Sleep monitoring method and system based on adenoid hypertrophy child patient

Abstract

The invention belongs to the technical field of sleep monitoring, and provides a sleep monitoring method and system based on an adenoid hypertrophy child patient, in a historical sleep monitoring period, blood oxygen saturation monitoring is performed on the child patient, and a mild hypoxia change curve is screened out; the mild hypoxia change curve in a plurality of historical sleep monitoring periods is analyzed to obtain a target interval distance stable value, the dynamic stability and trend characteristics of the mild hypoxia state in the sleep of the child are reflected, whether long-term mild hypoxia with a fixed amplitude exists or not can be identified, and the sleep quality of the child is improved. Data support is provided for evaluating the chronic influence of hypoxia on the organism, and the key monitoring total interval is screened out according to the target interval distance stable value, so that the monitoring work is focused on the key monitoring total interval, and the monitoring efficiency is improved; moreover, the potential long-term mild hypoxia problem of the child patient with adenoidal hypertrophy in the sleeping process can be found in time.

Description

Technical Field

[0001] The present invention belongs to the technical field of sleep monitoring, and in particular to a sleep monitoring method and system for children with adenoid hypertrophy. Background Art

[0002] Adenoid hypertrophy is a common childhood disease. Excessive adenoid hyperplasia can block the posterior nasal passages, affecting children's normal breathing, leading to a series of problems during sleep, among which mild hypoxia is a common manifestation. If mild hypoxia is not effectively monitored and intervened for a long time, it may have adverse effects on children's growth and development, nervous system function, and cardiovascular system. Therefore, accurate monitoring of the sleep process of children with adenoid hypertrophy, especially monitoring of mild hypoxia cycles, is of great clinical significance.

[0003] Existing technologies often lack a precise definition of mild hypoxia, resulting in the constructed curves being unable to accurately reflect the actual situation of mild hypoxia during children's sleep. In terms of screening key monitoring intervals, existing technologies generally do not fully consider the dynamic stability and trend characteristics of mild hypoxia, failing to focus on areas that truly require attention, thereby reducing monitoring efficiency and making it difficult to detect potential long-term mild hypoxia problems in children with adenoid hypertrophy during sleep.

[0004] Secondly, existing technologies typically use fixed intervals for sleep monitoring and the time points for sleep monitoring, which cannot be dynamically adjusted based on the actual changes in the patient's mild hypoxia. For children with adenoids, their mild hypoxia cycle can change at any time due to a variety of factors (such as sleeping posture and respiratory rate). Fixed monitoring intervals may not capture key changes in a timely manner, resulting in monitoring data that does not truly reflect the patient's condition and delaying treatment.

[0005] To this end, the present invention provides a sleep monitoring method and system for children with adenoid hypertrophy. Summary of the Invention

[0006] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0007] The technical solution adopted by the present invention to solve its technical problem is:

[0008] A sleep monitoring method for children with adenoid hypertrophy, comprising the following steps:

[0009] During the historical sleep monitoring period, the blood oxygen saturation of pediatric patients was monitored to construct a mild hypoxia change curve;

[0010] Analyze the change curves of mild hypoxia in multiple historical sleep monitoring cycles and screen out the key monitoring intervals;

[0011] Preset the key division window, divide the key monitoring interval, and conduct stability analysis on the multiple key monitoring sub-intervals after division to evaluate whether the division of multiple key monitoring sub-intervals is reasonable and determine the optimal key division window;

[0012] Based on the multiple key monitoring sub-intervals determined after the optimal key division window is determined, analyze whether the time interval between adjacent key monitoring sub-intervals is stable. If it is stable, the sleep monitoring interval value is statically set. If it fluctuates, the switching warning operation is performed to obtain the switching warning value, and the sleep monitoring time point is dynamically set according to the switching warning value.

[0013] As a further solution of the present invention, the process of constructing the mild hypoxia change curve is as follows:

[0014] The sleep monitoring cycle is evenly divided into several sleep monitoring nodes. The blood oxygen saturation at each sleep monitoring node is obtained, and a blood oxygen saturation change curve is constructed. The local blood oxygen saturation change curve where the blood oxygen saturation is maintained in the range of 90% to 95% is intercepted as the pending mild hypoxia change curve;

[0015] Extract the X coordinates of the two endpoints on the curve of the undetermined mild hypoxia change, perform subtraction processing, take the absolute value, and output the undetermined duration;

[0016] If the pending duration is less than or equal to the pending duration threshold, it is displayed that the child patient has mild hypoxia and is marked as a mild hypoxia change curve.

