An abdominal cavity drainage system based on real-time monitoring and intelligent early warning of hemoglobin

Abstract

This invention relates to the field of abdominal drainage technology, and more particularly to an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning. The technical solution includes an abdominal drainage tube, an optical sensing module, a microprocessor module, and a wireless communication module. The microprocessor module is configured to perform moving average filtering and dynamic trend modeling on hemoglobin concentration data; and to trigger early warnings based on preset multi-level alarm conditions. This invention, by real-time and accurate monitoring of hemoglobin concentration in abdominal drainage fluid, combined with intelligent early warning and personalized response mechanisms, overcomes the limitations of traditional manual observation, significantly improving the timeliness and accuracy of bleeding risk identification. Its closed design reduces the risk of infection, while its system integration capabilities optimize medical and nursing workflows, enabling data sharing and remote collaboration. This not only shortens the intervention time window and improves patient prognosis but also frees up nursing resources and improves medical quality, providing a comprehensive and efficient solution for postoperative monitoring.

Description

Technical Field

[0001] This invention relates to the field of abdominal drainage technology, and in particular to an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning. Background Technology

[0002] Pancreaticoduodenectomy (Whipple procedure) is a key surgical procedure for treating diseases such as periampullary cancer and pancreatic cancer. However, the postoperative bleeding complication rate is as high as 8-19%, with approximately 3-5% requiring reoperation due to severe bleeding. Current clinical practice relies primarily on medical staff manually observing the color changes of abdominal drainage fluid every 1-2 hours to assess bleeding, which has significant limitations.

[0003] Subjectivity and lag in human observation

[0004] Color judgment error is large: Clinical studies show that the Kappa value of different medical staff in classifying the color of drainage fluid (clear, light red, bloody) is only 0.42-0.58 (moderate consistency), and the misjudgment rate is even higher at night or in emergency situations. For example, when the hemoglobin concentration of drainage fluid is in the critical range of 1-3 g / dL, the probability of misjudgment is high.

[0005] Early signs of bleeding are difficult to detect: In the early stages of postoperative bleeding, the drainage fluid may only appear slightly cloudy or pale pink, making it difficult to detect with the naked eye. Studies have shown that when hemoglobin concentration rises by 20% from baseline (indicating early bleeding), the rate of missed diagnoses through manual observation is high.

[0006] Delayed intervention: The average time from the onset of bleeding to the discovery of typical bloody drainage by medical staff is 1.8 hours, by which time blood loss may have reached 500-800 ml. A retrospective study of 237 patients after Whipple surgery showed that the mortality rate of patients whose bleeding was discovered more than 2 hours later was 3.2 times that of the group receiving timely intervention (P<0.01).

[0007] Currently, there is a lack of medical devices on the market capable of real-time, continuous monitoring of hemoglobin concentration changes in abdominal drainage fluid. Although optical sensing technology has made progress in the field of blood analysis, existing devices have the following problems: they are not optimized for abdominal drainage scenarios and cannot adapt to dynamic fluid environments and complex component interference;

[0008] The lack of personalized alarm threshold algorithms makes it difficult to distinguish between normal postoperative exudate and active bleeding.

[0009] It is not integrated with the hospital information system, making it impossible to achieve automated early warning and medical resource scheduling.

[0010] In summary, this application proposes an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning. Summary of the Invention

[0011] The purpose of this invention is to address the problem in the current market that there is a lack of medical devices capable of real-time and continuous monitoring of changes in hemoglobin concentration in abdominal drainage fluid, and to propose an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning.

[0012] The technical solution of this invention: an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning, comprising:

[0013] Abdominal drainage tube: equipped with a transparent measuring window for drainage fluid flow;

[0014] Optical sensing module: Non-contactly installed outside the transparent measurement window, including a dual-wavelength light source and a photoelectric detection unit; the dual-wavelength light source includes miniature LEDs with wavelengths of 660nm and 940nm, used to emit light signals to penetrate the drainage fluid, and the photoelectric detection unit receives the transmitted light signals and converts them into electrical signals;

[0015] Microprocessor module: Connected to the optical sensing module, it is used to acquire electrical signals in real time and calculate hemoglobin concentration, perform dynamic trend analysis and multi-level alarm judgment;

[0016] Wireless communication module: connected to the microprocessor module, used to transmit monitoring data and alarm signals to an external terminal; the microprocessor module is configured to: perform moving average filtering and dynamic trend modeling on hemoglobin concentration data; trigger early warnings based on preset multi-level alarm conditions, including:

[0017] Level 1 alarm: Hemoglobin concentration increases by more than 20% within 5 minutes;

[0018] Level 2 alarm: The concentration continues to rise for 10 consecutive minutes with a cumulative increase rate of ≥30%;

[0019] Level 3 alarm: Concentration increase rate ≥ 40% within 3 minutes; Level 3 alarm signals are sent to medical staff terminals in real time via wireless communication module.

