Pediatric drug complication monitoring system

Abstract

The invention, which relates to the technical field of medical information, discloses a pediatric drug complication monitoring system comprising a data acquisition module, a data analysis module, an early warning generation module and a cloud database. Physiological parameters of a pediatric patient are acquired in real time through the data acquisition module, the physiological parameters are analyzed by the data analysis module through a preset algorithm, any change or abnormal condition possibly indicating a drug complication sign is recognized, if a potential drug complication sign is detected, the early warning generation module generates an early warning signal, and the early warning signal is sent to the pediatric patient. And the cloud database is not only used for data storage, but also used for continuously optimizing the complication prediction model through an integrated machine learning algorithm, so that the accuracy and the reliability of the system are improved, and the complication prediction model is more accurate and reliable along with the accumulation of more data. According to the system, early signs of drug complications can be identified more accurately, and powerful support is provided for clinical decision making.

Description

Technical Field

[0001] The invention relates to the field of medical information technology, in particular to a pediatric drug complication monitoring system. Background Art

[0002] The development of a pediatric drug complication monitoring system aims to achieve effective monitoring and management of drug side effects and complications by collecting, analyzing and processing various data of pediatric patients during the medication process. The system usually includes key components such as data acquisition module, data analysis module and early warning notification module, which can help medical staff to promptly detect and deal with potential drug complications, thereby improving the safety and treatment effects of children.

[0003] However, in actual applications, how to accurately monitor and warn of pediatric drug complications remains a challenge. This is mainly because children have different physical development stages and their responses to drugs vary greatly. In addition, there are many types of pediatric drugs, and it is necessary to consider multiple factors to accurately assess drug risks. In addition, the accuracy and completeness of data are also one of the key factors affecting the performance of the monitoring system. How to ensure data quality and effectively use big data technology for precise analysis is an urgent problem that needs to be solved. Therefore, building an efficient and reliable pediatric drug complication monitoring system still requires continuous exploration and improvement. Summary of the invention

[0004] In view of the above problems existing in the existing pediatric drug complication monitoring system, the present invention provides the following technical solutions: a pediatric drug complication monitoring system, comprising:

[0005] Data acquisition module, used to obtain physiological parameters of pediatric patients in real time;

[0006] a data analysis module for analyzing said physiological parameters and identifying potential signs of medication complications;

[0007] an early warning generation module, configured to generate an early warning signal when the data analysis module detects signs of drug complications;

[0008] The cloud database is used to store the physiological parameters and corresponding analysis results, and continuously optimize the complication prediction model through machine learning algorithms.

[0009] Preferably, the step of acquiring physiological parameters of pediatric patients in real time comprises:

[0010] Real-time monitoring of physiological signals of pediatric patients based on a sensor array, wherein the physiological signals include body temperature, heart rate and blood pressure;

[0011] Sending the physiological signal to a data processing unit via wireless transmission technology;

[0012] The physiological signal is sampled using a preset sampling frequency F, wherein the sampling frequency F needs to satisfy Shannon's sampling theorem to ensure that the signal is not distorted;

[0013] The sampled physiological signals are converted into digital signals and uploaded to the data analysis module.

[0014] Preferably, the step of real-time monitoring of physiological signals of pediatric patients based on a sensor array comprises:

[0015] The temperature sensor on the wearable device measures the skin surface temperature of the pediatric patient in real time. If the skin surface temperature is greater than the normal body temperature range, the abnormality is recorded for conditional judgment.

[0016] A heart rate sensor is used to monitor the heart rate of a pediatric patient. If the heart rate is greater than a normal heart rate range, the abnormality is recorded for conditional judgment.

[0017] Using a blood pressure sensor to measure the systolic and diastolic blood pressure of a pediatric patient, if the systolic and diastolic blood pressure are greater than a normal blood pressure range, the abnormality is recorded for conditional judgment;

[0018] Compare the above abnormal records with the normal physiological parameter range to determine whether further treatment is required.

