An intelligent neonatal respiratory monitoring system

Through the intelligent neonatal respiratory monitoring system, the respiratory characteristic interval is determined using numerical monitoring and waveform analysis, which solves the problem of inaccurate neonatal respiratory monitoring in the existing technology, and realizes timely identification and early warning of neonatal respiratory changes, ensuring newborns Children's safety.

CN118303869BActive Publication Date: 2024-12-06XIAN GAOXIN HOSPITAL CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202410502308.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-04-24
Publication Date
2024-12-06
Estimated Expiration
2044-04-24

AI Technical Summary

Technical Problem

When monitoring neonatal breathing, existing neonatal monitoring systems are prone to missed the best treatment opportunity, resulting in inaccurate discovery rates.

Method used

An intelligent neonatal respiratory monitoring system was designed to monitor the breathing amplitude in real time through the numerical monitoring end and generate a breathing waveform change curve. Based on the analysis value and variance processing during the identification period, the breathing characteristic interval and fluctuation interval are determined, and the processing signal is generated. Timely warning.

Benefits of technology

By defining the monitoring cycle and characteristic interval, the practicality of the monitoring system is improved, ensuring that the respiratory changes of each newborn can be confirmed and warned in a timely manner, and ensuring the safety of the newborn.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118303869B_ABST
    Figure CN118303869B_ABST
Patent Text Reader

Abstract

The present invention discloses an intelligent neonatal respiratory monitoring system, which relates to the technical field of neonatal monitoring, and solves the problem that although the previous monitoring method can also monitor related problems, it is easy to miss the best processing opportunity and the detection rate may not be accurate. The present invention determines the relevant respiratory characteristics of the corresponding neonate by limiting the monitoring cycle, and then uses the respiratory characteristics as the corresponding standard for subsequent monitoring and judgment, so as to improve the practicality of the intelligent monitoring system. Because each different newborn has different breathing habits or different breathing characteristics, if a unified judgment standard is used, it may cause untimely or inaccurate numerical judgment. Therefore, a method of determining relevant line segments by numerical monitoring is adopted, and the corresponding intervals are determined in turn to determine the relevant judgment signal.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of neonatal monitoring, and in particular to an intelligent neonatal respiratory monitoring system. Background Art

[0002] Neonatal care refers to the process of medical treatment, care and observation of infants within 28 days after birth to ensure their health and safety, including temperature monitoring: ensuring that the newborn is in a moderate temperature environment; heart rate and respiratory monitoring: using pulse oximeters and other equipment to monitor the heartbeat and breathing of the newborn; blood sugar monitoring: ensuring that the newborn's blood sugar level is within the normal range.

[0003] The application with publication number CN109276380A discloses a smart baby bed for intelligent monitoring of newborns, including a main control module, a radio frequency module, a voltage stabilization control module, a data storage module, a data acquisition and processing module, an alarm module, a bed operating panel and a bed adjustment device. The data collected by the data acquisition and processing module is transmitted to the main control module, and the main control module transmits the received data to the radio frequency module and the data storage module. The radio frequency module sends the collected data to the server through the radio frequency circuit and antenna to form real-time vital sign data. Finally, the real-time vital sign data is displayed to medical staff and parents through the hospital display system, app, WeChat, etc. The data automatically enters the electronic medical record, and an abnormal state alarm is promptly issued.

[0004] In the process of intelligent monitoring of newborns, it is generally based on the corresponding monitoring values ​​generated by the corresponding newborns to assess whether the newborns have relevant problems. However, this original monitoring method is more popular. Because the numerical standards and corresponding conditions generated by each newborn are inconsistent, if the past monitoring method is used, although relevant problems can be monitored, it is easy to miss the best time for treatment, and the detection rate may not be accurate. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent neonatal respiratory monitoring system, which solves the problem that although the previous monitoring method can also monitor related problems, it is easy to miss the best time to deal with it, and its detection rate may not be accurate.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent neonatal respiratory monitoring system, comprising:

