Biometric information acquisition device, processing device, and computer program

Abstract

To improve the interpretability of the processing results of biometric information obtained from subjects. [Solution] The receiving device 11 receives waveform data WD corresponding to the measured waveform of the electrocardiogram of the subject 30 from the electrodes 20, and obtains the values ​​PV of multiple feature parameters associated with the measured waveform based on the waveform data WD. The processing device 12 inputs the values ​​PV of the multiple feature parameters into a machine learning model 123 to obtain an inference result RS for at least one of the multiple classes to which the waveform data WD is classified, and identifies the importance of each of the multiple feature parameters for the inference result RS. The output device 13 outputs an index showing the result of adding up the identified importance for each of the multiple feature parameters associated with each of the multiple body parts of the subject 30.

Claims

1. A biological information acquisition device that acquires biological information of a subject, A receiving device that receives waveform data corresponding to the measurement waveform of the biological information from a sensor and acquires the values ​​of multiple feature parameters associated with the measurement waveform based on the waveform data, A processing device that inputs the values ​​of the plurality of feature parameters into a machine learning model to obtain an inference result for at least one of the plurality of classes to be classified as waveforms, and identifies the importance of each of the plurality of feature parameters for the inference result, An output device that outputs an index showing the result of adding up the importance of multiple characteristic parameters associated with each of the multiple body parts of the subject, It is equipped with A device for acquiring biological information.

2. The index is configured to allow comparison of the relative importance levels identified for at least two of the plurality of feature parameters. A biological information acquisition device according to claim 1.

3. The output device displays the indicator so as not to overlap with the measured waveform. A biological information acquisition device according to claim 1 or 2.

4. The index includes the value of at least one feature parameter. A biological information acquisition device according to any one of claims 1 to 3.

5. The aforementioned machine learning model is generated by machine learning using a neural network. A biological information acquisition device according to any one of claims 1 to 4.

6. A processing device for processing the biological information of a subject, An interface that receives values ​​of multiple feature parameters associated with the measurement waveform of the biological information, which are acquired based on waveform data corresponding to the measurement waveform, A processor that inputs the values ​​of the plurality of feature parameters into a machine learning model to obtain an inference result for at least one of the plurality of classes to be classified as waveform, identifies the importance of each of the plurality of feature parameters for the inference result, and outputs index data corresponding to an index that shows the result of adding up the importance identified for each of the plurality of feature parameters associated with each of the plurality of body parts of the subject. It is equipped with Processing device.

7. A computer program that can be executed by a processor installed in a processing device that processes the biological information of a subject, By being executed, the processing device will Based on waveform data corresponding to the measurement waveform of the said biological information, the system receives values ​​for multiple feature parameters associated with the measurement waveform. By inputting the values ​​of the aforementioned multiple feature parameters into the machine learning model, an inference result is obtained for at least one of the multiple classes to be waveform-classified. The importance of each of the multiple feature parameters for the inference result is identified, The system outputs index data corresponding to an index that shows the result of adding up the importance of multiple feature parameters associated with each of the multiple body parts of the subject. Computer program.

Images