[0019] Preferably, the temperature sensor on the wearable device measures the skin surface temperature of the pediatric patient in real time, and if the skin surface temperature is greater than the normal body temperature range, the step of recording the abnormality and making conditional judgment includes:

[0020] The skin surface temperature of the pediatric patient is obtained by a temperature sensor;

[0021] The normal temperature range is adjusted based on the age of the pediatric patient. If the pediatric patient is less than 1 year old, the normal temperature range is set to 5°C to 37.5°C; if the pediatric patient is not less than 1 year old, the normal temperature range is set to 36.0°C to 37.0°C;

[0022] If the skin surface temperature exceeds the above normal body temperature range, an abnormality is recorded;

[0023] Send the abnormal records to the data analysis module for subsequent processing.

[0024] Preferably, the step of sending the abnormal record to the data analysis module for subsequent processing includes:

[0025] Classify the received abnormal records according to timestamps, patient information, etc., and store them in the database;

[0026] Check and remove incomplete, duplicate or invalid records, and organize temperature values ​​and patient information into a unified format for analysis;

[0027] Statistical analysis was performed using the formula F 异常 =A 异常 / N 异常 To calculate the frequency of abnormal body temperature, where F 异常 Indicates abnormal frequency, A 异常 Indicates the number of abnormal records, N 异常 Indicate the total number of records, identify the proportion of patients with abnormalities, analyze the distribution of abnormal records according to age groups, and find out the high-risk group;

[0028] Conduct trend analysis to evaluate the temperature change trend of patients within a certain time range and compare the changes in abnormal records in different time periods, such as daily average, weekly average, monthly average, etc.

[0029] Preferably, the step of analyzing the physiological parameters and identifying potential signs of drug complications comprises:

[0030] Based on a preset physiological parameter threshold range, preliminarily screening the physiological parameters;

[0031] Conduct trend analysis on the screened physiological parameters to identify abnormal change trends;

[0032] Based on the matching degree between the abnormal change trend and the known drug complication characteristics, the complication risk level is assessed;

[0033] When the risk level exceeds a preset threshold, it is determined that there are signs of potential drug complications.

[0034] Preferably, the step of preliminarily screening the physiological parameters based on a preset physiological parameter threshold range comprises:

[0035] Get current physiological parameter values;

[0036] Determine whether the physiological parameter value exceeds the normal range. If the physiological parameter value is less than the lower limit of the normal range, it is considered abnormal;

[0037] If the physiological parameter value is greater than the upper limit of the normal range, it is considered abnormal;

[0038] Based on the abnormal judgment result, abnormal physiological parameters are identified;

[0039] The identified abnormal physiological parameters are passed to the next step for further analysis.

[0040] Preferably, the step of identifying abnormal physiological parameters based on the abnormal judgment result includes:

[0041] For each physiological parameter marked as abnormal, record its abnormal status;

[0042] Calculate the ratio of abnormal physiological parameters to the total monitored parameters using the formula: R = N 异常 / N 总 , where R represents the ratio, N 异常 Represents the number of abnormal physiological parameters, N 总 Indicates the total number of monitored parameters;

[0043] A judgment is made based on the ratio and a preset abnormal ratio threshold. If the ratio is not less than the abnormal ratio threshold, it is considered that there are multiple abnormal parameters, and the trend analysis step is entered.

[0044] Preferably, the trend analysis step comprises:

[0045] Collect and organize physiological parameter data that are marked as abnormal;

[0046] Select appropriate trend analysis methods;

[0047] Use graphs and charts to present abnormal physiological parameters and their trends;

[0048] Based on the results of trend analysis, interpret the data and record possible related factors.

[0049] Preferably, the step of selecting a suitable trend analysis method comprises:

[0050] Select the moving average method to smooth the series and identify the long-term trend. The formula is Among them, SMA t is the output result, X is the time series data, n is the window size of the moving average, t is the current time point, and i is the time sequence number;

[0051] The linear regression method is selected to identify the rate of change of the parameter over time. The formula is Y = a + bZ + c, where Y is the dependent variable, Z is the independent variable, a is the intercept, b is the slope, and c is the error term.