[0007] The numerical monitoring end monitors the breathing of the newborn and transmits the monitored breathing amplitude value to the waveform generating end;

[0008] The early warning end makes an early warning judgment on the breathing amplitude monitored in real time, and issues an early warning when the breathing amplitude monitored in real time exceeds the corresponding early warning range;

[0009] The waveform generating end generates a breathing waveform change curve in real time based on the relevant breathing amplitudes generated at different times, and transmits the generated breathing waveform change curve to the waveform analyzing end or the waveform feature determining end;

[0010] The waveform analysis end determines a set of identification cycles based on the initial moment of the respiratory waveform change curve, and analyzes the respiratory waveform generated within this identification cycle to determine the relevant respiratory characteristics and characteristic intervals of the newborn, including:

[0011] Based on the initial moment, a set of identification cycles T is determined in the future, where T is a preset value, and the respiratory waveform segments generated within the current identification cycle T are confirmed, and the confirmed respiratory waveform segments are marked as pending analysis segments;

[0012] Confirm the relevant points appearing in the pending analysis segment in sequence, the trend of the front segment of the relevant point is upward, and the trend of the rear segment is downward, and analyze the line segment characteristics between adjacent relevant points. The analysis method is: calibrate the breathing amplitude corresponding to the first relevant point of the line segment corresponding to the adjacent relevant point as H1, calibrate the breathing amplitude corresponding to the second relevant point as H2, and then calibrate the time interval between the two relevant points as JG, and use FX=|H1-H2|×C1+JG×C2 to determine the analysis value FX between the corresponding relevant points, where C1 and C2 are both preset fixed coefficient factors, and then confirm the analysis values ​​FX of different line segments from front to back in sequence, and generate their analysis value sorting sequence {FX1, FX2, ..., FXn};

[0013] The corresponding sorted values ​​in the sorted sequence of the analysis values ​​are processed with variance, starting with the first group of analysis values ​​FX1, and then confirming the related analysis values ​​step by step to determine their variance values ​​Fc. When Fc≤Y1, where Y1 is a preset value, the subsequent analysis values ​​are determined again. When the confirmed variance value Fc>Y1, the added analysis values ​​are marked as abnormal values, and several groups of analysis values ​​at the front of the abnormal values ​​are marked as similar values, and the line segments corresponding to the similar values ​​are marked as similar segments. Starting from the abnormal values, the analysis values ​​are confirmed backwards, and their variance values ​​Fc are determined. In the same way, the similar segments appearing in the pending analysis segment are confirmed in turn, and the related line segments between the similar segments are marked as fluctuation segments.

[0014] Based on the confirmed similar segments and fluctuating segments, the maximum value and the minimum value of the corresponding analysis value are selected, and based on the confirmed maximum value and the minimum value, a stable interval belonging to the similar segment is generated, and based on the maximum value and the minimum value generated by the fluctuating segment, a fluctuating interval belonging to the fluctuating segment is generated, and the stable interval and the fluctuating interval are transmitted to the fluctuation feature determination end;

[0015] The fluctuation feature determination end performs numerical analysis on the respiratory waveform change curve generated after the identification period T, determines the corresponding fluctuation feature, compares the determined fluctuation feature with the relevant feature interval, and generates different processing signals based on the comparison result; including:

[0016] The characteristic interval includes the fluctuation interval and the stable interval, and then the analysis value F generated by the subsequent change curve of the corresponding respiratory waveform after the identification period T is k Confirm and confirm the resulting analytical value F k The interval to which k belongs, where k represents the line segment between subsequent different related points;

[0017] When F k ∈ stable interval, a stable signal is generated and displayed through the display terminal;

[0018] When F k ∈ fluctuation range, a fluctuation signal is generated and displayed through the display terminal;

[0019] When the stable interval < F k When the fluctuation range is less than 0.01, an intervention signal is generated and displayed through the display terminal. External medical staff will determine whether to change the analysis value F based on the intervention signal. k Fill it into the fluctuation range to expand the corresponding range of the corresponding fluctuation range;