[0017] As a further solution of the present invention, the curves of changes in mild hypoxia during multiple historical sleep monitoring cycles are analyzed, and the process is as follows:

[0018] Filter out the coordinate points corresponding to the minimum Y-axis coordinate and the maximum Y-axis coordinate on each mild hypoxia change curve, perform subtraction, and output the mild hypoxia interval distance;

[0019] Randomly select a mild hypoxia interval distance as the target interval distance, and calculate the ratio of the historical sleep monitoring cycles with the target interval distance to the total number of historical sleep monitoring cycles as the target interval number ratio;

[0020] The historical sleep monitoring cycles with target interval distances are sorted according to the time series, and the adjacent sorted historical sleep monitoring cycles are sorted corresponding to the historical sleep monitoring cycle sequence, which are input into the convolutional layer of the convolutional neural network to obtain multiple historical monitoring cycle convolution layers, which are input into the Manhattan distance formula to output the continuous interval difference values.

[0021] As a further solution of the present invention, the screening process of the key monitoring total interval is as follows:

[0022] The ratio of the proportion of the number of target intervals to the difference value of the consecutive intervals was calculated to obtain the target interval distance stability value, and the total interval of mild hypoxia corresponding to the maximum target interval distance stability value was selected as the key monitoring total interval.

[0023] As a further solution of the present invention, the process of obtaining a preset key division window and dividing the key monitoring total interval is as follows:

[0024] Obtain the mild hypoxia change curve corresponding to the key monitoring total interval, and obtain the X-axis coordinates of the two endpoints of the mild hypoxia change curve, perform subtraction, take the absolute value, and output the total duration corresponding to the key monitoring total interval;

[0025] The total duration corresponding to the total key monitoring interval in each historical sleep monitoring cycle is averaged and the average key monitoring duration is output;

[0026] The distance between the mild hypoxia intervals corresponding to the total key monitoring intervals in each historical sleep monitoring cycle is averaged and the average key monitoring distance is output;

[0027] The ratio of the mean key monitoring distance to the mean key monitoring duration is calculated, and the output is the unit key division value, which is used as the preset key division window. According to the unit key division value, the total key monitoring interval is divided to obtain multiple key monitoring sub-intervals.

[0028] As a further solution of the present invention, stability analysis is performed on multiple key monitoring sub-intervals, and the process is as follows:

[0029] After obtaining the ratio of the duration corresponding to each key monitoring sub-interval to the average key monitoring duration, perform averaging calculation and output the average sub-interval duration;

[0030] Obtain the number of parameters of blood oxygen saturation monitored in each key monitoring sub-interval, and the ratio of the number of parameters to the total number of parameters of blood oxygen saturation monitored in the key monitoring total interval, perform averaging calculation, and output the mean number of parameters in the sub-interval;

[0031] According to the order of the historical sleep monitoring cycles in the historical sleep monitoring cycle sequence, the mean duration of each sub-interval and the mean number of parameters of each sub-interval are sorted respectively to construct a sub-interval duration analysis sequence and a sub-interval parameter number analysis sequence;

[0032] The data in the sub-interval duration analysis sequence and the sub-interval parameter quantity analysis sequence are respectively input into the Manhattan distance formula, and the output is the periodic sub-interval duration fluctuation value and the periodic sub-interval parameter quantity fluctuation value.

[0033] As a further solution of the present invention, the process of determining the optimal focus partitioning window is as follows:

[0034] The periodic sub-interval duration fluctuation value and the periodic sub-interval parameter quantity fluctuation value are summed to output the sub-interval stability analysis value. If the sub-interval stability analysis value is greater than the sub-interval stability analysis threshold, the key division window is reset and an evaluation operation is performed until the sub-interval stability analysis value is less than or equal to the sub-interval stability analysis threshold. The preset key division window is identified as the optimal key division window. If the sub-interval stability analysis value is less than or equal to the sub-interval stability analysis threshold, the preset key division window is identified as the optimal key division window.

[0035] As a further solution of the present invention, the time interval between adjacent key monitoring subintervals is analyzed, and the process is as follows:

[0036] The multiple key monitoring subintervals in each historical sleep monitoring cycle are sorted from large to small to construct a key monitoring subinterval sequence. The time intervals between adjacent key monitoring subintervals in the key monitoring subinterval sequence are obtained and averaged to obtain the mean of the periodic subinterval interval. The standard deviation of the periodic subinterval interval mean corresponding to each historical sleep monitoring cycle is calculated to obtain the time interval stability assessment value.

[0037] As a further solution of the present invention, if it is stable, the sleep monitoring interval value is statically set; if it fluctuates, the switching warning value is obtained and the sleep monitoring time point is dynamically set. The process is as follows:

[0038] If the interval stability evaluation value is less than or equal to the interval stability evaluation threshold, the mean interval values ​​of the period subintervals corresponding to all historical sleep monitoring cycles are averaged and the sleep monitoring interval value is output;

[0039] If the interval stability assessment value is greater than the interval stability assessment threshold, a switching warning signal is generated, and the change curve corresponding to the key monitoring sub-interval is intercepted from the mild hypoxia change curve corresponding to the key monitoring total interval, and divided according to the local change curves corresponding to the adjacent sleep monitoring nodes to obtain several unit key monitoring sub-curves, and the slope of each unit key monitoring sub-curve is obtained respectively;

[0040] The maximum unit key monitoring sub-slope is selected as the switching warning value, and the coordinate point corresponding to the blood oxygen saturation currently monitored in the key monitoring sub-interval is extracted. It is connected with the maximum limit value of the currently monitored key monitoring sub-interval according to the switching warning value to obtain the X-axis coordinate of the connected coordinate point as the sleep monitoring time point.

[0041] A sleep monitoring system for children with adenoid hypertrophy, comprising the following modules:

[0042] Curve construction module: Monitor the blood oxygen saturation of pediatric patients during the historical sleep monitoring cycle and construct a mild hypoxia change curve;

[0043] Analysis and screening module: Analyze the mild hypoxia change curves in multiple historical sleep monitoring cycles and screen out the key monitoring intervals;

[0044] Window evaluation module: presets the key division window, divides the key monitoring total interval, and performs stability analysis on the multiple key monitoring sub-intervals after division, evaluates whether the division of multiple key monitoring sub-intervals is reasonable, and determines the optimal key division window;

[0045] Monitoring setting module: Based on the multiple key monitoring sub-intervals determined after the optimal key division window, analyze whether the time interval between adjacent key monitoring sub-intervals is stable. If stable, the sleep monitoring interval value is statically set. If it fluctuates, the switching warning operation is executed to obtain the switching warning value, and the sleep monitoring time point is dynamically set according to the switching warning value.

[0046] The beneficial effects of the present invention are as follows:

[0047] 1. The present invention monitors blood oxygen saturation in children during historical sleep monitoring cycles, screens out mild hypoxia change curves, and analyzes these mild hypoxia change curves over multiple historical sleep monitoring cycles to obtain a target interval distance stability value. This value reflects the dynamic stability and trend characteristics of mild hypoxia during sleep in children, helps identify whether there is long-term, fixed-amplitude mild hypoxia, and provides data support for assessing the chronic effects of hypoxia on the body. Furthermore, based on the target interval distance stability value, key monitoring intervals are screened, thereby not only focusing monitoring efforts on key monitoring intervals and improving monitoring efficiency, but also promptly identifying potential long-term mild hypoxia problems in children with adenoid hypertrophy during sleep.

[0048] 2. The present invention presets a key division window, divides the total key monitoring interval, and performs stability analysis on the multiple key monitoring subintervals after division, evaluates whether the division of the multiple key monitoring subintervals is reasonable, and determines the optimal key division window. This not only helps optimize the monitoring strategy and ensures that the number of blood oxygen saturation parameters monitored in each key monitoring subinterval is relatively stable, but also helps to screen key monitoring subintervals with relatively stable durations, timely discover disease trend changes, and provide a strong basis for formulating personalized treatment plans. Based on the multiple key monitoring subintervals after the optimal key division window is determined, the stability of the time interval between adjacent key monitoring subintervals is analyzed. If stable, the sleep monitoring interval value is obtained, facilitating long-term tracking and analysis of the patient's mild hypoxia cycle. If it fluctuates, the switching warning value is obtained and the sleep monitoring time point is dynamically set. The monitoring time can be flexibly adjusted according to the actual changes in the patient's mild hypoxia, improving the accuracy of capturing key changes in the patient's mild hypoxia, and customizing the monitoring plan according to the specific situation of each patient in different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below with reference to the accompanying drawings.

[0050] Figure 1 This is a flowchart of the steps of a sleep monitoring method for children with adenoid hypertrophy according to the present invention;

[0051] Figure 2 is a schematic diagram of a sleep monitoring system for children with adenoid hypertrophy according to the present invention;

[0052] Figure 3 It is a flow chart for analyzing whether the time intervals between adjacent key monitoring sub-intervals are stable. DETAILED DESCRIPTION

[0053] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0054] Example 1

[0055] See also Figure 1 As shown, a sleep monitoring method for children with adenoid hypertrophy according to an embodiment of the present invention includes the following steps:

[0056] Step 1: During the historical sleep monitoring period, monitor the blood oxygen saturation of the child patient, construct a blood oxygen saturation change curve, and screen out the mild hypoxia change curve from the blood oxygen saturation change curve;

[0057] The historical sleep monitoring cycle is represented by the total sleep time corresponding to the previous sleep process of the child with adenoid hypertrophy;

[0058] In some embodiments, the sleep monitoring period is equally divided into a number of sleep monitoring nodes;

[0059] Specifically, the time intervals between adjacent sleep monitoring nodes are equal;

[0060] Use a fingertip oximeter to obtain the blood oxygen saturation at each sleep monitoring node, and construct a blood oxygen saturation change curve with time as the X-axis and blood oxygen saturation as the Y-axis;

[0061] It will be understood by those skilled in the art that the blood oxygen saturation during mild hypoxia will fluctuate between 90% and 95%;

[0062] The intercepted blood oxygen saturation will maintain the local blood oxygen saturation change curve in the range of 90% to 95%, which will serve as the pending mild hypoxia change curve;

[0063] Extract the X coordinates of the two endpoints on the curve of the undetermined mild hypoxia change, perform subtraction processing, take the absolute value, and output the undetermined duration;

[0064] If the pending duration is less than or equal to the pending duration threshold, it means that the duration of the analyzed pending mild hypoxia change curve remaining within the 90% to 95% range is short, indicating that the child patient has mild hypoxia.

