CN118303869B - Intelligence neonate respiratory monitoring system - Google Patents
Intelligence neonate respiratory monitoring system Download PDFInfo
- Publication number
- CN118303869B CN118303869B CN202410502308.XA CN202410502308A CN118303869B CN 118303869 B CN118303869 B CN 118303869B CN 202410502308 A CN202410502308 A CN 202410502308A CN 118303869 B CN118303869 B CN 118303869B
- Authority
- CN
- China
- Prior art keywords
- value
- analysis
- values
- group
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 49
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 32
- 230000029058 respiratory gaseous exchange Effects 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims description 22
- 238000012163 sequencing technique Methods 0.000 claims description 18
- 238000011282 treatment Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 abstract 1
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000008103 glucose Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000002106 pulse oximetry Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Measuring devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient; User input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Physiology (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Pulmonology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
本发明公开了一种智能新生儿呼吸监测系统，本发明涉及新生儿监护技术领域，解决了采用过往的监测方式，虽然也可监测出相关的问题，但很容易错过最佳的处理时机，其发现速率可能并不精准的问题，本发明通过限定监视周期，来确定其对应新生儿的相关呼吸特征，再依次此呼吸特征作为后续监测评判的相应标准，以此来提升本智能监护系统的实用性，因每个不同的新生儿均存在不同的呼吸习惯或不同的呼吸特征，若采用统一的评判标准可能会造成数值评判的不及时或不准确，故采用数值监测确定相关线段的方式，依次确定对应的区间，来确定相关的判定信号。
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.
Description
Technical Field
The invention relates to the technical field of neonatal monitoring, in particular to an intelligent neonatal respiratory monitoring system.
Background
Neonatal monitoring refers to the process of medical, nursing and viewing infants within 28 days after birth to ensure their health and safety, including body temperature monitoring to ensure that the neonate is in a moderate temperature environment, heart rate and respiration monitoring to monitor the neonate's heartbeat and respiration using pulse oximetry and other devices, and blood glucose monitoring to ensure that the neonate's blood glucose level is within normal ranges.
The application with the publication number of CN109276380A discloses an intelligent crib for neonate intelligent monitoring, which comprises a main control module, a radio frequency module, a voltage stabilizing control module, a data storage module, a data acquisition processing module, an alarm module, a bed body operation panel and a bed body adjusting device, wherein data acquired by the data acquisition processing module are transmitted to the main control module, the main control module transmits received data to the radio frequency module and the data storage module, the radio frequency module transmits the acquired data to a server through a radio frequency circuit and an antenna to form real-time physical sign data, finally the real-time physical sign data are displayed to medical staff and parents through a hospital display system, an app, a WeChat and the like, the data automatically enter an electronic medical record, and an abnormal state is alarmed in time.
In the process of intelligent monitoring of newborns, whether the newborns have related problems is generally evaluated based on corresponding monitoring values generated by the corresponding newborns, but the original monitoring mode is popular, because the numerical standard and corresponding condition generated by each newborns are inconsistent, if the past monitoring mode is adopted, the related problems can be monitored, but the optimal processing time is easily missed, and the discovery rate may not be accurate.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides an intelligent neonate respiratory monitoring system, which solves the problems that the optimal treatment time is easily missed and the discovery rate is possibly inaccurate even though the related problems can be monitored by adopting a past monitoring mode.