[0020] Also includes:

[0021] When F k When the value is less than the stable interval, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing successively are determined, and the determined analysis values ​​are sorted as: F1, F2, F3, F4, F5 and F6, among which F1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is less than the former group of analysis values, a group of assignments "-1" is generated; if the latter group of analysis values ​​is not less than the former group of analysis values, a group of assignments "0" is generated to determine the assignment sequence;

[0022] When F k > fluctuation range, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing successively are determined, and the determined analysis values ​​are sorted as: B1, B2, B3, B4, B5 and B6, among which B1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is greater than the former group of analysis values, a group of assignments "1" is generated; if the latter group of analysis values ​​is not greater than the former group of analysis values, a group of assignments "0" is generated;

[0023] Determine the total value of the assignment based on the generated assignment sequence, and then lock the absolute value JD of the total value of the assignment. If JD≥Y2, where Y2 is a preset value, directly generate an early warning signal, and control the early warning terminal to directly generate a relevant alarm to warn relevant external personnel. Otherwise, continue to monitor and compare;

[0024] Another set of comparisons is included:

[0025] When F k When the value is less than the stable interval, determine the subsequent consecutive analysis values ​​and lock the related analysis value sorting sequence, mark the latter group of analysis values ​​as Fh, and mark the former group of analysis values ​​as Fq. When (Fq÷2)<Fh<Fq, a group of assignments "-1" is generated. When Fh≤(Fq÷2), a group of assignments "-2" is generated. Otherwise, an assignment "0" is generated to determine the assignment sequence.

[0026] When F k > fluctuation range, determine the subsequent consecutive analysis values ​​and lock the related analysis value sorting sequence, mark the latter group of analysis values ​​as Bh, and mark the former group of analysis values ​​as Bq. When 2Bq>Bh>Bq, a group of assignments "1" is generated. When Bh≥2Bq, a group of assignments "2" is generated. Otherwise, a group of assignments "0" is generated to determine the assignment sequence.

[0027] The total value of the assignments is determined based on the generated sequence of assignments, and then the absolute value JD of the total value of the assignments is locked. If JD≥Y2, where Y2 is a preset value, a warning signal is directly generated, and the control warning terminal directly generates a relevant alarm to alert relevant external personnel. Otherwise, monitoring and comparison will continue.

[0028] The present invention provides an intelligent neonatal respiratory monitoring system. Compared with the prior art, it has the following advantages:

[0029] Beneficial effects:

[0030] The present invention determines the relevant respiratory characteristics of the corresponding newborn by limiting the monitoring cycle, and then uses the respiratory characteristics as the corresponding standard for subsequent monitoring and judgment, so as to improve the practicality of the intelligent monitoring system. Because each newborn has different breathing habits or different respiratory characteristics, if a unified judgment standard is used, it may cause untimely or inaccurate numerical judgment. Therefore, the method of determining the relevant line segments by numerical monitoring is adopted, and the corresponding intervals are determined in turn to determine the relevant judgment signals;

[0031] Subsequently, based on the relevant characteristic values ​​generated by the corresponding newborns, corresponding comparison signals are generated based on the comparison results and are available for external personnel to view. In this way, the respiratory changes of each newborn can be confirmed, and timely warnings can be issued. Based on the corresponding assignment sequence, the degree of abnormality can be identified to ensure the safety of the corresponding newborns. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the principle framework of the present invention;

[0033] Figure 2 It is a schematic diagram of the breathing amplitude change waveform of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1

[0036] See also Figure 1 , the present application provides an intelligent neonatal respiratory monitoring system, including a numerical monitoring terminal, an early warning terminal, a waveform generating terminal, a waveform analyzing terminal, a waveform feature determining terminal and a display terminal, wherein the numerical monitoring terminal is electrically connected to the early warning terminal or the waveform generating terminal input node, and the waveform generating terminal is electrically connected to the waveform analyzing terminal or the waveform feature determining terminal input node, and the waveform analyzing terminal is electrically connected to the waveform feature determining terminal input node, and the waveform feature determining terminal is electrically connected to the display terminal or the early warning terminal input node;

