CN-122004757-A - Diaphragm function track monitoring system and evaluation method for severe patients

CN122004757ACN 122004757 ACN122004757 ACN 122004757ACN-122004757-A

Abstract

The application discloses a diaphragm function track monitoring system and an evaluation method for an intensive patient, and belongs to the technical field of intensive care medical treatment. The method comprises the steps of synchronously collecting an ultrasonic image data stream related to diaphragm of a patient and a respiratory mechanics data stream related to a breathing machine of the patient, analyzing and generating a first time sequence physiological parameter sequence in real time based on the ultrasonic image data stream, calculating and generating a second time sequence physiological parameter sequence in real time based on the respiratory mechanics data stream, and generating a diaphragm function reserve index for representing the diaphragm function reserve state of the patient based on joint analysis of the first time sequence physiological parameter sequence and the second time sequence physiological parameter sequence. According to the application, through synchronously fusing and dynamically analyzing the multi-mode physiological data, a composite index capable of objectively, continuously and prospectively quantifying the anti-fatigue capacity of the diaphragm is constructed, and the problems that in the prior art, machine withdrawal evaluation depends on scattered and static indexes, and the judgment subjectivity is strong and the cognitive load is high are solved.

Inventors

REN YAYU
GAO CHUNHUA
Chu Junqing
QIAO WENBO
ZHOU FEIFEI
WENG MEILING
Deng Qionglin
CAI SHENGYUAN
Zhao Qiongchao

Assignees

浙江大学医学院附属第一医院(浙江省第一医院)

Dates

Publication Date: 20260512
Application Date: 20260126

Claims (10)

1. A method of evaluating the functional trajectory of the diaphragm muscle of a critically ill patient, comprising: Simultaneously acquiring an ultrasound image data stream associated with the diaphragm of a patient and a respiratory mechanics data stream associated with the mechanical ventilator of the patient; Determining a first sequence of physiological parameters comprising a plurality of first physiological parameters characterizing the morphological dynamics of the diaphragm based on the ultrasound image data stream; determining a second time-series physiological parameter sequence of a plurality of second physiological parameters characterizing the respiratory power of the patient based on the respiratory mechanics data stream; Generating a diaphragmatic function reserve index for characterizing the diaphragmatic function reserve status of the patient based on a joint analysis of the first and second time-ordered physiological parameter sequences over a preset time window.
2. The method of claim 1, wherein the first physiological parameter comprises an instantaneous diaphragm thickness and a diaphragm thickening fraction derived from the instantaneous diaphragm thickness over a respiratory cycle.
3. The method of claim 2, wherein said determining said first sequence of timing physiological parameters comprises: Applying a semantic segmentation model to each image frame in the ultrasound image data stream to identify and segment a binary mask of a diaphragmatic region; acquiring the instant diaphragm thickness based on the binary mask and a preset pixel-millimeter calibration scale; The diaphragm thickening fraction is obtained based on a preset baseline diaphragm thickness and the peak value of the instantaneous diaphragm thickness over a respiratory cycle.
4. The method of claim 1, wherein the second physiological parameter comprises a pressure-time product and work of breathing.
5. The method of claim 1, wherein the generating the diaphragmatic function reserve index comprises: Acquiring a working efficiency component based on the first time sequence physiological parameter sequence and the second time sequence physiological parameter sequence; acquiring an anti-fatigue capacity component based on the change trend of the first time sequence physiological parameter sequence in the preset time window; acquiring a recovery elasticity component based on morphological recovery characteristics corresponding to expiration of each respiratory cycle in the first sequence of physiological parameters; The diaphragm function reserve index is generated based on a weighted combination of the work efficiency component, the fatigue resistance component, and the recovery elasticity component.
6. The method of claim 5, wherein the step of determining the position of the probe is performed, The obtaining the working efficiency component comprises obtaining the correlation between the diaphragm thickening fraction and the pressure-time product in the preset time window; The obtaining the fatigue resistance component comprises obtaining an absolute value of a linear regression slope of the diaphragm thickening fraction changing along with time in the preset time window, and carrying out normalization processing on the absolute value; the obtaining of the recovered elastic component comprises the steps of obtaining a time constant of the decay of the instantaneous diaphragm thickness along with time aiming at the breathing phase of each breathing period in the preset time window, and normalizing the reciprocal of the mean value of the time constant.
7. The method of claim 6, wherein normalizing the absolute value comprises determining a normalized mapping based on a statistical distribution of absolute values of linear regression slope of diaphragm thickening scores over time in a predetermined reference patient database, and applying the normalized mapping for processing.
8. The method of claim 6, wherein normalizing the inverse of the mean value of the time constant comprises determining a normalized mapping based on a statistical distribution of inverse time constant mean values of instantaneous diaphragm thickness decaying over time in a predetermined reference patient database, and applying the normalized mapping for processing.
9. The method of claim 1, further comprising, prior to the synchronized acquisition: responding to a calibration instruction, and acquiring and storing a pixel-millimeter calibration scale for analyzing the ultrasonic image data stream; In a baseline calibration phase, a baseline diaphragm thickness is obtained and stored for calculating the diaphragm thickening fraction.
10. A monitoring system for the functional trajectory of the diaphragm muscle of a critically ill patient, comprising: a multi-modality synchronized data acquisition module configured to simultaneously acquire an ultrasound image data stream associated with a patient's diaphragm and a respiratory mechanics data stream associated with the patient's mechanical ventilator; An ultrasound image real-time parsing module configured to determine a first sequence of physiological parameters comprising a plurality of first physiological parameters characterizing the morphological dynamics of the diaphragm based on the ultrasound image data stream; a respiratory mechanics parameter calculation module configured for determining a second time-series physiological parameter sequence of a plurality of second physiological parameters characterizing a respiratory mechanics characteristic of the patient based on the respiratory mechanics data stream; A functional reserve index calculation module configured to generate a diaphragmatic muscle functional reserve index for characterizing a diaphragmatic muscle functional reserve status of the patient based on a joint analysis of the first and second time-ordered sequences of physiological parameters within a preset time window.

