The invention relates to the technical field of patient
recovery evaluation, and discloses a patient
recovery evaluation method and
system based on an
intelligent sensor. In a standard heart pulse simulator environment, the sensor
voltage and the reference
heart rate are preheated and collected, and static calibration and
scale reading are completed.
Voltage is collected at intervals during patient monitoring and converted into a
heart rate time sequence, and after three-point median filtering, abnormities are eliminated according to the median of the whole section and the
absolute deviation of the median; taking a median value from the first batch of steady-state samples as a baseline
heart rate, and calculating
absolute deviation to construct a deviation sequence; the median of the baseline segment deviation is taken, a threshold value is set in combination with the
absolute deviation of the whole segment, and a
recovery starting point is recognized through a sliding window; and finally, calculating a deviation accumulation area by using a composite trapezoid method, and generating a quantitative recovery
score by combining the
maximum deviation and duration normalization.