[0037] Among them, the numerical monitoring end monitors the breathing of the newborn and transmits the monitored breathing amplitude value to the waveform generation end. The monitor energizes between the two electrocardiogram electrodes on the chest of the newborn to measure the impedance breathing. The current is a harmless high-frequency current. When exhaling and inhaling, as the chest expands and contracts, the resistance (impedance) between the electrodes will also change. The monitor can confirm the relevant breathing amplitude from the impedance change;

[0038] Among them, the early warning end performs early warning judgment on the breathing amplitude monitored in real time. When the breathing amplitude monitored in real time exceeds the corresponding early warning range, an early warning is issued to alert relevant personnel. Among them, the specific methods of performing early warning judgment include:

[0039] The breathing amplitude is calibrated as HX i , where i represents different moments, the breathing amplitude HX i Compare with the preset warning range, when HX i ∈ warning range, no processing is performed. When the breathing amplitude exceeds the warning range, an alarm will be generated to warn relevant external personnel. This means that the breathing amplitude obviously exceeds the corresponding warning range and there is a relevant warning risk, which needs to be dealt with in time. If the situation is particularly dangerous, a relevant alarm will be issued to warn personnel.

[0040] The waveform generating end generates a breathing waveform change curve in real time based on the relevant breathing amplitudes generated at different times, and transmits the generated breathing waveform change curve to the waveform analyzing end or the waveform feature determining end. The specific method of generating the breathing waveform change curve in real time includes:

[0041] Based on the different related breathing amplitudes generated at different moments, the timeline is used as the horizontal coordinate axis, and the breathing amplitudes corresponding to different moments are used as the vertical coordinate axis. Different points are determined according to different values ​​corresponding to different moments, and the breathing waveform change curve is determined in the two-dimensional coordinate system, and the determined breathing waveform change curve is transmitted to the waveform analysis end or the waveform feature determination end;

[0042] Specifically, different breathing amplitudes correspond to different moments, and the corresponding points can be determined in the two-dimensional coordinate system. The corresponding points are then interconnected to determine the relevant breathing waveform change curve, which can fully demonstrate the relevant breathing conditions of the corresponding newborn.

[0043] The waveform analysis end determines a set of identification cycles based on the initial moment of the respiratory waveform change curve, analyzes the respiratory waveform generated in the identification cycle to determine the relevant respiratory characteristics of the newborn, and transmits the determined relevant respiratory characteristics to the waveform feature determination end. The specific method of determining the relevant respiratory characteristics includes:

[0044] Based on the initial moment, a set of identification cycles T is determined in the future, where T is a preset value, and its specific value is determined by the operator based on experience. The respiratory waveform segment generated within the current identification cycle T is confirmed, and the confirmed respiratory waveform segment is marked as the pending analysis segment;

[0045] Confirm the relevant points that appear in the pending analysis segment one by one. The trend of the front segment of the relevant point is upward, and the trend of the back segment is downward. Figure 2As shown, the line segment characteristics between adjacent related points are analyzed. The analysis method is as follows: the breathing amplitude corresponding to the first related point of the line segment corresponding to the adjacent related points is calibrated as H1, the breathing amplitude corresponding to the second related point is calibrated as H2, and then the time interval between the two related points is calibrated as JG. The analysis value FX between the corresponding related points is determined by FX=|H1-H2|×C1+JG×C2, wherein C1 and C2 are both preset fixed coefficient factors, and their specific values ​​are determined by the operator based on experience. Then, the analysis values ​​FX of different line segments are confirmed in turn from front to back, and the analysis value sorting sequence {FX1, FX2, ..., FXn} is generated;

[0046] The corresponding sorted values ​​in the sorted sequence of the analysis values ​​are processed with variance, starting with the first group of analysis values ​​FX1, and then confirming the related analysis values ​​step by step to determine their variance values ​​Fc. When Fc≤Y1, where Y1 is a preset value and its specific value is determined by the operator based on experience, the subsequent analysis values ​​are determined again. When the confirmed variance value Fc>Y1, the added analysis value is marked as an abnormal value, and several groups of analysis values ​​at the front of the abnormal value are marked as similar values, and the line segments corresponding to the similar values ​​are marked as similar segments. Starting from the abnormal value, its analysis value is confirmed backward, and its variance value Fc is determined. In the same way, the similar segments appearing in the pending analysis segment are confirmed in turn, and the related line segments between the similar segments are marked as fluctuation segments (where the related line segments do not belong to the similar segments), such as Figure 2 As shown, the segment from the center of the circle to the first group of horizontal dotted lines is a group of similar segments, the segment between the first group of horizontal dotted lines and the second group of horizontal dotted lines is a fluctuating segment, and its fluctuation is quite different from the previous and next segments, so it belongs to a fluctuating segment with a change, the segment between the second group of horizontal dotted lines and the third group of horizontal dotted lines is the second group of similar segments, the segment between the third group of horizontal dotted lines and the fourth group of horizontal dotted lines is the second group of fluctuating segments, and the segment from the fourth group of horizontal dotted lines to the subsequent end is a similar segment;

[0047] Its numerical processing method can be understood as follows: its sequence is: {1, 1.2, 2, 2.1, 2.2, 2.1, 2.15, 0.8, 0.75, 0.85, 0.84, 0.82}, and its analysis value is expressed as shown above. It can be seen that the first group of analysis values ​​and the second group of analysis values ​​are similar segments according to the variance processing method. When the third group of analysis values ​​intervenes in this variance processing, the corresponding variances generated by the first three groups of values ​​deviate from the original judgment method, then the third group of values ​​is an outlier, then the line segments corresponding to the first and second groups of values ​​are similar segments, the second group of values ​​to the third group of values ​​are the fluctuation segments, the third group of values ​​to the seventh group of values ​​are the similar segments, and subsequently a group of fluctuation segments and subsequent related similar segments can be determined, and so on, the subsequent similar segments and fluctuation segments can be confirmed in turn;

[0048] Based on the confirmed similar segments and fluctuating segments, the maximum value and the minimum value of the corresponding analysis value are selected, and based on the confirmed maximum value and the minimum value, a stable interval belonging to the similar segment is generated, and based on the maximum value and the minimum value generated by the fluctuating segment, a fluctuating interval belonging to the fluctuating segment is generated, and the stable interval and the fluctuating interval are transmitted to the fluctuation feature determination end;

[0049] Specifically, here, the respiratory changes of the corresponding newborn are determined according to the relevant characteristics generated by the corresponding waveform, and a relative monitoring interval is determined. Based on this monitoring interval, the respiratory parameters generated by the subsequent newborn are judged or warned, so as to improve the practicality of this intelligent monitoring system. Because each newborn has different breathing habits or different breathing characteristics, if a unified evaluation standard is used, it may cause untimely or inaccurate numerical evaluation. Therefore, the method of determining the relevant line segments by numerical monitoring is adopted, and the corresponding intervals are determined in turn to determine the relevant judgment signals.

[0050] The fluctuation feature determination end performs numerical analysis on the respiratory waveform change curve generated after the identification period T, determines the corresponding fluctuation feature, compares the determined fluctuation feature with the relevant feature interval, and generates different processing signals based on the comparison result. The specific method of performing the comparison includes:

[0051] The characteristic interval includes the fluctuation interval and the stable interval, and then the analysis value F generated by the subsequent change curve of the corresponding respiratory waveform after the identification period T is k Confirm and confirm the resulting analytical value F k The interval to which k belongs, where k represents the line segment between subsequent different related points;

