Sleep monitoring method and system for neurology department

Abstract

The invention provides a sleep monitoring method and system for the neurology department. The sleep monitoring method comprises the steps that dynamic signs and static signs of a target patient are extracted from sign data; determining the sleep identification degree of the target patient under each posture conversion according to the fluctuation characteristics of the sign parameters in the dynamic signs, and determining the disturbance degree of the posture conversion of the target patient to sleep according to all the identification degrees; determining a plurality of sleep periods when the body of the target patient is static through the static signs, and determining the sleep time delay of the target patient according to all the sleep periods; determining a confidence sleep index when the target patient sleeps on the bed according to the disturbance degree of sleep and the sleep time delay, and judging the sleep quality of the target patient in the sleep process based on the confidence sleep index. According to the scheme, the influence of the dynamic body state when the patient sleeps and the static body state when the patient does not sleep on monitoring of the sleep state of the patient can be reduced, and therefore the accuracy rate of monitoring of the sleep quality of the patient is improved.

Description

Technical Field

[0001] The present application relates to the technical field of sleep monitoring, and more specifically, to a sleep monitoring method and system for neurology. Background Art

[0002] Sleep monitoring includes assessing sleep quality, assisting in diagnosing sleep disorders, evaluating treatment effects and scientific research. It can record and analyze an individual's physiological information such as EEG, eye movements, and electromyography during sleep, understand their sleep structure and sleep cycle, and thus assess the quality and depth of sleep.

[0003] Sleep monitoring in neurology refers to polysomnography, which is an examination technology that uses a polysomnography instrument in a sleep monitoring room to continuously and synchronously collect, record and analyze multiple sleep physiological parameters and pathological events. These parameters are displayed in the form of curves, numbers, images, video and audio, and form information data that can be interpreted and analyzed. In the existing sleep monitoring process, the patient's physiological parameters are first collected and recorded, including electroencephalogram, electrooculogram, electromyogram, electrocardiogram, oral and nasal airflow, snoring, respiratory movement, pulse oxygen saturation, body position, etc., and the patient's sleep condition is analyzed based on the collected physiological parameters. Analysis can be used to judge the patient's sleep quality; if the patient turns over frequently or moves his limbs frequently during sleep, the device will record more awakenings and shorter sleep time; if the patient's body is very still when not asleep, and his heart rate and breathing are stable (such as lying down to read a book or watch a video), the device will misjudge it as a sleeping state, causing the patient to fall asleep earlier or wake up later; therefore, how to reduce the impact of the patient's body dynamics when sleeping and the static state of the body when not sleeping on the monitoring of the patient's sleep condition, thereby improving the accuracy of monitoring the patient's sleep quality has become a problem faced by the industry. Summary of the invention

[0004] The present application provides a sleep monitoring method and system for neurology, which can reduce the impact of the patient's body dynamics when sleeping and the body statics when not sleeping on monitoring the patient's sleep condition, thereby improving the accuracy of monitoring the patient's sleep quality.

[0005] In a first aspect, the present application provides a sleep monitoring method for neurology, comprising the following steps: Monitor vital sign data of target patients in neurology department while they are in bed; Extracting dynamic physical signs of the target patient when the patient is moving in bed and static physical signs of the target patient when the patient is still in bed from the physical sign data; Determine the recognition degree of the target patient's sleep under various posture changes according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, perform disturbance analysis on the target patient's sleep state in bed based on all the recognition degrees, and obtain the disturbance degree of the target patient's sleep caused by the posture change; Determine multiple sleep periods of the target patient when the body is still through the static physical signs, and perform reliable analysis on each sleep onset time point when the target patient falls asleep based on all the sleep periods, thereby obtaining the sleep onset delay of the target patient; The confidence sleep index of the target patient when sleeping in bed is determined by the sleep disturbance degree and the sleep onset delay, and the sleep quality of the target patient during sleep is judged based on the confidence sleep index.

[0006] In some embodiments, extracting the dynamic physical signs of the target patient when the patient is moving in bed and the static physical signs of the target patient when the patient is still in bed from the physical sign data specifically includes: Obtain the active time period when the target patient is physically active in bed and the static time period when the target patient is physically still in bed; Extracting dynamic physical signs of the target patient when he / she is physically active in bed from the physical sign data according to the activity period; Static physical signs of the target patient when the body is still on the bed are extracted from the physical sign data according to the static period.

[0007] In some embodiments, determining the recognition of the target patient's sleep under various posture transitions according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign specifically includes: Selecting a posture transition as a selected posture transition, and extracting the physical sign parameters corresponding to each monitoring time point of the selected posture transition from the dynamic physical signs; Determine the fluctuation characteristics of all extracted vital sign parameters; determining a plurality of sleep identification signs of the target patient under the selected posture transition according to the fluctuation characteristics; Determine the target patient's sleep recognition in the selected posture transition using all sleep recognition signs; Continue to determine the target patient's sleep recognition in each of the remaining posture transitions.

[0008] In some embodiments, the disturbance analysis of the target patient's sleeping state in bed is performed based on all recognition degrees to obtain the degree of disturbance of the target patient's posture change on sleep, specifically including: Determine the recognition sequence based on all the recognitions; Determine multiple disturbance values ​​of the target patient's sleeping state in bed through the recognition sequence; The degree of disturbance to sleep caused by posture changes of the target patient is determined based on all disturbance values.

[0009] In some embodiments, determining a plurality of sleep periods of the target patient when the body is at rest by using the static physical signs specifically includes: Determine the target patient's eye-closing period when the patient is lying still in bed; extracting a plurality of stable physical signs of the target patient during sleep from the static physical signs according to the eye-closing period; A plurality of sleep periods of the target patient while the body is at rest are determined based on all stationary signs.

[0010] In some embodiments, performing a reliable analysis on each sleep time point when the target patient falls asleep according to all sleep periods, and then obtaining the sleep delay of the target patient specifically includes: Determine a target patient's sleep duration threshold when the body is at rest; Extracting a plurality of credible sleeping periods from all sleeping periods according to the sleep duration threshold; Determine the various sleep onset points when the target patient falls asleep; Determine the sleep onset latency of the target patient using all credible sleep onset periods.

[0011] In some embodiments, determining the confidence sleep index of the target patient when sleeping in bed by the sleep disturbance degree and the sleep onset delay specifically includes: Identify multiple sleep-out points for the target patient when the body is at rest; Determine multiple sleep intervals of the target patient during sleep according to the sleep onset delay and all sleep waking time points; A confidence sleep index is determined for the target patient while sleeping in bed based on all sleep intervals and the degree of disturbance of the sleep.

[0012] In a second aspect, the present application provides a sleep monitoring system for neurology, comprising: A monitoring module is used to monitor the vital sign data of target patients in the neurology department while they are in bed; A processing module, used for extracting dynamic physical signs of the target patient when the patient is moving in bed and static physical signs of the target patient when the patient is still in bed from the physical sign data; The processing module is further used to determine the recognition degree of the target patient's sleep under various posture conversions according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, and to perform disturbance analysis on the target patient's sleep state in bed based on all the recognition degrees to obtain the disturbance degree of the target patient's sleep caused by the posture conversion; The processing module is further used to determine multiple sleep periods of the target patient when the body is at rest based on the static physical signs, and to perform a reliable analysis of each sleep onset time point when the target patient falls asleep based on all the sleep periods, thereby obtaining the sleep onset delay of the target patient; An execution module is used to determine a confidence sleep index of a target patient when sleeping in a bed according to the sleep disturbance degree and the sleep onset delay, and judge the sleep quality of the target patient during sleep based on the confidence sleep index.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned sleep monitoring method for neurology.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned sleep monitoring method for neurology is implemented.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the sleep monitoring method and system for neurology provided by the present application, first, the vital sign data of a target patient in neurology is monitored when the patient is in bed; the dynamic vital signs of the target patient when the patient is physically active in bed and the static vital signs of the target patient when the patient is at rest in bed are extracted from the vital sign data; the recognition degree of the target patient's sleep under various posture changes is determined according to the fluctuation characteristics of the vital sign parameters in the dynamic vital signs, and the sleep state of the target patient in bed is subjected to a disturbance analysis based on all the recognition degrees to obtain the disturbance degree of the target patient's sleep caused by the posture change; multiple sleep periods of the target patient when the patient is at rest are determined through the static vital signs, and a credible analysis is performed on various sleep onset time points when the target patient falls asleep based on all the sleep periods to obtain the sleep delay of the target patient; the confidence sleep index of the target patient when the patient is sleeping in bed is determined through the disturbance degree of sleep and the sleep delay, and the sleep quality of the target patient during sleep is judged based on the confidence sleep index.

[0016] Thus, it can be seen that in the sleep monitoring process of the present application, firstly, the dynamic physical signs of the target patient when the body is moving in bed and the static physical signs of the target patient when the body is still in bed are extracted from the physical sign data; secondly, the recognition degree of the target patient's sleep under various posture conversions is determined by analyzing the dynamic physical signs; the recognition degree is a parameter value reflecting the recognition degree of the target patient's sleep quality when the posture conversion is performed, which can be used to judge the target patient's falling asleep when the posture conversion is performed; and then the target patient's sleeping state in bed is judged by all the recognition degrees, and the disturbance degree of sleep caused by the posture conversion of the target patient is determined; the disturbance degree of sleep represents the parameter of the degree of interference with sleep when the posture conversion of the target patient is performed in bed, which can be used to analyze the sleep quality of the target patient, and reduces the influence of the target patient's body rotation on the sleep quality monitoring; and then, by analyzing the static physical signs, multiple sleep periods of the target patient when the body is still are determined; the sleep period represents The target patient's sleep time period is shown, which can be used to judge the target patient's sleep status, and then the target patient's sleep time period is used to perform a credible analysis of each sleep time point when the target patient enters sleep, and then the target patient's sleep delay is obtained. The credibility of the sleep time point represents the parameter value of the credibility of the sleep time point when the target patient enters the sleep state when he is stationary in bed, which can be used to judge the target patient's sleep quality, reducing the influence of the body state when it is static and not asleep on sleep monitoring. Thus, the confidence sleep index of the target patient when sleeping in bed is determined by the disturbance degree of sleep and the sleep delay. The confidence sleep index represents the parameter value of the target patient's sleep quality in bed, which can be used to judge the target patient's sleep quality, reducing the influence of the patient's body dynamics when sleeping and the body static state when not sleeping on monitoring the patient's sleep status. Finally, the sleep quality of the target patient during sleep is judged based on the confidence sleep index. The above scheme can reduce the influence of the patient's body dynamics when sleeping and the body static state when not sleeping on monitoring the patient's sleep status, thereby improving the accuracy of monitoring the patient's sleep quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flow chart of a sleep monitoring method for neurology according to some embodiments of the present application; Figure 2 is an exemplary flow chart of determining recognition according to some embodiments of the present application; Figure 3 is a flowchart of determining a sleep state according to some embodiments of the present application; Figure 4 is a schematic diagram of a sleep monitoring system for neurology according to some embodiments of the present application; Figure 5It is a structural schematic diagram of a computer device for implementing a sleep monitoring method for neurology according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1 , which is an exemplary flow chart of a sleep monitoring method for neurology according to some embodiments of the present application. The sleep monitoring method 100 for neurology mainly includes the following steps: In step 101 , vital sign data of a target patient in a neurology department while lying in bed is monitored.

[0020] In a specific implementation, the polysomnography technology in the prior art is used to monitor the vital sign parameters of the target patient in the neurology department at each monitoring time point when the patient is in bed, and the set of all the vital sign parameters is used as the vital sign data, wherein the vital sign data is a set of the vital sign parameters corresponding to each monitoring time point, and the vital sign parameters in the vital sign data include the electroencephalogram, electromyogram, electrocardiogram, oral and nasal airflow, respiratory movement, snoring, pulse oxygen saturation, body position, etc. of the target patient when the patient is in bed, which are used to evaluate the sleep quality of the target patient; in other embodiments, other methods can also be used for determination, which are not limited here.

[0021] It should be noted that the monitoring time point in the present application refers to the time point when the sleep monitoring of the target patient is carried out; the polysomnography technology can simultaneously record multiple physiological parameters of the target patient in the neurology department when he is in bed, and then comprehensively evaluate the individual's sleep state, sleep structure and possible sleep disorders through all physiological parameters.

[0022] In step 102, dynamic physical signs of the target patient when the body is moving in bed and static physical signs of the target patient when the body is still in bed are extracted from the physical sign data.

[0023] In some embodiments, extracting the dynamic physical signs of the target patient when the patient is moving in bed and the static physical signs of the target patient when the patient is still in bed from the physical sign data can be achieved by using the following steps: Obtain the active time period when the target patient is physically active in bed and the static time period when the target patient is physically still in bed; Extracting dynamic physical signs of the target patient when he / she is physically active in bed from the physical sign data according to the activity period; Static physical signs of the target patient when the body is still on the bed are extracted from the physical sign data according to the static period.

[0024] In specific implementation, obtaining the active time period when the target patient is physically active in bed and the static time period when the target patient is physically still in bed can be achieved in the following manner, namely: first, monitoring the target patient through a video monitoring device, then identifying whether the target patient is physically active or physically still in bed through image recognition technology, and finally, taking the set of all time periods corresponding to the target patient's physical activities in bed as the active time period when the target patient is physically active in bed, wherein the active time period represents the time period when the target patient is active in bed, and taking the set of all time periods when the target patient is physically still in bed as the static time period when the target patient is physically still in bed, wherein the static time period represents the time period when the target patient is physically still in bed; in other embodiments, other methods may also be used for determination, which are not limited here.

[0025] In specific implementation, the following method can be used to extract the dynamic vital signs of the target patient when the patient is physically active in bed from the vital sign data according to the activity period, namely: extract all monitoring time points in the activity period from all monitoring time points, extract the vital sign parameters of each monitoring time point in the activity period from the vital sign data, and use the set of all extracted vital sign parameters as the dynamic vital signs of the target patient when the patient is physically active in bed; the following method can be used to extract the static vital signs of the target patient when the patient is still in bed from the vital sign data according to the static period, namely: extract all monitoring time points in the static period from all monitoring time points, extract the vital sign parameters of each monitoring time point in the static period from the vital sign data, and use the set of all extracted vital sign parameters as the static vital signs of the target patient when the patient is still in bed; in other embodiments, other methods can also be used for determination, which are not limited here.

[0026] It should be noted that the dynamic physical signs in the present application refer to the physical signs of the target patient when he is active, and the dynamic physical signs include all physical sign parameters of the target patient when he is active, which can be used to judge the sleep condition of the target patient when he is active; the static physical signs refer to the physical signs of the target patient when his body is at rest, and the static physical signs include all physical sign parameters of the target patient when he is at ecological rest, which are used to judge the sleep condition of the target patient when he is active.

[0027] In step 103, the recognition degree of the target patient's sleep under various posture changes is determined according to the fluctuation characteristics of the sign parameters in the dynamic signs, and the sleeping state of the target patient in bed is disturbed by all the recognition degrees to obtain the disturbance degree of the target patient's sleep caused by the posture change.

[0028] In some embodiments, reference Figure 2As shown in FIG. 1 , this figure is a schematic diagram of a process for determining the recognition degree in some embodiments of the present application. In this embodiment, the recognition degree of the target patient sleeping under various posture transitions can be determined according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, which can be achieved by the following steps: First, in step 1031, a posture transition is selected as a selected posture transition, and the physical sign parameters corresponding to each monitoring time point of the selected posture transition are extracted from the dynamic physical signs; Next, in step 1032, the fluctuation characteristics of all extracted vital sign parameters are determined; Then, in step 1033, a plurality of sleep recognition signs of the target patient under the selected posture transition are determined according to the fluctuation characteristics; Thus, in step 1034, the recognition degree of the target patient's sleep in the selected posture transition is determined through all the sleep recognition signs; Finally, in step 1035 , the recognition degree of the target patient's sleep in each of the remaining posture transitions is continued to be determined.

[0029] It should be noted that the posture conversion in the present application means that the target patient changes from one posture to another while in bed. During the posture conversion, the target patient may be in a sleeping state (turning over or touching the limbs during sleep, etc.) or awake state. During the posture conversion, the sleep monitoring of the target patient will fluctuate, which will cause deviations in the sleep monitoring.

[0030] In specific implementation, the following steps can be adopted to extract the vital sign parameters corresponding to each monitoring time point of the selected posture conversion from the dynamic vital signs, namely: extracting each monitoring time point in the selected posture conversion process from all monitoring time points, and extracting the vital sign parameters of each monitoring time point in the selected posture conversion process from the dynamic vital signs; determining the fluctuation characteristics of all the extracted vital sign parameters can be implemented in the following manner, namely: arranging all the extracted vital sign parameters in the order of acquisition time, using the arranged sequence as the vital sign parameter sequence, and selecting a group of adjacent vital sign parameters in the vital sign parameter sequence as the selected adjacent vital sign parameters. , the sign difference values ​​of the selected adjacent sign parameters are analyzed by the statistical analysis software (such as SPSS, Python) in the prior art in combination with the selected adjacent sign parameters, and the sign difference values ​​of the remaining groups of adjacent sign parameters are continued to be determined, wherein the sign difference value represents the parameter value of the degree of difference between the adjacent sign parameters, and the set of all sign difference values ​​is used as the fluctuation characteristics of all extracted sign parameters, wherein the fluctuation characteristics represent the characteristics of the degree of fluctuation of the sign parameters during posture conversion, which can be used to analyze the sleep state during posture conversion; in other embodiments, other methods can also be used for determination, which are not limited here.

[0031] Determining multiple sleep identification signs of the target patient under the selected posture conversion according to the fluctuation characteristics can be achieved in the following manner, namely: first, using Python software to build a deep learning model, then, extracting all the sign parameters when just entering sleep from the historical sign data of the historical patient during sleep through data extraction in the deep learning model, and finally, the data analysis in the deep learning model is combined with all the extracted sign parameters to calculate the sign difference threshold, wherein the sign difference threshold represents the minimum threshold of the difference degree between the sign parameters of the patient during sleep, and each sign difference value in the fluctuation characteristics is compared with the sign difference threshold, and all the sign difference values ​​in the fluctuation characteristics that are less than the sign difference threshold are extracted, and the sign parameters corresponding to each extracted sign difference value are used as the sleep identification signs of the target patient under the selected posture conversion, wherein the sleep identification signs represent the sign parameters for identifying the sleep status of the target patient during the posture conversion, and are used to judge the sleep status of the target patient when the posture changes during sleep; in other embodiments, other methods can also be used for determination, which are not limited here.

[0032] In specific implementation, determining the recognition of the target patient's sleep under the selected posture transition through all sleep recognition signs can be achieved in the following manner, namely: initializing a recognition model, taking the collection time corresponding to each sleep recognition sign as a constraint parameter of the recognition model, taking all sleep recognition signs as initialization parameters of the recognition model, and outputting the recognition of the target patient's sleep under the selected posture transition through the recognition model. The recognition model is a recognition model that uses a machine learning algorithm (such as a regression algorithm, a neural network, etc.) to establish the recognition. For example, the recognition model is: recognition = all sleep recognition signs * A + the collection time corresponding to each sleep recognition sign * B, wherein A and B are weight coefficients, A and B can be determined based on a large number of recognitions, and can also be determined in other ways in other embodiments, which are not limited here.

[0033] It should be noted that the recognition degree in the present application is a parameter value that reflects the degree of recognition of the target patient's sleep quality when changing postures, and can be used to judge the target patient's sleep situation when changing postures. If the recognition degree is greater, it means that the target patient's sleep quality is better when changing postures, and vice versa, it means that the target patient's sleep quality is worse when changing postures, thereby reducing the impact of the target patient's body rotation on sleep quality monitoring.

[0034] In some embodiments, the following steps may be used to perform disturbance analysis on the target patient's sleeping state in bed using all recognition levels to obtain the disturbance level of the target patient's posture transition on sleep: Determine the recognition sequence based on all the recognitions; Determine multiple disturbance values ​​of the target patient's sleeping state in bed through the recognition sequence; The degree of disturbance to sleep caused by posture changes of the target patient is determined based on all disturbance values.

[0035] In specific implementation, determining the recognition sequence based on all the recognitions can be implemented in the following manner, namely: arranging all the recognitions in the order of the corresponding posture conversions, and using the sequence obtained by the arrangement as the recognition sequence; determining multiple disturbance values ​​of the target patient's sleep state in bed through the recognition sequence can be implemented in the following manner, namely: selecting a group of adjacent recognitions in the recognition sequence as selected adjacent recognitions, subtracting the first recognition from the second recognition in the selected adjacent recognitions, and using the subtracted value as the disturbance value of the selected adjacent recognition of the target patient in the sleep state in bed, and continuing to determine the disturbance values ​​of the remaining groups of adjacent recognitions of the target patient in the sleep state in bed, wherein the disturbance value represents a parameter value of the degree of interference with the sleep of the target patient when the adjacent postures are converted, and is used to judge the sleep quality of the target patient; in other embodiments, other methods can also be used for determination, which are not limited here.

[0036] In specific implementation, the following method can be used to determine the degree of disturbance to sleep caused by the posture change of the target patient based on all disturbance values, namely: all disturbance values ​​are added together, the added value is subjected to natural exponential operation, and the value obtained by the natural exponential operation is used as the degree of disturbance to sleep caused by the posture change of the target patient; in other embodiments, other methods can also be used for determination, which are not limited here.

[0037] It should be noted that the sleep disturbance degree in the present application represents a parameter representing the degree of disturbance to the sleep of the target patient when changing postures in bed, and can be used to analyze the sleep quality of the target patient, thereby reducing the impact of the target patient's physical activity on sleep quality monitoring.

[0038] In some embodiments, reference Figure 3 As shown, the figure is a flow chart of the sleep state shown in some embodiments of the present application, which is specifically described as follows: first, the target patient is initially in the sleep stage, and then, after the sleep stage is completed, enters the light sleep stage, and then, after the light sleep stage is completed, enters the light sleep stage, and finally, enters the deep sleep stage. In other embodiments, the sleep state also includes other stages, which are not limited here.

[0039] In step 104, multiple sleep periods of the target patient when the body is still are determined by the static physical signs, and a reliable analysis is performed on each sleep onset time point when the target patient falls asleep based on all the sleep periods, thereby obtaining the sleep onset delay of the target patient.

[0040] In some embodiments, determining a plurality of sleep periods of the target patient when the body is at rest by using the static physical signs can be achieved by using the following steps: Determine the closed period when the target patient is physically still in bed; extracting a plurality of stable physical signs of the target patient during sleep from the static physical signs according to the closed time period; A plurality of sleep periods of the target patient while the body is at rest are determined based on all stationary signs.

[0041] In specific implementation, determining the closed period when the target patient is still in bed can be achieved in the following manner, namely: monitoring the period when the target patient is still in bed and has eyes closed through a video monitoring device, and using the collected period as the closed period when the target patient is still in bed, wherein the closed period represents the period when the target patient is in bed with eyes closed, which is used to analyze the sleep condition of the target patient; extracting multiple stable signs of the target patient when sleeping from the static signs according to the closed period can be achieved in the following manner, namely: extracting each monitoring time point corresponding to the closed period from all monitoring time points, and extracting the sign parameters of each monitoring time point corresponding to the closed period from the static signs, and using each extracted sign parameter as the stable sign of the target patient when sleeping, wherein the stable sign represents the sign parameter of the target patient when the body is in a stable state in bed, which is used to predict the sleep condition of the target patient; in other embodiments, other methods can also be used for determination, which are not limited here.

[0042] In specific implementation, determining multiple sleep periods of the target patient when the body is at rest based on all stable signs can be achieved in the following manner, namely: analyzing all stable signs through physiological data analysis software in the prior art (such as LabChart and BioPac), determining various stable signs when falling asleep and various stable signs when waking up, wherein one falling asleep corresponds to one waking up, selecting a group of intervals of falling asleep and waking up as the selected intervals of falling asleep and waking up, and taking the time period from the collection time of the corresponding stable signs when falling asleep to the collection time of the corresponding stable signs when waking up in the selected intervals of falling asleep and waking up as the sleep period of the target patient when the body is at rest, and continuing to determine multiple sleep periods of the target patient when the body is at rest; in other embodiments, other methods may also be used for determination, which are not limited here.

[0043] It should be noted that the sleep period in the present application refers to the time period when the target patient is in stable sleep, that is, stable sleep refers to the sleep from falling asleep to waking up, which can be used to judge the sleep condition of the target patient and reduce the impact of the target patient's still state and not asleep on sleep monitoring.

[0044] In some embodiments, a reliable analysis is performed on each sleep time point when the target patient falls asleep according to all sleep periods, and then the sleep delay of the target patient is obtained, which can be achieved by the following steps: Determine a target patient's sleep duration threshold when the body is at rest; Extracting a plurality of credible sleeping periods from all sleeping periods according to the sleep duration threshold; Determine the various sleep onset points when the target patient falls asleep; Determine the sleep onset latency of the target patient using all credible sleep onset periods.

[0045] In specific implementation, determining the sleep duration threshold of the target patient when the body is at rest can be achieved in the following manner, namely: determining the sleep duration threshold of the target patient when the body is at rest by combining the sleep duration of historical patients with a machine learning model in the prior art (such as regression, classification, clustering, etc.), wherein the sleep duration threshold represents the threshold of the shortest duration of the patient's sleep, which can be used to judge the patient's sleep duration; extracting multiple credible sleep periods from all sleep periods according to the sleep duration threshold can be achieved in the following manner, namely: selecting a sleep period as the selected sleep period, judging the duration of the selected sleep period with the sleep duration threshold, if the duration of the selected sleep period is greater than or equal to the sleep duration threshold, then the selected sleep period is used as the credible sleep period, if the duration of the selected sleep period is less than the sleep duration threshold, then the selected sleep period is removed, and the remaining sleep periods are continuously judged to determine multiple credible sleep periods, wherein the credible sleep period represents the period when the target patient sleeps stably after entering the sleep state, which can be used to judge the sleep condition of the target patient; in other embodiments, other methods can also be used to determine, which are not limited here.

[0046] In specific implementation, determining the various sleep time points when the target patient falls asleep can be achieved in the following manner, namely: calculating all the sleep time points when the target patient falls asleep in bed by combining the sleep point detection algorithm in the prior art with the physical sign data of the target patient, wherein the sleep time point represents the time point when the target patient falls asleep when the body is still, which can be used to judge the sleep status of the target patient, and determining the sleep delay of the target patient through all credible sleep time periods can be achieved in the following manner, namely: taking the sleep time points in each credible sleep time period as the credible time points when the target patient falls asleep, wherein the credible time points represent the credible time points when the target patient falls asleep, selecting a sleep time point as the selected sleep time point, extracting the credible time point closest to the selected sleep time point from all the credible time points, taking the time interval between the extracted credible time point and the selected sleep time point as the sleep delay of the selected sleep time point, continuing to determine the sleep delays of the remaining sleep time points, and taking the set of all sleep delays as the sleep delay of the target patient; in other embodiments, other methods may be used for determination, which are not limited here.

[0047] It should be noted that the sleep onset delay in the present application refers to the sleep onset delay at the time when the target patient falls asleep while lying still in bed, which can be used to judge the sleep quality of the target patient, reducing the impact of the body's static and non-asleep state on sleep monitoring.

[0048] In step 105, a confidence sleep index of the target patient when sleeping in bed is determined according to the sleep disturbance degree and the sleep onset delay, and the sleep quality of the target patient during sleep is judged based on the confidence sleep index.

[0049] In some embodiments, determining the confidence sleep index of the target patient when sleeping in bed by the sleep disturbance degree and the sleep onset delay can be achieved by the following steps: Identify multiple sleep-out points for the target patient when the body is at rest; Determine multiple sleep intervals of the target patient during sleep according to the sleep onset delay and all sleep waking time points; A confidence sleep index is determined for the target patient while sleeping in bed based on all sleep intervals and the degree of disturbance of the sleep.

[0050] In specific implementation, determining multiple sleeping time points of the target patient when the body is at rest can be achieved in the following manner, namely: obtaining each credible sleeping period, and taking the corresponding time point of waking up in each credible sleeping period as the sleeping time point of the target patient when the body is at rest, wherein the sleeping time point represents the time point when the target patient wakes up when the body is at rest; determining multiple sleep intervals of the target patient during the sleep process according to the sleep delay and all sleeping time points can be achieved in the following manner, namely: arranging all sleeping time points and all sleeping time points in chronological order, taking the arranged sequence as the sleeping-waking up time point sequence, selecting a group of adjacent sleeping time points in the sleeping-waking up time point sequence The target patient's sleep onset time and sleep exit time are used as the selected adjacent sleep onset time and sleep exit time, a natural exponential operation is performed on the sleep delay corresponding to the sleep onset time in the selected adjacent sleep onset time and sleep exit time, the inverse of the value obtained by the natural exponential operation is multiplied by the difference between the selected adjacent sleep onset time and sleep exit time, and the multiplied value is used as the sleep interval of the target patient during the sleep process, and multiple sleep intervals of the target patient during the sleep process are continued to be determined, wherein the sleep interval represents the time interval from the last sleep exit time to the next sleep onset time of the target patient during the sleep process, which can be used to judge the sleep quality of the target patient; in other embodiments, other methods can also be used to determine, which are not limited here.

[0051] In specific implementation, determining the confidence sleep index of the target patient when sleeping in bed through all sleep intervals and the disturbance degree of the sleep can be implemented in the following manner, namely: initializing a confidence sleep index model, taking the disturbance degree of sleep as a constraint parameter of the confidence sleep index model, taking all sleep intervals as initialization parameters of the confidence sleep index model, and outputting the confidence sleep index of the target patient when sleeping in bed through the confidence sleep index model. The confidence sleep index model is an index model of the confidence sleep index established by a machine learning algorithm (such as a regression algorithm, a neural network, etc.). The index model is, for example: confidence sleep index=disturbance degree of sleep*C+all sleep intervals*D, wherein C and D are weight coefficients, C and D can be determined based on a large number of confidence sleep indices, and can also be determined in other ways in other embodiments, which are not limited here.

[0052] It should be noted that the confidence sleep index in the present application represents the parameter value of the target patient's sleep quality in bed, which can be used to judge the target patient's sleep quality and facilitate analysis of the target patient's physical condition.

[0053] In some embodiments, judging the sleep quality of the target patient during sleep based on the confidence sleep index can be achieved by the following steps: determining a sleep quality threshold for the target patient's sleep quality during sleep; comparing the sleep quality threshold with the confident sleep index; If the sleep quality threshold is greater than or equal to the confidence sleep index, the sleep quality of the target patient during sleep is marked as high-quality sleep; If the sleep quality threshold is less than the confidence sleep index, the sleep quality of the target patient during sleep is marked as poor quality sleep.

[0054] In specific implementation, the marked sleep quality results are transmitted to the sleep diagnosis database of the target patient, and a corresponding coping strategy is formulated for the target patient.

[0055] It should be noted that in the present application, the sleep quality threshold can be set according to the specific sleep needs of the target patient. For example, if the target patient is a child, the sleep quality threshold can be set in a high range. If the target patient is an elderly person, the sleep quality threshold can be set in a low range. In other embodiments, for example, when the target patient is a patient in the rehabilitation period, the sleep quality threshold can be set in a high range to improve the rehabilitation efficiency of the target patient.

[0056] In addition, in another aspect of the present application, in some embodiments, the present application provides a sleep monitoring system for neurology, referring to Figure 4 , which is a schematic diagram of the structure of a sleep monitoring system for neurology according to some embodiments of the present application. The sleep monitoring system 400 for neurology includes: a monitoring module 401, a processing module 402 and an execution module 403, which are described as follows: Monitoring module 401, in this application, monitoring module 401 is mainly used to monitor the vital sign data of the target patient in the neurology department when he is in bed; Processing module 402, in the present application, is used to extract dynamic physical signs of the target patient when the patient is moving in bed and static physical signs of the target patient when the patient is still in bed from the physical sign data; It should be noted that the processing module 402 in the present application is also used to determine the recognition degree of the target patient's sleep under various posture conversions according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, and perform disturbance analysis on the target patient's sleep state in bed based on all the recognition degrees to obtain the disturbance degree of the target patient's posture conversion on sleep; In addition, it should be noted that the processing module 402 in the present application is also used to determine multiple sleep periods of the target patient when the body is still through the static physical signs, and to perform a reliable analysis of each sleep onset time point when the target patient falls asleep according to all the sleep periods, thereby obtaining the sleep onset delay of the target patient; Execution module 403, in the present application, the execution module 403 is mainly used to determine the confidence sleep index of the target patient when sleeping in bed through the sleep disturbance degree and the sleep delay, and judge the sleep quality of the target patient during sleep based on the confidence sleep index.

[0057] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned sleep monitoring method for neurology.

[0058] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a sleep monitoring method for neurology according to some embodiments of the present application. The sleep monitoring method for neurology in the above embodiment can be performed by Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0059] The processor 501 may be a general-purpose central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0060] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0061] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0062] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The method used in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0063] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0064] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-core (singleCPU) processor or a multi-core (multiCPU) processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0065] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0066] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the sleep monitoring method for neurology is implemented.