In order to achieve the purpose, the invention is realized by the following technical scheme that the intelligent neonate respiratory monitoring system comprises:
the value monitoring end monitors the breath of the neonate and transmits the monitored breath amplitude value to the waveform generating end;
the early warning end carries out early warning judgment on the respiration amplitude monitored in real time, and when the respiration amplitude monitored in real time exceeds the corresponding early warning range, an early warning is sent out;
The waveform generation end generates a respiration waveform change curve in real time based on the related respiration amplitudes generated at different moments and transmits the generated respiration waveform change curve to the waveform analysis end or the waveform characteristic judgment end;
The waveform analysis end determines a group of recognition periods based on the initial time of the respiration waveform change curve, analyzes the respiration waveform generated in the recognition periods to determine the relevant respiration characteristics and characteristic intervals of the neonate, and comprises the following steps:
Determining a group of recognition periods T backwards based on the initial moment, wherein T is a preset value, confirming the breathing waveform segments generated in the recognition period T, and calibrating the confirmed breathing waveform segments as undetermined analysis segments;
Sequentially confirming the related points in the undetermined analysis section, wherein the trend of the front end line section of the related points is upward, the trend of the rear end line section is downward, analyzing the line segment characteristics between the adjacent related points, wherein the analysis mode is that the respiration amplitude corresponding to the first related point of the line segment corresponding to the adjacent related points is marked as H1, the respiration amplitude corresponding to the second related point is marked as H2, the time interval between the two related points is marked as JG, and the analysis value FX between the corresponding related points is determined by FX= |H 1-H2|xC1+JG xC 2, wherein both C1 and C2 are preset fixed coefficient factors, sequentially confirming the analysis values FX of different line segments according to the front to back, and generating an analysis value sequencing sequence { FX1, FX2, FXn };
Carrying out variance treatment on the corresponding sorting values in the sorting sequence of the analysis values, preferentially starting from a first group of analysis values FX1, gradually and later confirming the relevant analysis values to determine a variance value Fc, when Fc is less than or equal to Y1, wherein Y1 is a preset value, then determining the subsequent analysis values again, when the confirmed variance value Fc is greater than Y1, calibrating the added analysis values as abnormal values, calibrating a plurality of groups of analysis values at the front end of the abnormal values as similar values, calibrating line segments corresponding to the similar values as similar segments, starting from the abnormal values, later confirming the analysis values, determining the variance value Fc, sequentially confirming the similar segments appearing in the analysis segments to be determined in the same way, and calibrating relevant line segments among the similar segments as fluctuation segments;
Selecting a maximum value and a minimum value of a corresponding analysis value from the confirmed similar segments and the fluctuation segments, generating a stable section belonging to the similar segments according to the confirmed maximum value and the confirmed minimum value, generating a fluctuation section belonging to the fluctuation segments based on the maximum value and the minimum value generated by the fluctuation segments, and transmitting the stable section and the fluctuation section to a fluctuation characteristic judgment end;
The fluctuation feature determination end performs numerical analysis on a respiratory waveform change curve generated after the recognition period T, determines corresponding fluctuation features, compares the determined fluctuation features with related feature intervals, and generates different processing signals based on comparison results, wherein the method comprises the following steps:
The characteristic interval comprises a fluctuation interval and a stable interval, and then confirms an analysis value F k generated after the recognition period T corresponds to the follow-up respiration waveform change curve and confirms the section of the generated analysis value F k, wherein k represents a line segment between different follow-up related points;
when F k is in an epsilon stable interval, generating a stable signal and displaying the stable signal through a display end;
When F k epsilon fluctuation interval, generating a fluctuation signal and displaying through a display end;
When the stable interval is less than F k and the fluctuation interval is less than F k, generating an intervention signal, displaying through a display end, and judging whether the part of analysis value F k needs to be filled into the fluctuation interval or not by external medical staff based on the intervention signal so as to expand the corresponding range of the corresponding fluctuation interval;
Further comprises:
When F k is smaller than the stable interval, calibrating the analysis value appearing at the moment as an abnormal value, determining five groups of analysis values appearing continuously, and sequencing the determined analysis values as follows: f1, F2, F3, F4, F5 and F6, wherein F1 is an outlier calibrated at the present moment, and in the determined analysis value ranking sequence, when the latter set of analysis values is smaller than the former set of analysis values, a set of assignments "-1" is generated, and if the latter set of analysis values is not smaller than the former set of analysis values, a set of assignments "0" is generated, and the assignment sequence is determined;
When F k > fluctuates, calibrating the analysis value appearing at the moment as an abnormal value, determining five groups of analysis values appearing continuously, and sequencing the determined analysis values as B1, B2, B3, B4, B5 and B6, wherein B1 is the abnormal value calibrated at the moment, in the determined analysis value sequencing sequence, when the analysis value of the latter group is larger than the analysis value of the former group, generating a group of assignment '1', and if the analysis value of the latter group is not larger than the analysis value of the former group, generating a group of assignment '0';
Determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, directly generating an early warning signal if the JD is more than or equal to Y2, wherein Y2 is a preset value, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, and otherwise, continuing monitoring and comparison;
Still another set of alignment methods:
When F k is smaller than the stable interval, determining the subsequent analysis values which continuously appear and locking the related analysis value sequencing sequence, marking the next group of analysis values as Fh, marking the previous group of analysis values as Fq, generating a group of assignments '-1' when Fq/2 < Fh < Fq, generating a group of assignments '-2' when Fh is smaller than or equal to (Fq/2), otherwise, generating a group of assignments '-0', and determining the assignment sequence;
When F k > fluctuates, determining the subsequent analysis values which continuously appear and locking the related analysis value sequencing sequence, calibrating the next group of analysis values as Bh, calibrating the previous group of analysis values as Bq, generating a group of assignments '1' when 2Bq > Bh > Bq, generating a group of assignments '2' when Bh is more than or equal to 2Bq, otherwise, generating a assignment '0', and determining the assignment sequence;
Determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, directly generating an early warning signal if the JD is more than or equal to Y2, wherein Y2 is a preset value, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, and otherwise, continuing monitoring and comparison.