[0052] When F k ∈ stable interval, a stable signal is generated and displayed through the display terminal;

[0053] When F k ∈ fluctuation range, a fluctuation signal is generated and displayed through the display terminal;

[0054] When the stable interval < F k When the fluctuation range is less than 0.01, an intervention signal is generated and displayed through the display terminal. External medical staff will determine whether to change the analysis value F based on the intervention signal. k Fill it into the fluctuation range to expand the corresponding range of the corresponding fluctuation range. Whether the judgment range needs to be expanded is determined by external medical staff;

[0055] The specific methods of comparison also include:

[0056] When F k< stable interval, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing continuously in the future are determined, and the determined analysis values ​​are sorted as: F1, F2, F3, F4, F5 and F6, among which F1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is less than the former group of analysis values, a group of assignments "-1" is generated, and if the latter group of analysis values ​​is not less than the former group of analysis values, a group of assignments "0" is generated. For example: when F2 < F1, a group of assignments -1 is generated, and when F3 < F2, a group of assignments -1 is generated, and so on. The generated assignment sequence is determined to determine the assignment sequence;

[0057] When F k > fluctuation range, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing successively are determined, and the determined analysis values ​​are sorted as: B1, B2, B3, B4, B5 and B6, among which B1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is greater than the former group of analysis values, a group of assignments "1" is generated; if the latter group of analysis values ​​is not greater than the former group of analysis values, a group of assignments "0" is generated;

[0058] Determine the total value of the generated value sequence, and then lock the absolute value JD of the total value of the value. If JD≥Y2, where Y2 is a preset value, and its specific value is determined by the operator based on experience, then directly generate an early warning signal, and the control early warning terminal directly generates a relevant alarm to warn relevant external personnel. Otherwise, continue to monitor and compare;

[0059] Specifically, this situation means that the corresponding breathing amplitude changes more dramatically, either the breathing amplitude is getting larger or smaller, both of which are abnormal changes. Timely warnings are needed so that medical staff can intervene in time to ensure the safety of the corresponding newborns.

[0060] Embodiment 2

[0061] This embodiment is a further embodiment of the first embodiment. The difference from the first embodiment is that this embodiment also includes a more advanced determination method, mainly for F k <Stationary interval or F k >The fluctuation range, the specific contents are as follows:

[0062] The specific methods of comparison also include:

[0063] When F k<stable interval, lock the related analysis value sorting sequence, mark the next group of analysis values ​​as Fh, mark the previous group of analysis values ​​as Fq (where the previous group of analysis values ​​is the previous group of parameters relative to the next group of analysis values, such as F1, F2, F3, F4, F5 and F6, F1 is the previous group of analysis values ​​of F2, F2 is the next group of analysis values ​​of F1, F2 is the previous group of analysis values ​​of F3, F3 is the next group of analysis values ​​of F2, and so on), when (Fq÷2)<Fh<Fq, a group of assignments "-1" is generated, when Fh≤(Fq÷2), a group of assignments "-2" is generated, otherwise, an assignment "0" is generated, and the assignment sequence is determined;

[0064] When F k > fluctuation range, lock the related analysis value sorting sequence, mark the latter group of analysis values ​​as Bh, and mark the former group of analysis values ​​as Bq. When 2Bq>Bh>Bq, a group of assignments "1" is generated. When Bh≥2Bq, a group of assignments "2" is generated. Otherwise, a group of assignments "0" is generated to determine the assignment sequence.

[0065] Determine the total value of the generated value sequence, and then lock the absolute value JD of the total value of the value. If JD≥Y2, where Y2 is a preset value, and its specific value is determined by the operator based on experience, then directly generate an early warning signal, and the control early warning terminal directly generates a relevant alarm to warn relevant external personnel. Otherwise, continue to monitor and compare;

[0066] Specifically, the reason why the assignment 2 is added here on the basis of Example 1 is that according to the relevant comparison method of Example 1, when the change amplitude at a certain place is large or small, the corresponding assignment 1 is generated, which is not enough to show the change of its change amplitude. The larger the change amplitude, the larger the generated assignment should be, so that the abnormal situation can be more obviously reflected. Therefore, the determination method of Example 2 is more accurate than the determination method of Example 1, and the early warning signal generated is earlier, which can achieve better warning effect, thereby ensuring the monitoring effect of this monitoring system.

[0067] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0068] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent neonatal respiratory monitoring system, characterized in that: include: The numerical monitoring end monitors the breathing of the newborn and transmits the monitored breathing amplitude value to the waveform generating end; The early warning end makes an early warning judgment on the breathing amplitude monitored in real time, and issues an early warning when the breathing amplitude monitored in real time exceeds the corresponding early warning range; The waveform generating end generates a breathing waveform change curve in real time based on the relevant breathing amplitudes generated at different times, and transmits the generated breathing waveform change curve to the waveform analyzing end or the waveform feature determining end, including: Based on the different related breathing amplitudes generated at different moments, the timeline is used as the horizontal coordinate axis, and the breathing amplitudes corresponding to different moments are used as the vertical coordinate axis. Different points are determined according to different values ​​corresponding to different moments, and the breathing waveform change curve is determined in the two-dimensional coordinate system, and the determined breathing waveform change curve is transmitted to the waveform analysis end or the waveform feature determination end; The waveform analysis end determines a set of identification cycles based on the initial moment of the respiratory waveform change curve, and analyzes the respiratory waveform generated within this identification cycle to determine the relevant respiratory characteristics and characteristic intervals of the newborn, including: Based on the initial moment, a set of identification cycles T is determined in the future, where T is a preset value, and the respiratory waveform segments generated within the current identification cycle T are confirmed, and the confirmed respiratory waveform segments are marked as pending analysis segments; Confirm the relevant points appearing in the undetermined analysis segment in turn, the trend of the front segment of the relevant point is upward, and the trend of the rear segment is downward, and analyze the line segment characteristics between adjacent relevant points. The analysis method is: calibrate the breathing amplitude corresponding to the first relevant point of the line segment corresponding to the adjacent relevant point as H1, calibrate the breathing amplitude corresponding to the second relevant point as H2, and then calibrate the time interval between the two relevant points as JG, and use FX=|H1-H2|×C1+JG×C2 to determine the analysis value FX between the corresponding relevant points, where C1 and C2 are both preset fixed coefficient factors, and then confirm the analysis values ​​FX of different line segments from front to back in turn, and generate their analysis value sorting sequence {FX1, FX2, ..., FXn}; The corresponding sorted values ​​in the sorted sequence of the analysis values ​​are processed with variance, starting with the first group of analysis values ​​FX1, and then confirming the related analysis values ​​step by step to determine their variance values ​​Fc. When Fc≤Y1, where Y1 is a preset value, the subsequent analysis values ​​are determined again. When the confirmed variance value Fc>Y1, the added analysis values ​​are marked as abnormal values, and several groups of analysis values ​​at the front of the abnormal values ​​are marked as similar values, and the line segments corresponding to the similar values ​​are marked as similar segments. Starting from the abnormal values, the analysis values ​​are confirmed backwards, and their variance values ​​Fc are determined. In the same way, the similar segments appearing in the pending analysis segment are confirmed in turn, and the related line segments between the similar segments are marked as fluctuation segments. Based on the confirmed similar segments and fluctuating segments, the maximum value and the minimum value of the corresponding analysis value are selected, and based on the confirmed maximum value and the minimum value, a stable interval belonging to the similar segment is generated, and based on the maximum value and the minimum value generated by the fluctuating segment, a fluctuating interval belonging to the fluctuating segment is generated, and the stable interval and the fluctuating interval are transmitted to the fluctuation feature determination end; The fluctuation feature determination end performs numerical analysis on the respiratory waveform change curve generated after the identification period T, determines the corresponding fluctuation feature, compares the determined fluctuation feature with the relevant feature interval, and generates different processing signals based on the comparison results, including: The characteristic interval includes the fluctuation interval and the stable interval, and then the analysis value F generated by the subsequent change curve of the corresponding respiratory waveform after the identification period T is k Confirm and confirm the resulting analytical value F k The interval to which k belongs, where k represents the line segment between subsequent different related points; When F k ∈ stable interval, a stable signal is generated and displayed through the display terminal; When F k ∈ fluctuation range, a fluctuation signal is generated and displayed through the display terminal; When the stable interval < F k When the fluctuation range is less than 0.01, an intervention signal is generated and displayed through the display terminal. External medical staff will determine whether to change the analysis value F based on the intervention signal. k Fill it into the fluctuation range to expand the corresponding range of the corresponding fluctuation range; When F k When the value is less than the stable interval, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing successively are determined, and the determined analysis values ​​are sorted as: F1, F2, F3, F4, F5 and F6, where F1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is less than the former group of analysis values, a group of assignments "-1" is generated; if the latter group of analysis values ​​is not less than the former group of analysis values, a group of assignments "0" is generated to determine the assignment sequence; When F k > fluctuation range, the analysis value appearing at this moment is marked as an abnormal value, and the five groups of analysis values ​​appearing successively are determined, and the determined analysis values ​​are sorted as: B1, B2, B3, B4, B5 and B6, among which B1 is the abnormal value marked at this moment. In the determined analysis value sorting sequence, when the latter group of analysis values ​​is greater than the former group of analysis values, a group of assignments "1" is generated; if the latter group of analysis values ​​is not greater than the former group of analysis values, a group of assignments "0" is generated; The total value of the assignments is determined based on the generated sequence of assignments, and then the absolute value JD of the total value of the assignments is locked. If JD≥Y2, where Y2 is a preset value, a warning signal is directly generated, and the control warning terminal directly generates a relevant alarm to alert relevant external personnel. Otherwise, monitoring and comparison will continue.