[0052] The present invention provides a pediatric drug complication monitoring system. It has the following beneficial effects:

[0053] The present invention obtains the physiological parameters of pediatric patients in real time through the data acquisition module, analyzes them with a preset algorithm through the data analysis module, and identifies any changes or abnormalities that may indicate signs of drug complications. If potential signs of drug complications are detected, the early warning generation module will generate an early warning signal so that necessary intervention measures can be taken in time. The physiological parameters and analysis results will be uploaded to the cloud database for storage. The cloud database is not only used for data preservation, but also continuously optimizes the complication prediction model through an integrated machine learning algorithm, thereby improving the accuracy and reliability of the system. As more data is accumulated, the system can more accurately identify early signs of drug complications and provide strong support for clinical decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a structural schematic diagram of the pediatric drug complication monitoring system of the present invention;

[0055] Figure 2 It is a structural schematic diagram of the patient physiological data acquisition module of the present invention;

[0056] Figure 3 It is a schematic diagram of the process of real-time monitoring of the body temperature of pediatric patients based on a sensor array of the present invention;

[0057] Figure 4 It is a structural schematic diagram of the data analysis module of the present invention;

[0058] Figure 5 It is a structural schematic diagram of the trend analysis of the present invention. DETAILED DESCRIPTION

[0059] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0060] Depend on Figure 1-Figure 5 As shown, the Pediatric Medication Complications Monitoring System includes:

[0061] S1: Real-time acquisition of physiological parameters of pediatric patients through the patient physiological data acquisition module. This process involves the use of advanced sensor technology and medical equipment to monitor children's vital signs and other relevant physiological indicators. For example, key indicators such as heart rate, blood pressure, body temperature, and blood oxygen saturation can be continuously monitored through wearable devices or bedside monitors. In addition, more detailed biomarker information such as white blood cell counts and liver function tests can be obtained through blood sample analysis. These data are transmitted to the central processing unit of the monitoring system in real time to ensure that doctors and caregivers can obtain the latest patient status information in a timely manner. For example, after a child with asthma takes specific medications, changes in his or her respiratory rate and blood oxygen level will be continuously recorded for subsequent analysis;

[0062] S2: A data analysis module is used to analyze physiological parameters and identify potential signs of drug complications. This module uses complex algorithms and statistical methods to process data collected from patients to identify abnormal patterns that may be related to drug treatment. This includes but is not limited to trend analysis, outlier detection, and comparison with historical data. For example, if a child develops an abnormally high temperature and heart rate during antibiotic treatment, the system will automatically mark these changes as potential signs of adverse drug reactions. In addition, the data analysis module is able to combine the patient's medical history and personal information such as age, weight, allergy history, etc. for a comprehensive assessment, thereby improving recognition accuracy and sensitivity;

[0063] S3: Through the warning generation module, when the data analysis module detects signs of drug complications, a warning signal is generated. Once the data analysis module identifies any abnormal situation, the warning generation module will immediately trigger an alarm to notify medical staff to take necessary intervention measures. These alarms can be in the form of sound prompts, visual warnings, or notifications sent through mobile applications. For example, if the system detects that a child has an unusual arrhythmia after receiving a certain anti-epileptic drug, it will not only display a red warning sign on the monitoring screen, but also send an emergency text message reminder to the doctor in charge of the child;

[0064] S4: A cloud database is used to store physiological parameters and corresponding analysis results, and the complication prediction model is continuously optimized through machine learning algorithms. All collected data and their analysis results are securely stored in a cloud database for long-term tracking and retrospective research. More importantly, this database also supports the application of machine learning technology to improve the accuracy of the prediction model by continuously learning new cases. For example, over time, the system can identify the association between specific drug combinations and certain types of complications, thereby helping doctors better prevent future adverse events.

[0065] Through the above steps, the problem of "how to achieve accurate monitoring and early warning of pediatric drug complications" can be solved. The entire system is designed to improve the safety and effectiveness of pediatric drug treatment through real-time monitoring, intelligent analysis and instant feedback mechanisms. With the accumulation of more data and continuous optimization of algorithms, the system is expected to become an indispensable tool in pediatric clinical practice and provide strong support for protecting children's health.

