Wearable intelligent infusion method and related device

Abstract

The invention discloses a wearable intelligent infusion method and a related device. The method comprises the steps that a code scanning unit is used for pre-scanning a bar code on an infusion bag of an infusion patient to obtain infusion information, and a cloud server recommends an optimal infusion scheme according to historical medical records of the patient, current physiological data and medicine information; the optimal infusion scheme is wirelessly transmitted to a computer and a PDA information receiving system and is displayed to medical staff for confirmation; a medical worker initializes the infusion dripping speed through the dripping speed control unit and monitors the deviation between the actual dripping speed and the target dripping speed in real time to automatically adjust the output of the dripping speed control unit; and monitoring the physiological parameters of the patient by using a multi-parameter physiological monitoring unit, evaluating the deviation between the physiological parameters and the physiological parameter baseline model in real time according to the historical physiological parameters of the patient, and when the deviation exceeds a preset threshold value, judging that the physiological parameters are abnormal and triggering early warning. By monitoring the deviation between the actual dripping speed and the target dripping speed in real time and automatically adjusting the output of the dripping speed control unit, the accurate dripping speed in the infusion process is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a wearable intelligent infusion method and device, and a computing device. Background Art

[0002] Intravenous infusion is used to replenish body fluids, nutrients, and medications. Traditional infusion methods require medical staff to manually adjust the drip rate, which is not only labor-intensive but also prone to inaccurate drip rates, untimely monitoring, and even safety issues. With the aging population and the increasing number of patients with chronic diseases, the demand for efficient, safe, and intelligent infusion equipment is growing. Wearable medical devices offer the possibility of real-time, continuous monitoring of physiological parameters. Combining wearable technology with infusion technology to achieve intelligent infusion is currently a hot research topic in the medical device field.

[0003] Currently, some infusion pumps on the market offer drip rate control, but most simply deliver infusions at a set rate. They lack intelligent infusion plan recommendations and physiological parameter monitoring, making them incapable of tailoring individual patient needs. Furthermore, traditional infusion pumps are typically standalone devices that cannot be integrated with physiological parameter monitoring equipment. Medical staff must manually record and analyze physiological data, which is labor-intensive and error-prone. They also lack remote monitoring and management capabilities, making them difficult to meet the needs of telemedicine.

[0004] To solve the above problems, the present invention proposes a wearable intelligent infusion method, which monitors the deviation between the actual drip rate and the target drip rate in real time and automatically adjusts the output of the drip rate control unit to ensure accurate drip rate during the infusion process. Summary of the Invention

[0005] In view of the above problems, the present invention provides a wearable intelligent infusion method and device, and a computing device.

[0006] According to one aspect of the present invention, a wearable intelligent infusion method is provided, comprising:

[0007] A barcode scanning unit is used to pre-scan the barcode on the infusion bag of the infusion patient to obtain infusion information, and the infusion information is uploaded to the cloud server. The cloud server recommends the optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes pharmacist prescription review, medication risk classification, venipuncture difficulty pre-rating, infusion tool priority level ranking, target drip rate curve and physiological parameter monitoring threshold provided according to a machine learning algorithm; the infusion information includes patient identity information, infusion medication name, drug concentration, dosage, specification, medication method, medication frequency, medication time, prescribing physician, prescription pharmacist, intravenous medication information and related time node information;

[0008] The optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff receives the infusion information and verifies the patient's identity through the PDA; based on the optimal infusion plan, the nurse evaluates the patient and confirms the venipuncture difficulty rating, selects an infusion tool to complete the venipuncture, initializes the infusion drip rate through the drip rate control unit, and uses a PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit;

[0009] A multi-parameter physiological monitoring unit is used to monitor the patient's physiological parameters. A physiological parameter baseline model is established based on the patient's historical physiological parameters to evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and an early warning is triggered; wherein, the physiological parameters include body temperature, heart rate / pulse, respiration, blood pressure, and blood oxygen saturation.

[0010] In an optional manner, the dripping rate control unit uses a peristaltic pump driven by a stepping motor to control the infusion dripping rate;

[0011] There is a proportional relationship between the instantaneous flow rate of the peristaltic pump and the speed of the stepping motor; the required target flow rate is calculated according to the target dripping rate and the number of drops per milliliter, and the target speed is calculated according to the target flow rate and the proportional relationship;

[0012] The speed of the stepper motor is controlled by adjusting the pulse frequency, wherein the controller calculates the required pulse frequency according to the target speed and generates a corresponding pulse signal to drive the stepper motor.

[0013] In an optional manner, the controller uses a sinusoidal S-curve acceleration and deceleration control algorithm to calculate the required pulse frequency according to the target speed;

[0014] The acceleration of the sinusoidal S curve a(t) = A×sin(πt / T), and the speed of the sinusoidal S curve is A is the maximum acceleration and T is the acceleration / deceleration time.