[0020] Optionally, the optical sensing module includes:

[0021] Polycarbonate shell: 25mm long × 10mm wide × 5mm thick, with a groove in the center to fit the transparent window of the drainage tube;

[0022] Quick clamp: Located on the back of the housing, used to secure the module to the outside of the drainage tube;

[0023] Dual-wavelength LED light source and photodiode: symmetrically distributed in the groove, with a distance of 3-5mm between the light source and the detector to ensure effective reception of the light signal after it penetrates the drainage fluid.

[0024] Optionally, the microprocessor module is further configured as follows:

[0025] The formula for calculating the rate of increase in hemoglobin concentration is:

[0026]

[0027] in, The current concentration, The concentration at the previous time point. This is a preset time interval;

[0028] Based on rate of change and time series data, a dynamic trend model is used to predict bleeding risk;

[0029] The microprocessor module performs the calculation and trend prediction of the rate of change in hemoglobin concentration, specifically including:

[0030] Dynamic baseline calibration: Based on hemoglobin concentration data from the first 2 hours post-surgery, an individualized baseline concentration is established for each patient. The calculation formula is:

[0031]

[0032] in, This refers to the number of data points within the first 2 hours after surgery (N=12, data sampling interval 10 minutes). For the first Hemoglobin concentration measurements at various time points;

[0033] Rate of change calculation: The data is smoothed using the Exponentially Weighted Moving Average (EWMA) method to eliminate instantaneous fluctuations. The calculation formula is as follows:

[0034]

[0035] in, This is the smoothed hemoglobin concentration value. For smoothing coefficients, This is the original concentration value at the current time point. This is the smoothed concentration value from the previous time point;

[0036] Calculate the rate of change based on the smoothed data:

[0037]

[0038] in, The percentage increase in hemoglobin concentration relative to baseline;

[0039] Dynamic trend model: Time series analysis is used to predict the concentration change in the next 30 minutes. If the percentage change rate of the predicted value relative to the baseline exceeds 50% and meets the alarm conditions, an early warning will be triggered.

[0040] Optionally, the multi-level alarm conditions further include:

[0041] When a Level 3 alarm is triggered, the hospital's emergency medical system is activated simultaneously and the patient's location information is pushed out.

[0042] Alarm levels are linked to the response priority of medical staff; alarms of level two and above require a pop-up notification in the mobile app.

[0043] A multi-level alarm mechanism is linked to clinical response strategies, specifically including:

[0044] Level 1 alarm: A yellow alert is sent to the nurse station terminal, requiring a re-examination of the drainage fluid within 30 minutes;

[0045] Level 2 alarm: A red pop-up window is pushed to the attending physician's mobile device, and the electronic medical record system is activated simultaneously to retrieve the patient's coagulation function data;

[0046] Level 3 alarm: Activates the hospital emergency system, automatically allocates emergency beds and broadcasts the patient's location to the surgical team, while controlling the drainage tube solenoid valve to limit the drainage rate to avoid further blood loss.

[0047] Optionally, the wireless communication module supports dual-mode transmission of Bluetooth Low Energy and Wi-Fi, and integrates medical IoT protocols (such as HL7 and FHIR) for interfacing with the hospital's central monitoring system; the data transmission method of the wireless communication module includes:

[0048] Dual-mode redundant transmission: Prioritizes uploading data to the hospital's private cloud via Wi-Fi; if the signal is lost, it switches to the Bluetooth Mesh network, with relay nodes in the wards taking over the transmission.

[0049] Data encryption protocol: AES-256 encryption is used for drainage fluid data packets, and the patient ID hash value (SHA-3 algorithm) is appended to the packet header to prevent information tampering;

[0050] Offline caching mechanism: The built-in Flash memory caches data for at least 72 hours when the network is disconnected, and automatically resumes transmission after the connection is restored.

[0051] Optionally, the microprocessor module integrates a machine learning model, which generates personalized early warning thresholds by training on historical patient data. The machine learning model is a lightweight convolutional neural network (CNN), and its training and execution process includes:

[0052] Input layer: Receives multidimensional time-series data, including hemoglobin concentration, patient heart rate (obtained from the monitor via Bluetooth), and drainage fluid temperature (measured by a thermocouple embedded in the tube wall).

[0053] Feature extraction layer: Local trend features are extracted using a one-dimensional convolutional kernel (window size = 5 minutes), and long-term dependencies are captured through an LSTM layer;

[0054] Output layer: Generate personalized alarm thresholds The calculation formula is:

[0055]

[0056] in, For the final personalized alarm threshold, This represents the individual patient's baseline concentration. This represents the average risk threshold for a patient population undergoing similar surgeries.

[0057] Incremental learning: After monitoring 100 patients, the model parameters are automatically updated and submitted for doctor review.