[0066] Furthermore, the step of obtaining physiological parameters of pediatric patients in real time includes:

[0067] S5: Real-time monitoring of physiological signals of pediatric patients based on sensor arrays, including body temperature, heart rate and blood pressure, which involves installing a series of non-invasive sensors on pediatric patients, which can continuously monitor and record key physiological parameters such as body temperature, heart rate and blood pressure. For example, a skin patch-type temperature sensor can be used to monitor body temperature changes, a heart rate belt or smart watch can be used to monitor heart rate, and a blood pressure cuff can be used to monitor blood pressure. These sensors are usually designed to be very small and comfortable so that they can be worn for a long time without causing discomfort to the patient;

[0068] S6: sending the physiological signals to a data processing unit via wireless transmission technology. Once the sensors collect the physiological signals, they transmit the signals to the data processing unit in real time via wireless communication technology such as Bluetooth, Wi-Fi or a dedicated medical-grade wireless network. The data processing unit can be a server located inside the hospital or a cloud server to ensure data security and privacy. For example, the sensor can be configured to send an update to the data processing unit every minute to ensure that doctors and nurses can obtain the latest patient information in a timely manner.

[0069] S7: Sampling the physiological signal using a preset sampling frequency F, wherein the sampling frequency F needs to satisfy Shannon sampling theorem to ensure that the signal is not distorted. In order to accurately capture and analyze changes in physiological signals, data acquisition needs to be performed at a certain sampling frequency. According to Shannon sampling theorem, the sampling frequency should be at least twice the highest frequency component of the signal to avoid aliasing. For example, if the highest frequency component in the heart rate signal is 5 Hz, the sampling frequency should be set to at least 10 Hz to ensure signal integrity.

[0070] S8: Convert the sampled physiological signals into digital signals and upload them to the data analysis module. In the data processing unit, the analog physiological signals are converted into digital signals for further processing and analysis. This process usually involves the application of an analog-to-digital converter ADC, which can convert continuous analog signals into discrete digital signals. Subsequently, these digital signals are uploaded to the data analysis module, which is responsible for executing data analysis algorithms to identify patterns or abnormalities that may be related to drug complications. For example, the data analysis module may detect a sudden increase in heart rate and mark it as a potential drug side effect.

[0071] Furthermore, the step of real-time monitoring of physiological signals of pediatric patients based on the sensor array includes:

[0072] S9: Based on the temperature sensor on the wearable device, the skin surface temperature of the pediatric patient is measured in real time. If the skin surface temperature is greater than the normal body temperature range, the abnormality is recorded for conditional judgment. In the present invention, the pediatric drug complication monitoring system includes a temperature sensor integrated in the wearable device, which is used to continuously monitor the skin surface temperature T of the pediatric patient. When the measured skin surface temperature T exceeds the preset normal body temperature range, the system will automatically record the abnormality and trigger the corresponding conditional judgment mechanism to evaluate whether further measures need to be taken;

[0073] S10: using a heart rate sensor to monitor the heart rate of the pediatric patient. If the heart rate is greater than the normal heart rate range, the abnormality is recorded for conditional judgment. In addition, the system is also equipped with a heart rate sensor for real-time monitoring of the heart rate HR of the pediatric patient. Once the monitored heart rate HR exceeds the normal heart rate range, the system will also record the abnormality and determine the subsequent operation according to the preset conditional judgment mechanism.

[0074] S11: using a blood pressure sensor to measure the systolic and diastolic blood pressure of a pediatric patient. If the systolic and diastolic blood pressure are greater than the normal blood pressure range, the abnormality is recorded for conditional judgment. The pediatric drug complication monitoring system also includes a blood pressure sensor for measuring the systolic blood pressure SBP and diastolic blood pressure DBP of a pediatric patient. If the monitored blood pressure value exceeds the normal blood pressure range, the system will record the abnormal data and determine whether further action needs to be taken according to a preset conditional judgment mechanism.

[0075] S12: Compare the above abnormal records with the normal physiological parameter range to determine whether further processing is required. Finally, the system compares all the above abnormal records with the preset normal physiological parameter range. If any physiological indicator is found to deviate from the normal range, the system will automatically start the corresponding alarm or notification function according to the preset rules and processes, so as to promptly remind medical staff to pay attention to and deal with potential health problems.

