,David; Boehmke,Scott K.; Gasbarro,James; Kovacs,Gregory; Pelletier,Raymond; Kasabach,Christopher, Method and apparatus for measuring heart related parameters.
Niida Kazuo (Yokohama JPX) Koshijima Ichirou (Zushi JPX) Tani Jun (Kawasaki JPX) Hirobe Toshikazu (Tokyo JPX), Method for recognition of abnormal conditions using neural networks.
Borchers Hans-Werner,DEX ; Otte Ralf,DEX ; Speh Rainer,DEX ; Weisang Claus,DEX, Process diagnosis system and method for the diagnosis of processes and states in an technical process.
Petsche Thomas (Neshanic Station NJ) Garrett Charles (Plainsboro NJ), Radial basis function neural network autoassociator and method for induction motor monitoring.
Petsche Thomas (Neshanic Station NJ) Garrett Charles (Plainsboro NJ), Radial basis function neural network autoassociator and method for induction motor monitoring.
James, Mark L.; Mackey, Ryan M. E.; Park, Han G.; Zak, Michail, Real-time spatio-temporal coherence estimation for autonomous mode identification and invariance tracking.
Keeler James D. (Austin TX) Havener John P. (Austin TX) Godbole Devendra (Austin TX) Ferguson ; II Ralph B. (Austin TX), Virtual emissions monitor for automobile.
Keeler James David (Austin TX) Havener John Paul (Austin TX) Godbole Devendra (Austin TX) Ferguson ; II Ralph Bruce (Austin TX), Virtual emissions monitor for automobile and associated control system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.