CN117059220A - Patient follow-up method, follow-up system and follow-up device - Google Patents
Patient follow-up method, follow-up system and follow-up device Download PDFInfo
- Publication number
- CN117059220A CN117059220A CN202311192155.5A CN202311192155A CN117059220A CN 117059220 A CN117059220 A CN 117059220A CN 202311192155 A CN202311192155 A CN 202311192155A CN 117059220 A CN117059220 A CN 117059220A
- Authority
- CN
- China
- Prior art keywords
- follow
- data
- patient
- case
- plan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000003814 drug Substances 0.000 claims abstract description 25
- 229940079593 drug Drugs 0.000 claims abstract description 23
- 201000010099 disease Diseases 0.000 claims abstract description 20
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 20
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000003066 decision tree Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 22
- 239000008280 blood Substances 0.000 claims description 7
- 210000004369 blood Anatomy 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 235000006694 eating habits Nutrition 0.000 claims description 5
- 238000003058 natural language processing Methods 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000007418 data mining Methods 0.000 claims description 4
- 238000013079 data visualisation Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 4
- 210000000577 adipose tissue Anatomy 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 2
- -1 examination index Substances 0.000 claims description 2
- 239000008103 glucose Substances 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000007635 classification algorithm Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 229930186147 Cephalosporin Natural products 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 229940124587 cephalosporin Drugs 0.000 description 1
- 150000001780 cephalosporins Chemical class 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005686 eating Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000021590 normal diet Nutrition 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Toxicology (AREA)
- Pharmacology & Pharmacy (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a patient follow-up method, a follow-up system and a follow-up device. The patient follow-up method comprises the following steps: collecting case data and characteristic data of a patient; predicting the case data and the feature data by using a naive Bayesian algorithm to obtain posterior probability of the case category; classifying the cases of the patient into different categories according to the posterior probability, and obtaining disease risk data and drug response data of the patient; automatically generating a personalized follow-up plan by using a decision tree algorithm on the characteristic data, the basic information data, the disease risk data and the drug response data of the patient; automatically making a follow-up call according to the personalized follow-up plan, and performing system automatic follow-up; the voice content in the follow-up telephone is identified in real time, and the identification result is converted into text data. The invention has the beneficial effects of improving follow-up efficiency, reducing labor cost, improving follow-up quality, reducing follow-up misdiagnosis, improving patient satisfaction and the like.
Description
Technical Field
The invention relates to the technical field of medical treatment, in particular to a patient follow-up method, a follow-up system and a follow-up device.
Background
In the field of modern medicine, follow-up is an indispensable part of the treatment and rehabilitation process. Through follow-up visit, doctors can know the illness state and the treatment condition of the patient in time and adjust the treatment scheme in time, thereby improving the treatment effect and the satisfaction degree of the patient. However, the traditional follow-up mode often requires a doctor to manually dial a phone call or communicate with a manual consultation face to face, the follow-up efficiency is low, and the follow-up mode is easily affected by human factors, so that follow-up data is not accurate and comprehensive enough, problems that the follow-up data is not standard and difficult to analyze easily occur, and accurate patient health information is difficult to provide for the doctor.
Disclosure of Invention
Based on the above, it is necessary to provide a patient follow-up method, a follow-up system and a follow-up device for solving the problems that the existing follow-up mode is low in efficiency, and the follow-up data is not accurate enough and difficult to analyze.
A patient follow-up method comprising the steps of:
step S1, collecting case data C and characteristic data x of a patient;
s2, predicting the case data C and the feature data x by using a naive Bayesian algorithm to obtain a case category C k Posterior probability P (C) k |x 1 ，x 2 ，...，x m )；
Step S3, according to the posterior probability P (C k |x 1 ，x 2 ，...，x m ) Classifying the cases of the patient into different categories, and obtaining disease risk data and drug response data of the patient;
s4, automatically generating a personalized follow-up plan for the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient by using a decision tree algorithm;
s5, automatically making follow-up call according to the personalized follow-up plan, and performing system automatic follow-up;
s6, identifying voice content in the follow-up telephone in real time, and converting the identification result into text data;
s7, carrying out structuring treatment on the text data to obtain structured follow-up data;
s8, analyzing the structural follow-up data to obtain updated characteristic data x, basic information data, disease risk data and drug response data;
steps S1 to S8 are repeated every planning time, wherein the doctor can intervene manually in steps S3, S4 and S5 and feed back the follow-up result to the patient.