The invention provides an intelligent neonate respiratory monitoring system. Compared with the prior art, the device has the following
The beneficial effects are that:
The invention determines the relevant respiratory characteristics of the corresponding newborns by limiting the monitoring period, and sequentially uses the respiratory characteristics as the corresponding standard of the subsequent monitoring judgment, thereby improving the practicability of the intelligent monitoring system, and because each different newborns have different respiratory habits or different respiratory characteristics, if the unified judging standard is adopted, the numerical judgment can be not timely or accurate, the corresponding interval is sequentially determined by adopting the mode of determining the relevant line segment by numerical monitoring, so as to determine the relevant judging signal;
Subsequently, based on the relevant characteristic values generated by the corresponding newborns, corresponding comparison signals are generated based on the comparison results and are checked by external personnel, so that the breathing change condition of each different newborns can be confirmed and early-warned in time, and the abnormal degree of the newborns is identified based on the corresponding assignment sequences, so that the safety of the corresponding newborns is ensured.
Drawings
FIG. 1 is a schematic diagram of a principal frame of the present invention;
fig. 2 is a schematic diagram of a respiration amplitude variation waveform according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, the application provides an intelligent neonatal respiratory monitoring system, which comprises a numerical monitoring end, an early warning end, a waveform generating end, a waveform analyzing end, a waveform characteristic judging end and a display end, wherein the numerical monitoring end is respectively and electrically connected with an input node of the early warning end or the waveform generating end, the waveform generating end is respectively and electrically connected with an input node of the waveform analyzing end or the waveform characteristic judging end, the waveform analyzing end is electrically connected with an input node of the waveform characteristic judging end, and the waveform characteristic judging end is respectively and electrically connected with an input node of the display end or the early warning end;
wherein, the numerical value monitoring end monitors the breath of the neonate and transmits the value of the monitored breath amplitude to the waveform generating end, the monitor is electrified between two electrocardiogram electrodes of the neonate chest to measure the impedance breath, the current is harmless high-frequency current, the resistance (impedance) between the electrodes can be changed along with the expansion and contraction of the chest during expiration and inspiration, and the monitor can confirm the related respiration amplitude from the impedance change;
The early warning end carries out early warning judgment on the respiration amplitude monitored in real time, and when the respiration amplitude monitored in real time exceeds the corresponding early warning range, early warning is sent out to warn related personnel, wherein the specific mode for carrying out early warning judgment comprises the following steps:
The respiratory amplitude is marked as HX i, wherein i represents different moments, the respiratory amplitude HX i is compared with a preset early warning range, when HX i epsilon the early warning range, no treatment is carried out, and when When the early warning range is reached, relevant alarms are directly generated to warn external relevant personnel, the respiratory amplitude is obviously beyond the corresponding early warning range, relevant early warning risks exist, the early warning risks need to be treated in time, the conditions belong to the special danger level, and relevant alarm alarms are generated to warn personnel.
The method comprises the steps of generating a respiration waveform change curve of a waveform generating end in real time based on related respiration amplitudes generated at different moments, and transmitting the generated respiration waveform change curve to a waveform analyzing end or a waveform characteristic judging end, wherein the specific mode of generating the respiration waveform change curve in real time comprises the following steps:
Based on different related respiration amplitudes generated at different moments, using a time line as a transverse coordinate axis, using respiration amplitudes corresponding to different moments as a vertical coordinate axis, determining different points according to different values corresponding to different moments, determining respiration waveform change curves in a two-dimensional coordinate system, and transmitting the determined respiration waveform change curves to a waveform analysis end or a waveform characteristic determination end;
specifically, the corresponding point positions can be determined in the two-dimensional coordinate system according to different respiration amplitudes at different moments, then the corresponding point positions are interconnected, the relevant respiration waveform change curve is determined, and the relevant respiration condition of the corresponding neonate can be fully displayed by the respiration waveform change curve.
