CN105956372A - Remote multi-sensor monitoring medical system - Google Patents

Abstract

A remote multi-sensor monitoring medical system is characterized in that it includes a hospital system, a home system and a remote monitoring center, the hospital system includes a medical examination device, a patient status grading module, an intelligent diagnosis module, and a data integration server, and the home system includes a portable multi- Sensor monitoring device.

Description

A remote multi-sensor monitoring medical system

technical field

The invention belongs to the field of intelligent equipment, in particular to a remote multi-sensor monitoring medical system.

Background technique

The intelligent medical system uses computer analysis, retrieval, and calculation to obtain scientific, reasonable, and comprehensive diagnostic results, pathological examination, etc., and provides relevant factors for the diagnosis of each disease in the diagnostic results. However, most of the current smart medical systems are limited to the collection of basic patient information and medical records. Diagnosis and treatment plans are made by doctors. The workload of doctors has not been reduced, and there is a lack of home care monitoring.

Contents of the invention

The technical problem to be solved by the present invention is how to realize the evaluation and formulation of disease diagnosis and treatment plan through algorithms. For this, the present invention provides a medical remote multi-sensor monitoring medical system, which includes a hospital system, a home system and a remote monitoring center ,

The hospital system includes medical examination devices, patient status grading modules, intelligent diagnosis modules, data integration servers,

Home systems include portable multi-sensor monitoring devices,

The attending physician realizes the medical examination, diagnosis and formulation of the treatment plan for the patient through the hospital system. The attending physician obtains the real-time data of nursing patients at home through the portable multi-sensor monitoring device of the home system. The portable multi-sensor monitoring device is also wirelessly connected with the remote monitoring center , so as to be able to respond in time when the patient has an emergency, and notify the attending physician and upload the data integration server at the same time,

When the patient is in the hospital system, the medical examination device detects multiple medical examination data of the patient and inputs them into the patient status grading module. The patient status grading module uses an evaluation algorithm to evaluate the patient's condition, and the attending doctor enters the patient status grading through identity authentication. The module verifies the evaluation results of the division. If the attending doctor believes that the evaluation results of the division are correct, the relevant information and medical examination data of the patient will be archived according to the evaluation results and input into the intelligent diagnosis module. If it is correct, the attending doctor will determine the evaluation result of the patient, and then file the relevant information and medical examination data of the patient according to the evaluation results, and input them into the intelligent diagnosis module; the intelligent diagnosis module automatically The corresponding treatment plan is generated, and the attending doctor enters the intelligent diagnosis module to verify the treatment plan through identity authentication. If the attending doctor thinks that the treatment plan is correct, the relevant information of the patient, medical examination data, treatment plan and evaluation results are uploaded to the data integration server , if the attending doctor thinks that the treatment plan is incorrect, the attending doctor will formulate a new treatment plan, and then upload the patient's relevant information, medical examination data, treatment plan and evaluation results to the data integration server;

The evaluation algorithm of the patient status grading module is specifically:

To classify each medical examination data, then

The overall detection measurements are:

$\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; =</span>\frac{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; m</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$

Among them, OPM is the overall detection measurement value, T _i is the grade value of the i-th medical examination data, i=1,2,...,N, T _i =1,2,...,M, M is the maximum Grade value, M≥2, N is the total number of medical examination data;

The maximum overall measurements are:

$\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}}$

OPM_MAX is the maximum overall measurement value

Then the evaluation value of the patient's condition as the evaluation result is:

$\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; ;</span>$

Determine whether the patient can be cared for at home according to the evaluation value C and the opinion of the attending doctor. If the evaluation value is C≥0.4, the patient needs to be hospitalized; if the evaluation value is 0<C<0.1, this type of patient has basically recovered and no further diagnosis is required. Monitoring services; if the evaluation value is 0.1≤C<0.4 and the attending physician agrees, the patient can go to home care;

When the patient is in the home system, judge the basic diagnosis service, advanced diagnosis service, form of diagnosis report, type of attending physician, monitoring time and monitoring cycle required by the home care patient according to the evaluation value;

When 0.1≤C<0.2, such patients are mild patients,

Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, and respiration rate;