[0076] Furthermore, the temperature sensor on the wearable device measures the skin surface temperature of the pediatric patient in real time. If the skin surface temperature is greater than the normal body temperature range, the step of recording the abnormality and making conditional judgment includes:

[0077] S13: Obtaining the skin surface temperature of a pediatric patient by a temperature sensor, which involves integrating a temperature sensor into a wearable device that fits tightly against the skin of the pediatric patient to ensure accurate measurement of the skin surface temperature. The temperature sensor continuously monitors and records temperature data, which is then used to assess the body temperature status of the pediatric patient;

[0078] S14: Adjust the normal temperature range based on the age of the pediatric patient A. The system automatically adjusts the normal temperature range according to the age of the pediatric patient. Specifically, for infants under 1 year old, the normal temperature range is set to 5°C to 37.5°C; and for children 1 year old and above, the normal temperature range is set to 36.0°C to 37.0°C. This adjustment is necessary because the normal temperature range of children of different ages is different;

[0079] S15: If the skin surface temperature exceeds the normal body temperature range, the abnormality is recorded. The system will continuously compare the measured skin surface temperature with the normal body temperature range set according to age. Once the skin surface temperature is detected to be beyond the normal range, the system will automatically record the abnormality and mark it as requiring further attention.

[0080] S16: Send the abnormal record to the data analysis module for subsequent processing. Once the abnormal situation is recorded, the system will immediately send this information to the data analysis module, which is responsible for analyzing the abnormal data to determine whether further action is needed, such as notifying medical staff or initiating other monitoring measures, which helps to timely detect and respond to abnormal changes in body temperature that may be caused by drugs.

[0081] Furthermore, the step of sending the abnormal record to the data analysis module for subsequent processing includes:

[0082] S17: Classify the received abnormal records according to timestamps, patient information, etc., and store them in a database;

[0083] S18: Check and remove incomplete, duplicate or invalid records, and organize temperature values ​​and patient information into a unified format for analysis;

[0084] S19: Perform statistical analysis using formula F 异常 =A 异常 / N 异常 To calculate the frequency of abnormal body temperature, where F 异常 Indicates abnormal frequency, A 异常 Indicates the number of abnormal records, N 异常 Indicates the total number of records, identifies the proportion of patients with abnormalities, analyzes the distribution of abnormal records by age group, and identifies high-risk groups; the system continuously monitors the skin surface temperature T of pediatric patients and compares it with the normal body temperature range set according to age. If the measured skin surface temperature T exceeds the set normal body temperature range, the system will record this abnormality. This step can be achieved by collecting body temperature data in real time through sensors and comparing these data with the preset normal range. Once an abnormality is found, the system will trigger an abnormal recording mechanism, such as generating an alarm, sending a notification to medical staff, etc.;

[0085] S20: Perform trend analysis to evaluate the temperature change trend of patients within a certain time range and compare the abnormal record changes in different time periods, such as daily average, weekly average, monthly average, etc.

[0086] Through the above steps, the pediatric drug complications monitoring system can effectively adjust the normal body temperature range according to the age of pediatric patients, and timely monitor and record abnormal body temperature, thereby helping medical staff to better manage patients' health conditions.

[0087] Further, the step of analyzing the physiological parameters and identifying potential signs of drug complications includes:

[0088] S21: Preliminary screening of the physiological parameters based on the preset physiological parameter threshold ranges. This process is completed based on the preset physiological parameter threshold ranges. For example, normal range values ​​are set for indicators such as heart rate and blood pressure. If a physiological parameter exceeds these thresholds, it is marked as abnormal data, thereby entering the next step of detailed analysis. For example, assuming that the heart rate range of a normal child is 60 to 100 beats per minute, if the monitored heart rate is lower than 60 or higher than 100, it will be considered abnormal;

[0089] S22: Perform trend analysis on the screened physiological parameters to identify abnormal change trends. This step aims to identify whether the change trend of these abnormal data conforms to a certain pattern. For example, the heart rate measured several times in a row shows an upward trend. This trend analysis can be achieved through statistical methods or machine learning algorithms to determine whether the trend of abnormal changes is persistent or periodic.

[0090] S23: Based on the matching degree between the abnormal change trend and the known drug complication characteristics, the complication risk level is evaluated. In this step, the system compares the identified abnormal trend with the known drug complication characteristics in the database to determine whether the current patient has a risk of a specific drug complication. For example, if the continuously monitored heart rate increase trend matches a known drug side effect, the system will consider that there is a high risk of complications.