The waveform analysis end determines a group of recognition periods based on the initial moment of a respiratory waveform change curve, analyzes respiratory waveforms generated in the recognition periods to determine relevant respiratory characteristics of the neonate, and transmits the determined relevant respiratory characteristics to the waveform characteristic determination end, wherein the specific mode of determining the relevant respiratory characteristics comprises the following steps:
Determining a group of recognition periods T backwards based on the initial moment, wherein T is a preset value, the specific value of the T is determined by an operator according to experience, the breathing waveform segments generated in the recognition period T are confirmed, and the confirmed breathing waveform segments are calibrated to be undetermined analysis segments;
Sequentially confirming the related points appearing in the undetermined analysis section, wherein the trend of the front end line section of the related points is upward, the trend of the rear end line section is downward, the related points are confirmed as shown in fig. 2, line segment characteristics between adjacent related points are analyzed, the analysis mode is that the respiration amplitude corresponding to the first related point of the line segment corresponding to the adjacent related points is marked as H1, the respiration amplitude corresponding to the second related point is marked as H2, the time interval between the two related points is marked as JG, the analysis values between the corresponding related points are confirmed by FX= |H 1-H2|C1+JGxC 2, wherein C1 and C2 are all preset fixed coefficient factors, the specific values are planned according to experience by an operator, the analysis values FX of different line segments are sequentially confirmed according to the previous to the later, and analysis value sequencing sequences { FX1, FX.. FXn };
Carrying out variance treatment on the corresponding sequencing values in the sequencing sequence of the analysis values, preferentially starting from a first group of analysis values FX1, gradually and later confirming the relevant analysis values to determine a variance value Fc, when Fc is smaller than or equal to Y1, wherein Y1 is a preset value, the specific value is planned by an operator according to experience, then the subsequent analysis values are determined again, when the confirmed variance value Fc is larger than Y1, the added analysis values are calibrated as abnormal values, a plurality of groups of analysis values at the front end of the abnormal values are calibrated as similar values, a line segment corresponding to the similar values is calibrated as a similar segment, then starting from the abnormal value, later confirming the analysis values, determining the variance value Fc, and adopting the same mode to sequentially confirm the similar segments appearing in the analysis segments to be determined, and calibrating the relevant analysis segments between the similar segments as fluctuation segments (wherein the relevant line segments do not belong to the similar segments), as shown in the figure 2, the situation from the center of circle to the first group of the same type of the horizontal dashed line segment is a similar segment, the first group of the horizontal dashed line segment is a similar segment, the situation between the first group of the horizontal dashed line segment and the second group of the horizontal dashed line segment is a similar segment, the second group of the horizontal dashed line segment is a similar to a second group of the horizontal dashed line segment is a big difference between the first group of the horizontal dashed line and a similar segment and a second group of the horizontal dashed line is a similar line segment is a similar to a similar line segment;
The numerical processing mode can be understood that the sequence is {1, 1.2, 2, 2.1, 2.2, 2.1, 2.15, 0.8, 0.75, 0.85, 0.84 and 0.82}, and the expression forms of the analysis values are shown as above, so that the first group of analysis values and the second group of analysis values are similar segments according to the variance processing mode, when the third group of analysis values intervene in the variance processing mode, the corresponding variances generated by the first three groups of values deviate from the original judging mode, the third group of values are abnormal values, the line segments corresponding to the first group of values and the second group of values are similar segments, the line segments between the second group of values and the third group of values are fluctuation segments, the line segments between the third group of values and the seventh group of values are similar segments, a group of fluctuation segments and the subsequent similar segments related to the third group of analysis values can be determined, and the subsequent similar segments appearing in sequence can be confirmed by analogy;
Selecting a maximum value and a minimum value of a corresponding analysis value from the confirmed similar segments and the fluctuation segments, generating a stable section belonging to the similar segments according to the confirmed maximum value and the confirmed minimum value, generating a fluctuation section belonging to the fluctuation segments based on the maximum value and the minimum value generated by the fluctuation segments, and transmitting the stable section and the fluctuation section to a fluctuation characteristic judgment end;
Specifically, the respiratory variation condition of the corresponding neonate is determined according to the related characteristics generated by the corresponding waveforms, so as to determine a relative monitoring interval, and the respiratory parameters generated by the subsequent neonate are determined or early-warned based on the monitoring interval, so that the practicability of the intelligent monitoring system is improved, and if the unified judging standard is adopted, the numerical judgment is possibly untimely or inaccurate, the corresponding interval is sequentially determined by adopting the mode of determining the relevant line segment by adopting the numerical monitoring, so that the related judging signal is determined.