[0015] In an optional manner, the multi-parameter physiological monitoring unit includes:

[0016] The ECG sensor, which contacts the patient's skin through a wearable conductive patch, is used to collect ECG signals in real time and calculate the instantaneous heart rate using the R-wave peak interval in the ECG signals;

[0017] Infrared temperature sensor, integrated into the wristband, measures the patient's surface temperature in a non-contact manner;

[0018] A piezoelectric film-based respiratory sensor detects the patient's respiratory rate by detecting tiny changes in the chest cavity during breathing.

[0019] The non-invasive blood pressure monitoring module inflates and deflates the air bag integrated into the wristband through an air pump;

[0020] The non-invasive blood oxygen saturation module measures the patient's blood oxygen saturation through an optical sensor worn on the wrist or finger.

[0021] In an optional manner, the wearable intelligent infusion device further includes a detachable infusion bag fixing device, which adopts a magnetic connection method to quickly fix and remove the infusion bag;

[0022] Among them, a weight sensor is provided on the infusion bag fixing device, which is used to monitor the weight changes of the infusion bag in real time and transmit it to the cloud server. When an abnormal change in the weight of the infusion bag is detected, an alarm is automatically issued to prompt medical staff to check the infusion equipment.

[0023] In an optional manner, a plurality of sensors are provided inside the pipeline of the wearable intelligent infusion device for real-time monitoring of the fluid state in the infusion pipeline;

[0024] Among them, the multiple sensors include pressure sensors and bubble detection sensors; when abnormal pressure is detected in the infusion pipeline, the drip rate control unit is automatically adjusted to ensure the stability of the infusion; when bubbles are detected in the infusion pipeline, an alarm is automatically issued to prompt medical staff to eliminate the bubbles.

[0025] In an optional manner, the wearable intelligent infusion device is connected to and detached from the replaceable tubing unit by a snap-fit ​​structure or a threaded connection;

[0026] The replaceable tubing unit consists of a silicone hose, a drip bucket, a flow stop clamp, a tubing sensor, and an intravenous needle connected to the patient;

[0027] The pipeline sensor includes an optical drop count sensor integrated under the drip bucket. The optical drop count sensor uses an infrared LED as a light source and identifies drops by detecting changes in light intensity received by a photodiode.

[0028] In an optional manner, one end of the replaceable tubing unit is connected to the patient's vein via a Luer connector, and the other end is connected to the detachable interface of the control module via a snap-fit ​​structure or a threaded connection.

[0029] According to another aspect of the present invention, there is provided a wearable intelligent infusion device, comprising:

[0030] An infusion plan recommendation module is used to use a barcode scanning unit to pre-scan the barcode on the infusion patient's fluid bag to obtain infusion information, and upload the infusion information to a cloud server. The cloud server recommends an optimal infusion plan based on the patient's historical medical history, current physiological data, and drug information based on a pre-trained infusion plan matching model. The optimal infusion plan includes pharmacist prescription review, medication risk classification, venipuncture difficulty pre-rating, infusion tool priority ranking, target drip rate curve, and physiological parameter monitoring threshold provided by a machine learning algorithm; the infusion information includes patient identity information, infusion medication name, drug concentration, dosage, specification, medication method, medication frequency, medication time, prescribing physician, prescription pharmacist, intravenous medication information, and related time node information;

[0031] The intelligent drip rate control module is used to wirelessly transmit the optimal infusion plan to a computer and PDA information receiving system and display it to medical staff for confirmation; the medical staff receives the infusion information and verifies the patient's identity via the PDA; based on the optimal infusion plan, the nurse assesses the patient and confirms the venipuncture difficulty rating, selects an infusion tool to complete the venipuncture, initializes the infusion drip rate via the drip rate control unit, and uses a PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued via the automatic voice alarm unit;

[0032] The parameter monitoring and early warning module is used to monitor the patient's physiological parameters using a multi-parameter physiological monitoring unit, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and triggers an early warning; wherein, the physiological parameters include body temperature, heart rate / pulse, respiration, blood pressure, and blood oxygen saturation.

[0033] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0034] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned wearable intelligent infusion method.

[0035] According to the solution provided by the present invention, a barcode scanning unit is used to pre-scan the barcode on the patient's fluid bag to obtain infusion information, and the infusion information is uploaded to a cloud server. The cloud server recommends an optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes a target drip rate curve and a physiological parameter monitoring threshold; the infusion information includes the drug name, dosage and drip rate range; the optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff initially selects the optimal infusion plan through the drip rate control unit. Initialize the infusion drip rate, and use the PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit; use a multi-parameter physiological monitoring unit to monitor the patient's physiological parameters, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds the preset threshold, it is determined to be a physiological abnormality and trigger an early warning; wherein, the physiological parameters include body temperature, heart rate, respiration and blood pressure. The present invention ensures the accuracy of the drip rate during the infusion process by monitoring the deviation between the actual drip rate and the target drip rate in real time and automatically adjusting the output of the drip rate control unit.