[0091] S24: When the assessed risk level exceeds the preset threshold, the data analysis module determines that there are potential signs of drug complications and triggers the corresponding alarm mechanism. For example, if the above-mentioned upward trend in heart rate is highly consistent with a certain drug side effect and the risk level reaches or exceeds the preset high-risk threshold, the system will automatically send a warning message to medical staff, prompting them to pay attention to possible drug complications of the patient.

[0092] Furthermore, the step of preliminarily screening the physiological parameters based on the preset physiological parameter threshold range includes:

[0093] S25: Obtaining the current physiological parameter value. The system first collects the patient's physiological parameter data in real time through sensors or other monitoring devices. These data may include but are not limited to heart rate, blood pressure, body temperature, etc. For example, for the heart rate parameter, the system will continuously monitor and record the patient's heartbeats;

[0094] S26: Determine whether the physiological parameter value exceeds the normal range. After obtaining the physiological parameter value, the system compares these values ​​with the preset normal range. The normal range is pre-set based on factors such as age and gender. For example, for a 5-year-old child, the normal heart rate range may be 70-110 beats / minute. If the monitored heart rate is lower than 70 beats / minute or higher than 110 beats / minute, the system will determine that the heart rate is abnormal;

[0095] S27: Based on the abnormal judgment result, the abnormal physiological parameter is identified. If the physiological parameter is determined to be abnormal, the system will mark or highlight the parameter in the data record for subsequent processing. For example, when an abnormal heart rate is detected, the system may display the value in red font on the user interface with a warning icon;

[0096] S28: The identified abnormal physiological parameters are passed to the next step for further analysis. Finally, all physiological parameters marked as abnormal will be sent to a higher-level analysis module or directly notified to medical staff. For example, abnormal heart rate data can be sent to a software module specifically used to analyze arrhythmias, or directly notified to the doctor in charge of the child via SMS or in-app messages.

[0097] Furthermore, the step of identifying abnormal physiological parameters based on the abnormal judgment result includes:

[0098] S29: For each physiological parameter marked as abnormal, record its abnormal state. The system continuously collects data from sensors, which represent the vital signs of child patients, such as heart rate, blood pressure, etc. Once the monitored physiological parameters exceed the normal range, the system will automatically mark it as abnormal and record the time point when the parameter is in the abnormal state. For example, if a child's body temperature exceeds 38℃, the system will mark it as abnormal and record the event.

[0099] S30: Calculate the ratio of the number of abnormal physiological parameters to the total monitored parameters, the formula is: R = N 异常 / N 总 , where R represents the ratio, N 异常 Represents the number of abnormal physiological parameters, N 总Indicates the total number of monitored parameters. The system further analyzes these abnormal marks, counts the number of all physiological parameters marked as abnormal, and calculates the proportion of these abnormal parameters to all monitored parameters. For example, at a certain moment, if the system monitors 10 physiological parameters, of which 6 parameters are marked as abnormal, the abnormal proportion is 60%;

[0100] S31: Compare the abnormal ratio with a preset threshold to determine whether further analysis is needed. The system compares the calculated abnormal ratio with a preset threshold, such as 50%. If the abnormal ratio reaches or exceeds this threshold, the system determines that there are multiple abnormal parameters and triggers a more in-depth trend analysis. For example, if the abnormal ratio is 60%, that is, it exceeds the threshold of 50%, the system will automatically enter the next trend analysis process;

[0101] S32: A judgment is made based on the ratio and a preset abnormal ratio threshold. If the ratio is not less than the abnormal ratio threshold, it is considered that there are multiple abnormal parameters, and the trend analysis step is entered. Once it is confirmed that there are multiple abnormal parameters, the system will perform a trend analysis on the historical data of these parameters to identify potential deterioration trends or patterns. For example, if the child's body temperature continues to rise and the heart rate also increases abnormally in several consecutive measurements, the system may prompt the doctor to pay attention to possible risks of serious complications and recommend appropriate intervention measures.