The fluctuation feature determination end performs numerical analysis on a respiratory waveform change curve generated after the recognition period T, determines corresponding fluctuation features, compares the determined fluctuation features with related feature intervals, and generates different processing signals based on comparison results, wherein the specific modes for comparison comprise:
The characteristic interval comprises a fluctuation interval and a stable interval, and then confirms an analysis value F k generated after the recognition period T corresponds to the follow-up respiration waveform change curve and confirms the section of the generated analysis value F k, wherein k represents a line segment between different follow-up related points;
when F k is in an epsilon stable interval, generating a stable signal and displaying the stable signal through a display end;
When F k epsilon fluctuation interval, generating a fluctuation signal and displaying through a display end;
When the stable interval is less than F k and the fluctuation interval is less than F k, generating an intervention signal, displaying the intervention signal through a display end, and judging whether the part of analysis value F k needs to be filled into the fluctuation interval or not by an external medical staff based on the intervention signal so as to enlarge the corresponding range of the corresponding fluctuation interval, wherein whether the judging range needs to be enlarged or not is determined by the external medical staff by oneself;
the specific mode for comparison also comprises the following steps:
When F k is smaller than the former group of analysis values in the determined analysis value sorting sequence, generating a group of assignments '-1', and generating a group of assignments '-0', if the latter group of analysis values is not smaller than the former group of analysis values, for example, generating a group of assignments-1, F3< F2, and generating a group of assignments-1, and so on, determining the generated assignment sequence, and determining the assignment sequence;
When F k > fluctuates, calibrating the analysis value appearing at the moment as an abnormal value, determining five groups of analysis values appearing continuously, and sequencing the determined analysis values as B1, B2, B3, B4, B5 and B6, wherein B1 is the abnormal value calibrated at the moment, in the determined analysis value sequencing sequence, when the analysis value of the latter group is larger than the analysis value of the former group, generating a group of assignment '1', and if the analysis value of the latter group is not larger than the analysis value of the former group, generating a group of assignment '0';
determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, and if the value JD is more than or equal to Y2, wherein Y2 is a preset value, the specific value of the value is determined by an operator according to experience, directly generating an early warning signal, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, otherwise, continuing monitoring and comparison;
Specifically, this kind of condition represents that the breathing amplitude that corresponds changes comparatively violently, or breathe the range and become larger and larger, or breathe the range and become lower, all is in abnormal change condition, just needs timely early warning, makes medical personnel in time intervene, alright guarantee its safety that corresponds the neonate.
Example two
The present embodiment is a further embodiment for implementing one, and is different from the embodiment in that the present embodiment further includes a further advanced determination manner, mainly for the case of F k < plateau area or F k > fluctuation area, and the specific contents thereof are as follows:
the specific mode for comparison also comprises the following steps:
Locking the related ordered sequence of analysis values when F k < plateau, calibrating the next set of analysis values to Fh, calibrating the previous set of analysis values to Fq (wherein the previous set of analysis values is a previous set of parameters relative to the next set of analysis values, such as F1, F2, F3, F4, F5 and F6, F1 is a previous set of analysis values of F2, F2 is a next set of analysis values of F1, F2 is a previous set of analysis values of F3, F3 is a next set of analysis values of F2, and so on), generating a set of assignments "-1" when (Fq 2) < Fh < Fq, generating a set of assignments "-2" when Fh is less than or equal to (Fq 2), otherwise generating a set of assignments "-0", determining the sequence;
When F k > fluctuates, locking the related analysis value sequencing sequence, calibrating the latter group of analysis values as Bh, calibrating the former group of analysis values as Bq, generating a group of assignments '1' when 2Bq > Bh > Bq, generating a group of assignments '2' when Bh is more than or equal to 2Bq, otherwise, generating a assignment '0', and determining the assignment sequence;
determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, and if the value JD is more than or equal to Y2, wherein Y2 is a preset value, the specific value of the value is determined by an operator according to experience, directly generating an early warning signal, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, otherwise, continuing monitoring and comparison;
Specifically, the assignment 2 is added on the basis of the first embodiment, and because according to the correlation comparison method of the first embodiment 1, when the change amplitude is larger or smaller at a certain place, the corresponding assignment 1 is generated, the change condition of the change amplitude is not enough to be displayed, and the larger the change amplitude is, the larger the generated assignment is, the abnormal condition can be more obviously represented, so that the determination mode of the second embodiment is more accurate than the determination mode of the first embodiment, the generated early warning signal is more advanced, and a better warning effect can be achieved, thereby ensuring the monitoring effect of the monitoring system.