[0036] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0038] Figure 1 A schematic diagram showing a flow chart of a wearable intelligent infusion method according to an embodiment of the present invention is shown;

[0039] Figure 2 A schematic structural diagram of a replaceable piping unit according to an embodiment of the present invention is shown;

[0040] Figure 3 A schematic diagram showing a framework of a wearable intelligent infusion device according to an embodiment of the present invention is shown;

[0041] Figure 4 A schematic structural diagram of a computing device according to an embodiment of the present invention is shown.

[0042] Reference numerals:

[0043] 1. Silicone hose; 2. Optical drop count sensor; 3. Luer connector; DETAILED DESCRIPTION

[0044] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0045] Figure 1 FIG. 1 is a flow chart showing a wearable intelligent infusion method according to an embodiment of the present invention. Specifically, Figure 1 As shown, the following steps are included:

[0046] Step S101: Use a barcode scanning unit to pre-scan the barcode on the infusion bag of the infusion patient to obtain infusion information, and upload the infusion information to a cloud server. The cloud server recommends an optimal infusion plan based on a pre-trained infusion plan matching model and the patient's historical medical history, current physiological data and drug information. The optimal infusion plan includes providing pharmacist prescription review, medication risk classification, venipuncture difficulty pre-rating, infusion tool priority level ranking, target drip rate curve and physiological parameter monitoring threshold according to a machine learning algorithm; the infusion information includes patient identity information, infusion medication name, drug concentration, dosage, specification, medication method, medication frequency, medication time, prescribing doctor, prescription pharmacist, intravenous medication information and related time node information.

[0047] In this embodiment, the infusion information is automatically obtained through the code scanning unit, which improves the efficiency of information entry. The cloud server recommends the optimal infusion plan based on the pre-trained infusion plan matching model, combined with the patient's historical medical history, current physiological data and drug information, to achieve truly personalized infusion.

[0048] Specifically, the barcode scanning unit is a barcode scanner or camera integrated into the wearable device, which can read the barcode on the infusion bag to obtain the infusion information contained therein. The barcode contains information such as the drug name, dosage, production batch number, and expiration date. The barcode scanning unit uploads the obtained infusion information to the cloud server via a wireless network (such as Wi-Fi, Bluetooth, or mobile network). The cloud server stores the patient's medical history data, physiological data, drug information, and a pre-trained infusion plan matching model. The infusion plan matching model establishes a mapping relationship between the infusion plan and patient characteristics by learning from a large amount of historical data. The model's training data includes the patient's historical medical history (diagnosis, medical history, allergy history), the patient's physiological data (age, gender, weight, body temperature, heart rate, blood pressure), drug information (drug name, concentration, dosage, indications, contraindications), and the infusion plan (drip rate, infusion time, infusion frequency, and physiological parameter monitoring thresholds). After receiving the infusion information, the cloud server extracts information such as the drug name and dosage, and inputs it into the infusion plan matching model based on the patient's historical medical history and current physiological data. The infusion plan matching model recommends the optimal infusion plan based on the input information, including a target drip rate curve and physiological parameter monitoring thresholds. The target drip rate curve describes how the drip rate changes over time during the infusion process and is adjusted based on the patient's condition. The cloud server transmits the recommended optimal infusion plan via the wireless network to the computer and PDA information receiving system.

[0049] For example, when a 65-year-old patient with hypertension and diabetes is receiving an infusion, the medical staff uses a code scanning unit to scan the barcode on the infusion bag to obtain the drug name (glucose and sodium chloride injection), dosage (500ml) and drip rate range (20-40 drops / minute). The code scanning unit uploads this information to the cloud server. After receiving the information, the cloud server extracts information such as the drug name and dosage, and combines it with the patient's historical medical history (hypertension, diabetes) and current physiological data (blood pressure 160 / 100mmHg, heart rate 80 times / minute) to input it into the infusion plan matching model. The infusion plan matching model recommends the optimal infusion plan based on the input information.

[0050] Among them, the target drip rate curve is:

[0051] 0-30 minutes: 25 drops / minute

[0052] 30-60 minutes: 30 drops / minute

[0053] 60-90 minutes: 35 drops / minute

[0054] 90-120 minutes: 30 drops / minute

[0055] After 120 minutes: 25 drops / minute

[0056] Physiological parameter monitoring thresholds are:

[0057] Upper limit of blood pressure: 170 / 110 mmHg

[0058] Lower blood pressure limit: 110 / 70 mmHg

[0059] Heart rate limit: 100 beats / minute

[0060] Heart rate lower limit: 60 beats / minute

[0061] The cloud server transmits the above optimal infusion plan to the computer and PDA information receiving system for pharmacists to review and confirm.

[0062] In step S102, the optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff receives the infusion information and verifies the patient's identity through the PDA; based on the optimal infusion plan, the nurse evaluates the patient and confirms the venipuncture difficulty rating, selects an infusion tool to complete the venipuncture, initializes the infusion drip rate through the drip rate control unit, and uses the PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit.

[0063] In this embodiment, the optimal infusion plan is wirelessly transmitted to a computer and PDA, reducing errors in information transmission and saving medical staff time. Manual drip rate adjustment is easily affected by subjective factors, while the PID dynamic drip rate control algorithm can accurately control the infusion drip rate, reduce human error, and ensure the accuracy and safety of the infusion. Real-time monitoring of drip rate deviation, infusion completion, and blockages, and prompt notification of medical staff through voice alarms, enhance the safety of the infusion process.

[0064] For example, for an inpatient requiring an infusion of a specific antibiotic, the doctor will create an infusion plan with a specific drip rate curve. The cloud server matches the doctor's prescription and the patient's medical history to the optimal infusion plan, including the antibiotic name, dosage, and pharmacist approval; a Level II medication risk classification; a Level III venipuncture difficulty pre-rating; a ranking of preferred infusion tools (peripheral intravenous catheters, peripheral intravenous catheters, and standard No. 7 infusion needles); a target drip rate curve (20 drops / minute for the first 30 minutes, 15 drops / minute for the next 60 minutes, and 10 drops / minute for the final 30 minutes); and physiological parameter monitoring thresholds (alarm for heart rate exceeding 120 beats / minute and blood pressure below 90 / 60 mmHg). The plan is transmitted via a wireless network to the nurse's station computer and the nurse's handheld PDA. After confirming the plan on the PDA and verifying the patient's identity, the nurse clicks "Patient Assessment" based on the optimal infusion plan. The nurse then clicks "Infusion Tool Selection" to begin the infusion. After the venipuncture is complete, the nurse clicks "Puncture Successful" on the PDA. The PDA transmits the initial drip rate (20 drops / minute) to the drip rate control unit of the wearable smart infusion device, and the peristaltic pump begins operating at that rate. During the infusion, an optical drop count sensor continuously monitors the actual drip rate and feeds this data back to the controller. If the actual drip rate deviates from the target drip rate by more than 2 drops / minute, a PID algorithm automatically adjusts the peristaltic pump speed to maintain a stable drip rate. If the pressure sensor detects a sudden increase in line pressure during the infusion, indicating a blockage, the voice alarm unit issues a voice prompt, "Line blocked, please check," alerting the nurse to address the issue promptly. When the infusion bag is nearly empty, the weight sensor detects the change in weight, and the voice alarm unit issues a voice prompt, "Infusion is almost complete, please prepare to replace."

[0065] In an optional manner, the dripping rate control unit uses a peristaltic pump driven by a stepping motor to control the infusion dripping rate;

[0066] There is a proportional relationship between the instantaneous flow rate of the peristaltic pump and the speed of the stepping motor; the required target flow rate is calculated according to the target dripping rate and the number of drops per milliliter, and the target speed is calculated according to the target flow rate and the proportional relationship;

[0067] The speed of the stepper motor is controlled by adjusting the pulse frequency, wherein the controller calculates the required pulse frequency according to the target speed and generates a corresponding pulse signal to drive the stepper motor.

[0068] In this embodiment, the peristaltic pump is transported by squeezing the hose, and the liquid only contacts the inner wall of the hose, avoiding contact with other parts of the pump body, reducing the risk of contamination, and ensuring the sterility of the infusion. The speed of the stepper motor is controlled by adjusting the pulse frequency, which is convenient for digital connection with the controller. For example, a certain drug needs to be infused at a rate of 15 drops / minute and the infusion device has 20 drops per milliliter. The flow coefficient of the selected peristaltic pump is 0.5 ml / rev, and the step angle of the stepper motor is 1.8 degrees. Calculation target flow rate = 15 drops / minute / 20 drops / ml = 0.75 ml / min, calculation target speed = 0.75 ml / min / 0.5 ml / rev = 1.5 rpm (RPM), calculation pulse frequency = 360 degrees / rev / 1.8 degrees / step = 200 steps / rev, pulse frequency = 1.5 rpm * 200 steps / rev / 60 seconds / minute = 5Hz. The controller generates a pulse signal with a frequency of 5 Hz and inputs it into the stepper motor driver. The stepper motor driver drives the stepper motor to rotate at a speed of 1.5 rpm, thereby driving the peristaltic pump to deliver the drug at a flow rate of 0.75 ml / min, that is, 15 drops / min.

[0069] In an optional manner, the controller uses a sinusoidal S-curve acceleration and deceleration control algorithm to calculate the required pulse frequency according to the target speed;

[0070] The acceleration of the sinusoidal S curve a(t) = A×sin(πt / T), and the speed of the sinusoidal S curve is A is the maximum acceleration and T is the acceleration / deceleration time.

[0071] In this embodiment, the sinusoidal S-curve offers superior smoothness compared to acceleration and deceleration curves such as trapezoidal and exponential curves. Because the acceleration change is continuous (sine function), the shock and vibration caused by sudden acceleration changes are avoided. In the intelligent infusion system, more precise drip rate control is achieved, preventing patient discomfort caused by drastic fluctuations in infusion rate. It also reduces noise during stepper motor operation caused by sudden acceleration changes.

[0072] Step S103: Use a multi-parameter physiological monitoring unit to monitor the patient's physiological parameters, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate in real time the deviation between the physiological parameters and the physiological parameter baseline model. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and triggers an early warning; wherein, the physiological parameters include body temperature, heart rate / pulse, respiration, blood pressure, and blood oxygen saturation.

[0073] In this embodiment, by establishing a baseline model of the patient's physiological parameters, physiological abnormalities can be detected earlier. Even if the current physiological parameters are still within the normal range, but there are significant deviations from the patient's baseline, timely warnings can be provided. Each patient's physiological parameter baseline model is established based on their historical data, which can avoid misinterpreting physiological fluctuations within the normal range as abnormalities.

[0074] In an optional manner, the multi-parameter physiological monitoring unit includes:

[0075] The ECG sensor, which contacts the patient's skin through a wearable conductive patch, is used to collect ECG signals in real time and calculate the instantaneous heart rate using the R-wave peak interval in the ECG signals;

[0076] Infrared temperature sensor, integrated into the wristband, measures the patient's surface temperature in a non-contact manner;

[0077] A piezoelectric film-based respiratory sensor detects the patient's respiratory rate by detecting tiny changes in the chest cavity during breathing.

[0078] The non-invasive blood pressure monitoring module inflates and deflates the air bag integrated into the wristband through an air pump;

[0079] The non-invasive blood oxygen saturation module measures the patient's blood oxygen saturation through an optical sensor worn on the wrist or finger.

[0080] In this embodiment, non-invasive methods such as wearable conductive patches, infrared body temperature sensors, and piezoelectric films are used to reduce patient discomfort and facilitate monitoring anytime, anywhere, suitable for both inpatients and outpatients.

[0081] In an optional manner, the wearable intelligent infusion device further includes a detachable infusion bag fixing device, which adopts a magnetic connection method to quickly fix and remove the infusion bag;

[0082] Among them, a weight sensor is provided on the infusion bag fixing device, which is used to monitor the weight changes of the infusion bag in real time and transmit it to the cloud server. When an abnormal change in the weight of the infusion bag is detected, an alarm is automatically issued to prompt medical staff to check the infusion equipment.

[0083] In this embodiment, a magnetic connection facilitates quick attachment and removal of the infusion bag by medical personnel, saving time. A weight sensor monitors the weight changes of the infusion bag in real time, deriving the infusion volume and transmitting it to a cloud server, enabling precise monitoring of the infusion volume. When an abnormal weight change in the infusion bag is detected, such as an infusion rate that is too fast or too slow, infusion stopped, or a leak in the bag, an alarm automatically sounds, prompting medical personnel to promptly inspect the infusion equipment and ensure patient safety. For example, the infusion bag fixture utilizes a magnetic connection mechanism comprising a magnet mounted on the fixture and a metal sheet or magnetic material mounted on the bag. This magnetic force securely secures the bag to the fixture. A weight sensor is provided on the infusion bag fixture to monitor the weight changes of the bag in real time. The weight sensor is connected to a data transmission module, which transmits the collected weight data to the cloud server via wireless communication. The cloud server processes and analyzes the weight data, calculating the infusion volume and infusion rate based on the weight change and comparing it with the pre-set infusion plan to determine if any anomalies exist. When it is detected that the infusion volume or infusion speed deviates greatly from the preset plan or the weight changes abnormally, the alarm system is triggered and an alarm is issued through a computer, PDA or wearable smart infusion device to alert medical staff.

[0084] In an optional manner, a plurality of sensors are provided inside the pipeline of the wearable intelligent infusion device for real-time monitoring of the fluid state in the infusion pipeline;

[0085] Among them, the multiple sensors include pressure sensors and bubble detection sensors; when abnormal pressure is detected in the infusion pipeline, the drip rate control unit is automatically adjusted to ensure the stability of the infusion; when bubbles are detected in the infusion pipeline, an alarm is automatically issued to prompt medical staff to eliminate the bubbles.

[0086] In this embodiment, air bubbles are detected to prevent air from entering the patient's body and causing air embolism. Pressure anomalies are detected to determine whether the infusion line is clogged or pressurized, automatically adjusting the drip rate. When pressure anomalies or bubbles are detected, an alarm is issued, prompting medical staff to intervene and reducing potential risks to the patient.

[0087] Specifically, a micro pressure sensor is integrated below the drip bucket of the infusion line or near the patient end to monitor the pressure inside the line in real time and transmit the data to the control module. When the line is blocked, the pressure will increase. The pressure sensor detects the pressure increase, triggers an alarm, and automatically reduces or stops the drip rate. When the line is squeezed, the pressure will decrease. The pressure sensor detects the pressure decrease, triggers an alarm, and automatically adjusts the drip rate. A bubble detection sensor (ultrasonic or optical sensor) is integrated below the drip bucket or at the position of the line to monitor the presence of bubbles in the line in real time and transmit the data to the control module. When bubbles are detected passing through, an alarm is immediately triggered, prompting medical staff to remove the bubbles to prevent air embolism. The data from the pressure sensor and the bubble detection sensor are linked to the drip rate control unit. When the pressure is too high or too low, the drip rate control unit automatically adjusts the speed of the peristaltic pump to maintain a stable drip rate. When bubbles are detected, the rotation of the peristaltic pump is stopped immediately and an alarm is issued. After the bubbles are removed, the infusion is resumed manually or automatically.

[0088] In an optional manner, the wearable intelligent infusion device is connected to and detached from the replaceable tubing unit by a snap-fit ​​structure or a threaded connection;

[0089] The replaceable tubing unit consists of a silicone hose, a drip bucket, a flow stop clamp, a tubing sensor, and an intravenous needle connected to the patient;

[0090] The pipeline sensor includes an optical drop count sensor integrated under the drip bucket. The optical drop count sensor uses an infrared LED as a light source and identifies drops by detecting changes in light intensity received by a photodiode.

[0091] In this embodiment, Figure 2 As shown, the snap-fit ​​structure or threaded connection method reduces the time of replacing the pipeline unit and avoids cross infection between different patients. The optical drop count sensor 2 adopts a non-contact measurement method to avoid direct interference with the dripping liquid.

[0092] Specifically, the wearable smart infusion device is provided with a raised buckle, and a corresponding slot is provided on the replaceable tubing unit. When connecting, align the slot with the buckle and press. When disassembling, press the release button on the buckle to detach. Alternatively, the wearable smart infusion device is provided with a threaded interface, and a corresponding threaded cap is provided on the replaceable tubing unit. When connecting, align the Luer connector with the threaded interface and tighten it clockwise. When disassembling, loosen it counterclockwise. The silicone hose 1 has good biocompatibility and flexibility and is used to connect the infusion bag, drip chamber, and intravenous needle. The stop clamp is used to manually adjust or stop the infusion. The intravenous needle is connected to the patient's vein with a needle (such as a butterfly needle). The intravenous needle is connected to the Luer connector 3 and connected to various intravenous access routes. The photodiode acts as a light receiver and is located on the other side of the drip chamber to receive infrared light. When no drip is passing, the light intensity received by the photodiode is higher. When dripping, the light intensity received by the photodiode decreases due to the refraction and absorption of light by the liquid. By detecting the frequency of the light intensity changes, the frequency of the dripping can be accurately identified and the dripping rate can be calculated. One end of the replaceable tubing unit is connected to the patient's vein via a Luer connector 3, and the other end is connected to the detachable interface of the control module via a snap-fit ​​structure or a threaded connection.

[0093] According to the solution provided by the present invention, a barcode scanning unit is used to pre-scan the barcode on the patient's fluid bag to obtain infusion information, and the infusion information is uploaded to a cloud server. The cloud server recommends an optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes a target drip rate curve and a physiological parameter monitoring threshold; the infusion information includes the drug name, dosage and drip rate range; the optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff initially selects the optimal infusion plan through the drip rate control unit. Initialize the infusion drip rate, and use the PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit; use a multi-parameter physiological monitoring unit to monitor the patient's physiological parameters, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds the preset threshold, it is determined to be a physiological abnormality and trigger an early warning; wherein, the physiological parameters include body temperature, heart rate, respiration and blood pressure. The present invention ensures the accuracy of the drip rate during the infusion process by monitoring the deviation between the actual drip rate and the target drip rate in real time and automatically adjusting the output of the drip rate control unit.