[0058] Optionally, the optical sensing module is further equipped with a near-infrared LED light source with a wavelength of 805nm to correct for ambient light interference and improve the accuracy of hemoglobin detection, specifically through the following steps:

[0059] 1) Collect the intensity of transmitted light at multiple wavelengths and calculate the absorbance ratio:

[0060]

[0061] in, : Absorbance of light with a wavelength of 660nm in the drainage fluid; : Absorbance of light with a wavelength of 805nm in the drainage fluid; : Absorbance of light with a wavelength of 940nm in the drainage fluid; , : Absorbance ratio;

[0062] 2) Hemoglobin concentration was inverted based on the ratio-concentration calibration curve;

[0063] The accuracy optimization method for multi-wavelength detection includes:

[0064] Three-wavelength differential absorption detection: Calculation of the normalized absorbance ratio using a combination of 660nm / 940nm / 805nm light sources.

[0065]

[0066] in, , This is the normalized absorbance ratio used to eliminate ambient light interference;

[0067] Dynamic calibration database: Pre-stored data for different hemoglobin concentrations The mapping table uses bilinear interpolation to match real-time data;

[0068] Hemolysis interference exclusion: When If the interference is detected, it is determined to be due to free hemoglobin, and spectral resampling is initiated to remove abnormal data points.

[0069] Optionally, the optical sensing module and the drainage tube are designed as separate units. The sensing module can be disassembled, sterilized, and reused, while the drainage tube is a disposable sterile component. The separate design specifically includes:

[0070] Quick connection interface: The groove of the optical sensing module is embedded with a magnetic alignment pin, and ferromagnetic material rings are embedded on both sides of the transparent window of the drainage tube;

[0071] The outer casing material can withstand high-temperature steam sterilization at 134℃, and the LED light source and photodiode are encapsulated with medical-grade epoxy resin.

[0072] Optionally, the system can be further extended to thoracic surgery pleural drainage or gynecological pelvic drainage scenarios; the cross-departmental extension function is achieved through the following methods:

[0073] Context-based algorithm switching:

[0074] Thoracic surgery modality: Adds detection of neutrophil elastase (calculated using the 940nm / 735nm absorbance ratio) for infection early warning;

[0075] Gynecological mode: Integrating pH sensor data, when pH>7.5 and hemoglobin rises, it indicates a risk of fallopian tube damage.

[0076] Optionally, the optical sensing module integrates an adaptive ambient light compensation algorithm, specifically including:

[0077] Ambient light intensity was periodically collected when no drainage fluid was flowing through it.

[0078] The formula for subtracting ambient light background noise from the real-time signal is as follows:

[0079]

[0080] in, To represent the corrected signal strength; This indicates the measured signal strength; Indicates the background signal strength;

[0081] The ambient light compensation is achieved through a hardware-software collaboration:

[0082] Hardware layer: A narrow-band filter film is deposited on the surface of the photodiode, allowing only 660±5nm, 940±5nm, and 805±5nm light to pass through;

[0083] Software layer:

[0084] Ambient light background signal was acquired at a frequency of 100Hz when there was no drainage fluid flow. ;

[0085] A wavelet denoising algorithm (Daubechies 4 basis functions) is used to separate ambient light from the effective signal. The compensation formula is as follows:

[0086] ( (Time interval between last calibrations)

[0087] in, The corrected effective light intensity signal The original light intensity signal received by the photodiode. Ambient light background intensity The time interval since the last ambient light calibration. Exponential decay factor.

[0088] Compared with the prior art, this application includes at least one of the following beneficial technical effects:

[0089] Overcoming the limitations of traditional manual observation, this method enables continuous dynamic monitoring of hemoglobin concentration in peritoneal drainage fluid, allowing for timely detection of early signs of bleeding. Through multi-wavelength differential absorption technology and a hemolysis interference exclusion algorithm, it significantly improves detection accuracy and reduces interference from ambient light and non-target substances.

[0090] Personalized alarm thresholds are established based on machine learning models to automatically identify bleeding risk trends and avoid missed diagnoses and overtreatment. A multi-level alarm mechanism is linked to the hospital information system to achieve fully automated response from notification to emergency resource dispatch.

[0091] Reducing the frequency of manual observation frees up nursing resources for more critical patient care tasks. Digital recording and analysis capabilities support clinical decision-making and improve the efficiency of medical quality management.

[0092] The closed design avoids frequent contact with the drainage system, reducing the chance of iatrogenic infection. The modular structure facilitates disinfection and reuse, complying with hospital infection control standards. It seamlessly integrates with existing hospital information systems, enabling the integration and sharing of patient data. It provides early warning of bleeding risks, shortens the intervention window, and reduces the incidence of postoperative complications. Objective data supports the development of personalized treatment plans, promoting rapid patient recovery.

[0093] This invention overcomes the limitations of traditional manual observation by real-time and precise monitoring of hemoglobin concentration in peritoneal drainage fluid, combined with intelligent early warning and personalized response mechanisms. It significantly improves the timeliness and accuracy of bleeding risk identification. Its closed design reduces the risk of infection, while its system integration capabilities optimize medical and nursing workflows, enabling data sharing and remote collaboration. This not only shortens the intervention time window and improves patient prognosis, but also frees up nursing resources and improves the quality of medical care, providing a comprehensive and efficient solution for postoperative monitoring. Attached Figure Description

[0094] Figure 1 This is a schematic diagram of an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning. Detailed Implementation

[0095] The technical solution of the present invention will be further described below with reference to specific embodiments.

