CN-121122743-B - Early evaluation and processing system for severe wounds based on virtual-real combination interaction

CN121122743BCN 121122743 BCN121122743 BCN 121122743BCN-121122743-B

Abstract

The invention relates to the technical field of emergency patient information processing, in particular to a severe wound early evaluation and processing system based on virtual-real combined interaction. According to the invention, through the synchronization of abnormal time interval positioning and multi-terminal data, feature analysis is carried out by fusing multi-source data under a unified time sequence, continuous triggering of risk early warning and grading response is realized, wound indexes are automatically generated and geographical position information is linked, seamless information circulation and task pushing between multi-terminal platforms are realized, automatic synchronization, intelligent grading and scheduling response of data from site to hospital are promoted, system advantages are established in aspects of multi-link coordination, information closed loop and early wound discrimination, visual feedback of physiological processes, grading task closed loop and real-time resource matching are further supported, and early identification and treatment efficiency of severe patients is improved.

Inventors

XU FENG
YANG PENG
LI JUNGEN
LI XIAOQIN
YU LU
XU WEN
CHEN QIANG

Assignees

厦门立方幻境科技有限公司
苏州大学附属第一医院

Dates

Publication Date: 20260508
Application Date: 20251113

Claims (6)

1. A severe early-trauma assessment and processing system based on virtual-real combined interaction, the system comprising: The scene risk perception module analyzes the motion signal change, the illumination condition and the collision monitoring signal based on the IoT wearable device, judges the scene risk sequence, adjusts the acquisition frequency of each monitoring channel, and obtains the risk monitoring acquisition rate; the dynamic physiological extraction module is used for identifying continuous fluctuation of electrocardiosignals based on the risk monitoring acquisition rate, analyzing heart rate trend, blood pressure change and fluctuation in blood oxygen period, and positioning abnormal moments of multiple physiological parameters to obtain time sequence fluctuation positioning characteristics; The image feature analysis module analyzes a wound image acquired by the portable image equipment based on the time sequence fluctuation positioning feature, screens data loss, screens texture parameters after the complement, and compares the image with physiological changes to obtain a linkage abnormal index set; The image feature analysis module comprises: The image parameter screening submodule analyzes the distribution of the color channels and the brightness channels of the main area of the wound image based on the time sequence fluctuation positioning characteristics, judges whether the channels have complete data structures, screens samples with channel missing or abnormal distribution, and complements the channel content to obtain a main area channel data integration structure; the format standardization processing submodule calculates the spatial resolution and the color space consistency of an image to be processed based on the main area channel data integrated structure, judges samples with different formats, adjusts the pixel structure and unifies the coding mode, screens the image which accords with the unification standard, and obtains a standardized pixel structure set; The texture feature comparison sub-module calculates the texture density and uniformity of each block based on the standardized pixel structure set, combines time sequence fluctuation positioning features, compares image texture indexes with brightness sampling content under the same time sequence, acquires texture-brightness response mapping offset, screens the delay structure of texture parameters, and obtains a linkage abnormal index set; the abnormal grade judging module analyzes collision monitoring and blood pressure fluctuation parameters based on the linkage abnormal index set, weights multiple data, judges abnormal conditions of a patient through a severe judging standard, and obtains a grading risk judging factor; the abnormality level determination module includes: The collision feature extraction submodule analyzes acceleration change and continuous impact performance in collision monitoring signals based on the linkage abnormal index set, judges the change trend of impact amplitude and direction in a sampling interval, identifies continuous segments of the signals, optimizes shielding interference judging flow, compares physical feature differences of the segments, and calculates the motion performance of the impact segments to obtain collision physical feature indexes; The physiological fluctuation recognition submodule calculates amplitude changes of systolic pressure, heart rate and blood oxygen signals in a corresponding acquisition period based on the collision physical characteristic indexes, judges trend consistency of physiological parameters, screens intervals with the change amplitude higher than an amplitude threshold value, and compares fluctuation relevance among multichannel signals to obtain physiological abnormality response factors; Based on the physiological abnormal response factors, the severe risk assessment molecular module jointly analyzes the fluctuation interval of the blood pressure sequence, the collision impact amplitude performance and the heart rate regulation characteristics, calculates an abnormal performance dependent variable, and positions the sampling time proportion covered by the continuous offset section of the abnormal performance dependent variable to obtain a grading risk judgment factor; and the priority scheduling grading module analyzes the geographic position and the traffic time consumption of the patient based on the grading risk judging factors, and ranks the priorities of the patients according to grading index, distance and time consumption standardization processing to obtain scheduling priority configuration.
