Apparatus for processing physiological sensor data using a physiological model and method of operation therefor
View Patent ↗A pulse oximeter system comprises a data processor configured to perform a method that combines a sigma point Kalman filter (SPKF) or sequential Monte Carlo (SMC) algorithm with Bayesian statistics and a mathematical model comprising a cardiovascular model and a plethysmography model to remove contaminating noise and artifacts from the pulse oximeter sensor output and measure blood oxygen saturation, heart rate, left-ventricular stroke volume, aortic pressure and systemic pressures.
1. A method for generating a physiological estimate from input data, comprising the steps of:
generating input data using a biomedical monitoring device comprising a data processor configured to run a dual estimation algorithm, wherein the input data comprises at least one of:
a photoplethysmogram; and
an electrocardiogram,
processing said input data using said dual estimation algorithm, said dual estimation algorithm configured to use a dynamic state-space model to operate on the input data using both an iterative state estimator and an iterative model parameter estimator in generation of said physiological estimate, said dynamic state-space model configured to: mathematically represent probabilities of physiological processes that generate said physiological estimate and mathematically represent probabilities of physical processes that affect collection of the input data;
said state estimator iteratively:
operating on an initial input probability distribution function or a re-sampled probability distribution function using said dynamic state-space model to generate a second probability distribution function;
applying Bayes rule to said second probability distribution function and the input data to form a third probability distribution function; and
re-sampling said third probability distribution function as said re-sampled probability distribution function;
generating said physiological estimate using said model parameter estimator, said physiological estimate comprising:
a blood oxygen saturation; and
a left-ventricular stroke volume; and
warning of a hemorrhage using said physiological estimate.
2. The method of claim 1 , further comprising the step of:
said dynamic state-space model processing said second probability distribution function using a sequential Monte Carlo algorithm.
3. The method of claim 2 , further comprising the steps of said model parameter estimator iteratively:
providing an initial model parameter or providing an updated model parameter as an input to said dynamic state-space model to generate a current value for said physiological estimate;
using said third probability function and said current model parameter to form an expectation model; and
combining said expectation model with the input data using unsupervised machine learning to generate said updated model parameter.
4. The method of claim 3 , further providing an age input and a gender input in generation of said expectation model.
5. The method of claim 3 , wherein said expectation model comprises a confidence interval representing an accuracy probability of said current model parameter.
6. The method of claim 1 , further comprising the step of:
combining into the input data at least two of:
said plethysmogram;
said electrocardiogram; and
blood pressure monitor data.