2. An intelligent neonatal respiratory monitoring system according to claim 1, characterized in that: The specific method of making a warning judgment at the early warning end includes: The breathing amplitude is calibrated as HX i , where i represents different moments, the breathing amplitude HX i Compare with the preset warning range, when HX i ∈ warning range, no processing is performed. i ∉When the warning range is exceeded, the relevant alarm will be generated directly.

3. The intelligent neonatal respiratory monitoring system according to claim 1, characterized in that: The specific manner in which the fluctuation feature determination end compares the determined fluctuation feature with the relevant feature interval also includes: When F k <stable interval, determine the subsequent continuous analysis values ​​and lock the related analysis value sorting sequence, mark the latter group of analysis values ​​as Fh, and mark the former group of analysis values ​​as Fq. When (Fq÷2)<Fh<Fq, a group of assignments "-1" is generated; when Fh≤(Fq÷2), a group of assignments "-2" is generated; otherwise, an assignment "0" is generated to determine the assignment sequence; When F k > fluctuation range, determine the subsequent consecutive analysis values ​​and lock the related analysis value sorting sequence, mark the latter group of analysis values ​​as Bh, and mark the former group of analysis values ​​as Bq. When 2Bq>Bh>Bq, a group of assignments "1" is generated; when Bh≥2Bq, a group of assignments "2" is generated; otherwise, a group of assignments "0" is generated to determine the assignment sequence; The total value of the assignments is determined based on the generated sequence of assignments, and then the absolute value JD of the total value of the assignments is locked. If JD≥Y2, where Y2 is a preset value, a warning signal is directly generated, and the control warning terminal directly generates a relevant alarm to alert relevant external personnel. Otherwise, monitoring and comparison will continue.

Citation Information

Patent Citations

  • Smart crib used for intelligent monitoring of newborns

    CN109276380A

  • Non-contact neonatal respiration monitoring system and device and storage medium

    CN112971743A

  • A method and system for generating a respiration alert

    CN113347917A