[0102] Furthermore, the trend analysis step includes:

[0103] S33: by collecting and collating physiological parameter data marked as abnormal;

[0104] S34: Select an appropriate trend analysis method. If there are multiple abnormal parameters, perform trend analysis. This step involves using historical data to analyze the changing trends of abnormal parameters over time to help predict possible problems in the future and take preventive measures. Trend analysis can be achieved through statistical methods, machine learning algorithms, or other data analysis tools to provide in-depth insights into the patient's health status.

[0105] S35: Use charts to display abnormal physiological parameters and their trends, such as line charts or bar charts;

[0106] S36: Based on the results of trend analysis, interpret the data and record possible related factors, including environmental changes, psychological state, and treatment measures taken.

[0107] Furthermore, the step of selecting a suitable trend analysis method includes:

[0108] S37: Select the moving average method to smooth the series and identify the long-term trend. The formula is Among them, SMAt is the output result, X is the time series data, n is the window size of the moving average, t is the current time point, and i is the time sequence number;

[0109] S38: Select the linear regression method to identify the rate of change of parameters over time. The formula is Y=a+bZ+c, where Y is the dependent variable, Z is the independent variable, a is the intercept, b is the slope, and c is the error term.

[0110] During operation, when the device is in use, the pediatric drug complication monitoring system achieves effective monitoring and early warning of complications that may occur during drug treatment of pediatric patients through close collaboration between various modules. First, the patient's physiological data acquisition module will obtain the physiological parameters of pediatric patients in real time. These parameters may include but are not limited to key indicators such as heart rate, blood pressure, and blood oxygen saturation. Subsequently, after receiving these physiological parameters, the data analysis module uses a preset algorithm to analyze them and identify any changes or abnormalities that may indicate signs of drug complications. If the data analysis module detects potential signs of drug complications, the early warning generation module will be activated to generate an early warning signal so that medical staff can take necessary intervention measures in time. At the same time, all physiological parameters and their corresponding analysis results will be uploaded to the cloud database for storage. The cloud database is not only used for data storage, but also continuously optimizes the complication prediction model through an integrated machine learning algorithm, thereby improving the accuracy and reliability of the system. With the accumulation of more data, the system can more accurately identify early signs of drug complications and provide strong support for clinical decision-making. The entire process reflects the integrated design concept from data acquisition, analysis and processing to early warning feedback, aiming to provide a safer and more effective drug treatment environment for pediatric patients.

[0111] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A pediatric drug complication monitoring system, characterized in that: include: Data acquisition module, used to obtain physiological parameters of pediatric patients in real time; a data analysis module for analyzing said physiological parameters and identifying potential signs of medication complications; an early warning generation module, configured to generate an early warning signal when the data analysis module detects signs of drug complications; The cloud database is used to store the physiological parameters and corresponding analysis results, and continuously optimize the complication prediction model through machine learning algorithms.

2. The pediatric drug complication monitoring system according to claim 1, characterized in that: The step of obtaining physiological parameters of pediatric patients in real time comprises: Real-time monitoring of physiological signals of pediatric patients based on a sensor array, wherein the physiological signals include body temperature, heart rate and blood pressure; Sending the physiological signal to a data processing unit via wireless transmission technology; The physiological signal is sampled using a preset sampling frequency F, wherein the sampling frequency F needs to satisfy Shannon's sampling theorem to ensure that the signal is not distorted; The sampled physiological signals are converted into digital signals and uploaded to the data analysis module.

3. The pediatric drug complication monitoring system according to claim 2, characterized in that: The step of real-time monitoring of physiological signals of pediatric patients based on a sensor array comprises: The temperature sensor on the wearable device measures the skin surface temperature of the pediatric patient in real time. If the skin surface temperature is greater than the normal body temperature range, the abnormality is recorded for conditional judgment. A heart rate sensor is used to monitor the heart rate of a pediatric patient. If the heart rate is greater than a normal heart rate range, the abnormality is recorded for conditional judgment. Using a blood pressure sensor to measure the systolic and diastolic blood pressure of a pediatric patient, if the systolic and diastolic blood pressure are greater than a normal blood pressure range, the abnormality is recorded for conditional judgment; Compare the above abnormal records with the normal physiological parameter range to determine whether further treatment is required.

4. The pediatric drug complication monitoring system according to claim 3, characterized in that: The step of measuring the skin surface temperature of a pediatric patient in real time based on a temperature sensor on a wearable device, and if the skin surface temperature is greater than a normal body temperature range, recording the abnormality and making a conditional judgment comprises: The skin surface temperature of the pediatric patient is obtained by a temperature sensor; The normal temperature range is adjusted based on the age of the pediatric patient. If the pediatric patient is less than 1 year old, the normal temperature range is set to 5°C to 37.5°C; if the pediatric patient is not less than 1 year old, the normal temperature range is set to 36.0°C to 37.0°C; If the skin surface temperature exceeds the above normal body temperature range, an abnormality is recorded; Send the abnormal records to the data analysis module for subsequent processing.

5. The pediatric drug complication monitoring system according to claim 4, characterized in that: The step of sending the abnormal record to the data analysis module for subsequent processing includes: Classify the received abnormal records according to timestamps, patient information, etc., and store them in the database; Check and remove incomplete, duplicate or invalid records, and organize temperature values ​​and patient information into a unified format for analysis; Statistical analysis was performed using the formula F 异常 =A 异常 / N 异常 To calculate the frequency of abnormal body temperature, where F 异常 Indicates abnormal frequency, A 异常 Indicates the number of abnormal records, N 异常 Indicate the total number of records, identify the proportion of patients with abnormalities, analyze the distribution of abnormal records according to age groups, and find out the high-risk group; Conduct trend analysis to evaluate the temperature change trend of patients within a certain time range and compare the changes in abnormal records in different time periods, such as daily average, weekly average, monthly average, etc.

6. The pediatric drug complication monitoring system according to claim 1, characterized in that: The step of analyzing the physiological parameters and identifying potential signs of drug complications includes: Based on a preset physiological parameter threshold range, preliminarily screening the physiological parameters; Conduct trend analysis on the screened physiological parameters to identify abnormal change trends; Based on the matching degree between the abnormal change trend and the known drug complication characteristics, the complication risk level is assessed; When the risk level exceeds a preset threshold, it is determined that there are signs of potential drug complications.

7. The pediatric drug complication monitoring system according to claim 6, characterized in that: The step of preliminarily screening the physiological parameters based on the preset physiological parameter threshold range includes: Get current physiological parameter values; Determine whether the physiological parameter value exceeds the normal range. If the physiological parameter value is less than the lower limit of the normal range, it is considered abnormal; If the physiological parameter value is greater than the upper limit of the normal range, it is considered abnormal; Based on the abnormal judgment result, abnormal physiological parameters are identified; The identified abnormal physiological parameters are passed to the next step for further analysis.

8. The pediatric drug complication monitoring system according to claim 7, characterized in that: The step of identifying abnormal physiological parameters based on the abnormal judgment result includes: For each physiological parameter marked as abnormal, record its abnormal status; Calculate the ratio of abnormal physiological parameters to the total monitored parameters using the formula: R = N 异常 / N 总 , where R represents the ratio, N 异常 Represents the number of abnormal physiological parameters, N 总 Indicates the total number of monitored parameters; A judgment is made based on the ratio and a preset abnormal ratio threshold. If the ratio is not less than the abnormal ratio threshold, it is considered that there are multiple abnormal parameters, and the trend analysis step is entered.

9. The pediatric drug complication monitoring system according to claim 8, characterized in that: The trend analysis step comprises: Collect and organize physiological parameter data that are marked as abnormal; Select appropriate trend analysis methods; Use graphs and charts to present abnormal physiological parameters and their trends; Based on the results of trend analysis, interpret the data and record possible related factors.

10. The pediatric drug complication monitoring system according to claim 9, characterized in that: The step of selecting a suitable trend analysis method comprises: Select the moving average method to smooth the series and identify the long-term trend. The formula is Among them, SMA t is the output result, X is the time series data, n is the window size of the moving average, t is the current time point, and i is the time sequence number; The linear regression method is selected to identify the rate of change of the parameter over time. The formula is Y = a + bZ + c, where Y is the dependent variable, Z is the independent variable, a is the intercept, b is the slope, and c is the error term.

Images