Method for determining blood pressure utilizing a neural network

• US 5,339,818 A
• Filed: 09/09/1993
• Issued: 08/23/1994
• Est. Priority Date: 09/20/1989
• Status: Expired due to Term

• Current Assignee: University of Utah Research Foundation (State of Utah)
• Original Assignee: University of Utah Research Foundation (State of Utah)
• Inventors: Baker, Phillip D., Egbert, Timothy P., Orr, Joseph A., Westenskow, Dwayne R.
• Primary Examiner(s): Cohen, Lee S.
• Assistant Examiner(s): Nasser, Robert L.
• Application Number:
  US08/119,451
• Time in Patent Office: 348 Days
• Field of Search: 395/22, 395/924, 128/677-685, 364/413.03
• US Class Current: 600/490
• CPC Class Codes: A61B 5/02156 Calibration means
• CPC Class Codes: A61B 5/022 by applying pressure to close blood vessels, e.g. against the skin; Ophthalmodynamometers
• CPC Class Codes: A61B 5/087 Measuring breath flow
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61M 16/026 specially adapted for predicting, e.g. for determining an information representative of a flow limitation during a ventilation cycle by using a root square technique or a regression analysis
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: Y10S 128/925 Neural network
• CPC Class Codes: Y10S 706/924 Medical

Abstract

A method and device for indirect, quantitative estimation of blood pressure attributes and similar variable physiological parameters utilizing indirect techniques. The method of practice includes (i) generating a sequence of signals which are quantitative dependent upon the variable parameter, (ii) transmitting and processing the signals within a computer system and associated neural network capable of generating a single output signal for the combined input signals, (iii) directly determining an actual value for the parameter concurrent with the indirect generation of signals of the previous steps, (iv) applying weighting factors within the neural network at interconnecting nodes to force the output signal of the neural network to match the true value of the parameter as determined invasively, (v) recording the input signals, weighting factors and true value as training data within memory of the computer, and (vi) repeating the previous steps to develop sufficient training data to enable the neural network to accurately estimate parameter value upon future receipt of on-line input signals. Procedures are also described for preclassification of signals and artifact rejection. Following training of the neural network, further direct measurement is unnecessary and the system is ready for diagnostic application and noninvasive estimation of parameter values.

Claims

1. A method for on-line calculation of a variable physiological parameter of a patient, said method comprising the steps of:

(1.1) identifying the physiological parameter to be quantitatively monitored and estimated;

(1.2) coupling at least one sensor to the patient, said sensor being responsive to register changes in the physiological parameter, which changes are quantitatively dependent on a particular value for the parameter;

(1.3) activating the sensor to generate a sequence of on-line signals which register changes in the physiological parameter;

(1.4) transmitting the on-line signals as input signals to a computer system, including input nodes of a neural network supported by the computer system, which neural network is capable of calculating an output signal corresponding to a parameter value from the on-line, input signals;

(1.5) processing the input signals within the neural network to convert the sequence of input signals to an on-line output signal corresponding to a parameter value by applying fixed weighting factors to the input signals;

(1.6) generating said fixed weighting factors by retrieving weighting factors which were previously generated by applying a training algorithm with respect to previously collected training data comprising neural network input signals and corresponding known parameter values.

2. A method as defined in claim 1, further comprising the steps of:

(2.1) selecting a plurality of sample signals from the sequence of signals for processing through a neural network which has been trained to associate such sample signals with a related value for the physiological parameter; and

(2.2) identifying at least one feature within the sample signals which can be processed through the neural network as a feature signal.

3. A method as defined in claim 2, wherein step 2.2 includes the step of identifying amplitude of oscillatory signals as the feature which defines the feature signal, said method further including the step of developing a waveform based on the sequential signals generated in step 1.3, said waveform being represented by the locus of points representing the amplitude of each oscillatory signal graphed with respect to a measurement of blood pressure over a time period comprising a single measurement procedure.

4. A method as defined in claim 3, wherein step 2.2 comprises the more specific step of selecting at least two sample signals from all signals generated pursuant to step 3 for the single measurement procedure and processing the amplitude feature signal of these sample signals in accordance with the remaining steps of claim 1 to estimate the parameter value without processing all signals being generated.

5. A method as defined in claim 3, wherein steps 1.3 and 1.4 include the more specific steps as follows:

(5.1) developing a waveform for each single measurement procedure comprising a predetermined number of sample signals, which number corresponds approximately to the number of input nodes existing in the neural network;

(5.2) storing in memory the sample signals; and

(5.3) transmitting the stored sample signals of the waveform to respective input nodes of the neural network.

6. A method as defined in claim 5, wherein step 5.1 comprises the more specific step of selecting at least two sample signals from all signals generated pursuant to step 1.3 for the single measurement procedure and processing the amplitude feature signal of these sample signals in accordance with the remaining steps of claim 1 to apply on-line signals at the neural network to calculate the estimated parameter value by sampling only several representative signals from the sequence of signals being generated.

7. A method as defined in claim 2, comprising the more specific step of identifying the physiological parameter for monitoring and estimation to be a blood pressure parameter selected from the group consisting of diastolic, means, and systolic intraarterial blood pressures.

8. A method as defined in claim 7 for estimating blood pressure parameters, including the additional steps of:

(8.1) generating a sequence of oscillometric signals representing heart pulse from a pressure sensing means coupled externally to a patient'"'"'s anatomy in sensing proximity to a heart pulse sensing location; and

(8.2) identifying the feature within the oscillometric signals to be pulse amplitude.

9. A method as defined in claim 8, comprising the more specific step of measuring and recording pressure values at predetermined increments over pressure ranges from approximately 20 to 200 torr.

10. A method as defined in claim 8, including the more specific step of selecting less than all generated signals of step 8.1 for transmittal to the input nodes of the neural network.

11. A method as defined in claim 10, comprising the more specific step of selecting a representative sampling of at least two generated signals, thereby estimating the waveform developed by the signals transmitted to the input nodes of the neural network without requiring processing of all signals through all interactive nodes of the neural network to generate the desired output signal corresponding to the value of the blood pressure parameter.

12. A method for on-line calculation of a variable physiological parameter of a patient, said method comprising the steps of:

(12.1) identifying the physiological parameter to be quantitatively monitored and estimated;

(12.2) coupling at least one sensor to the patient, said sensor being responsive to register changes in the physiological parameter, which changes are quantitatively dependent on a particular value for the parameter;

(12.3) activating the sensor to generate a sequence of on-line signals which register changes in the physiological parameter;

(12.4) transmitting the on-line signals as input signals to a computer system, including input nodes of a neural network supported by the computer system, which neural network is capable of calculating an output signal corresponding to a parameter value from the on-line, input signals;

(12.5) processing the input signals within the neural network to convert the sequence of input signals to an on line output signal corresponding to a parameter value in accordance with the following substeps;

12.5a) processing the input signals within the neural network through at least one neural network layer having at least one node by applying fixed weighting factors to the input signals;

14. A method as defined in claim 12, further comprising the steps of processing the output of the at least one hidden layer node from step 12.5g) by repeating steps 12.5c) through 12.5g) until the at least one node output defined in step 12.5(e)f) representing the estimated physiological parameter has been displayed.

13. 5b) generating said fixed weighting factors by retrieving fixed weighting factors which were previously determined by applying a training algorithm with respect to previously collected training data comprising neural network input signals and corresponding known parameter values to generate said fixed weighting factors;

12.5c) for each input signal of each node within the neural network layer, calculating a product of the input signal and fixed weighting factor corresponding to each input signal and node combination;

12.5d) for each node within the neural network layer, summing the products of each input signal and fixed weighting factor combination calculated in the previous step 12.5c);

12.5e) for each node within the neural network layer, calculating a node output by applying an input/output function to the sum calculated in the previous step 12.5d);

12.5f) where the output of each node calculated in step 12.5e) represents the neural network output, displaying at least one node output as an estimated physiological parameter, or

12.5g) where the output of each node calculated in step 12.5e) represents the output of at least one hidden layer node, passing at least one output from outputs calculated in 12.5e) as input to any subsequent layer of nodes in the neural network.