No Advanced Diagnostic Services;

Diagnostic reports are in the form of web page notifications and emails;

The type of attending physician is an attending physician with less than 10 years of experience;

The monitoring time is 1 day;

The monitoring cycle is once an hour;

When 0.2≤C<0.3, such patients are moderate patients,

Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, and blood oxygen testing;

No Advanced Diagnostic Services;

Diagnostic reports are in the form of web page notifications and emails;

The type of attending physician is an attending physician with less than 10 years of experience;

The monitoring period is 7 days;

The monitoring cycle is once an hour;

When 0.3≤C<0.4, such patients are severe patients,

Basic diagnostic services include patient basic information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, blood sugar testing, cardiopulmonary testing, cholesterol level testing, cardiac assessment, and cardiac imaging;

Advanced diagnostic services are virtual heart, expert consultation;

Diagnosis report in the form of mobile phone, webpage notification and email;

The type of attending physician is an attending physician with more than 10 years of experience;

The monitoring period is 30 days;

The monitoring period is 1 minute;

Through the above grading, different treatment and nursing methods can be adopted according to the condition of different patients, so as to rationally allocate medical resources and reduce medical costs.

Among them, the pulse, electrocardiogram, and respiration rate in the basic diagnosis service are realized through a portable multi-sensor monitoring device,

The portable multi-sensor monitoring device includes a heart sound sensor, a pulse sensor, a respiration sensor, an acquisition and conditioning circuit, a power management module, an alarm circuit, a communication device, a display, a main controller, a memory and a keyboard;

Heart sound sensor, pulse sensor, respiration sensor to realize the measurement of electrocardiogram, pulse and respiration rate;

The main controller collects data signals from the heart sound sensor, pulse sensor, and respiration sensor through the acquisition and conditioning circuit, and transmits them to the remote monitoring center in real time through the communication device;

Adjust the working parameters of the portable multi-sensor monitoring device through the keyboard, and display the patient's physiological condition through the monitor;

The memory is used to store relevant information of patients, medical records and data information collected by the main controller;

The power management module is used to control the power supply to the portable multi-sensor monitoring device, and reduce power consumption while maintaining normal operation;

The acquisition and conditioning circuit is composed of a signal acquisition circuit, a primary amplifier circuit, a secondary amplifier circuit, a low-pass filter circuit, a limiter circuit and an A/D conversion circuit;

Signal amplification, filtering and analog-to-digital conversion are realized through the acquisition and conditioning circuit;

The alarm circuit is used to send out sound and light signals for alarm when the patient is in an emergency.

Beneficial effects of the present invention:

(1) Realize the evaluation of the patient's condition through the evaluation algorithm, so as to provide a basis for the selection of the patient's treatment plan and the patient's treatment environment;

(2) It has a home system, thus ensuring the round-the-clock monitoring of the patient's home care;

(3) Introduce intelligent diagnosis methods and automatically generate treatment plans, thereby greatly reducing the labor intensity of doctors.

Description of drawings

Fig. 1 is a system block diagram of the present invention;

Fig. 2 is a composition block diagram of the intelligent diagnosis module of the present invention;

Fig. 3 is a composition block diagram of the portable multi-sensor monitoring device of the present invention;

detailed description

The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

Embodiments of the present invention are shown with reference to FIGS. 1-3 .

A medical remote multi-sensor monitoring medical system, which includes a hospital system, a home system and a remote monitoring center,

The hospital system includes medical examination devices, patient status grading modules, intelligent diagnosis modules, data integration servers,

Home systems include portable multi-sensor monitoring devices,

The attending physician realizes the medical examination, diagnosis and formulation of the treatment plan for the patient through the hospital system. The attending physician obtains the real-time data of nursing patients at home through the portable multi-sensor monitoring device of the home system. The portable multi-sensor monitoring device is also wirelessly connected with the remote monitoring center , so as to be able to respond in time when the patient has an emergency, and notify the attending physician and upload the data integration server at the same time,

When the patient is in the hospital system, the medical examination device detects multiple medical examination data of the patient and inputs them into the patient status grading module. The patient status grading module uses an evaluation algorithm to evaluate the patient's condition, and the attending doctor enters the patient status grading through identity authentication. The module verifies the evaluation results of the division. If the attending doctor believes that the evaluation results of the division are correct, the relevant information and medical examination data of the patient will be archived according to the evaluation results and input into the intelligent diagnosis module. If it is correct, the attending doctor will determine the evaluation result of the patient, and then file the relevant information and medical examination data of the patient according to the evaluation results, and input them into the intelligent diagnosis module; the intelligent diagnosis module automatically Generate a corresponding treatment plan, and the attending doctor enters the intelligent diagnosis module to verify the treatment plan through identity authentication. If the attending doctor thinks that the treatment plan is correct, the relevant information of the patient, medical examination data, treatment plan and evaluation results will be uploaded to the data integration server , if the attending doctor thinks that the treatment plan is incorrect, the attending doctor will formulate the treatment plan again, and then upload the patient's relevant information, medical examination data, treatment plan and evaluation results to the data integration server;

The evaluation algorithm of the patient status grading module is specifically:

By classifying each medical examination data, the overall detection measurement value is:

$\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; =</span>\frac{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; m</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$

Among them, OPM is the overall detection measurement value, T _i is the grade value of the i-th medical examination data, i=1,2,...,N, T _i =1,2,...,M, M is the maximum Grade value, M≥2, N is the total number of medical examination data;

The maximum overall measurements are:

$\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}}$

OPM_MAX is the maximum overall measurement value

Then the evaluation value of the patient's condition as the evaluation result is:

$\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}}$

The above evaluation calculation can effectively evaluate the patient's condition, so as to classify and archive.

Further, M=5, N=6

Medical inspection devices include blood glucose meters, ECG detectors, respiratory rate detectors, cholesterol level detectors, blood pressure meters, X-ray machines,

Medical examination data include blood sugar concentration, ECG data evaluation, respiratory rate, cholesterol level, blood pressure status, X-ray fluoroscopy evaluation,

Further,

Among them, the evaluation grades of blood glucose concentration are shown in the table below;

grade 1 2 3 4 5 Blood glucose concentration (mg/DL) <98 98-154 155-183 184-254 >254

The evaluation grades of respiratory frequency are shown in the table below;

grade 1 2 3 4 5 Respiratory rate (times/min) 12-18 9-11, 19-21 6-8, 22-24 3-5, 25-27 <3,>27

The rating scale of cholesterol level is shown in the table below;

grade 1 2 3 4 5 Cholesterol level (mmolg/l) <5.2 5.2-5.5 5.6-5.8 5.9-6.0 >6.0

The evaluation grades of blood pressure status are shown in the table below;

ECG data evaluation refers to the grade evaluation made by doctors only based on ECG;

X-ray fluoroscopy evaluation refers to the grade evaluation made by doctors only based on X-ray films;

The intelligent diagnosis module includes a dynamic comprehensive database, a neural network learning module, an inference engine, an explanation module, a sample knowledge base, a neural network structure knowledge base, a clinical symptom description knowledge base, a disease knowledge base, a treatment plan knowledge base, a historical record knowledge base, knowledge database management module,

Experts can adjust, manage, maintain and update the neural network learning module and each knowledge base through the knowledge base management module;

The interpretation module is a communication bridge between the system and the attending physician, responsible for converting the attending physician's diagnosis into information that the system can recognize, and converting the final output of the system into information that the attending physician can understand;

The reasoning machine uses the knowledge already possessed by the system, combined with the specific information of the injection molding process contained in the dynamic comprehensive database, to reason and obtain the corresponding treatment plan. The inference engine includes two parts: a neural network reasoning module and a rule-based reasoning module. The reasoning between "clinical symptoms-disease" uses a neural network module, and the reasoning between "disease-treatment options" uses rule-based reasoning;

The neural network learning module proposes the neural network structure including the number of network layers, input, output, and number of hidden nodes, organizes learning samples to be trained, and neural network learning algorithms, learns through sample knowledge base extraction, and obtains weight distribution , complete knowledge acquisition.

Furthermore, the neural network structure is realized through the combination of fuzzy logic and neural network, and the neural network learning algorithm is BP algorithm.

The sample knowledge base, the neural network structure knowledge base, the clinical symptom description knowledge base, the disease knowledge base, the treatment plan knowledge base, and the historical record knowledge base respectively store corresponding knowledge data.

The knowledge database management module has complete database operation functions. Experts can query, add, delete and modify each knowledge base through the knowledge database management module.

The dynamic comprehensive database receives and stores relevant patient information, medical examination data and evaluation results;

The working process of the inference engine is as follows:

(1) Fuzzify the patient's relevant information, medical examination data and evaluation results, and use it as the input mode of each sub-neural network;

(2) read in the weight matrix of each sub-neural network from the neural network structure knowledge base;

(3) In conjunction with the weight matrix between each sub-neural network input layer and the hidden layer, calculate the output of each sub-neural network input layer neuron, and use the output as the input of the hidden layer neuron;

(4) Combine the weight matrix between each sub-neural network hidden layer and the output layer to calculate the output value of the output layer neuron;

(5) Carry out the reasoning of the rule reasoning module according to the output value of the output layer neuron in combination with the relevant information in the dynamic comprehensive database, determine the cause of the disease, and give the credibility;

(6) According to the final determined cause, combined with relevant information, give a treatment plan corresponding to the specific cause;

Intelligent diagnosis is truly realized through the intelligent diagnosis module, which can provide doctors with detailed treatment plans and reduce their work intensity.

Determine whether the patient can be cared for at home according to the evaluation value C and the opinion of the attending doctor. If the evaluation value is C≥0.4, the patient needs to be hospitalized; if the evaluation value is 0<C<0.1, this type of patient has basically recovered and no further diagnosis is required. Monitoring services; if the evaluation value is 0.1≤C<0.4 and the attending physician agrees, the patient can go to home care;

When the patient is in the home system, judge the basic diagnosis service, advanced diagnosis service, form of diagnosis report, type of attending physician, monitoring time and monitoring cycle required by the home care patient according to the evaluation value;

When 0.1≤C<0.2, such patients are mild patients,

Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, and respiration rate;

No Advanced Diagnostic Services;

Diagnostic reports are in the form of web page notifications and emails;

The type of attending physician is an attending physician with less than 10 years of experience;

The monitoring time is 1 day;

The monitoring cycle is once an hour;

When 0.2≤C<0.3, such patients are moderate patients,

Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, and blood oxygen testing;

No Advanced Diagnostic Services;

Diagnostic reports are in the form of web page notifications and emails;

The type of attending physician is an attending physician with less than 10 years of experience;

The monitoring period is 7 days;

The monitoring cycle is once an hour;

When 0.3≤C<0.4, such patients are severe patients,

Basic diagnostic services include patient basic information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, blood sugar testing, cardiopulmonary testing, cholesterol level testing, cardiac assessment, and cardiac imaging;

Advanced diagnostic services are virtual heart, expert consultation;

Diagnosis report in the form of mobile phone, webpage notification and email;

The type of attending physician is an attending physician with more than 10 years of experience;

The monitoring period is 30 days;

The monitoring period is 1 minute;

Through the above grading, different treatment and nursing methods can be adopted according to the condition of different patients, so as to rationally allocate medical resources and reduce medical costs.

Among them, the pulse, electrocardiogram, and respiration rate in the basic diagnosis service are realized through a portable multi-sensor monitoring device,

The portable multi-sensor monitoring device includes a heart sound sensor, a pulse sensor, a respiration sensor, an acquisition and conditioning circuit, a power management module, an alarm circuit, a communication device, a display, a main controller, a memory and a keyboard;

Heart sound sensor, pulse sensor and respiration sensor realize the measurement of electrocardiogram, pulse and respiration rate;

The main controller collects data signals from the heart sound sensor, pulse sensor, and respiration sensor through the acquisition and conditioning circuit, and transmits them to the remote monitoring center in real time through the communication device;

Adjust the working parameters of the portable multi-sensor monitoring device through the keyboard, and display the patient's physiological condition through the monitor;

The memory is used to store relevant information of patients, medical records and data information collected by the main controller;

The power management module is used to control the power supply to the portable multi-sensor monitoring device, and reduce power consumption while maintaining normal operation;

The acquisition and conditioning circuit is composed of a signal acquisition circuit, a primary amplifier circuit, a secondary amplifier circuit, a low-pass filter circuit, a limiter circuit and an A/D conversion circuit;

Signal amplification, filtering and analog-to-digital conversion are realized through the acquisition and conditioning circuit;

The alarm circuit is used to send out sound and light signals for alarm when the patient is in an emergency.

The above-mentioned embodiment is only an embodiment of the present invention, but should not be construed as limiting the scope of the present invention. It should be pointed out that those skilled in the art can make several modifications and improvements without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims (9)

1. A medical system for remote multi-sensor monitoring, characterized in that: it comprises a hospital system, a home system and a remote monitoring center, The hospital system includes medical examination devices, patient status grading modules, intelligent diagnosis modules, data integration servers, Home systems include portable multi-sensor monitoring devices, The attending physician realizes the medical examination, diagnosis and formulation of the treatment plan for the patient through the hospital system. The attending physician obtains the real-time data of nursing patients at home through the portable multi-sensor monitoring device of the home system. The portable multi-sensor monitoring device is also wirelessly connected with the remote monitoring center , so as to be able to respond in time when the patient has an emergency, and notify the attending physician and upload the data integration server at the same time, When the patient is in the hospital system, the medical examination device detects multiple medical examination data of the patient and inputs them into the patient status grading module. The patient status grading module uses an evaluation algorithm to evaluate the patient's condition, and the attending doctor enters the patient status grading through identity authentication. The module verifies the evaluation results of the division. If the attending doctor believes that the evaluation results of the division are correct, the relevant information and medical examination data of the patient will be archived according to the evaluation results and input into the intelligent diagnosis module. If it is correct, the attending doctor will determine the evaluation result of the patient, and then file the relevant information and medical examination data of the patient according to the evaluation results, and input them into the intelligent diagnosis module; the intelligent diagnosis module automatically The corresponding treatment plan is generated, and the attending doctor enters the intelligent diagnosis module to verify the treatment plan through identity authentication. If the attending doctor thinks that the treatment plan is correct, the relevant information of the patient, medical examination data, treatment plan and evaluation results are uploaded to the data integration server , if the attending doctor thinks that the treatment plan is incorrect, the attending doctor will formulate a new treatment plan, and then upload the patient's relevant information, medical examination data, treatment plan and evaluation results to the data integration server; The evaluation algorithm of the patient status grading module is specifically: To classify each medical examination data, then The overall detection measurements are: $\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; =</span>\frac{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 3</span>}}<span\; class="notranslate">\; +</span><span\; class="notranslate">\; ...</span><span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; T</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}<span\; class="notranslate">\; \&times;</span>{\mathrm{<span\; class="notranslate">\; m</span>}}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$ Among them, OPM is the overall detection measurement value, T _i is the grade value of the i-th medical examination data, i=1,2,...,N, T _i =1,2,...,M, M is the maximum Grade value, M≥2, N is the total number of medical examination data; The maximum overall measurements are: $\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; the\; s</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 360</span>}<span\; class="notranslate">\; /</span>\mathrm{<span\; class="notranslate">\; N</span>}<span\; class="notranslate">\; )</span>}{\mathrm{<span\; class="notranslate">\; 2</span>}}$ OPM_MAX is the maximum overall measurement value Then the evaluation value of the patient's condition as the evaluation result is: $\mathrm{<span\; class="notranslate">\; C</span>}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; P</span>}\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; \_</span>\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; A</span>}\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; ;</span>$ Determine whether the patient can be cared for at home according to the evaluation value C and the opinion of the attending doctor. If the evaluation value is C≥0.4, the patient needs to be hospitalized; if the evaluation value is 0<C<0.1, this type of patient has basically recovered and no further diagnosis is required. Monitoring services; if the evaluation value is 0.1≤C<0.4 and the attending physician agrees, the patient can go to home care; When the patient is in the home system, judge the basic diagnosis service, advanced diagnosis service, form of diagnosis report, type of attending physician, monitoring time and monitoring cycle required by the home care patient according to the evaluation value; When 0.1≤C<0.2, such patients are mild patients, Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, and respiration rate; No Advanced Diagnostic Services; Diagnostic reports are in the form of web page notifications and emails; The type of attending physician is an attending physician with less than 10 years of experience; The monitoring time is 1 day; The monitoring cycle is once an hour; When 0.2≤C<0.3, such patients are moderate patients, Basic diagnostic services include basic patient information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, and blood oxygen testing; No Advanced Diagnostic Services; Diagnostic reports are in the form of web page notifications and emails; The type of attending physician is an attending physician with less than 10 years of experience; The monitoring period is 7 days; The monitoring cycle is once an hour; When 0.3≤C<0.4, such patients are severe patients, Basic diagnostic services include patient basic information, medical records, pulse, electrocardiogram, respiration rate, blood pressure testing, blood sugar testing, cardiopulmonary testing, cholesterol level testing, cardiac assessment, and cardiac imaging; Advanced diagnostic services are virtual heart, expert consultation; Diagnosis report in the form of mobile phone, webpage notification and email; The type of attending physician is an attending physician with more than 10 years of experience; The monitoring period is 30 days; The monitoring period is 1 minute; Among them, the pulse, electrocardiogram, and respiration rate in the basic diagnosis service are realized through a portable multi-sensor monitoring device, The portable multi-sensor monitoring device includes a heart sound sensor, a pulse sensor, a respiration sensor, an acquisition and conditioning circuit, a power management module, an alarm circuit, a communication device, a display, a main controller, a memory and a keyboard; Heart sound sensor, pulse sensor and respiration sensor realize the measurement of electrocardiogram, pulse and respiration rate; The main controller collects data signals from the heart sound sensor, pulse sensor, and respiration sensor through the acquisition and conditioning circuit, and transmits them to the remote monitoring center in real time through the communication device; Adjust the working parameters of the portable multi-sensor monitoring device through the keyboard, and display the patient's physiological condition through the monitor; The memory is used to store relevant information of patients, medical records and data information collected by the main controller; The power management module is used to control the power supply to the portable multi-sensor monitoring device, and reduce power consumption while maintaining normal operation; The acquisition and conditioning circuit is composed of a signal acquisition circuit, a primary amplifier circuit, a secondary amplifier circuit, a low-pass filter circuit, a limiter circuit and an A/D conversion circuit; Signal amplification, filtering and analog-to-digital conversion are realized through the acquisition and conditioning circuit; The alarm circuit is used to send out sound and light signals for alarm when the patient is in an emergency. 2. A medical system for remote multi-sensor monitoring according to claim 1, characterized in that: M=5, N=6, Medical inspection devices include blood glucose meters, ECG detectors, respiratory rate detectors, cholesterol level detectors, blood pressure meters, X-ray machines, Medical examination data includes blood glucose concentration, ECG data evaluation, respiratory rate, cholesterol level, blood pressure status, and X-ray fluoroscopy evaluation. 3. A medical system for remote multi-sensor monitoring according to claim 2, characterized in that: The grades of blood glucose concentration are shown in the table below, grade 1 2 3 4 5 Blood glucose concentration (mg/DL) <98 98-154 155-183 184-254 >254 The classification of respiratory frequency is shown in the table below, grade 1 2 3 4 5 Respiratory rate (times/min) 12-18 9-11, 19-21 6-8, 22-24 3-5, 25-27 <3,>27 Cholesterol levels are graded as shown in the table below, grade 1 2 3 4 5 Cholesterol level (mmolg/l) <5.2 5.2-5.5 5.6-5.8 5.9-6.0 >6.0 The classification of blood pressure status is shown in the table below, ECG data evaluation refers to the evaluation made by physicians only based on ECG; X-ray fluoroscopy evaluation refers to the evaluation made by doctors only based on X-ray films. 4. the medical system of a kind of remote multi-sensor monitoring described in claim 1 is characterized in that: intelligent diagnosis module comprises dynamic comprehensive database, neural network learning module, inference engine, explanation module, sample knowledge base, neural network structure knowledge base , clinical symptom description knowledge base, disease knowledge base, treatment program knowledge base, historical record knowledge base, knowledge database management module, Experts can adjust, manage, maintain and update the neural network learning module and each knowledge base through the knowledge base management module; The interpretation module is a communication bridge between the system and the attending physician, responsible for converting the attending physician's diagnosis into information that the system can recognize, and converting the final output of the system into information that the attending physician can understand; The reasoning machine uses the knowledge already possessed by the system, combined with the specific information of the injection molding process contained in the dynamic comprehensive database, to reason and obtain the corresponding treatment plan. The inference engine includes two parts: a neural network reasoning module and a rule-based reasoning module. The reasoning between "clinical symptoms-disease" uses a neural network module, and the reasoning between "disease-treatment options" uses rule-based reasoning; The neural network learning module proposes the neural network structure including the number of network layers, input, output, and number of hidden nodes, organizes learning samples to be trained, and neural network learning algorithms, learns through sample knowledge base extraction, and obtains weight distribution , complete knowledge acquisition. 5. A medical system for remote multi-sensor monitoring according to claim 4, characterized in that: the neural network structure is realized by combining fuzzy logic and neural network, and the learning algorithm of neural network is BP algorithm. The sample knowledge base, the neural network structure knowledge base, the clinical symptom description knowledge base, the disease knowledge base, the treatment plan knowledge base, and the historical record knowledge base respectively store corresponding knowledge data. The knowledge database management module has complete database operation functions. Experts can query, add, delete and modify each knowledge base through the knowledge database management module. A dynamic comprehensive database receives and stores patient-related information, medical examination data, and evaluation results. 6. A kind of remote multi-sensor monitoring medical system according to claim 5, characterized in that: the working process of the reasoning machine is as follows: (1) Fuzzify the patient's relevant information, medical examination data and evaluation results, and use it as the input mode of each sub-neural network; (2) read in the weight matrix of each sub-neural network from the neural network structure knowledge base; (3) In conjunction with the weight matrix between each sub-neural network input layer and the hidden layer, calculate the output of each sub-neural network input layer neuron, and use the output as the input of the hidden layer neuron; (4) Combine the weight matrix between each sub-neural network hidden layer and the output layer to calculate the output value of the output layer neuron; (5) Carry out the reasoning of the rule reasoning module according to the output value of the output layer neuron in combination with the relevant information in the dynamic comprehensive database, determine the cause of the disease, and give the credibility; (6) According to the final determined cause, combined with relevant information, give a treatment plan corresponding to the specific cause. 7. The medical system of a kind of remote multi-sensor monitoring according to claim 1, characterized in that: the pulse wave detection module comprises a pulse wave sensor, a pulse wave signal conditioning circuit; the pulse wave signal conditioning circuit consists of a primary amplifier circuit, a secondary The stage amplifier circuit, low-pass filter circuit and limiter circuit are sequentially connected to form. 8. The medical system of a kind of remote multi-sensor monitoring according to claim 1, characterized in that: the ECG detection module comprises electrodes, a band-pass filter, a trap circuit, and a leg drive circuit; the band-pass filter is used for filtering In addition to interference, the frequency range is 0.3-120Hz. The band-pass filter is composed of a low-pass filter circuit and a high-pass filter circuit. The cut-off frequency of the low-pass filter circuit is 120Hz. 9. The medical system of a kind of remote multi-sensor monitoring according to claim 1, characterized in that: the central processing unit module collects pulse wave detection module, electrocardiogram detection module, blood pressure detection module, blood oxygen saturation detection module The data signal is transmitted to the remote monitoring center in real time through the communication module; Adjust the working parameters of the portable multi-sensor monitoring device and display the patient's physiological condition through the touch screen module; The memory module is used for storing relevant information of the patient, medical records and data information collected by the central processor module; The power management module is used to control the power supply to the portable multi-sensor monitoring device, and reduce power consumption while maintaining normal work.