[0065] If the pending duration is greater than the pending duration threshold, it means that the analyzed pending mild hypoxia change remains within the range of 90% to 95% for a longer period of time, indicating that the child patient does not experience mild hypoxia;

[0066] The undetermined mild hypoxia change curve corresponding to the mild hypoxia phenomenon in the pediatric patient is used as the mild hypoxia change curve;

[0067] Step 2: Analyze the mild hypoxia change curves in multiple historical sleep monitoring cycles and screen out the key monitoring intervals;

[0068] It should be noted that each historical sleep monitoring cycle corresponds to a mild hypoxia change curve;

[0069] In some embodiments, the Y-axis coordinates of all coordinate points on each mild hypoxia change curve are extracted and compared, and the coordinate points corresponding to the minimum Y-axis coordinate and the maximum Y-axis coordinate are respectively screened out and recorded as the total mild hypoxia interval, and the corresponding maximum Y-axis coordinate is subtracted from the minimum Y-axis coordinate to output the mild hypoxia interval distance;

[0070] Randomly select a mild hypoxia interval distance as the target interval distance;

[0071] Count the number of historical sleep monitoring cycles with a target interval distance, calculate the ratio with the total number of historical sleep monitoring cycles, and output the target interval ratio;

[0072] Sort multiple historical sleep monitoring cycles according to a time series to obtain a historical sleep monitoring cycle sequence;

[0073] The historical sleep monitoring cycles with a target interval distance are sorted according to the time series, and the adjacent sorted historical sleep monitoring cycles are input into the convolution layer of the convolutional neural network to obtain multiple historical monitoring cycle convolution layers;

[0074] The Manhattan distance formula is used to calculate the convolution layer of multiple historical monitoring cycles, and the output is the continuous interval difference value D lx ;

[0075] Specifically, the Manhattan distance formula is: Among them, m represents the total number of convolutional layers in the historical monitoring cycle, It is represented as the order of the q-1th historical sleep monitoring cycle in the convolution layer of the mth historical monitoring cycle in the historical sleep monitoring cycle sequence. It is represented as the order of the qth historical sleep monitoring cycle in the convolution layer of the mth historical monitoring cycle in the historical sleep monitoring cycle sequence;

[0076] The ratio of the target interval number ratio to the difference value of the consecutive intervals is calculated to obtain the target interval distance stability value;

[0077] It is understood that the target interval distance stability value means that by quantifying the correlation between the consistency of the total interval distance monitored and the regularity of the intervals between consecutive cycles, it reflects the dynamic stability and trend characteristics of the mild hypoxia state during children's sleep. This helps to identify the presence of long-term mild hypoxia with a fixed amplitude, and provides data support for evaluating the chronic effects of hypoxia on the body.

[0078] Compare the target interval distance stability values ​​corresponding to all target interval distances, and select the mild hypoxia total interval corresponding to the maximum target interval distance stability value as the key monitoring total interval;

[0079] Those skilled in the art will understand that the purpose of obtaining the key monitoring total interval is to:

[0080] Objective 1: Quantitative analysis of the stability and continuity of the key monitoring intervals will help identify the presence of long-term, fixed-amplitude mild hypoxia and promptly detect potential long-term mild hypoxia during sleep in children with adenoid hypertrophy.

[0081] Objective 2: The determination of the key monitoring intervals allows for more focused monitoring, avoids unnecessary monitoring and analysis, and improves monitoring efficiency. Furthermore, the dynamic stability and trend characteristics of mild hypoxia reflected in the key monitoring intervals can be used to improve the accuracy of diagnosing the condition of children.

[0082] The specific solution of this embodiment is as follows: during the historical sleep monitoring cycle, the blood oxygen saturation of the child patient is monitored, the mild hypoxia change curve is screened out, and the mild hypoxia change curves during multiple historical sleep monitoring cycles are analyzed to obtain a target interval distance stability value, which reflects the dynamic stability and trend characteristics of the mild hypoxia state during the child's sleep, helps to identify whether there is long-term mild hypoxia of a fixed amplitude, and provides data support for evaluating the chronic impact of hypoxia on the body. In addition, based on the target interval distance stability value, the key monitoring total interval is screened out, thereby not only focusing the monitoring work on the key monitoring total interval and improving monitoring efficiency, but also timely discovering potential long-term mild hypoxia problems in children with adenoids hypertrophy during sleep.