[0067] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0068] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A sleep monitoring method for neurology, characterized in that: The steps include: Monitor vital sign data of target patients in neurology department while they are in bed; Extracting dynamic physical signs of the target patient when the patient is moving in bed and static physical signs of the target patient when the patient is still in bed from the physical sign data; Determine the recognition degree of the target patient's sleep under various posture changes according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, perform disturbance analysis on the target patient's sleep state in bed based on all the recognition degrees, and obtain the disturbance degree of the target patient's sleep caused by the posture change; Determine multiple sleep periods of the target patient when the body is still through the static physical signs, and perform reliable analysis on each sleep onset time point when the target patient falls asleep based on all the sleep periods, thereby obtaining the sleep onset delay of the target patient; The confidence sleep index of the target patient when sleeping in bed is determined by the sleep disturbance degree and the sleep onset delay, and the sleep quality of the target patient during sleep is judged based on the confidence sleep index.

2. The method according to claim 1, characterized in that Extracting the dynamic physical signs of the target patient when the patient is moving in bed and the static physical signs of the target patient when the patient is still in bed from the physical sign data specifically includes: Obtain the active time period when the target patient is physically active in bed and the static time period when the target patient is physically still in bed; Extracting dynamic physical signs of the target patient when he / she is physically active in bed from the physical sign data according to the activity period; Static physical signs of the target patient when the body is still on the bed are extracted from the physical sign data according to the static period.

3. The method according to claim 1, characterized in that Determining the recognition of the target patient's sleep under various posture transitions according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign specifically includes: Selecting a posture transition as a selected posture transition, and extracting the physical sign parameters corresponding to each monitoring time point of the selected posture transition from the dynamic physical signs; Determine the fluctuation characteristics of all extracted vital sign parameters; determining a plurality of sleep identification signs of the target patient under the selected posture transition according to the fluctuation characteristics; Determine the target patient's sleep recognition in the selected posture transition using all sleep recognition signs; Continue to determine the target patient's sleep recognition in each of the remaining posture transitions.

4. The method according to claim 1, characterized in that The target patient's sleeping state in bed is disturbed by all recognitions, and the disturbance degree of the target patient's posture change on sleep is obtained, including: Determine the recognition sequence based on all the recognitions; Determine multiple disturbance values ​​of the target patient's sleeping state in bed through the recognition sequence; The degree of disturbance to sleep caused by posture changes of the target patient is determined based on all disturbance values.

5. The method according to claim 1, characterized in that Determining multiple sleep periods of the target patient when the body is still through the static physical signs specifically includes: Determine the target patient's eye-closing period when the patient is lying still in bed; extracting a plurality of stable physical signs of the target patient during sleep from the static physical signs according to the eye-closing period; A plurality of sleep periods of the target patient while the body is at rest are determined based on all stationary signs.

6. The method according to claim 1, characterized in that According to all sleep periods, a reliable analysis is performed on each sleep time point when the target patient falls asleep, and the sleep delay of the target patient is obtained, including: Determine a target patient's sleep duration threshold when the body is at rest; Extracting a plurality of credible sleeping periods from all sleeping periods according to the sleep duration threshold; Determine the various sleep onset points when the target patient falls asleep; Determine the sleep onset delay of the target patient using all credible sleep onset periods.

7. The method according to claim 1, characterized in that Determining the confidence sleep index of the target patient when sleeping in bed by the sleep disturbance degree and the sleep delay specifically includes: Identify multiple sleep-out points for the target patient when the body is at rest; Determine multiple sleep intervals of the target patient during sleep according to the sleep onset delay and all sleep waking time points; A confidence sleep index is determined for the target patient while sleeping in bed based on all sleep intervals and the degree of disturbance of the sleep.

8. A sleep monitoring system for neurology, characterized in that: include: A monitoring module is used to monitor the vital sign data of target patients in the neurology department while they are in bed; A processing module, used for extracting dynamic physical signs of the target patient when the patient is moving in bed and static physical signs of the target patient when the patient is still in bed from the physical sign data; The processing module is further used to determine the recognition degree of the target patient's sleep under various posture conversions according to the fluctuation characteristics of the physical sign parameters in the dynamic physical sign, and to perform disturbance analysis on the target patient's sleep state in bed based on all the recognition degrees to obtain the disturbance degree of the target patient's sleep caused by the posture conversion; The processing module is further used to determine multiple sleep periods of the target patient when the body is at rest through the static physical signs, and to perform a reliable analysis of each sleep onset time point when the target patient falls asleep according to all the sleep periods, thereby obtaining the sleep onset delay of the target patient; An execution module is used to determine a confidence sleep index of a target patient when sleeping in a bed according to the sleep disturbance degree and the sleep onset delay, and judge the sleep quality of the target patient during sleep based on the confidence sleep index.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the sleep monitoring method for neurology according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the sleep monitoring method for neurology according to any one of claims 1 to 7 is implemented.

Images