As a preferred example, in step S1, the characteristic data x is selected and preprocessed according to characteristics of the patient, wherein the characteristics of the patient include age, sex, medication, examination index, blood glucose level, eating habits, lifestyle and condition change.
As a preferred example, the selection and pretreatment of the characteristics of the patient comprises the steps of:
s11, carrying out correlation analysis and principal component analysis on the characteristics of a patient to obtain important characteristic data;
step S12, carrying out normalization processing on important characteristic data;
and S13, performing missing value filling processing on the important characteristic data after normalization processing to obtain characteristic data x.
As a preferred example, in step S2, the prediction using the naive bayes algorithm includes the steps of:
step S21, suggesting a case data set containing the total number of cases collected;
step S22, calculating according to the case data C to obtain the case category C k The proportion of cases to the total number of cases, i.e. each case class C k Is (C) k )；
Step S23, according to the prior probability P (C k ) And the feature data x are calculated to obtain each feature in each case category C k Conditional probability P (x) j |C k )；
Step S24, for conditional probability P (x j |C k ) Performing maximum likelihood estimation processing;
step S25, for maximumConditional probability P (x) j |C k ) Calculation of case category C using Bayesian theorem k Posterior probability P (C) k |x 1 ，x 2 ，...，x m )。
As a preferred example, in step S4, the basic information data includes age, sex, BMI, body fat rate, contact number.
As a preferred example, the personalized follow-up plan includes a follow-up time, a follow-up frequency, follow-up content, and follow-up advice.
As a preferred example, in step S5, the follow-up content and follow-up suggestion of the system automatic follow-up are pre-recorded voice content.
As a preferred example, if the automatic dialing of follow-up telephone is unsuccessful, medical personnel are automatically scheduled for manual contact.
As a preferred example, in step S7, the structuring process of the text data includes the steps of:
step S71, extracting key information from the text data;
step S72, analyzing the extracted text data by utilizing data visualization, data mining and natural language processing;
and step 73, classifying and archiving the analyzed text data to obtain the structured follow-up data.
As a preferred example, the contents that the doctor can perform manual intervention include adjusting the follow-up time, the follow-up frequency, the follow-up contents and follow-up advice, adding or deleting characteristic data x, basic information data, disease risk data, and drug response data to the system.
A patient follow-up system to which the above-described patient follow-up method is applied, the patient follow-up system comprising:
the follow-up plan module is used for automatically generating a personalized follow-up plan according to the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient;
the automatic dialing module is used for automatically dialing follow-up call according to the personalized follow-up plan;
the voice recognition and processing module is used for recognizing voice contents in the follow-up telephone in real time and converting a recognition result into text data;
the follow-up data structuring module is used for structuring the text data and obtaining structured follow-up data;
and the database module is used for storing and managing the structured follow-up data of the patient and providing the functions of inquiring and analyzing.
The invention also provides a patient follow-up device comprising a processor, a memory and a computer program stored on the memory and executable by the processor, which when executed by the processor, implements the steps of the patient follow-up method as described above.
Compared with the prior art, the patient follow-up method, the follow-up system and the follow-up device provided by the invention have the following beneficial effects:
1. and the follow-up efficiency is improved: while the traditional manual follow-up mode requires a doctor or nurse to spend a great deal of time and effort for follow-up, the patient follow-up method and the follow-up system adopt an automatic technology, and follow-up telephone can be automatically dialed according to a follow-up plan, so that the follow-up efficiency is greatly improved.
2. The labor cost is reduced: the traditional manual follow-up mode requires a special staff to be employed by a hospital for follow-up, and has higher cost, and the patient follow-up method automatically dials a follow-up call through the system, so that the employment of the special follow-up staff is reduced, and the labor cost can be reduced.
3. And the follow-up quality is improved: the patient follow-up method can automatically structure follow-up data according to follow-up contents, classify and file information provided by patients, enable doctors to better know the illness state and treatment condition of the patients, and formulate more personalized treatment schemes, so that follow-up quality is improved.
4. And the follow-up misdiagnosis is reduced: the traditional manual follow-up mode is easy to cause misdiagnosis, and the patient follow-up method can analyze follow-up data through technologies such as data analysis and artificial intelligence, so that doctors can better know the illness state and treatment condition of patients, and the risk of follow-up misdiagnosis is reduced.
5. Improving patient satisfaction: the follow-up visit method for the patient has high follow-up visit efficiency, can inform the patient of the illness state and the treatment condition of the patient and the treatment scheme and advice of the next step through the feedback of the follow-up visit result of a doctor, and improves the satisfaction degree of the patient.
Drawings
FIG. 1 is a flowchart of a patient follow-up method according to an embodiment of the present invention;
FIG. 2 is a flow chart of the feature data x obtained in the patient follow-up method;
FIG. 3 is a schematic flow diagram of the naive Bayesian algorithm prediction in FIG. 1;
FIG. 4 is a schematic flow chart of the structuring process of the text data in FIG. 1;
FIG. 5 is a schematic diagram of a patient follow-up system according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a flow relationship between a patient follow-up system and a doctor, a patient according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a patient follow-up device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "or/and" as used herein includes any and all combinations of one or more of the associated listed items.
In the patient follow-up method, a doctor generates a follow-up plan through the system and automatically dials a follow-up call through the system at preset follow-up time. During the follow-up, the patient provides the condition and treatment, and the voice content in the follow-up telephone is converted into text data by voice recognition technology. The system then performs a structuring process on the identified text data to generate structured follow-up data. According to the generated structured follow-up data, the system can analyze the follow-up data by utilizing the technologies of data visualization, data mining, natural language processing, artificial intelligence and the like, so that doctors can better know the illness state and the treatment condition of patients and formulate more personalized treatment schemes. Finally, the doctor needs to adjust the follow-up plan according to the analysis result, and feed back the follow-up result to the patient in time to inform the patient of the illness state and the treatment condition, and the treatment scheme and advice of the next step.
Referring to fig. 1, a flow chart of a patient follow-up method according to an embodiment of the invention is shown, the patient follow-up method includes the following steps:
step S1, collecting case data C and characteristic data x of a patient;
in the step, the case data C is a set of past cases of the patient, the characteristic data x is obtained by selecting and preprocessing according to the characteristics of the patient, wherein the characteristics of the patient comprise age, gender, medication condition, inspection indexes, blood sugar level, eating habits, life style and disease condition change, the characteristics are all registered and recorded when the patient visits, and the characteristics can be collected through a hospital outpatient system together with the case data C.
Referring to fig. 2, in order to ensure the quality and reliability of the feature data x, and to improve the accuracy of the classification algorithm, the feature of the patient needs to be selected and preprocessed to obtain the feature data x, which includes the following steps:
s11, carrying out correlation analysis and principal component analysis on the characteristics of a patient to obtain important characteristic data;
step S12, carrying out normalization processing on important characteristic data;
and S13, performing missing value filling processing on the important characteristic data after normalization processing to obtain characteristic data x.
S2, predicting the case data C and the feature data x by using a naive Bayesian algorithm to obtain a case category C k Posterior probability P (C) k |x 1 ，x 2 ，...，x m )；
Referring to fig. 3, the naive bayes algorithm-based prediction process in this step includes the following steps:
step S21, suggesting a case data set comprising n total cases collected, each case comprising m patient characteristics x j ；
Step S22, calculating according to the case data C to obtain the case category C k The proportion of cases to the total number of cases, i.e. each case class C k Is (C) k )；
Specifically, assume that the case is classified as C k Where K ε {1,2,..K }, K represents the number of categories, each category C k Is (C) k ) I.e. in the whole case dataset, belonging to category C k The ratio of the cases to the total number of cases is calculated by the following formula:
wherein y is i Representing the category of the ith case, [ y ] i ＝C k ]When y is expressed as i ＝C k The value is 1, otherwise 0.
Step S23, according to the prior probability P (C k ) And the feature data x are calculated to obtain each feature in each case category C k Conditional probability P (x) j |C k )；
The conditional probability P (x j |C k ) To belong to category C in known cases k In the case of (a), feature x j Probability of occurrence since the naive Bayes algorithm assumes that the features are independent of each other, sinceThis can represent the conditional probability as the product of the conditional probabilities of the various features, namely:
wherein x is j Representing the value of the j-th feature.
Step S24, for conditional probability P (x j |C k ) Performing maximum likelihood estimation processing;
the maximum likelihood estimation method is adopted for the conditional probability P (x j |C k ) Calculation is performed, i.e. when the known case belongs to category C k In the case of (a), feature x j Probability of taking a certain value can be used for characteristic x in case j Taking the case duty cycle of this value to estimate, namely:
wherein x is ij Value of the j-th feature representing the i-th case [&]Representing logical and operators.