Description

Diaphragm function track monitoring system and evaluation method for severe patients Technical Field The application relates to the technical field of medical monitoring, in particular to a diaphragm function track monitoring system and an evaluation method for an critically ill patient. Background In intensive care medicine, mechanical ventilation is a critical means of maintaining vital signs in critically ill patients. However, long-term mechanical ventilation can lead to a number of complications, such as ventilator-associated pneumonia, diaphragmatic atrophy, and the like. Therefore, accurately judging whether the patient has the ability to break away from the breathing machine and grasping the optimal machine withdrawal time is a core problem and challenge in ICU clinical work. The prior art relies mainly on the comprehensive evaluation of a series of discrete physiological indexes such as respiratory rate, tidal volume, maximum inspiratory pressure, etc. by a clinician, and may be aided by bedside ultrasound to observe diaphragmatic thickening scores. The method has fundamental technical contradiction that on one hand, the data sources are enriched, the high-frequency breathing machine data flow and the dynamic ultrasonic image provide unprecedented information quantity, on the other hand, the decision process is lagged and subjectively made, doctors need to carry out 'intra-brain synthesis' of high cognitive load on the data which are split in time and isomerically heterogeneous by means of personal experience, and objective, continuous and prospective quantitative judgment on diaphragm function 'reserve' and 'fatigue trend' is difficult to form. This results in limited accuracy and repeatability of the withdrawal decisions, with high rates of withdrawal failure. Disclosure of Invention The first aspect of the application provides an evaluation method of diaphragm function tracks of severe patients, and aims to solve the technical problems that in the prior art, evaluation of ventilator withdrawal time depends on scattered and static indexes, so that judgment subjectivity is strong, cognitive load is high and prospective prediction capability is lacking. The application provides an evaluation method of diaphragm function tracks of a severe patient, which comprises the steps of synchronously collecting ultrasonic image data flow related to the diaphragm of the patient and respiratory mechanics data flow related to a mechanical breathing machine of the patient, determining a first time sequence physiological parameter sequence formed by a plurality of first physiological parameters representing the morphological dynamics of the diaphragm based on the ultrasonic image data flow, determining a second time sequence physiological parameter sequence formed by a plurality of second physiological parameters representing the respiratory mechanics characteristics of the patient based on the respiratory mechanics data flow, and generating a diaphragm function reserve index representing the diaphragm function reserve state of the patient based on joint analysis of the first time sequence physiological parameter sequence and the second time sequence physiological parameter sequence in a preset time window. Optionally, according to the foregoing aspect, the first physiological parameter includes an instantaneous diaphragm thickness and a diaphragm thickening fraction derived from the instantaneous diaphragm thickness over a respiratory cycle. Optionally, according to the foregoing, the determining the first sequence of timing physiological parameters includes applying a semantic segmentation model to each image frame in the ultrasound image data stream to identify and segment a binary mask of a diaphragm region, obtaining the instantaneous diaphragm thickness based on the binary mask and a predetermined pixel-millimeter scale, and obtaining the diaphragm thickening score based on a predetermined baseline diaphragm thickness and a peak value of the instantaneous diaphragm thickness over a breathing period. Optionally, according to the foregoing aspect, the second physiological parameter includes a pressure-time product and work of breathing. Optionally, according to the foregoing aspect, the generating the diaphragmatic function reserve index includes obtaining a working efficiency component based on the first time-series physiological parameter sequence and the second time-series physiological parameter sequence, obtaining an anti-fatigue capacity component based on a variation trend of the first time-series physiological parameter sequence within the preset time window, obtaining a recovery elasticity component based on morphological recovery characteristics corresponding to exhalation of each respiratory cycle in the first time-series physiological parameter sequence, and generating the diaphragmatic function reserve index based on a weighted combination of the working efficiency component, the anti-fatigue capa