[0096] Example 1

[0097] like Figure 1 As shown, this invention proposes an abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning, comprising an abdominal drainage tube, an optical sensing module, a microprocessor module, and a wireless communication module. Each component is described in detail below.

[0098] 1. In this embodiment, the abdominal drainage tube is provided with a transparent measuring window for the flow of drainage fluid.

[0099] II. The optical sensing module is non-contactly installed outside the transparent measurement window, and includes a dual-wavelength light source and a photoelectric detection unit; the dual-wavelength light source includes miniature LEDs with wavelengths of 660nm and 940nm, used to emit light signals to penetrate the drainage fluid; the photoelectric detection unit receives the transmitted light signals and converts them into electrical signals; the optical sensing module includes:

[0100] Medical-grade high-transparency polycarbonate shell: 25mm long × 10mm wide × 5mm thick, with a groove in the center to fit the transparent window of the drainage tube;

[0101] Quick clamp: Located on the back of the housing, used to secure the module to the outside of the drainage tube;

[0102] Dual-wavelength LED light source and photodiode: symmetrically distributed in the groove, with a distance of 3-5mm between the light source and the detector to ensure effective reception of the light signal after it penetrates the drainage fluid.

[0103] In this embodiment, the optical sensing module is further equipped with a near-infrared LED light source with a wavelength of 805nm to correct for ambient light interference and improve the accuracy of hemoglobin detection. This is achieved through the following steps:

[0104] 1) Collect the intensity of transmitted light at multiple wavelengths and calculate the absorbance ratio:

[0105]

[0106] in, : Absorbance of light with a wavelength of 660nm in the drainage fluid; : Absorbance of light with a wavelength of 805nm in the drainage fluid; : Absorbance of light with a wavelength of 940nm in the drainage fluid; , : Absorbance ratio;

[0107] 2) Hemoglobin concentration was inverted based on the ratio-concentration calibration curve;

[0108] The accuracy optimization method for multi-wavelength detection includes:

[0109] Three-wavelength differential absorption detection: Calculation of the normalized absorbance ratio using a combination of 660nm / 940nm / 805nm light sources.

[0110]

[0111] in, , This is the normalized absorbance ratio used to eliminate ambient light interference;

[0112] Dynamic calibration database: Pre-stored data for different hemoglobin concentrations The mapping table uses bilinear interpolation to match real-time data;

[0113] Hemolysis interference exclusion: When If the interference is detected, it is determined to be due to free hemoglobin, and spectral resampling is initiated to remove abnormal data points.

[0114] It is worth noting that the optical sensing module and the drainage tube are designed as separate units. The sensing module can be disassembled, sterilized, and reused, while the drainage tube is a disposable sterile component. The specific features of this separate design include:

[0115] Quick-connect interface: The groove of the optical sensing module is embedded with a magnetic alignment pin, and ferromagnetic material rings are embedded on both sides of the transparent window of the drainage tube for millimeter-level precision self-alignment;

[0116] The outer shell material can withstand high-temperature steam sterilization at 134℃, and the LED light source and photodiode are encapsulated with medical epoxy resin to ensure that the light transmittance decreases by less than 5% after 100 sterilization cycles.

[0117] In addition, the optical sensing module integrates an adaptive ambient light compensation algorithm, specifically including:

[0118] Ambient light intensity was periodically collected when no drainage fluid was flowing through it.

[0119] The formula for subtracting ambient light background noise from the real-time signal is as follows:

[0120]

[0121] in, To represent the corrected signal strength; This indicates the measured signal strength; Indicates the background signal strength;

[0122] Ambient light compensation is achieved through a combination of hardware and software:

[0123] Hardware layer: A narrow-band filter film is deposited on the surface of the photodiode, allowing only 660±5nm, 940±5nm, and 805±5nm light to pass through;

[0124] Software layer:

[0125] Ambient light background signal was acquired at a frequency of 100Hz when there was no drainage fluid flow. ;

[0126] A wavelet denoising algorithm (Daubechies 4 basis functions) is used to separate ambient light from the effective signal. The compensation formula is as follows:

[0127] ( (Time interval between last calibrations)

[0128] in, The corrected effective light intensity signal The original light intensity signal received by the photodiode. Ambient light background intensity The time interval since the last ambient light calibration. Exponential decay factor.

[0129] The optical sensing module utilizes multi-wavelength light sources (660nm / 940nm / 805nm) and a non-contact design to achieve accurate real-time detection of hemoglobin concentration in drainage fluid. Narrow-band filters and ambient light compensation algorithms effectively eliminate external interference, while hemolysis interference recognition technology ensures the stability and accuracy of signal acquisition. The modular structure allows for quick installation into the transparent window of the drainage tube without invasive procedures, reducing the risk of infection.

[0130] III. The microprocessor module is connected to the optical sensing module for real-time acquisition of electrical signals and calculation of hemoglobin concentration, performing dynamic trend analysis and multi-level alarm judgment; the microprocessor module is further configured as follows:

[0131] The formula for calculating the rate of increase in hemoglobin concentration is:

[0132]

[0133] in, The current concentration, The concentration at the previous time point. This is a preset time interval;

[0134] Based on rate of change and time series data, a dynamic trend model is used to predict bleeding risk;

[0135] The microprocessor module performs the calculation and trend prediction of the rate of change in hemoglobin concentration, specifically including:

[0136] Dynamic baseline calibration: Based on hemoglobin concentration data from the first 2 hours post-surgery, an individualized baseline concentration is established for each patient. The calculation formula is:

[0137]

[0138] in, This refers to the number of data points within the first 2 hours after surgery (N=12, data sampling interval 10 minutes). For the first Hemoglobin concentration measurements at various time points;

[0139] Rate of change calculation: The data is smoothed using the Exponentially Weighted Moving Average (EWMA) method to eliminate instantaneous fluctuations. The calculation formula is as follows:

[0140]

[0141] in, This is the smoothed hemoglobin concentration value. For smoothing coefficients, This is the original concentration value at the current time point. This is the smoothed concentration value from the previous time point;

[0142] Calculate the rate of change based on the smoothed data:

[0143]

[0144] in, The percentage increase in hemoglobin concentration relative to baseline;

[0145] Trend prediction model: Time series analysis (ARIMA model) is used to predict concentration changes over the next 30 minutes. If the predicted value exceeds the baseline by 50% and meets alarm conditions, an early warning is triggered. The microprocessor module integrates dynamic baseline calibration, exponentially weighted smoothing filtering, and time series prediction algorithms to analyze hemoglobin concentration trends in real time, supporting personalized bleeding risk assessment. Machine learning model (CNN) generates personalized alarm thresholds based on individual patient data, avoiding the limitations of fixed thresholds; multi-level alarm logic (level one / two / three) corresponds to different response strategies, from basic review to emergency activation, achieving tiered early warning and precise intervention. In this embodiment, the microprocessor module is configured to: perform moving average filtering and dynamic trend modeling on hemoglobin concentration data; trigger early warnings based on preset multi-level alarm conditions, including:

[0146] Level 1 alarm: Hemoglobin concentration increases by more than 20% within 5 minutes;

[0147] Level 2 alarm: The concentration continues to rise for 10 consecutive minutes with a cumulative increase rate of ≥30%;

[0148] Level 3 alarm: Concentration increase rate ≥ 40% within 3 minutes; graded alarm signals are sent to medical staff terminals in real time via wireless communication module. The multi-level alarm conditions further include:

[0149] When a Level 3 alarm is triggered, the hospital's emergency medical system is activated simultaneously and the patient's location information is pushed out.

[0150] Alarm levels are linked to the response priority of medical staff; alarms of level two and above require a pop-up notification in the mobile app.

[0151] A multi-level alarm mechanism is linked to clinical response strategies, specifically including:

[0152] Level 1 alarm: A yellow alert is sent to the nurse station terminal, requiring a re-examination of the drainage fluid within 30 minutes;

[0153] Level 2 alarm: A red pop-up window is pushed to the attending physician's mobile device, and the electronic medical record system is activated simultaneously to retrieve the patient's coagulation function data;

[0154] Level 3 alarm: Activates the hospital emergency system, automatically allocates emergency beds and broadcasts the patient's location to the surgical team, while controlling the drainage tube solenoid valve to limit the drainage rate to avoid further blood loss.

[0155] It is worth noting that the microprocessor module integrates a machine learning model, which generates personalized early warning thresholds by training on historical patient data. This machine learning model is a lightweight convolutional neural network (CNN), and its training and execution process includes:

[0156] Input layer: Receives multidimensional time-series data, including hemoglobin concentration, patient heart rate (obtained from the monitor via Bluetooth), and drainage fluid temperature (measured by a thermocouple embedded in the tube wall).

[0157] Feature extraction layer: Local trend features are extracted using a one-dimensional convolutional kernel (window size = 5 minutes), and long-term dependencies are captured through an LSTM layer;

[0158] Output layer: Generate personalized alarm thresholds The calculation formula is:

[0159]

[0160] in, For the final personalized alarm threshold, This represents the individual patient's baseline concentration. This represents the average risk threshold for a patient population undergoing similar surgeries.

[0161] Incremental learning: After monitoring 100 patients, the model parameters are automatically updated and submitted for doctor review.

[0162] IV. The wireless communication module is connected to the microprocessor module to transmit monitoring data and alarm signals to an external terminal; the wireless communication module supports dual-mode transmission of Bluetooth Low Energy and Wi-Fi, and integrates medical IoT protocols (such as HL7, FHIR) for interfacing with the hospital's central monitoring system; the data transmission methods of the wireless communication module include:

[0163] Dual-mode redundant transmission: Prioritizes uploading data to the hospital's private cloud via Wi-Fi; if the signal is lost, it switches to the Bluetooth Mesh network, with relay nodes in the wards taking over the transmission.

[0164] Data encryption protocol: AES-256 encryption is used for drainage fluid data packets, and the patient ID hash value (SHA-3 algorithm) is appended to the packet header to prevent information tampering;

[0165] Offline caching mechanism: The built-in Flash memory caches at least 72 hours of data when the network is offline, and automatically resumes transmission after the connection is restored. The wireless communication module adopts dual-mode redundant transmission (Wi-Fi + Bluetooth Mesh) and medical-grade encryption protocol (AES-256 + SHA-3) to ensure the stability and security of data transmission. The offline caching function ensures that monitoring data is not lost in network outage scenarios and automatically resumes transmission after the connection is restored; it seamlessly integrates with hospital information systems through the HL7 / FHIR protocol, supports remote monitoring and real-time linkage with multiple terminals (medical staff APP, central monitoring, emergency system), and improves medical collaboration efficiency.

[0166] Example 2

[0167] I. System Overall Architecture

[0168] The abdominal drainage system includes an abdominal drainage tube, an optical sensing module, a microprocessor module, a wireless communication module, and an external terminal. The abdominal drainage tube is made of medical-grade silicone, with a 15mm long and 8mm wide transparent measuring window in the middle section and a smooth inner wall to reduce fluid residue; a solenoid valve is integrated downstream, and the microprocessor module controls the on / off state and drainage speed.

[0169] II. Implementation Details of the Optical Sensing Module

[0170] The optical sensing module is held in place by a spring-slider mechanism on the back of the quick-clamping device, positioned outside the transparent window of the drainage tube. A magnetic alignment pin and the ferromagnetic ring of the drainage tube achieve millimeter-level alignment. Inside the medical-grade, highly transparent polycarbonate shell, dual-wavelength LEDs and photodiodes are symmetrically distributed with a 4mm spacing. The light sources emit 660nm, 940nm, and 805nm near-infrared light that penetrates the drainage fluid. The hardware layer uses a narrow-band filter to limit stray light, while the software layer acquires the ambient light background signal at 100Hz when there is no drainage fluid. Background noise is then removed using a wavelet denoising algorithm to ensure accurate acquisition of the transmitted light signal.

[0171] III. Microprocessor Module Data Processing Flow

[0172] Dynamic baseline calibration: Within the first 2 hours post-surgery, hemoglobin concentration data were collected at 10-minute intervals for 12 sets to calculate individualized baseline concentrations.

[0173] in, This refers to the data points collected within the first two hours after surgery. For the first The hemoglobin concentration measurements at each time point were used as the benchmark for subsequent rate of change calculations.

[0174] Signal smoothing and trend analysis: The real-time concentration data was smoothed using the exponentially weighted moving average method (EWMA, α=0.7) to eliminate instantaneous interference such as infusion shock and patient position changes; the smoothed data was analyzed for time series using the ARIMA model to predict the concentration change trend in the next 30 minutes.

[0175] Multi-level alarm triggering logic:

[0176] Level 1 alarm: When the rate of increase in hemoglobin concentration is 20% within 5 minutes ( (20%), send a yellow alert to the nurses' station, prompting a follow-up examination within 30 minutes.

[0177] Level 2 alarm: If the concentration increase rate is ≥30% for 10 consecutive minutes, a red pop-up window will be triggered on the attending physician's mobile device, and coagulation function data (such as platelet count and prothrombin time) will be retrieved from the electronic medical record system simultaneously.

[0178] Level 3 alarm: If the concentration increase rate is ≥40% within 3 minutes, the hospital emergency system will be activated immediately, automatically allocating emergency beds, broadcasting the patient's location to the surgical team, and controlling the solenoid valve to limit the drainage rate to 5ml / min to delay blood loss.

[0179] IV. Wireless Communication and System Integration

[0180] The wireless communication module adopts a dual-mode design of low-power Bluetooth and Wi-Fi. It prioritizes uploading encrypted (AES-256 + SHA-3 hash) monitoring data (including hemoglobin concentration, alarm level, and patient ID) to the hospital's private cloud via Wi-Fi. In case of signal interruption, it switches to a Bluetooth Mesh network for transmission via ward relay nodes. When the network is down, the built-in Flash memory caches 72 hours of data, automatically resuming transmission upon reconnection. Through medical IoT protocols such as HL7 and FHIR, it interfaces in real-time with the hospital's central monitoring system and electronic medical record system, enabling data sharing and coordinated response.

[0181] V. Hardware Design and Reuse Mechanism

[0182] The optical sensing module and drainage tube adopt a separate structure: the sensing module shell can withstand high-temperature steam sterilization at 134℃, and the LED light source and photodiode are potted with medical epoxy resin. After 100 sterilization cycles, the light transmittance decreases by less than 5%, and it is reusable; the drainage tube is a disposable sterile component, reducing the risk of infection. The quick clamp supports drainage tubes with a diameter of 6-12mm, and the spring slider self-adaptive clamping meets the drainage tube specifications of different departments such as general surgery, thoracic surgery, and gynecology.

[0183] VI. Cross-departmental application expansion

[0184] Thoracic Surgery Mode: When the object of detection is pleural drainage fluid, the system automatically switches to the thoracic surgery algorithm, calculates the concentration of neutrophil elastase by the absorbance ratio of 940nm / 735nm, combines it with changes in hemoglobin concentration, and simultaneously warns of bleeding and infection risks.

[0185] Gynecological mode: An integrated pH sensor monitors the pH value of pelvic drainage fluid. When the pH is greater than 7.5 and the hemoglobin concentration increases, it indicates possible fallopian tube damage and triggers a targeted examination process.

[0186] VII. Machine Learning Model Training and Update

[0187] The microprocessor module incorporates a lightweight CNN model. Input data includes time-series data of hemoglobin concentration, Bluetooth-synchronized heart rate signals, and drainage fluid temperature measured by thermocouples on the tube wall. The model is trained using historical patient data to generate personalized alarm thresholds. in, For the final personalized alarm threshold, This represents the individual patient's baseline concentration. (This is the average risk threshold for a patient group undergoing similar surgeries). After monitoring 100 patients, the model parameters are automatically updated and pushed to the doctor's terminal for review, ensuring that the threshold is suitable for different patient groups.

[0188] VIII. Work Process

[0189] Post-operatively, a drainage tube is inserted into the patient's abdominal cavity and connected to an external drainage bag. An optical sensing module is fixed to a transparent window using a quick-release clamp. A dual-wavelength light source emits light signals that penetrate the drainage fluid. A photodiode receives the transmitted light and converts it into an electrical signal, which is then transmitted to a microprocessor after ambient light compensation. The microprocessor calculates hemoglobin concentration in real time, performing moving average filtering, EWMA smoothing, and dynamic baseline calibration, and predicts trends using an ARIMA model. When the concentration change meets alarm criteria, a corresponding alarm signal is sent to an external terminal via a wireless communication module, triggering a medical response or emergency procedure.

[0190] The above specific embodiments are merely several optional embodiments of the present invention. Based on the technical solutions of the present invention and the relevant teachings of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

Claims

1. An abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning, characterized in that, include: Abdominal drainage tube: equipped with a transparent measuring window for drainage fluid flow; Optical sensing module: Non-contactly installed outside the transparent measurement window, including a dual-wavelength light source and a photoelectric detection unit; the dual-wavelength light source includes miniature LEDs with wavelengths of 660nm and 940nm, used to emit light signals to penetrate the drainage fluid, and the photoelectric detection unit receives the transmitted light signals and converts them into electrical signals; Microprocessor module: connected to the optical sensing module, used for real-time acquisition of electrical signals and calculation of hemoglobin concentration, performing dynamic trend analysis and multi-level alarm judgment; the microprocessor module is further configured as follows: The formula for calculating the rate of increase in hemoglobin concentration is: in, The current concentration, The concentration at the previous time point. This is a preset time interval; Based on rate of change and time series data, the risk of bleeding is predicted using a dynamic trend model. The microprocessor module performs the calculation and trend prediction of the rate of change in hemoglobin concentration, specifically including: Dynamic baseline calibration: Hemoglobin concentration data is measured in advance to establish individualized baseline concentrations for each patient. The calculation formula is: in, This refers to the data points collected within the first two hours after surgery. For the first Hemoglobin concentration measurements at various time points; Rate of change calculation: The data is smoothed using the exponentially weighted moving average method to eliminate instantaneous fluctuations. The calculation formula is as follows: in, This is the smoothed hemoglobin concentration value. For smoothing coefficients, This is the original concentration value at the current time point. This is the smoothed concentration value from the previous time point; Calculate the rate of change based on the smoothed data: in, The percentage change in hemoglobin concentration relative to baseline; Dynamic trend model: Time series analysis is used to predict the concentration change in the next 30 minutes. If the percentage change rate of the predicted value relative to the baseline exceeds 50% and meets the alarm conditions, an early warning will be triggered. Wireless communication module: connected to the microprocessor module, used to transmit monitoring data and alarm signals to an external terminal; the microprocessor module is configured to: perform moving average filtering and dynamic trend modeling on hemoglobin concentration data; trigger early warnings based on preset multi-level alarm conditions, including: Level 1 alarm: Hemoglobin concentration increases by more than 20% within 5 minutes; Level 2 alarm: The concentration continues to rise for 10 consecutive minutes with a cumulative increase rate of ≥30%; Level 3 alarm: Concentration increase rate ≥ 40% within 3 minutes; Level 3 alarm signals are sent to medical staff terminals in real time via wireless communication module.

2. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The optical sensing module includes: The polycarbonate shell has a central groove that fits into the transparent window of the drainage tube; A quick clamp, located on the back of the housing, is used to secure the module to the outside of the drainage tube; Dual-wavelength LED light sources and photodiodes are symmetrically distributed in the groove, with a distance of 3-5mm between the light source and the detector.

3. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The multi-level alarm conditions further include: When a Level 3 alarm is triggered, the hospital's emergency medical system is activated simultaneously and the patient's location information is pushed out. Alarm levels are linked to the response priority of medical staff; alarms of level two and above require a pop-up notification in the mobile app. A multi-level alarm mechanism is linked to clinical response strategies, specifically including: Level 1 alarm: Send a yellow alert to the nurse station terminal and recheck the drainage fluid; Level 2 alarm: A red pop-up window is pushed to the attending physician's mobile device, and the electronic medical record system is activated simultaneously to retrieve the patient's coagulation function data; Level 3 alarm: Activates the hospital emergency system, automatically allocates emergency beds, sends patient location, and simultaneously controls the drainage tube solenoid valve to limit drainage speed.

4. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The wireless communication module supports dual-mode transmission of Bluetooth Low Energy and Wi-Fi, and integrates medical IoT protocols for interfacing with the hospital's central monitoring system; the data transmission method of the wireless communication module includes: Dual-mode redundant transmission: Prioritizes uploading data to the hospital's private cloud via Wi-Fi; if the signal is lost, it switches to the Bluetooth Mesh network, with relay nodes in the wards taking over the transmission. Data encryption protocol: AES-256 encryption is used for drainage fluid data packets, and the patient ID hash value is appended to the packet header to prevent information tampering; Offline caching mechanism: The built-in Flash memory caches data for at least 72 hours when the network is disconnected, and automatically resumes transmission after the connection is restored.

5. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The microprocessor module integrates a machine learning model, which generates personalized early warning thresholds by training on historical patient data. The machine learning model is a lightweight convolutional neural network, and its training and execution process includes: Input layer: Receives multidimensional time-series data, including hemoglobin concentration, patient heart rate, and drainage fluid temperature; Feature extraction layer: Uses one-dimensional convolutional kernels to extract local trend features and captures long-term dependencies through LSTM layers; Output layer: Generate personalized alarm thresholds The calculation formula is: in, For the final personalized alarm threshold, This represents the individual patient's baseline concentration. The average risk threshold for a patient group undergoing the same type of surgery; Incremental learning: After monitoring 100 patients, the model parameters are automatically updated and submitted for doctor review.

6. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The optical sensing module is further equipped with a near-infrared LED light source with a wavelength of 805nm to correct for ambient light interference and improve the accuracy of hemoglobin detection. This is achieved through the following steps: 1) Collect the intensity of transmitted light at multiple wavelengths and calculate the absorbance ratio: in, : Absorbance of light with a wavelength of 660nm in the drainage fluid; : Absorbance of light with a wavelength of 805nm in the drainage fluid; : Absorbance of light with a wavelength of 940nm in the drainage fluid; , : Absorbance ratio; 2) Hemoglobin concentration was inverted based on the ratio-concentration calibration curve; The accuracy optimization method for multi-wavelength detection includes: Three-wavelength differential absorption detection: Calculation of the normalized absorbance ratio using a combination of 660nm / 940nm / 805nm light sources. in, , This is the normalized absorbance ratio used to eliminate ambient light interference; Dynamic calibration database: Pre-stored data for different hemoglobin concentrations The mapping table uses bilinear interpolation to match real-time data; Hemolysis interference exclusion: When If the interference is detected, it is determined to be due to free hemoglobin, and spectral resampling is initiated to remove abnormal data points.

7. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The optical sensing module and the drainage tube are designed as separate units. The sensing module can be disassembled, sterilized, and reused, while the drainage tube is a disposable sterile component. The specific features of this separate design include: Quick connection interface: The groove of the optical sensing module is embedded with a magnetic alignment pin, and ferromagnetic material rings are embedded on both sides of the transparent window of the drainage tube; The outer casing material can withstand high-temperature steam sterilization at 134℃, and the LED light source and photodiode are encapsulated with medical-grade epoxy resin.

8. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The system can be further extended to thoracic surgery pleural drainage or gynecological pelvic drainage scenarios. Its extended applications are achieved through the following methods: Context-based algorithm switching: Thoracic surgery modality: Adds detection of neutrophil elastase for infection early warning; Gynecological mode: Integrating pH sensor data, when pH>7.5 and hemoglobin rises, it indicates a risk of fallopian tube damage.

9. The abdominal drainage system based on real-time hemoglobin monitoring and intelligent early warning according to claim 1, characterized in that, The optical sensing module integrates an adaptive ambient light compensation algorithm, specifically including: Ambient light intensity was periodically collected when no drainage fluid was flowing through it. The formula for subtracting ambient light background noise from the real-time signal is as follows: in, To represent the corrected signal strength; This indicates the measured signal strength; Indicates the background signal strength; The ambient light compensation is achieved through a hardware-software collaboration: Hardware layer: A narrow-band filter film is deposited on the surface of the photodiode to allow light at 660±5nm, 940±5nm, and 805±5nm to pass through; Software layer: Ambient light background signal was acquired at a frequency of 100Hz when there was no drainage fluid flow. ; Wavelet denoising algorithm is used to separate ambient light from effective signal, and the compensation formula is as follows: in, The corrected effective light intensity signal The original light intensity signal received by the photodiode. Ambient light background intensity The time interval since the last ambient light calibration. Exponential decay factor.

Images