Ventilator patient synchronization
4 Assignments
0 Petitions
Accused Products
Abstract
A method and apparatus that provides an expert system for determining respiratory phase during ventilatory support of a subject. Discrete phase states are partitioned and prior probability functions and observed probability functions for each state are defined. The probability functions are based upon relative duration of each state as well as the flow characteristics of each state. These functions are combined to determine phase probabilities for each state using Bayes'"'"' theorem. The calculated probabilities for the states may then be compared to determine which state the subject is experiencing. A ventilator may then conform respiratory support in accordance with the most probable phase. To provide a learning feature, the probability functions may be adjusted during use to provide a more subject specific response that accounts for changing respiratory characteristics.
57 Citations
75 Claims
-
1-42. -42. (canceled)
-
43. A method for estimating a subject'"'"'s respiratory phase in patient respiration by probability functions wherein the respiratory support of a ventilator can match the phase of the respiratory cycle of the patient comprising
partitioning the respiratory cycle into discrete phase states comprising respiratory states of inspiration and expiration and additional states within inspiration and expiration, calculating the probabilities of each phase state from probability functions.
- 52. A method for estimating a subject'"'"'s respiratory phase comprising utilizing previously calculated state probabilities to adjust prior probabilities wherein the respiratory patterns or characteristics of the patient are learned.
-
55. A method and apparatus for improved ventilator patient synchronization wherein the most likely phase is determined on the basis of flow and rate of change of flow information using Bayes'"'"' theorem or some similar formula for assessing conditional probability comprising
dividing or partitioning the respiratory cycle into a number of distinct states, making flow and pressure observations continuously and at each time point in a measuring determining probabilities or likelihoods in a calculating step, and determining the likelihood of the phase corresponding to each of the states
- 72. A system providing ventilatory support that automatically adjusts the support to accommodate the patient'"'"'s phase by adjusting a pressure gain associated with the particular state of the determined phase, wherein the probability for the phase L(Hi) is modified after calculations to improve subsequent determinations by adjusting L(Hi) to equal or approach the determined phase likelihoods L(HilFj) by a function of L(HilFj).
-
74. A ventilator apparatus having a processor programmed with an algorithm that accomplishes the following preferred method:
-
I. Repeat the following with a first time constant;
(a) Update the prior likelihood for each state L(Hi) (b) Update the likelihood of each observation, given each state L(FjlHi) II. Repeat the following with a second time constant;
(a) Measure flow, determine rate of change of flow (b) Calculate the likelihood L(HilF,) for each state using Bayes'"'"' theorem. (c) Phase is determined to be the most likely state. - View Dependent Claims (75)
-
Specification