Step S25, the conditional probability P (x j |C k ) Calculation of case category C using Bayesian theorem k Posterior probability P (C) k |x 1 ，x 2 ，...，x m )。
Posterior probability P (C) k |x 1 ，x 2 ，...，x m ) Representing the assignment of individual characteristic values to known cases to class C k The posterior probability of (2) is calculated using the following formula:
step S3, according to the posterior probability P (C k |x 1 ，x 2 ，...，x m ) Classifying cases of patients into different categories, e.g. category C 1 Class C 2 Up to category C k Obtaining disease risk data and drug response data of the patient according to different categories;
s4, automatically generating a personalized follow-up plan for the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient by using a decision tree algorithm;
the basic information data comprises age, sex, BMI, body fat rate and contact number, and the information is registered and recorded when the patient is in medical treatment, collected by a hospital outpatient system, and also selected, preprocessed and dataized to ensure the accuracy of a classification algorithm. The classification algorithm model adopts a decision tree algorithm model, and in order to more clearly express the operation logic of the decision tree algorithm model in the patient follow-up method, the following description is given by way of example:
a. according to the collected basic information data of the patient, the algorithm model judges the classification of the patient into different categories, such as entry information of young females, middle-aged males, young obese males, middle-aged lean females and the like;
b. according to the collected characteristic data x of the patient, the algorithm model judges further judging conditions of the patient, such as low blood sugar level of young females, taking cephalosporin medicines by middle-aged males, eating meat of young obese males, and more night stay of middle-aged lean females;
c. according to the preset association information in the system, associating the obtained entry information with disease risk data and drug response data, analyzing the illness state and treatment effect of a patient through association results, predicting possible problems in the future, and triggering related suggestions;
d. based on the above information, the system may generate personalized follow-up plans and suggestions, for example, 1, generate vocabulary entries that the patient is young female with low blood sugar level, poor dietary habits, irregular life work and rest, etc., analyze the problem that the patient may continue to maintain low blood sugar level according to the vocabulary entry association result, and may cause related complications, and the system continues to suggest the patient to increase exercise amount, adjust diet, keep regular work and rest, take related drugs appropriately, etc. according to the association result; 2. generating vocabulary entries of which the patient is a male with a young normal body type, has normal diet, a life work and rest rule, good blood sugar control and the like, and analyzing the body of the patient to be in a good state according to the vocabulary entry association structure by the system so as to suggest the patient to keep a healthy life style.
S5, automatically making follow-up call according to the personalized follow-up plan, and performing system automatic follow-up;
the automatic call-up of the follow-up call can be realized by accessing a telephone network or using a voice over internet protocol (VoIP) technology, the personalized follow-up schedule comprises a follow-up time, a follow-up frequency, follow-up contents and follow-up suggestions, the follow-up contents are generally in a form of a one-answer, and the system plays corresponding pre-recorded voice contents according to the information of the patient.
For example, when a task of calling is needed in the personalized follow-up plan, the system can automatically dial the telephone number of the patient, after the patient is on the telephone, the system can firstly play greetings or voice prompts, and then sequentially ask preset problems including problems of state of illness, medicine taking condition, life style, eating habits, physical feeling and the like, and when the follow-up is finished, the voice prompts are played.
On the other hand, if the automatic call making fails to connect the patient, the system can automatically schedule the medical staff to make manual contact, for example, make contact with the patient by means of short messages, mails, etc., or make manual call making by the medical staff to make contact with the patient.
S6, identifying voice content in the follow-up telephone in real time, and converting the identification result into text data;
in this step, the call content is recorded in the whole process and recognized in real time, and the recognition and conversion of the voice content can be realized by using the existing voice recognition technology, such as the natural language processing technology based on deep learning.
S7, carrying out structuring treatment on the text data to obtain structured follow-up data;
the structured follow-up data obtained in this step can facilitate doctors to better understand the condition and treatment of patients, judge the progress and treatment effect of the diseases, provide references for making personalized treatment schemes, please refer to fig. 4, and the treatment process comprises the following steps:
step S71, extracting key information from the text data;
step S72, analyzing the extracted text data by utilizing data visualization, data mining and natural language processing;
and step 73, classifying and archiving the analyzed text data to obtain the structured follow-up data.