2. The early evaluation and processing system of severe trauma based on virtual-real combined interaction according to claim 1, wherein the risk monitoring collection rate comprises scene category codes, channel prioritization, real-time adjustment markers, the time sequence fluctuation positioning features comprise anomaly detection tags, change distribution curves, key positioning moments, the linkage anomaly index set comprises color saturation, brightness mean, texture grading factors, the grading risk decision factors comprise risk classification codes, grade evaluation numbers, reference comparison tags, and the scheduling priority configuration comprises priority tags, scheduling object identification, and transportation recommendation schemes.
3. The early severe trauma assessment and processing system based on virtual-real combined interaction of claim 1, wherein the scene risk perception module comprises: The wearable signal acquisition submodule is based on an internet of things (IoT) wearable device, and the data sources deployed on the chest and wrist nodes of a patient are used for sorting data streams of acceleration tracks, direction deviation channels and ambient illuminance channels in a time synchronization mode, and time labels output by the channels are matched to obtain a multichannel synchronous acquisition fragment set; The motion trend extraction submodule is used for synchronously collecting segment sets based on the multiple channels, comparing the acceleration of each segment with the direction deviation channel data, calculating the change amplitude of the speed and the direction between the segments, judging the consistency or turning point of the motion trend, and marking the trend change section and the duration time by combining the segment sequence numbers to obtain a continuous trend change marking group; The channel frequency configuration sub-module analyzes illuminance channel data and collision signal tracks in corresponding segments based on the continuous trend change labeling group, compares the illuminance balance with the continuous characteristics of collision change, and adjusts the data acquisition priority sequence of each monitoring channel to obtain risk monitoring acquisition rate.
4. The early severe trauma assessment and processing system based on virtual-real combined interaction of claim 1 wherein the dynamic physiological extraction module comprises: The electrocardiographic wave dynamic identification submodule analyzes the electrocardiographic signals of the priority channel based on the risk monitoring acquisition rate, judges the waveform change of continuous heartbeat cycles, screens intervals with consistent waveform stability and fluctuation trend by identifying ascending and descending stages of each cycle, and adjusts signal label distribution by combining sampling frequency to obtain an electrocardiographic wave dynamic change index set; The parameter trend comparison submodule is used for comparing heart rate data with blood pressure data based on the electrocardiographic wave change index set, analyzing trend directions and change formats of the two groups of data, screening intervals with trend synchronous change and trend consistency, and obtaining a synchronous trend matching section set; And the time sequence feature positioning sub-module analyzes the fluctuation distribution of the data in the blood oxygen channel in the period according to the synchronous trend matching section set, and performs time coordinate mapping on all fluctuation points by comparing turning points of electrocardio and blood pressure parameters, so as to establish a fluctuation corresponding relation of the multichannel physiological signals and obtain the time sequence fluctuation positioning feature.
5. The early severe trauma assessment and processing system based on virtual-real combined interaction of claim 1 wherein the priority scheduling hierarchy module comprises: the position analysis submodule analyzes the space coordinates between the patient positioning information and the hospital positioning information based on the grading risk judging factors, compares the geographic relative relation between the patient positioning information and the hospital positioning information, judges the space distribution condition of the current position and the target hospital, screens positioning parameters and obtains a geographic distance calculation result; The traffic time-consuming evaluation submodule optimizes the path data obtained by the geographical distance calculation result, analyzes the road grade and traffic information of each transit route, judges the communication condition and traffic trend of each path node, screens continuous traffic routes and obtains path traffic evaluation indexes; And the priority ordering configuration submodule arranges grading priority parameters of each patient based on the path passing evaluation index, adjusts the corresponding relation between the patient and the emergency vehicle, establishes a priority number sequence and obtains scheduling priority configuration.
6. The early severe trauma assessment and processing system based on virtual-real combined interaction of claim 1, wherein the IoT wearable device refers to an internet of things device capable of being worn on a patient for acquiring vital sign and on-site environment data in real time, the physiological change refers to the time of the extracted abnormal physiological parameter, and corresponds to the image acquisition time one to one, and the patient abnormal condition refers to the risk level or criticality of the patient under classification at the current time.

Description

Early evaluation and processing system for severe wounds based on virtual-real combination interaction Technical Field The invention relates to the technical field of emergency patient information processing, in particular to a severe wound early-stage evaluation and processing system based on virtual-real combined interaction. Background The field of emergency patient information processing mainly relates to matters such as physiological parameter acquisition, data transmission, case information management, diagnosis and treatment information integration, multi-terminal information sharing and the like of patients in an emergency scene, and covers multi-level medical collaborative scenes such as pre-hospital emergency, emergency department treatment and trauma center, and the like, so that the high-efficiency acquisition, dynamic analysis and real-time sharing of early information of critical and severe patients such as severe wounds are mainly realized, and the intelligent and informationized level of a clinical treatment process is improved. The traditional severe trauma early evaluation and treatment system based on virtual-real combination interaction is characterized in that medical image acquisition, patient physiological parameter monitoring and clinical inquiry data are combined, and a wounded patient is rapidly evaluated and classified through scene simulation and clinical actual operation linkage, so that medical staff is supported to complete preliminary condition judgment and treatment scheme formulation. In the prior art, under the scene of first-aid trauma evaluation and grading treatment, medical staff still rely on to manually input sign data, subjective judgment is easy to cause evaluation delay and key information omission, pre-hospital and intra-hospital data stream are disjointed, vital signs and injury images cannot be synchronously transmitted in real time, the response of an intra-hospital team is affected, a grading mechanism mainly depends on manual operation and is difficult to respond to a severe patient rapidly and preferentially, the data fusion realizes multi-source integration but has a feedback mode basis, vision and touch linkage is insufficient, task and resource coordination between the site and the hospital are lagged, and the overall level of severe trauma recognition and intelligent grading scheduling is limited. Disclosure of Invention The invention aims to solve the defects in the prior art, and provides a severe wound early-stage evaluation and treatment system based on virtual-real combination interaction. In order to achieve the aim, the invention adopts the following technical scheme that the early severe wound assessment and treatment system based on virtual-real combined interaction comprises: The scene risk perception module analyzes the motion signal change, the illumination condition and the collision monitoring signal based on the IoT wearable device, judges the scene risk sequence, adjusts the acquisition frequency of each monitoring channel, and obtains the risk monitoring acquisition rate; the dynamic physiological extraction module is used for identifying continuous fluctuation of electrocardiosignals based on the risk monitoring acquisition rate, analyzing heart rate trend, blood pressure change and fluctuation in blood oxygen period, and positioning abnormal moments of multiple physiological parameters to obtain time sequence fluctuation positioning characteristics; The image feature analysis module analyzes a wound image acquired by the portable image equipment based on the time sequence fluctuation positioning feature, screens data loss, screens texture parameters after the complement, and compares the image with physiological changes to obtain a linkage abnormal index set; the abnormal grade judging module analyzes collision monitoring and blood pressure fluctuation parameters based on the linkage abnormal index set, weights multiple data, judges abnormal conditions of a patient through a severe judging standard, and obtains a grading risk judging factor; and the priority scheduling grading module analyzes the geographic position and the traffic time consumption of the patient based on the grading risk judging factors, and ranks the priorities of the patients according to grading index, distance and time consumption standardization processing to obtain scheduling priority configuration. The invention improves that the risk monitoring acquisition rate comprises scene category codes, channel priority ordering and real-time adjustment marks, the time sequence fluctuation positioning characteristics comprise anomaly detection labels, change distribution curves and key positioning moments, the linkage anomaly index set comprises color saturation, brightness mean values and texture classification factors, the classification risk judgment factors comprise risk classification codes, class evaluation numbers and reference comparison labels, and the scheduli