[0094] Figure 3 The schematic diagram of the framework of the wearable intelligent infusion device according to an embodiment of the present invention is shown. The wearable intelligent infusion device includes:

[0095] The infusion plan recommendation module 310 is used to use the barcode scanning unit to pre-scan the barcode on the infusion patient's fluid bag to obtain infusion information, and upload the infusion information to the cloud server. The cloud server recommends the optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on the pre-trained infusion plan matching model, wherein the optimal infusion plan includes a target drip rate curve and physiological parameter monitoring threshold; the infusion information includes the drug name, dosage and drip rate range; the intelligent drip rate control module is used to wirelessly transmit the optimal infusion plan to the computer and PDA information receiving system and display it to the medical staff for confirmation; the medical staff initializes the infusion drip rate through the drip rate control unit, and uses the PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds the preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit;

[0096] The intelligent drip rate control module 320 is used to wirelessly transmit the optimal infusion plan to a computer and PDA information receiving system and display it to medical staff for confirmation; the medical staff receives the infusion information and verifies the patient's identity via the PDA; based on the optimal infusion plan, the nurse assesses the patient and confirms the venipuncture difficulty rating, selects an infusion tool to complete the venipuncture, initializes the infusion drip rate via the drip rate control unit, and uses a PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued via the automatic voice alarm unit;

[0097] The parameter monitoring and early warning module 330 is used to monitor the patient's physiological parameters using a multi-parameter physiological monitoring unit, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and triggers an early warning; wherein, the physiological parameters include body temperature, heart rate / pulse, respiration, blood pressure, and blood oxygen saturation.

[0098] Figure 4 The schematic diagram of the structure of the computing device embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0099] like Figure 4 As shown, the computing device may include: a processor 402 , a communications interface 404 , a memory 406 , and a communication bus 408 .

[0100] Processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other devices, such as client devices or other server network elements. Processor 402 is used to execute program 410, which can specifically perform the relevant steps of the above-mentioned wearable intelligent infusion method embodiment.

[0101] Specifically, the program 410 may include program codes, which include computer operation instructions.

[0102] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in a computing device may be processors of the same type, such as one or more CPUs, or processors of different types, such as one or more CPUs and one or more ASICs.

[0103] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0104] According to the solution provided by the present invention, a barcode scanning unit is used to pre-scan the barcode on the patient's fluid bag to obtain infusion information, and the infusion information is uploaded to a cloud server. The cloud server recommends an optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes a target drip rate curve and a physiological parameter monitoring threshold; the infusion information includes the drug name, dosage and drip rate range; the optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff initially selects the optimal infusion plan through the drip rate control unit. Initialize the infusion drip rate, and use the PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit; use a multi-parameter physiological monitoring unit to monitor the patient's physiological parameters, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds the preset threshold, it is determined to be a physiological abnormality and trigger an early warning; wherein, the physiological parameters include body temperature, heart rate, respiration and blood pressure. The present invention ensures the accuracy of the drip rate during the infusion process by monitoring the deviation between the actual drip rate and the target drip rate in real time and automatically adjusting the output of the drip rate control unit.

[0105] Those skilled in the art will appreciate that modules in the devices of the embodiments may be adaptively modified and deployed in one or more devices different from the embodiments. Modules, units, or components in the embodiments may be combined into a single module, unit, or component, and furthermore, they may be divided into multiple submodules, subunits, or subcomponents. All features disclosed in this specification (including the accompanying claims, abstract, and drawings), as well as all processes or units of any method or device disclosed therein, may be combined in any combination, except where at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that provides the same, equivalent, or similar purpose. Furthermore, those skilled in the art will appreciate that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination. The present invention may be implemented using hardware comprising a number of different elements and using a suitably programmed computer. In a unit claim that lists several means, several of these means may be embodied by the same hardware item. Unless otherwise specified, the steps in the above embodiments should not be understood as limiting the order of execution.

Claims

1. A wearable intelligent infusion method for infusion therapy of inpatients and outpatients, characterized in that: include: A barcode scanning unit is used to pre-scan the barcode on the infusion bag of the infusion patient to obtain infusion information, and the infusion information is uploaded to the cloud server. The cloud server recommends the optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes pharmacist prescription review, medication risk classification, venipuncture difficulty pre-rating, infusion tool priority level ranking, target drip rate curve and physiological parameter monitoring threshold provided according to a machine learning algorithm; the infusion information includes patient identity information, infusion medication name, drug concentration, dosage, specification, medication method, medication frequency, medication time, prescribing physician, prescription pharmacist, intravenous medication information and related time node information; The optimal infusion plan is wirelessly transmitted to a computer and PDA information receiving system and displayed to medical staff for confirmation; the medical staff receives the infusion information and verifies the patient's identity through the PDA; based on the optimal infusion plan, the nurse evaluates the patient and confirms the venipuncture difficulty rating, selects an infusion tool to complete the venipuncture, initializes the infusion drip rate through the drip rate control unit, and uses a PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through the automatic voice alarm unit; A multi-parameter physiological monitoring unit is used to monitor the patient's physiological parameters. A physiological parameter baseline model is established based on the patient's historical physiological parameters to evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and an early warning is triggered; wherein, the physiological parameters include body temperature, heart rate / pulse, respiration, blood pressure, and blood oxygen saturation.

2. The wearable intelligent infusion method according to claim 1, characterized in that: The dripping rate control unit uses a peristaltic pump driven by a stepping motor to control the infusion dripping rate; There is a proportional relationship between the instantaneous flow rate of the peristaltic pump and the speed of the stepping motor; the required target flow rate is calculated according to the target dripping rate and the number of drops per milliliter, and the target speed is calculated according to the target flow rate and the proportional relationship; The speed of the stepper motor is controlled by adjusting the pulse frequency, wherein the controller calculates the required pulse frequency according to the target speed and generates a corresponding pulse signal to drive the stepper motor.

3. The wearable intelligent infusion method according to claim 2, characterized in that: The controller uses a sinusoidal S-curve acceleration and deceleration control algorithm to calculate the required pulse frequency according to the target speed; The acceleration of the sinusoidal S curve a(t) = A×sin(πt / T), and the speed of the sinusoidal S curve is A is the maximum acceleration and T is the acceleration / deceleration time.

4. The wearable intelligent infusion method according to claim 1, characterized in that: The multi-parameter physiological monitoring unit comprises: The ECG sensor, which contacts the patient's skin through a wearable conductive patch, is used to collect ECG signals in real time and calculate the instantaneous heart rate using the R-wave peak interval in the ECG signals; Infrared temperature sensor, integrated into the wristband, measures the patient's surface temperature in a non-contact manner; A piezoelectric film-based respiratory sensor detects the patient's respiratory rate by detecting tiny changes in the chest cavity during breathing. The non-invasive blood pressure monitoring module inflates and deflates the air bag integrated into the wristband through an air pump; The non-invasive blood oxygen saturation module measures the patient's blood oxygen saturation through an optical sensor worn on the wrist or finger.

5. The wearable intelligent infusion method according to claim 1, characterized in that: The wearable intelligent infusion device further includes a detachable infusion bag fixing device, which adopts a magnetic connection method to quickly fix and remove the infusion bag; Among them, a weight sensor is provided on the infusion bag fixing device, which is used to monitor the weight changes of the infusion bag in real time and transmit it to the cloud server. When an abnormal change in the weight of the infusion bag is detected, an alarm is automatically issued to prompt medical staff to check the infusion equipment.

6. The wearable intelligent infusion method according to claim 1, characterized in that: The wearable intelligent infusion device is provided with a plurality of sensors inside the pipeline for real-time monitoring of the fluid status in the infusion pipeline; Among them, the multiple sensors include pressure sensors and bubble detection sensors; when abnormal pressure is detected in the infusion pipeline, the drip rate control unit is automatically adjusted to ensure the stability of the infusion; when bubbles are detected in the infusion pipeline, an alarm is automatically issued to prompt medical staff to eliminate the bubbles.

7. The wearable intelligent infusion method according to claim 1, characterized in that: The wearable intelligent infusion device is connected to and removed from the replaceable tubing unit via a snap-fit ​​structure or a threaded connection; The replaceable tubing unit consists of a silicone hose, a drip bucket, a flow stop clamp, a tubing sensor, and an intravenous needle connected to the patient; The pipeline sensor includes an optical drop count sensor integrated under the drip bucket. The optical drop count sensor uses an infrared LED as a light source and identifies drops by detecting changes in light intensity received by a photodiode.

8. The wearable intelligent infusion method according to claim 7, characterized in that: One end of the replaceable tubing unit is connected to the patient's vein via a Luer connector, and the other end is connected to the detachable interface of the control module via a snap-fit ​​structure or a threaded connection.

9. A wearable intelligent infusion device, characterized in that: include: An infusion plan recommendation module is used to use a barcode scanning unit to pre-scan the barcode on the infusion patient's fluid bag to obtain infusion information, and upload the infusion information to a cloud server. The cloud server recommends an optimal infusion plan based on the patient's historical medical history, current physiological data and drug information based on a pre-trained infusion plan matching model, wherein the optimal infusion plan includes a target drip rate curve and a physiological parameter monitoring threshold; the infusion information includes the drug name, dosage and drip rate range; an intelligent drip rate control module is used to wirelessly transmit the optimal infusion plan to a computer and PDA information receiving system and display it to medical staff for confirmation; the medical staff initializes the infusion drip rate through a drip rate control unit, and uses a PID dynamic drip rate control algorithm to monitor the deviation between the actual drip rate and the target drip rate in real time to automatically adjust the output of the drip rate control unit; wherein, when the drip rate deviation exceeds a preset threshold or the infusion is completed or blocked, a voice alarm is issued through an automatic voice alarm unit; The parameter monitoring and early warning module is used to monitor the patient's physiological parameters using a multi-parameter physiological monitoring unit, establish a physiological parameter baseline model based on the patient's historical physiological parameters, and evaluate the deviation between the physiological parameters and the physiological parameter baseline model in real time. When the deviation exceeds a preset threshold, it is determined to be a physiological abnormality and triggers an early warning; wherein, the physiological parameters include body temperature, heart rate, respiration and blood pressure.

10. A computing device comprising: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the above-mentioned wearable intelligent infusion method.

Images