S8, analyzing the structural follow-up data to obtain updated characteristic data x, basic information data, disease risk data and drug response data;
the steps S1 to S8 are repeated every other planning time, the planning time is generated by the system to visit the time, or the doctor manually presets the planning time, and the information and data of the patient are continuously updated, so that the system and the doctor can adjust the follow-up plan, such as follow-up time, follow-up frequency, follow-up content, follow-up advice and the like, even the doctor can directly provide more personalized service and follow-up advice, and the treatment effect is improved.
In the process, the doctor can manually intervene in the steps S3, S4 and S5, namely, the characteristic data x, the basic information data, the disease risk data, the drug response data and other information data of the patient can be manually adjusted, so that the content of the follow-up method is more accurate, and after the follow-up is finished, the doctor needs to feed back the follow-up result to the patient by checking the analyzed structured follow-up data, so that the patient is informed of the illness state and the treatment condition of the patient, and the treatment scheme and advice of the next step. Meanwhile, the treatment confidence and treatment effect of the patient can be improved by feeding back the follow-up result.
Through the implementation of the patient follow-up system, the comprehensive and personalized follow-up service for the patient can be realized, the condition and the treatment condition of the patient can be mastered in time, the targeted medical service is provided, and the treatment confidence and the treatment effect of the patient can be improved.
In order to implement the patient follow-up method, the present invention also provides a patient follow-up system, please refer to fig. 5, which is a schematic frame diagram of the patient follow-up system provided by the present invention, the patient follow-up system includes: the system comprises a follow-up planning module, an automatic dialing module, a voice recognition and processing module, a follow-up data structuring module and a database module.
Specifically, the follow-up plan module is used for automatically generating a personalized follow-up plan according to the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient;
the automatic dialing module is used for automatically dialing follow-up call according to the personalized follow-up plan;
the voice recognition and processing module is used for recognizing voice contents in the follow-up telephone in real time and converting a recognition result into text data;
the follow-up data structuring module is used for structuring the text data and obtaining structured follow-up data;
and the database module is used for storing and managing the structured follow-up data of the patient and providing the functions of inquiring and analyzing.
It should be noted that, for convenience and brevity of description, a specific working process of each module and unit in the above-described patient follow-up system is clearly understood by those skilled in the art, as shown in fig. 6, and a schematic diagram of a flow relationship between the patient follow-up system and a doctor and a patient provided by the present invention may refer to a corresponding process in the foregoing patient follow-up method, which is not described herein again. Through above-mentioned patient follow-up system, can realize more intelligent, high-efficient and convenient follow-up service, improve doctor's work efficiency, also can help the patient to manage own health condition better simultaneously.
In addition, the invention also provides a patient follow-up device.
Referring to fig. 7, a schematic structural diagram of a patient follow-up device according to an embodiment of the present invention includes a processor, a memory, a communication bus, a network interface, and a computer program stored in the memory and executable by the processor.
The processor may in some embodiments be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor or other data processing chip for running program code or processing data stored in the memory, such as a program for performing a patient follow-up method or the like.
The memory includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory may be used not only for storing the application software installed in the patient follow-up system and the executable computer program, such as code of a program implementing the patient follow-up method, etc., but also for temporarily storing data that has been output or is to be output.
The communication bus is used to enable connected communication between these components.
The network interface may comprise a standard wired interface, a wireless interface (e.g., WI-FI interface), and is typically used to establish a communication connection between the patient follow-up device and other electronic equipment.
In an embodiment of one of the patient follow-up devices, a computer program for implementing the patient follow-up method is stored in the memory, and the processor executes the computer program stored in the memory.