Some of the data in the above formulas are numerical calculated by removing their dimensionality, and the contents not described in detail in the present specification are all well known in the prior art.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (3)
1. An intelligent neonatal respiratory monitoring system, comprising:
the value monitoring end monitors the breath of the neonate and transmits the monitored breath amplitude value to the waveform generating end;
the early warning end carries out early warning judgment on the respiration amplitude monitored in real time, and when the respiration amplitude monitored in real time exceeds the corresponding early warning range, an early warning is sent out;
The waveform generation end generates a respiration waveform change curve based on the related respiration amplitudes generated at different moments in real time and transmits the generated respiration waveform change curve to the waveform analysis end or the waveform characteristic judgment end, and the waveform generation end comprises:
Based on different related respiration amplitudes generated at different moments, using a time line as a transverse coordinate axis, using respiration amplitudes corresponding to different moments as a vertical coordinate axis, determining different points according to different values corresponding to different moments, determining respiration waveform change curves in a two-dimensional coordinate system, and transmitting the determined respiration waveform change curves to a waveform analysis end or a waveform characteristic determination end;
The waveform analysis end determines a group of recognition periods based on the initial time of the respiration waveform change curve, analyzes the respiration waveform generated in the recognition periods to determine the relevant respiration characteristics and characteristic intervals of the neonate, and comprises the following steps:
Determining a group of recognition periods T backwards based on the initial moment, wherein T is a preset value, confirming the breathing waveform segments generated in the recognition period T, and calibrating the confirmed breathing waveform segments as undetermined analysis segments;
Sequentially confirming the related points in the undetermined analysis section, wherein the trend of the front end line section of the related points is upward, the trend of the rear end line section is downward, analyzing the line segment characteristics between the adjacent related points, wherein the analysis mode is that the respiration amplitude corresponding to the first related point of the line segment corresponding to the adjacent related points is marked as H1, the respiration amplitude corresponding to the second related point is marked as H2, the time interval between the two related points is marked as JG, and the analysis value FX between the corresponding related points is determined by FX= |H 1-H2|xC1+JG xC 2, wherein both C1 and C2 are preset fixed coefficient factors, sequentially confirming the analysis values FX of different line segments according to the front to back, and generating an analysis value sequencing sequence { FX1, FX2, FXn };
Carrying out variance treatment on the corresponding sorting values in the sorting sequence of the analysis values, preferentially starting from a first group of analysis values FX1, gradually and later confirming the relevant analysis values to determine a variance value Fc, when Fc is less than or equal to Y1, wherein Y1 is a preset value, then determining the subsequent analysis values again, when the confirmed variance value Fc is greater than Y1, calibrating the added analysis values as abnormal values, calibrating a plurality of groups of analysis values at the front end of the abnormal values as similar values, calibrating line segments corresponding to the similar values as similar segments, starting from the abnormal values, later confirming the analysis values, determining the variance value Fc, sequentially confirming the similar segments appearing in the analysis segments to be determined in the same way, and calibrating relevant line segments among the similar segments as fluctuation segments;
Selecting a maximum value and a minimum value of a corresponding analysis value from the confirmed similar segments and the fluctuation segments, generating a stable section belonging to the similar segments according to the confirmed maximum value and the confirmed minimum value, generating a fluctuation section belonging to the fluctuation segments based on the maximum value and the minimum value generated by the fluctuation segments, and transmitting the stable section and the fluctuation section to a fluctuation characteristic judgment end;
the fluctuation feature determination end performs numerical analysis on a respiratory waveform change curve generated after the recognition period T, determines corresponding fluctuation features, compares the determined fluctuation features with related feature intervals, and generates different processing signals based on comparison results, wherein the method comprises the following steps:
The characteristic interval comprises a fluctuation interval and a stable interval, and then confirms an analysis value F k generated after the recognition period T corresponds to the follow-up respiration waveform change curve and confirms the section of the generated analysis value F k, wherein k represents a line segment between different follow-up related points;
when F k is in an epsilon stable interval, generating a stable signal and displaying the stable signal through a display end;
When F k epsilon fluctuation interval, generating a fluctuation signal and displaying through a display end;
When the stable interval is less than F k and the fluctuation interval is less than F k, generating an intervention signal, displaying through a display end, and judging whether the part of analysis value F k needs to be filled into the fluctuation interval or not by external medical staff based on the intervention signal so as to expand the corresponding range of the corresponding fluctuation interval;
When F k is smaller than the stable interval, calibrating the analysis value appearing at the moment as an abnormal value, determining five groups of analysis values appearing continuously, and sequencing the determined analysis values as follows: f1, F2, F3, F4, F5 and F6, wherein F1 is an outlier calibrated at the present moment, and in the determined analysis value ranking sequence, when the latter set of analysis values is smaller than the former set of analysis values, a set of assignments "-1" is generated, and if the latter set of analysis values is not smaller than the former set of analysis values, a set of assignments "0" is generated, and the assignment sequence is determined;
When F k > fluctuates, calibrating the analysis value appearing at the moment as an abnormal value, determining five groups of analysis values appearing continuously, and sequencing the determined analysis values as B1, B2, B3, B4, B5 and B6, wherein B1 is the abnormal value calibrated at the moment, in the determined analysis value sequencing sequence, when the analysis value of the latter group is larger than the analysis value of the former group, generating a group of assignment '1', and if the analysis value of the latter group is not larger than the analysis value of the former group, generating a group of assignment '0';
Determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, directly generating an early warning signal if the JD is more than or equal to Y2, wherein Y2 is a preset value, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, and otherwise, continuing monitoring and comparison.
2. The intelligent neonatal respiratory monitoring system of claim 1, wherein the specific manner of performing the early warning decision at the early warning end includes:
The respiratory amplitude is marked as HX i, wherein i represents different moments, the respiratory amplitude HX i is compared with a preset early warning range, when HX i epsilon the early warning range, no treatment is carried out, and when HX i ∉ the early warning range, a relevant alarm is directly generated.
3. The intelligent neonatal respiratory monitoring system of claim 1, wherein the means for comparing the determined fluctuation signature to the relevant signature interval further comprises:
When F k is smaller than the stable interval, determining the subsequent analysis values which continuously appear and locking the related analysis value sequencing sequence, marking the next group of analysis values as Fh, marking the previous group of analysis values as Fq, generating a group of assignments '-1' when Fq/2 < Fh < Fq, generating a group of assignments '-2' when Fh is smaller than or equal to (Fq/2), otherwise, generating a group of assignments '-0', and determining the assignment sequence;
When F k > fluctuates, determining the subsequent analysis values which continuously appear and locking the related analysis value sequencing sequence, calibrating the next group of analysis values as Bh, calibrating the previous group of analysis values as Bq, generating a group of assignments '1' when 2Bq > Bh > Bq, generating a group of assignments '2' when Bh is more than or equal to 2Bq, otherwise, generating a assignment '0', and determining the assignment sequence;
Determining a value sum based on the generated value sequence, locking an absolute value JD of the value sum, directly generating an early warning signal if the JD is more than or equal to Y2, wherein Y2 is a preset value, controlling an early warning terminal to directly generate a related alarm to warn external related personnel, and otherwise, continuing monitoring and comparison.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410502308.XA CN118303869B (en) | 2024-04-24 | 2024-04-24 | Intelligence neonate respiratory monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410502308.XA CN118303869B (en) | 2024-04-24 | 2024-04-24 | Intelligence neonate respiratory monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118303869A CN118303869A (en) | 2024-07-09 |
| CN118303869B true CN118303869B (en) | 2024-12-06 |
Family
ID=91730873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410502308.XA Active CN118303869B (en) | 2024-04-24 | 2024-04-24 | Intelligence neonate respiratory monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118303869B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118553427A (en) * | 2024-07-26 | 2024-08-27 | 苏州工业园区东诚智能网络技术有限公司 | A rehabilitation process tracking method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112971743A (en) * | 2021-02-08 | 2021-06-18 | 南京泓鼎感知技术有限责任公司 | Non-contact neonatal respiration monitoring system, device and storage medium |
| CN113347917A (en) * | 2019-01-29 | 2021-09-03 | 皇家飞利浦有限公司 | Method and system for generating a respiratory alert |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4365636A (en) * | 1981-06-19 | 1982-12-28 | Medicon, Inc. | Method of monitoring patient respiration and predicting apnea therefrom |
| CN1977767B (en) * | 2005-12-08 | 2010-10-06 | 深圳迈瑞生物医疗电子股份有限公司 | The Method of Improving Respiratory Wave Recognition Rate |
| US20130197385A1 (en) * | 2012-01-31 | 2013-08-01 | Medtronic, Inc. | Respiratory function detection |
| CN104739371B (en) * | 2013-12-31 | 2020-02-14 | 深圳迈瑞生物医疗电子股份有限公司 | Monitor and automatic multi-lead signal switching method and device thereof |
| CN104771166A (en) * | 2015-05-04 | 2015-07-15 | 思澜科技（成都）有限公司 | Sleep breath state signal acquisition device based on biological resistance and monitoring system |
| JP2018130513A (en) * | 2017-02-15 | 2018-08-23 | 修 池田 | Respiration component extraction method |
| EP3695776A1 (en) * | 2019-02-13 | 2020-08-19 | Koninklijke Philips N.V. | A method and system for generating a respiration instability signal |
| US20230095345A1 (en) * | 2021-09-30 | 2023-03-30 | Covidien Lp | Non-contact systems and methods for monitoring and addressing breathing events in neonates |
| CN115089164A (en) * | 2022-06-23 | 2022-09-23 | 北京清雷科技有限公司 | Method, device and storage medium for extracting respiratory rate variability data |
| CN115517653A (en) * | 2022-08-18 | 2022-12-27 | 江苏人先医疗科技有限公司 | Respiration monitoring method, respiration monitor and storage medium |
-
2024
- 2024-04-24 CN CN202410502308.XA patent/CN118303869B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113347917A (en) * | 2019-01-29 | 2021-09-03 | 皇家飞利浦有限公司 | Method and system for generating a respiratory alert |
| CN112971743A (en) * | 2021-02-08 | 2021-06-18 | 南京泓鼎感知技术有限责任公司 | Non-contact neonatal respiration monitoring system, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118303869A (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12226240B2 (en) | Alarm threshold setting suggestion method, system and monitor | |
| TW201918222A (en) | Method and apparatus for high accuracy photoplethysmogram based atrial fibrillation detection using wearable device | |
| WO2012117316A2 (en) | Patient deterioration detection | |
| EP2931119A2 (en) | Patient monitoring for sub-acute patients based on activity state and posture | |
| CA2787170A1 (en) | Multivariate residual-based health index for human health monitoring | |
| US20140032241A1 (en) | Method, apparatus and computer program product for monitoring clinical state of a subject | |
| US20250114002A2 (en) | An Interactive Health-Monitoring Platform for Wearable Wireless Sensor System | |
| CN118303869B (en) | Intelligence neonate respiratory monitoring system | |
| CN104684472B (en) | Systems and methods for assessing patient health status based on recovery response from oxygen desaturation | |
| US20160163187A1 (en) | System and method for physiological monitoring | |
| CN113226154B (en) | Early warning score display method, monitoring device and system | |
| CN116847904A (en) | stimulation system | |
| CN112911992B (en) | Monitoring method, monitor and computer storage medium | |
| CN110897623A (en) | Intelligent sleep monitoring system with good vital sign detection effect | |
| JP6213983B2 (en) | Sleep stage estimation apparatus and method, and program | |
| US20230051939A1 (en) | Physiological monitoring apparatus and physiological monitoring method | |
| CN117315885B (en) | A remote shared alarm system for monitoring urine bag urine volume and ECG monitor | |
| Sujin et al. | Public e-health network system using arduino controller | |
| WO2024224391A1 (en) | Sleep apnea event determination using terahertz radar | |
| CN106725457A (en) | An inpatient monitoring system based on brain-computer artificial intelligence technology | |
| CN118121165A (en) | Sleep analysis method, sleep analysis device, terminal equipment and storage medium | |
| US10299739B2 (en) | Medical monitoring apparatus | |
| US20180166159A1 (en) | Age-adaptive pulse oximetry | |
| CN113180615B (en) | Organ sleep detection method and system for physical sign data analysis of wearable equipment | |
| Mukti et al. | Design of smart wearable for cardiopulmonary monitoring with adaptive feedback loop |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |