A multi-point pressure detection and pressure sore early warning system based on flexible pressure sensor

Abstract

The present invention belongs to the field of medical equipment technology, and is specifically a multi-point pressure detection and pressure sore warning system based on a flexible pressure sensor, including a pressure data acquisition module, a pressure data preprocessing module, a communication module, and a host computer. By introducing a regression model constructed by a multi-layer neural network as a threshold adjustment module in the alarm module of the host computer, the pressure threshold and time threshold are calculated in real time, and accurate warning of the pressure warning system is achieved without manual intervention. The present invention can provide personalized services for different patients, specifically higher reliability and adaptability, and effectively prevent and reduce the risk of pressure sores in bedridden patients.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical equipment, and in particular relates to a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor. Background Art

[0002] Pressure sores are a phenomenon in which bedridden patients suffer from long-term local tissue compression, persistent ischemia, hypoxia, and malnutrition, leading to tissue infection, ulceration, and necrosis. It is common in patients who are bedridden or sitting immobile for a long time, especially the elderly and the disabled. The high cost and long course of treatment have brought burdens to both patients and the medical system. How to prevent pressure sores has become a key issue in rehabilitation treatment and nursing.

[0003] Traditional methods of preventing and detecting pressure sores mainly rely on body position changes, regular turning over, and visual inspection. However, these methods all rely on the memory and observation of nursing staff, which can easily lead to problems such as missed or false positives. To solve this problem, some researchers have provided a pressure sore early warning system based on flexible sensors to remind patients to adjust their body positions:

[0004] For example, the Chinese patent application number CN202210922974.X discloses a pressure sore early warning system based on multi-point intelligent pressure detection of the Internet of Things. The system includes a load-bearing module and a support module. Through multi-point shear force and pressure monitoring, the local shear force and pressure can be reduced through autonomous adjustment when abnormal monitoring is detected, thereby avoiding most of the risks of pressure sores. At the same time, in a few cases where autonomous adjustment cannot avoid the risk, an alarm will be issued in time to remind the patient to adjust his body position in time.

[0005] Another example is the "Pressure Monitoring and Alarm Device for Preventing Pressure Ulcers in Surgery" disclosed in the Chinese patent application number CN201721492508.3. The device connects a liquid pressure pad to a pressure sensor. The pressure sensor sends the collected pressure signal to the control module. The control unit performs local display and alarm through the display module and the alarm module, and communicates with the monitoring end through the communication module. The real-time monitoring and alarm function of pressure is realized through the liquid pressure pad.

[0006] However, in the above-mentioned two pressure sore warning systems, the support devices or liquid pressure pads used do not take into account the individual differences between different patients, such as height, weight and body shape, and cannot provide personalized services for different patients. Summary of the invention

[0007] The purpose of the present invention is to provide a multi-point pressure detection and pressure sore warning system based on a flexible pressure sensor to provide personalized services for different patients, with higher reliability and adaptability, and effectively prevent and reduce the risk of pressure sores in bedridden patients.

[0008] To solve the above problem, the present invention adopts the following technical solution:

[0009] A multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor, comprising:

[0010] The pressure data acquisition module is used to collect the pressure data of each part of the monitored object in real time, and generate analog signals to be transmitted to the pressure data preprocessing module; the collected pressure data includes but is not limited to the voltage value and resistance value of the pressure sensors installed in the sacrum, both hips and both heels;

[0011] The pressure data preprocessing module is used to amplify, convert analog-to-digital and calculate the pressure of the received analog signal, and obtain a digital signal to transmit to the communication module;

[0012] Communication module, transmits the received digital signal to the host computer;

[0013] The host computer includes an early warning module, which includes a feature extraction module, a threshold adjustment module and an alarm module; the feature extraction module receives a digital signal, and is used to extract a pressure time domain feature from the received digital signal and transmit it to the threshold adjustment module, wherein the pressure time domain feature is used to characterize the pressure level and change trend of different parts of the patient; the threshold adjustment module is a regression model constructed by a multi-layer neural network, and is used to receive the pressure time domain feature and the initial threshold, and perform adaptive regression calculation on the pressure threshold and time threshold of different parts of different patients according to the pressure time domain feature and the initial threshold, and obtain the pressure threshold and time threshold of each part of the patient and transmit them to the alarm module; an alarm value is set in the alarm module, and when the pressure threshold and time threshold received at a certain part exceed the alarm value, an alarm signal is issued to remind medical staff to immediately adjust the patient's position to reduce pressure.

[0014] Furthermore, the host computer also includes a display module, which includes a preset module and a pressure data spatiotemporal distribution display module;

[0015] The preset module is used to input and store patient personal information and physician experience data to generate an initial threshold value and transmit it to the threshold adjustment module. The patient personal information includes height, weight, and gender.

[0016] The pressure data spatiotemporal distribution display module is connected to the communication module, and is used to receive the digital signal from the communication module, extract the spatial distribution and pressure value of each part of the monitored object from the digital signal, and display it in a thermal map.

[0017] Furthermore, the display module also includes a pressure data table display module, which receives the digital signal from the communication module, extracts the spatial distribution and pressure value of each part of the monitored object from the digital signal, and generates an Excel table to facilitate monitoring by medical staff.

[0018] Furthermore, the alarm signal in the alarm module is given as a reminder in the form of voice broadcast using a voice sensor.

[0019] Furthermore, the multi-layer neural network is composed of an input layer, a fully connected layer, a Drop-out layer, and an output layer connected in sequence.

[0020] The present invention provides a multi-point pressure detection and pressure sore warning system based on a flexible pressure sensor. By introducing a regression model constructed by a multi-layer neural network as a threshold adjustment module in the system, the pressure threshold and time threshold can be calculated in real time without human intervention, thereby achieving accurate warning of the pressure warning system and effectively preventing and reducing the risk of pressure sores in bedridden patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a system block diagram of a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor in an embodiment;

[0022] Figure 2 This is a diagram of an early warning module in a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor in an embodiment;

[0023] Figure 3 This is the schematic diagram of the pressure solving circuit. DETAILED DESCRIPTION

[0024] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] This embodiment provides a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor, such as Figure 1 As shown, a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor includes a pressure data acquisition module, a pressure data preprocessing module, a communication module and a host computer connected in sequence.

[0026] The pressure data acquisition module is used to collect pressure data of various parts of the monitored object in real time. The pressure data includes pressure value and resistance value. The piezoresistive pressure sensor has the characteristic that the pressure is proportional to the inverse of the resistance. Therefore, this embodiment uses a piezoresistive pressure sensor as a pressure sensor to measure the single-point pressure value. The selected piezoresistive pressure sensor has a range of 10g to 10kg, a size of 40mm*40mm, an effective measurement area of ​​36mm*36mm square area, and a thickness of 0.45mm.

[0027] Taking bedridden patients as an example, when in use, multiple piezoresistive pressure sensors are arranged at various parts under the contact surface between the monitored object and the bed (such as the sacrum, both hips and both heels) according to needs. The piezoresistive pressure sensor converts the pressure F generated by various parts of the contact surface between the monitored person and the bed into a change in resistance 1 / R, thereby generating an analog signal that is transmitted to the pressure data preprocessing module.

[0028] The pressure data preprocessing module adopts a single-chip microcomputer system, which is an ESP32-WROOM module with a WIFI module. The module has a built-in multi-channel selection module. The ESP32 of the module samples the voltage values ​​of 12 analog-to-digital conversion channels in a time-division multiplexing manner. It is used to amplify the received analog signal U, then perform analog-to-digital conversion to obtain a digital signal representing the voltage value U, and finally reverse the digital signal and transmit it to the communication module. The pressure solution process is as follows: Figure 3 As shown;

[0029] According to the resistor voltage division:

[0030]

[0031] Among them, V + The positive input voltage of the operational amplifier, V - The voltage at the inverting input of the operational amplifier, V in The input terminal voltage of the operational amplifier, R1, R2 and R3 represent the resistance value of the first piezoresistive pressure sensor, R2 represents the resistance value of the second piezoresistive pressure sensor, and R3 represents the resistance value of the third piezoresistive pressure sensor.

[0032] According to the virtual short characteristics of the operational amplifier:

[0033] V - =V +

[0034] According to the operational amplifier continuous virtual break characteristics and Kirchhoff's current theorem:

[0035]

[0036] Among them, V out represents the output voltage of the operational amplifier, R L represents the resistance value of the Lth piezoresistive pressure sensor;

[0037] Combine the constants selected in the design, leaving R1 and V in have:

[0038]

[0039] in, At this time V out and Approximately a linear relationship.

[0040] Assuming that the system of this embodiment is a 3.3V system, the AD sampling range of ESP32 is 0-3.3V. To maximize the accuracy, the output of the operational amplifier should be equal to the AD sampling range. Considering that the weight is 10kg, the piezoresistive pressure sensor R1 is 0.442kΩ; then V in =3.3V, R2=100kΩ, R3=10kΩ, R L =4.4kΩ,

[0041]

[0042] The communication module transmits the received digital signal to the host computer. The communication module of this embodiment adopts the TCP / IP protocol to connect the single-chip computer system and the host computer to the same local area network, and transmits the pressure values ​​of each part calculated by the single-chip computer system to the host computer by searching the host IP and monitoring the preset port.

[0043] The host computer includes an early warning module and a display module. The host computer of this embodiment is also used as a user interface. Its structure is as follows Figure 2 As shown:

[0044] The early warning module includes a feature extraction module, a threshold adjustment module and an alarm module. The feature extraction module receives a digital signal and is used to extract the pressure time domain feature from the received digital signal and transmit it to the threshold adjustment module; the pressure time domain feature is used to characterize the pressure level and change trend of different parts of the patient. The threshold adjustment module is a regression model constructed by a multi-layer neural network. The regression model constructed by the multi-layer neural network is an end-to-end model, which is composed of an input layer, a fully connected layer, a Drop-out layer, and an output layer connected in sequence; its input is the pressure time domain feature and the initial threshold. According to the pressure time domain feature and the initial threshold, the pressure threshold and time threshold of different parts of different patients are adaptively regressed and calculated, and the pressure threshold and time threshold of each part of the patient are obtained and transmitted to the alarm module. An alarm value is set in the alarm module. When the pressure threshold and time threshold received by a certain part exceed the alarm value, an alarm signal is issued to remind medical staff to immediately adjust the patient's position to reduce pressure. The alarm module uses an alarm sensor to send an alarm signal. The alarm sensor can use any existing method to alarm and remind. The alarm signal in this embodiment preferably uses a voice sensor to perform a voice broadcast to remind. In order to obtain better warning accuracy, when the pressure threshold and time threshold received by a certain part exceed the alarm value, the alarm module can also use voice broadcast combined with deepening the color of the current part of the thermal map to remind.

[0045] The display module includes a preset module, a pressure data spatiotemporal distribution display module, and a pressure data table display module; the preset module is used to input and store patient personal information and physician experience data to generate an initial threshold value and transmit it to the threshold adjustment module, and the patient personal information includes height, weight, and gender. The pressure data spatiotemporal distribution display module is connected to the communication module, and is used to receive the digital signal from the communication module, extract the spatial distribution and pressure value of each part of the monitored object from the digital signal, and display it in a thermal map, so that medical staff can observe the changes in the pressure value at the sensor in real time. The pressure data table display module, the pressure data table display module receives the digital signal from the communication module, extracts the time, space distribution and pressure value of each part of the monitored object from the digital signal, and generates an Excl table to facilitate monitoring by medical staff. During implementation, the pressure data spatiotemporal distribution display module and the pressure data table display module are set according to needs, or both are set.

[0046] This embodiment provides a multi-point pressure detection and pressure sore warning system based on a flexible pressure sensor. The regression model constructed by introducing a multi-layer neural network in the host computer is an end-to-end model as a threshold adjustment model, so that the pressure threshold and time threshold can be calculated in real time without human intervention, so as to improve the accuracy and reliability of the pressure warning system. When in use, the system can adjust and set different pressure thresholds and durations according to the information of different patients at any time, and realize personalized settings and automated data analysis. This enables the system to better adapt to the needs of various patients, reduce the workload of medical staff, and provide faster and more accurate analysis results, providing patients with more effective pressure sore prevention and care, and can be widely used in medical institutions, nursing homes, home care and other places to improve the efficiency and quality of pressure sore care.

[0047] The above-mentioned implementation modes are only used to illustrate the technical solutions of the present invention and cannot be used to limit the scope of protection of the present invention. Any non-substantial changes and substitutions made by technicians in this field on the basis of the present invention shall fall within the scope of protection required by the present invention.

Claims

1. A multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor, comprising a pressure data acquisition module, a pressure data preprocessing module, a communication module and a host computer, characterized in that: The pressure data acquisition module is used to collect pressure data of various parts of the monitored object in real time, and generate analog signals to be transmitted to the pressure data preprocessing module; the collected pressure data includes but is not limited to the voltage value and resistance value of the pressure sensors installed in the sacrum, both hips and both heels; The pressure data preprocessing module is used to amplify, perform analog-to-digital conversion and pressure calculation on the received analog signal to obtain a digital signal and transmit it to the communication module; The communication module transmits the received digital signal to the host computer; The host computer includes an early warning module, which includes a feature extraction module, a threshold adjustment module and an alarm module; The feature extraction module receives a digital signal, and is used to extract the pressure time domain feature from the received digital signal and transmit it to the threshold adjustment module, wherein the pressure time domain feature is used to characterize the pressure level and change trend of different parts of the patient; the threshold adjustment module is a regression model constructed by a multi-layer neural network, and is used to receive the pressure time domain feature and the initial threshold, and perform adaptive regression calculation on the pressure threshold and time threshold of different parts of different patients according to the pressure time domain feature and the initial threshold, and obtain the pressure threshold and time threshold of each part of the patient and transmit them to the alarm module; the alarm module is provided with an alarm value, and when the pressure threshold and time threshold received by a certain part exceed the alarm value, an alarm signal is issued to remind medical staff to immediately adjust the patient's position to reduce pressure; The host computer also includes a display module, which includes a preset module and a pressure data spatiotemporal distribution display module; the preset module is used to enter and store patient personal information and physician experience data to generate an initial threshold value for transmission to the threshold adjustment module, and the patient personal information includes height, weight, and gender; the pressure data spatiotemporal distribution display module is connected to the communication module, and is used to receive a digital signal from the communication module, extract the spatial distribution and pressure values ​​of each part of the monitored object from the digital signal, and display it in a thermal map.

2. According to claim 1, a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor is characterized in that: The display module also includes a pressure data table display module, which receives the digital signal from the communication module, extracts the spatial distribution and pressure value of each part of the monitored object from the digital signal, and generates an Excel table to facilitate monitoring by medical staff.

3. According to claim 1, a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor is characterized in that: The alarm signal in the alarm module is given by voice broadcasting using a voice sensor.

4. According to claim 1, a multi-point pressure detection and pressure sore early warning system based on a flexible pressure sensor is characterized in that: The multi-layer neural network consists of an input layer, a fully connected layer, a Drop-out layer and an output layer connected in sequence.

Images