In conclusion, the invention realizes the functions of automatic dialing of follow-up call, voice recognition, processing and the like according to the follow-up plan through an automatic technology, improves the follow-up efficiency, reduces the labor cost, and simultaneously improves the follow-up quality and the satisfaction degree of patients; by carrying out structural processing on the follow-up data, the readability and the analyzability of the data are improved, so that the treatment effect of doctors and the satisfaction degree of patients are improved; the follow-up data is analyzed through the data analysis and artificial intelligence technology, personalized follow-up contents and follow-up plans are generated, doctors are helped to better know the illness state and treatment condition of patients, and the risk of follow-up misdiagnosis is reduced.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (10)
1. A method of patient follow-up comprising the steps of:
step S1, collecting case data C and characteristic data x of a patient;
s2, predicting the case data C and the feature data x by using a naive Bayesian algorithm to obtain a case category C k Posterior probability P (C) k |x 1 ，x 2 ，…，x m )；
Step S3, according to the posterior probability P (C k |x 1 ，x 2 ，…，x m ) Classifying the cases of the patient into different categories, and obtaining disease risk data and drug response data of the patient;
s4, automatically generating a personalized follow-up plan for the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient by using a decision tree algorithm;
s5, automatically making follow-up call according to the personalized follow-up plan, and performing system automatic follow-up;
s6, identifying voice content in the follow-up telephone in real time, and converting the identification result into text data;
s7, carrying out structuring treatment on the text data to obtain structured follow-up data;
s8, analyzing the structural follow-up data to obtain updated characteristic data x, basic information data, disease risk data and drug response data;
steps S1 to S8 are repeated every planning time, wherein the doctor can intervene manually in steps S3, S4 and S5 and feed back the follow-up result to the patient.
2. The patient follow-up method according to claim 1, wherein in step S1, the characteristic data x is selected and pre-processed according to characteristics of the patient, wherein the characteristics of the patient include age, sex, medication, examination index, blood glucose level, eating habits, lifestyle and condition change.
3. A patient follow-up method according to claim 2, wherein the selection and pre-treatment of the characteristics of the patient comprises the steps of:
s11, carrying out correlation analysis and principal component analysis on the characteristics of a patient to obtain important characteristic data;
step S12, carrying out normalization processing on important characteristic data;
and S13, performing missing value filling processing on the important characteristic data after normalization processing to obtain characteristic data x.
4. A patient follow-up method according to claim 3, wherein in step S2, the predicting using a naive bayes algorithm comprises the steps of:
step S21, suggesting a case data set containing the total number of cases collected;
step S22, calculating according to the case data C to obtain the case category C k The proportion of cases to the total number of cases, i.e. each case class C k Is (C) k )；
Step S23, according to the prior probability P (C k ) And the feature data x are calculated to obtain each feature in each case category C k Conditional probability P (x) j |C k )；
Step S24, for conditional probability P (x j |C k ) Performing maximum likelihood estimation processing;
step S25, the conditional probability P (x j |C k ) Calculation of case category C using Bayesian theorem k Posterior probability P (C) k |x 1 ，x 2 ，…，x m )。
5. The patient follow-up method according to claim 1, wherein in step S4, the basic information data includes age, sex, BMI, body fat rate, contact number;
the personalized follow-up plan includes a follow-up time, a follow-up frequency, follow-up content, and follow-up advice.
6. The patient follow-up method according to claim 1, wherein in step S5, the follow-up content and follow-up advice of the system automatic follow-up are pre-recorded speech content;
if the automatic dialing follow-up call is unsuccessful, automatically scheduling medical staff to conduct manual contact.
7. The patient follow-up method according to claim 1, wherein in step S7, the structuring of the text data comprises the steps of:
step S71, extracting key information from the text data;
step S72, analyzing the extracted text data by utilizing data visualization, data mining and natural language processing;
and step 73, classifying and archiving the analyzed text data to obtain the structured follow-up data.
8. The patient follow-up method according to claim 1, wherein the content that the doctor can perform manual intervention includes adjusting follow-up time, follow-up frequency, follow-up content and follow-up advice, adding or deleting characteristic data x, basic information data, disease risk data, and drug response data to the system.
9. A patient follow-up system to which the patient follow-up method according to any one of claims 1 to 8 is applied, characterized in that the patient follow-up system comprises:
the follow-up plan module is used for automatically generating a personalized follow-up plan according to the characteristic data x, the basic information data, the disease risk data and the drug response data of the patient;
the automatic dialing module is used for automatically dialing follow-up call according to the personalized follow-up plan;
the voice recognition and processing module is used for recognizing voice contents in the follow-up telephone in real time and converting a recognition result into text data;
the follow-up data structuring module is used for structuring the text data and obtaining structured follow-up data;
and the database module is used for storing and managing the structured follow-up data of the patient and providing the functions of inquiring and analyzing.
