Search

CN-121987149-A - Dynamic evaluation method for patient reviving progress in anesthesia recovery stage of operating room

CN121987149ACN 121987149 ACN121987149 ACN 121987149ACN-121987149-A

Abstract

The invention relates to the technical field of vital sign monitoring and evaluation, in particular to a dynamic evaluation method for the patient wakeup progress in the anesthesia recovery stage of an operating room, which comprises the following steps: the method comprises the steps of obtaining intervention behaviors in an anesthesia recovery stage, performing time sequence arrangement, performing segmentation and statistics according to time dimension, analyzing intervention density change, adjusting an evaluation time range, and performing association analysis by combining vital sign signals in a corresponding time period to form a dynamic evaluation conclusion of patient awakening progress. According to the invention, a structural intervention operation sequence is constructed, and the time granularity is used for carrying out subsection statistics, so that quantitative expression and change trend capture of intervention density are realized, an evaluation boundary is adjusted by combining a density difference direction, the focusing capability of a state active period is improved, continuous electroencephalogram and blood oxygen signal sequences are extracted on the basis, pairing analysis is carried out, the cooperative fluctuation characteristics of nerve and blood oxygen response are identified, dynamic quantitative judgment on a wakeup process is formed, and the accuracy and timeliness of state identification are enhanced.

Inventors

  • Xian Yalin
  • ZHOU JINGYI
  • QIN XUE
  • LI FENG
  • NIE XIN

Assignees

  • 中国人民解放军陆军军医大学第一附属医院

Dates

Publication Date
20260508
Application Date
20260128

Claims (10)

  1. 1. The dynamic evaluation method for the patient wakeup progress in the anesthesia recovery stage of the operating room is characterized by comprising the following steps of: S1, acquiring intervention behaviors recorded in an anesthesia recovery stage, marking triggering time, operation types and execution sequence, constructing an intervention operation chain according to time sequence, and cutting according to preset time interval granularity to generate an operation behavior sequence; S2, calling the operation behavior sequence, summarizing the occurrence times of the intervention types of the time segments, calling a preset intervention grade parameter set, carrying out grading statistics on the intervention types, carrying out product operation according to preset grade coefficients, summing, superposing the intervention behavior quantity and the intensity grade in a weighted mode, and constructing a time scale map by combining the intervention operation time continuity to generate an intervention frequency distribution map; S3, calling the intervention frequency distribution diagram, collecting intervention density change results in a sliding window, calculating the intervention density difference direction of an adjacent window, judging trend change, extracting time nodes with density change trend, and outputting trend change marks; S4, calling the trend change mark, comparing the density increasing direction with the current evaluation time period, controlling the time boundary to shrink and extend towards the density concentration characteristic direction, and constructing a time evaluation boundary section; S5, calling the time evaluation boundary section, intercepting vital sign monitoring data, acquiring an electroencephalogram rhythm signal sequence and a blood oxygen saturation signal sequence, analyzing a period and a fluctuation direction, identifying a cooperative fluctuation phenomenon, and outputting a dynamic evaluation conclusion of the patient wakeup progress.
  2. 2. The method of claim 1, wherein the sequence of operational actions includes an intervention trigger time stamp, an operation type code, an execution sequence number, and a time granularity segment, wherein the intervention frequency profile includes an intervention type hierarchy, a weighted intervention intensity value, and a time continuity map, wherein the trend change stamp includes an intervention density difference direction, a trend change continuity identifier, and a change trend time node, wherein the time assessment boundary section includes a boundary contraction section, a boundary extension section, and an adjusted boundary combination, and wherein the patient wakeup progress dynamic assessment conclusion includes an electroencephalogram rhythm change characteristic, a blood oxygen saturation fluctuation characteristic, and a neuroblood oxygen cooperative fluctuation relationship.
  3. 3. The method according to claim 1, wherein the time node with a tendency to change density is a key time point in which the trend of change in the intervention density calculated by sliding window in the intervention frequency distribution map includes increase and decrease.
  4. 4. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the identification of the cooperative fluctuation phenomenon is a phenomenon in which the direction of periodic variation is kept consistent and fluctuates synchronously in the electroencephalogram rhythm and blood oxygen saturation signals.
  5. 5. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the specific steps of S1 are: S101, acquiring intervention behaviors of anesthesia recovery stages recorded in a nurse operation terminal, extracting a time stamp field in each intervention behavior record, calling an operation field in a corresponding intervention record by taking the time stamp field as the trigger time of the intervention behavior, acquiring operation instruction content, marking the operation sequence of the intervention behaviors by traversing sequence number fields, and generating an intervention behavior parameter set; S102, based on the triggering time, the operation type and the operation sequence extracted from the intervention behavior parameter set, adopting the operation sequence as a sequencing basis, carrying out incremental sequencing on all intervention behaviors, constructing an operation linked list structure according to a sequencing result, connecting adjacent intervention behavior nodes through the linked list structure, and establishing intervention operation linked list structure data; S103, invoking time stamp information of each node in the intervention operation linked list structure data, splitting time periods of the nodes in the operation linked list according to preset time interval granularity, and generating an operation behavior sequence according to the original sequence of the nodes included in each time period.
  6. 6. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the specific steps of S2 are: S201, invoking time segment data in the operation behavior sequence, traversing the intervention instruction content in each time segment, identifying an intervention type identifier corresponding to a differentiated behavior instruction, counting the number value of the intervention types in the same time segment, and independently counting according to the intervention type distinction to generate an intervention type frequency matrix; S202, according to the intervention type frequency matrix, a preset intervention grade parameter set is called to carry out grade matching on the intervention types in the same time segment, grade coefficients corresponding to each intervention type are extracted, and the product operation is carried out on the number of the intervention types and the grade coefficients in the time segment by adopting a weighted superposition mode and then the summation is carried out, so that an intervention intensity numerical value distribution table is obtained; S203, establishing an equal-length time scale axis according to the time start-stop positions in each time segment based on the time segment sequences in the intervention intensity value distribution table, mapping the intervention intensity values onto the time scale axis according to the time segment positions, and connecting adjacent data points according to the time sequence to form a continuous value curve so as to generate an intervention frequency distribution diagram.
  7. 7. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the specific step of S3 is: S301, calling intervention intensity values on a continuous time axis in the intervention frequency distribution diagram, setting parameters of an equal-width sliding window, intercepting an intervention intensity value set in a corresponding time period in sequence in a window sliding mode, calculating arithmetic average values of all the intervention intensity values in each sliding window, and generating a sliding window intervention density sequence; S302, based on density values of two adjacent sliding window positions in the sliding window intervention density sequence, performing difference operation between the current position density value and the previous window density value, extracting a difference sign to judge a density variation direction, and continuously judging whether the direction of the difference is reversed or not to acquire a density variation trend direction sequence; S303, according to the positions of the turning points of the symbols of the density direction change in the density change trend direction sequence, retrieving all time index nodes with direction change in the continuous detection period range, extracting the corresponding time positions on the time scale axis, and outputting trend change marks.
  8. 8. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the specific step of S4 is: S401, calling time identification nodes in the trend change marks, extracting continuously arranged density growth direction marks, setting start-stop boundary values of a current evaluation time period, carrying out index comparison on the continuous density growth marks by using time axis scales, screening all growth mark nodes positioned in the current time period range, and obtaining a density concentration trend node set; S402, analyzing the sequence of the boundary positions of the time nodes and the current evaluation time period according to the density concentration trend node set, judging whether the direction of the variation trend tends to be close to the central position of the time period, and if so, sequentially reducing and adjusting the starting boundary and the ending boundary to the central position to obtain a boundary contraction interval parameter set; S403, replacing the current evaluation time period according to the adjusted start-stop boundary according to the boundary regulation result of the boundary contraction interval parameter set, constructing a continuous change section structure, and executing combination aggregation operation on all the change sections to generate a time evaluation boundary section.
  9. 9. The method for dynamically assessing the progress of patient recovery during the recovery phase of anesthesia in an operating room according to claim 1, wherein the specific step of S5 is: S501, invoking a start-stop boundary in the time evaluation boundary section, intercepting vital sign monitoring data frames according to time periods, extracting an electroencephalogram channel original signal and a blood oxygen monitoring channel original signal under corresponding sampling frequency within the intercepting range, separating data according to channel types, and obtaining an electroencephalogram blood oxygen combined signal sequence set; S502, according to the electroencephalogram blood oxygen combined signal sequence set, matching the electroencephalogram rhythm signal sequence and the blood oxygen saturation signal sequence point by point in a synchronous index mode under a unified time axis, respectively extracting local periods and fluctuation trends, and comparing phase change directions and period duration in adjacent intervals to generate a neuroblood oxygen fluctuation comparison result matrix; And S503, counting the number of time sequence segments with synchronous rising and synchronous falling trends in a time period according to the extracted periodical periodic direction consistency characteristics in the nerve blood oxygen fluctuation comparison result matrix, marking the time sequence segments as a response event node sequence, connecting and combining adjacent response event nodes, and outputting a dynamic evaluation conclusion of the patient waking progress.
  10. 10. The method for dynamically evaluating the wakeup progress of a patient in an anesthesia recovery stage of an operating room according to claim 9, wherein the response event node sequence indicates that the electroencephalogram rhythm and the blood oxygen saturation signal show the same trend change on a unified time axis, and includes a continuous time point set corresponding to the consistent phase direction and the periodic synchronization, and marks a time sequence node of the neural blood oxygen cooperative response in the wakeup process of the patient.

Description

Dynamic evaluation method for patient reviving progress in anesthesia recovery stage of operating room Technical Field The invention relates to the technical field of vital sign monitoring and evaluation, in particular to a dynamic evaluation method for the patient wakeup progress in the anesthesia recovery stage of an operating room. Background The technical field of vital sign monitoring and evaluation relates to continuous or intermittent acquisition, analysis and evaluation of key physiological parameters of a human body such as heart rate, blood pressure, respiratory frequency, blood oxygen saturation, brain electrical activity and the like by using a sensor, monitoring equipment and a physiological signal acquisition means so as to assist in disease condition judgment, treatment feedback and rehabilitation management in a medical process. The field covers a plurality of core matters such as a physiological signal acquisition method, a physiological parameter evaluation model, a dynamic monitoring system, a man-machine interaction evaluation interface, a disease trend identification means and the like, has an important role in clinical application scenes such as operation, intensive care, pre-hospital first aid, rehabilitation evaluation and the like, and has a key meaning for accurately identifying and evaluating the state change of a patient after operation in an operating room and an anesthesia management process. The traditional dynamic evaluation method for the patient awakening progress in the anesthesia recovery stage of an operating room refers to the method that the patient enters the recovery stage after undergoing the operation anesthesia, a series of physiological behaviors such as spontaneous breathing recovery, eye opening reaction, limb movement, speech capacity and the like of the patient are observed, and the parameters such as static electrocardiogram, blood oxygen, blood pressure and the like are combined to carry out staged judgment, generally, a medical staff observation and recording mode is adopted to assist in carrying out state evaluation by using single-point physiological parameters acquired at regular time, experience is relied on, a real-time quantification means for continuous dynamic change of the awakening process is lacked, evaluation granularity is coarse, subjectivity is strong, and reaction is lagged behind the actual state change of the patient. In the prior art, the patient awakening assessment is carried out by adopting staged physiological parameters and behavior observation, the problem of lack of real-time correspondence between monitoring response and intervention behavior exists in an operation mode, the direct influence of an intervention event on the state change of the patient cannot be presented, so that the state identification lacks intervention background support, in addition, the physiological parameters acquired by single points lack the descriptive capacity of fluctuation trend, the tracking value of the abnormal state evolution process is not possessed, the continuity characteristic of the state change is difficult to embody by the assessment result, the condition judgment is limited by the intermittence of observation records and the unstructured expression of the assessment standard, the subjective interference is easy to cause feedback lag, and the recognition requirement of the high-frequency dynamic change in the postoperative awakening stage is difficult to be satisfied. Disclosure of Invention In order to achieve the above purpose, the invention adopts the following technical scheme that the method for dynamically evaluating the patient wakeup progress in the anesthesia recovery stage of an operating room comprises the following steps: S1, acquiring intervention behaviors recorded in an anesthesia recovery stage, marking triggering time, operation types and execution sequence, constructing an intervention operation chain according to time sequence, and cutting according to preset time interval granularity to generate an operation behavior sequence; S2, calling the operation behavior sequence, summarizing the occurrence times of the intervention types of the time segments, calling a preset intervention grade parameter set, carrying out grading statistics on the intervention types, carrying out product operation according to preset grade coefficients, summing, superposing the intervention behavior quantity and the intensity grade in a weighted mode, and constructing a time scale map by combining the intervention operation time continuity to generate an intervention frequency distribution map; S3, calling the intervention frequency distribution diagram, collecting intervention density change results in a sliding window, calculating the intervention density difference direction of an adjacent window, judging trend change, extracting time nodes with density change trend, and outputting trend change marks; S4, calling the trend change mark, compar