[0083] Example 2

[0084] See also Figure 1 As shown, the sleep monitoring method for children with adenoid hypertrophy according to an embodiment of the present invention further includes the following steps:

[0085] Step 3: Preset the key division window, divide the key monitoring interval into multiple key monitoring sub-intervals, and perform stability analysis on the multiple key monitoring sub-intervals to evaluate whether the division of the multiple key monitoring sub-intervals is reasonable and determine the optimal key division window;

[0086] In some embodiments, a key partition window is preset, and the process of obtaining multiple key monitoring sub-intervals is as follows:

[0087] Exemplarily, a mild hypoxia change curve corresponding to the key monitoring total interval is obtained, and the X-axis coordinates of the two endpoints of the mild hypoxia change curve are obtained, and the difference is taken, and the absolute value is taken to output the total duration corresponding to the key monitoring total interval;

[0088] The total duration corresponding to the total key monitoring interval in each historical sleep monitoring cycle is averaged and the average key monitoring duration is output;

[0089] The distance between the mild hypoxia intervals corresponding to the total key monitoring intervals in each historical sleep monitoring cycle is averaged and the average key monitoring distance is output;

[0090] The ratio of the mean key monitoring distance to the mean key monitoring duration is calculated and the output is the unit key division value, which is used as the preset key division window;

[0091] Based on the unit key division value, the key monitoring total interval is divided into multiple key monitoring sub-intervals;

[0092] It should be noted that one key monitoring total interval corresponds to one historical sleep monitoring cycle, and after dividing the key monitoring total interval according to the unit key division value, multiple key monitoring sub-intervals are obtained and also exist in one historical sleep monitoring cycle;

[0093] The stability analysis of multiple key monitoring sub-intervals is carried out as follows:

[0094] After obtaining the ratio of the duration corresponding to each key monitoring sub-interval to the average key monitoring duration, perform averaging calculation and output the average sub-interval duration;

[0095] Sort the mean duration of each sub-interval according to the order of the historical sleep monitoring cycle in the historical sleep monitoring cycle sequence to construct a sub-interval duration analysis sequence;

[0096] Input the mean of the duration of adjacent subintervals in the subinterval duration analysis sequence into the Manhattan distance formula, and output the periodic subinterval duration fluctuation value D t ;

[0097] Specifically, the Manhattan distance formula is: Among them, u represents the total number of sub-interval duration means in the sub-interval duration analysis sequence, It is expressed as the mean value of the k-1th subinterval duration in the subinterval duration analysis sequence, It is expressed as the mean value of the kth subinterval duration in the subinterval duration analysis sequence;

[0098] Similarly, the number of parameters of the blood oxygen saturation monitored in each key monitoring sub-interval is obtained, and after the ratio calculation is performed with the total number of parameters of the blood oxygen saturation monitored in the key monitoring total interval, the average calculation is performed to output the average number of parameters in the sub-interval;

[0099] Sort the mean value of the number of parameters in each sub-interval according to the order of the historical sleep monitoring period in the historical sleep monitoring period sequence, and construct a sub-interval parameter number analysis sequence;

[0100] Input the mean of the number of adjacent sub-interval parameters in the sub-interval parameter quantity analysis sequence into the Manhattan distance formula, and output the periodic sub-interval parameter quantity fluctuation value D sl ;

[0101] Specifically, the Manhattan distance formula is: Among them, n represents the total number of sub-interval parameter means in the sub-interval parameter number analysis sequence, Expressed as the mean value of the number of parameters in the r-1th sub-interval in the sub-interval parameter analysis sequence, Expressed as the mean of the number of parameters in the rth subinterval in the subinterval parameter analysis sequence;

[0102] The periodic subinterval duration fluctuation value and the periodic subinterval parameter quantity fluctuation value are summed up to obtain the subinterval stability analysis value;

[0103] It can be understood that the meaning of the sub-interval stability analysis value is: the value obtained by comprehensively analyzing the stability of the key monitoring sub-interval in terms of duration and number of blood oxygen saturation parameters, taking into account the fluctuations in the sub-interval duration and the fluctuations in the number of blood oxygen saturation parameters monitored within the sub-interval, reflecting the stability of the key monitoring sub-interval during the monitoring of mild hypoxia cycles in children with adenoid hypertrophy;

[0104] Its role is to:

[0105] Function 1: It can measure the fluctuation of the number of blood oxygen saturation parameters within the key monitoring sub-intervals, which helps optimize the monitoring strategy and ensure the relative stability of the number of blood oxygen saturation parameters monitored in each key monitoring sub-interval, thereby improving the accuracy of the patient medical record information provided to doctors;

[0106] Function 2: It can quantify the fluctuations in the duration of key monitoring sub-intervals, helping to screen out key monitoring sub-intervals with relatively stable durations. This allows subsequent doctors to more accurately analyze the cyclical characteristics of patients' mild hypoxia based on these stable sub-interval data, promptly identify trends in the patient's condition, and provide a strong basis for formulating personalized treatment plans.

[0107] The subinterval stability analysis value is compared with the subinterval stability analysis threshold value. The process is as follows:

[0108] If the subinterval stability analysis value is greater than the subinterval stability analysis threshold, it means that the multiple key monitoring subintervals divided according to the unit key division value have large fluctuations in duration and the number of blood oxygen saturation parameters, which is displayed as a preset division improvement signal. In this case, the key division window is reset and an evaluation operation is performed until the subinterval stability analysis value is less than or equal to the subinterval stability analysis threshold. The preset key division window is marked as the optimal key division window;

[0109] If the subinterval stability analysis value is less than or equal to the subinterval stability analysis threshold, it means that the multiple key monitoring subintervals divided according to the unit key division value have small fluctuations in duration and the number of blood oxygen saturation parameters, indicating that the preset division is reasonable, and the preset key division window is marked as the optimal key division window;

[0110] Step 4: Based on the multiple key monitoring sub-intervals determined after the optimal key division window is determined, analyze whether the time intervals between adjacent key monitoring sub-intervals are stable. If stable, statically set the sleep monitoring interval value. If fluctuating, perform a switching warning operation to obtain a switching warning value, and dynamically set the sleep monitoring time point based on the switching warning value;

[0111] In some embodiments, the process of analyzing whether the time intervals between adjacent key monitoring subintervals are stable is as follows:

[0112] Sort multiple key monitoring subintervals in each historical sleep monitoring cycle from largest to smallest to construct a key monitoring subinterval sequence;

[0113] For example, if the multiple key monitoring subintervals in the α historical sleep monitoring cycle are key monitoring subinterval A, key monitoring subinterval B, key monitoring subinterval C, and key monitoring subinterval D, then the order of the key monitoring subinterval sequence is key monitoring subinterval A, key monitoring subinterval B, key monitoring subinterval C, and key monitoring subinterval D.

[0114] The multiple key monitoring subintervals in the β historical sleep monitoring period are key monitoring subinterval A, key monitoring subinterval B, key monitoring subinterval C, and key monitoring subinterval D, and the order of the key monitoring subinterval sequence is key monitoring subinterval A, key monitoring subinterval B, key monitoring subinterval C, and key monitoring subinterval D;

[0115] Obtain the time intervals between adjacent key monitoring subintervals in the key monitoring subinterval sequence, perform averaging calculations, and output the mean of the periodic subinterval intervals;

[0116] Calculate the standard deviation of the period subinterval mean corresponding to each historical sleep monitoring period, and output the time interval stability evaluation value;

[0117] It can be understood that the time interval stability evaluation value means: reflecting the degree of fluctuation of the time interval between adjacent key monitoring sub-intervals in different historical sleep monitoring cycles;

[0118] Its function is to provide data support for the subsequent static setting of sleep monitoring time intervals, ensure the regularity of the monitoring process, enable doctors to obtain monitoring data at fixed time intervals, and facilitate long-term tracking and analysis of patients' mild hypoxia cycles;

[0119] If the interval stability assessment value is less than or equal to the interval stability assessment threshold, it means that the time interval distribution between adjacent key monitoring sub-intervals is relatively uniform and stable. The mean interval of the period sub-intervals corresponding to all historical sleep monitoring cycles is averaged and calculated to output the sleep monitoring interval value;

[0120] If the time interval stability assessment value is greater than the time interval stability assessment threshold, it means that the time interval distribution difference between adjacent key monitoring sub-intervals is large, and a switching warning signal is generated;

[0121] Based on the switching warning signal, the change curve corresponding to the key monitoring sub-interval is extracted from the mild hypoxia change curve corresponding to the key monitoring total interval, and divided according to the local change curves corresponding to the adjacent sleep monitoring nodes to obtain several unit key monitoring sub-curves;

[0122] Obtain the slope of each unit's key monitoring sub-curve separately. The process is as follows:

[0123] Extract the coordinates of the two endpoints of the unit key monitoring sub-curve and input them into the slope calculation formula to output the unit key monitoring sub-slope K d ;

[0124] Specifically, the slope calculation formula is: in, Represented as the coordinate of one of the endpoints on the unit key monitoring sub-curve, Represented as the coordinate of another endpoint on the unit key monitoring sub-curve;

[0125] Compare the slopes of all key monitoring sub-units, select the largest key monitoring sub-unit slope as the switching warning value, extract the coordinate point corresponding to the blood oxygen saturation currently monitored in the key monitoring sub-interval, and connect it with the maximum limit value of the current key monitoring sub-interval according to the switching warning value to obtain the X-axis coordinate of the connected coordinate point as the sleep monitoring time point;

[0126] It should be noted that the purpose of obtaining sleep monitoring time points is:

[0127] Objective 1: By obtaining the switching warning value and dynamically setting the sleep monitoring time point, the monitoring time can be flexibly adjusted according to the actual changes in the patient's mild hypoxia, avoiding unnecessary monitoring during periods of no change or slow change, improving monitoring efficiency, and rationally allocating monitoring resources;

[0128] Purpose 2: Dynamically setting sleep monitoring time points when the sleep interval is unstable can capture key changes in patients' mild hypoxia more promptly and develop personalized monitoring plans based on the specific conditions of each patient in different scenarios;

[0129] The specific solution of this embodiment is as follows: a key partitioning window is preset to divide the total key monitoring interval, and stability analysis is performed on the multiple key monitoring subintervals after the division. The rationality of the division of the multiple key monitoring subintervals is evaluated, and the optimal key partitioning window is determined. This not only helps optimize the monitoring strategy and ensure the relatively stable number of blood oxygen saturation parameters monitored within each key monitoring subinterval, but also helps to screen key monitoring subintervals with relatively stable durations, timely identify disease trends, and provide a strong basis for formulating personalized treatment plans. Based on the multiple key monitoring subintervals after the optimal key partitioning window is determined, the stability of the time intervals between adjacent key monitoring subintervals is analyzed. If stable, the sleep monitoring interval value is obtained to facilitate long-term tracking and analysis of the patient's mild hypoxia cycle. If it fluctuates, the switching warning value is obtained and the sleep monitoring time point is dynamically set. The monitoring time can be flexibly adjusted according to the actual changes in the patient's mild hypoxia, improving the accuracy of capturing key changes in the patient's mild hypoxia, and customizing the monitoring plan according to the specific conditions of each patient in different scenarios.

[0130] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A sleep monitoring method for children with adenoid hypertrophy, characterized by: include: During the historical sleep monitoring period, the blood oxygen saturation of pediatric patients was monitored to construct a mild hypoxia change curve; Analyze the change curves of mild hypoxia in multiple historical sleep monitoring cycles and screen out the key monitoring intervals; Preset the key division window, divide the key monitoring interval, and conduct stability analysis on the multiple key monitoring sub-intervals after division to evaluate whether the division of multiple key monitoring sub-intervals is reasonable and determine the optimal key division window; Based on the multiple key monitoring sub-intervals determined after the optimal key division window is determined, analyze whether the time interval between adjacent key monitoring sub-intervals is stable. If it is stable, the sleep monitoring interval value is statically set. If it fluctuates, the switching warning operation is performed to obtain the switching warning value, and the sleep monitoring time point is dynamically set according to the switching warning value.

2. A sleep monitoring method for children with adenoid hypertrophy according to claim 1, characterized in that: The construction process of the mild hypoxia change curve is as follows: The sleep monitoring cycle is evenly divided into several sleep monitoring nodes. The blood oxygen saturation at each sleep monitoring node is obtained, and a blood oxygen saturation change curve is constructed. The local blood oxygen saturation change curve where the blood oxygen saturation is maintained in the range of 90% to 95% is intercepted as the pending mild hypoxia change curve; Extract the X coordinates of the two endpoints on the curve of the undetermined mild hypoxia change, perform subtraction processing, take the absolute value, and output the undetermined duration; If the pending duration is less than or equal to the pending duration threshold, it is displayed that the child patient has mild hypoxia and is marked as a mild hypoxia change curve.

3. The sleep monitoring method for children with adenoid hypertrophy according to claim 1, characterized in that: The analysis of the mild hypoxia change curves in multiple historical sleep monitoring cycles is as follows: Filter out the coordinate points corresponding to the minimum Y-axis coordinate and the maximum Y-axis coordinate on each mild hypoxia change curve, perform subtraction, and output the mild hypoxia interval distance; Randomly select a mild hypoxia interval distance as the target interval distance, and calculate the ratio of the historical sleep monitoring cycles with the target interval distance to the total number of historical sleep monitoring cycles as the target interval number ratio; The historical sleep monitoring cycles with target interval distances are sorted according to the time series, and the adjacent sorted historical sleep monitoring cycles are sorted corresponding to the historical sleep monitoring cycle sequence, which are input into the convolutional layer of the convolutional neural network to obtain multiple historical monitoring cycle convolution layers, which are input into the Manhattan distance formula to output the continuous interval difference values.

4. The sleep monitoring method for children with adenoid hypertrophy according to claim 3, characterized in that: The screening process for key monitoring intervals is as follows: The ratio of the proportion of the number of target intervals to the difference value of the consecutive intervals was calculated to obtain the target interval distance stability value, and the total interval of mild hypoxia corresponding to the maximum target interval distance stability value was selected as the key monitoring total interval.

5. The sleep monitoring method for children with adenoid hypertrophy according to claim 1, characterized in that: The process of obtaining the preset key division window and dividing the key monitoring interval is as follows: Obtain the mild hypoxia change curve corresponding to the key monitoring total interval, and obtain the X-axis coordinates of the two endpoints of the mild hypoxia change curve, perform subtraction, take the absolute value, and output the total duration corresponding to the key monitoring total interval; The total duration corresponding to the total key monitoring interval in each historical sleep monitoring cycle is averaged and the average key monitoring duration is output; The distance between the mild hypoxia intervals corresponding to the total key monitoring intervals in each historical sleep monitoring cycle is averaged and the average key monitoring distance is output; The ratio of the mean key monitoring distance to the mean key monitoring duration is calculated, and the output is the unit key division value, which is used as the preset key division window. According to the unit key division value, the total key monitoring interval is divided to obtain multiple key monitoring sub-intervals.

6. The sleep monitoring method for children with adenoid hypertrophy according to claim 5, characterized in that: The stability analysis of multiple key monitoring sub-intervals is carried out as follows: After obtaining the ratio of the duration corresponding to each key monitoring sub-interval to the average key monitoring duration, perform averaging calculation and output the average sub-interval duration; Obtain the number of parameters of blood oxygen saturation monitored in each key monitoring sub-interval, and the ratio of the number of parameters to the total number of parameters of blood oxygen saturation monitored in the key monitoring total interval, perform averaging calculation, and output the mean number of parameters in the sub-interval; According to the order of the historical sleep monitoring cycles in the historical sleep monitoring cycle sequence, the mean duration of each sub-interval and the mean number of parameters of each sub-interval are sorted respectively to construct a sub-interval duration analysis sequence and a sub-interval parameter number analysis sequence; The data in the sub-interval duration analysis sequence and the sub-interval parameter quantity analysis sequence are respectively input into the Manhattan distance formula, and the output is the periodic sub-interval duration fluctuation value and the periodic sub-interval parameter quantity fluctuation value.

7. The sleep monitoring method for children with adenoid hypertrophy according to claim 1, characterized in that: The process of determining the optimal focus partitioning window is as follows: The periodic sub-interval duration fluctuation value and the periodic sub-interval parameter quantity fluctuation value are summed to output the sub-interval stability analysis value. If the sub-interval stability analysis value is greater than the sub-interval stability analysis threshold, the key division window is reset and an evaluation operation is performed until the sub-interval stability analysis value is less than or equal to the sub-interval stability analysis threshold. The preset key division window is identified as the optimal key division window. If the sub-interval stability analysis value is less than or equal to the sub-interval stability analysis threshold, the preset key division window is identified as the optimal key division window.

8. The sleep monitoring method for children with adenoid hypertrophy according to claim 1, characterized in that: The time intervals between adjacent key monitoring sub-intervals are analyzed as follows: The multiple key monitoring subintervals in each historical sleep monitoring cycle are sorted from large to small to construct a key monitoring subinterval sequence. The time intervals between adjacent key monitoring subintervals in the key monitoring subinterval sequence are obtained and averaged to obtain the mean of the periodic subinterval interval. The standard deviation of the periodic subinterval interval mean corresponding to each historical sleep monitoring cycle is calculated to obtain the time interval stability assessment value.

9. The sleep monitoring method for children with adenoid hypertrophy according to claim 8, characterized in that: If it is stable, set the sleep monitoring interval value statically. If it fluctuates, obtain the switch warning value and dynamically set the sleep monitoring time point. The process is as follows: If the interval stability evaluation value is less than or equal to the interval stability evaluation threshold, the mean interval values ​​of the period subintervals corresponding to all historical sleep monitoring cycles are averaged and the sleep monitoring interval value is output; If the interval stability assessment value is greater than the interval stability assessment threshold, a switching warning signal is generated, and the change curve corresponding to the key monitoring sub-interval is intercepted from the mild hypoxia change curve corresponding to the key monitoring total interval, and divided according to the local change curves corresponding to the adjacent sleep monitoring nodes to obtain several unit key monitoring sub-curves, and the slope of each unit key monitoring sub-curve is obtained respectively; The maximum unit key monitoring sub-slope is selected as the switching warning value, and the coordinate point corresponding to the blood oxygen saturation currently monitored in the key monitoring sub-interval is extracted. It is connected with the maximum limit value of the currently monitored key monitoring sub-interval according to the switching warning value to obtain the X-axis coordinate of the connected coordinate point as the sleep monitoring time point.

10. A sleep monitoring system for children with adenoid hypertrophy, characterized by: Includes the following modules: Curve construction module: Monitor the blood oxygen saturation of pediatric patients during the historical sleep monitoring cycle and construct a mild hypoxia change curve; Analysis and screening module: Analyze the mild hypoxia change curves in multiple historical sleep monitoring cycles and screen out the key monitoring intervals; Window evaluation module: presets the key division window, divides the key monitoring total interval, and performs stability analysis on the multiple key monitoring sub-intervals after division, evaluates whether the division of multiple key monitoring sub-intervals is reasonable, and determines the optimal key division window; Monitoring setting module: Based on the multiple key monitoring sub-intervals determined after the optimal key division window, analyze whether the time interval between adjacent key monitoring sub-intervals is stable. If stable, the sleep monitoring interval value is statically set. If it fluctuates, the switching warning operation is executed to obtain the switching warning value, and the sleep monitoring time point is dynamically set according to the switching warning value.

Images