10. A patient follow-up device comprising a processor, a memory and a computer program stored on the memory and executable by the processor, which when executed by the processor, implements the steps of the patient follow-up method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311192155.5A CN117059220A (en) | 2023-09-15 | 2023-09-15 | Patient follow-up method, follow-up system and follow-up device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311192155.5A CN117059220A (en) | 2023-09-15 | 2023-09-15 | Patient follow-up method, follow-up system and follow-up device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117059220A true CN117059220A (en) | 2023-11-14 |
Family
ID=88662760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311192155.5A Pending CN117059220A (en) | 2023-09-15 | 2023-09-15 | Patient follow-up method, follow-up system and follow-up device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117059220A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239647A (en) * | 2016-03-28 | 2017-10-10 | 孙少燕 | A kind of disease analysis system based on bayesian algorithm |
| CN107315906A (en) * | 2017-06-01 | 2017-11-03 | 北京瑞启医药信息科技有限公司 | The method and system of the automatic follow-up of chronic are realized based on chat robots |
| CN110265153A (en) * | 2019-05-16 | 2019-09-20 | 平安科技（深圳）有限公司 | Chronic disease follow-up method and electronic device |
| CN112542252A (en) * | 2020-11-27 | 2021-03-23 | 上海市疾病预防控制中心 | Voice follow-up method, management system and voice follow-up platform for chronic patients |
| CN113380424A (en) * | 2020-12-07 | 2021-09-10 | 北京左医科技有限公司 | Automatic generation method and automatic generation device for follow-up plan and storage medium |
| CN114512240A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Gout prediction model system, equipment and storage medium |
-
2023
- 2023-09-15 CN CN202311192155.5A patent/CN117059220A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239647A (en) * | 2016-03-28 | 2017-10-10 | 孙少燕 | A kind of disease analysis system based on bayesian algorithm |
| CN107315906A (en) * | 2017-06-01 | 2017-11-03 | 北京瑞启医药信息科技有限公司 | The method and system of the automatic follow-up of chronic are realized based on chat robots |
| CN110265153A (en) * | 2019-05-16 | 2019-09-20 | 平安科技（深圳）有限公司 | Chronic disease follow-up method and electronic device |
| CN112542252A (en) * | 2020-11-27 | 2021-03-23 | 上海市疾病预防控制中心 | Voice follow-up method, management system and voice follow-up platform for chronic patients |
| CN113380424A (en) * | 2020-12-07 | 2021-09-10 | 北京左医科技有限公司 | Automatic generation method and automatic generation device for follow-up plan and storage medium |
| CN114512240A (en) * | 2022-02-08 | 2022-05-17 | 吾征智能技术(北京)有限公司 | Gout prediction model system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11810671B2 (en) | System and method for providing health information | |
| US8805756B2 (en) | Enhanced DeepQA in a medical environment | |
| US8510340B2 (en) | Categorization of information using natural language processing and predefined templates | |
| US11275985B2 (en) | Artificial intelligence advisory systems and methods for providing health guidance | |
| JP2019016235A (en) | Disease onset prediction device, disease onset prediction method and program | |
| CN111933291A (en) | Medical information recommendation device, method, system, equipment and readable storage medium | |
| US20200058408A1 (en) | Systems, methods, and apparatus for linking family electronic medical records and prediction of medical conditions and health management | |
| US11875884B2 (en) | Expression of clinical logic with positive and negative explainability | |
| CN112908481A (en) | Automatic personal health assessment and management method and system | |
| CN111008269A (en) | Data processing method and device, storage medium and electronic terminal | |
| CN114121266A (en) | Intelligent auxiliary diagnosis method and system | |
| CN112542242A (en) | Data transformation/symptom scoring | |
| CN112908452A (en) | Event data modeling | |
| CN112447270A (en) | Medication recommendation method, device, equipment and storage medium | |
| CN111403025A (en) | Intelligent diagnosis and treatment system based on internet medical service | |
| CN111274351A (en) | Method and device for automatically adjusting user priority, electronic equipment and storage medium | |
| CN117216322A (en) | Method, device, equipment and storage medium for generating electronic medical record | |
| CN117672451A (en) | Medicine recommendation method for type 2 diabetics | |
| CN115148332A (en) | Intelligent follow-up system and method for myeloma | |
| US10431339B1 (en) | Method and system for determining relevant patient information | |
| CN117059220A (en) | Patient follow-up method, follow-up system and follow-up device | |
| US20230005603A1 (en) | Intelligent emergency triage system | |
| CN113658688A (en) | Clinical decision support method based on word segmentation-free deep learning | |
| CN110473636B (en) | Intelligent medical advice recommendation method and system based on deep learning | |
| CN111667922A (en) | Clinical diagnosis and treatment data entry system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |