CN114429820A - Intelligent rehabilitation evaluation system and method for hospital rehabilitation department - Google Patents
Intelligent rehabilitation evaluation system and method for hospital rehabilitation department Download PDFInfo
- Publication number
- CN114429820A CN114429820A CN202210072620.0A CN202210072620A CN114429820A CN 114429820 A CN114429820 A CN 114429820A CN 202210072620 A CN202210072620 A CN 202210072620A CN 114429820 A CN114429820 A CN 114429820A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- rehabilitation
- similarity
- medical record
- patient
- 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
Images
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
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses an intelligent rehabilitation evaluation system and an intelligent rehabilitation evaluation method for a hospital rehabilitation department, and solves the problems that an evaluation table cannot be quickly searched in the existing rehabilitation evaluation process, the evaluation results of a patient cannot be compared and the like. The intelligent rehabilitation evaluation system comprises a doctor workstation, an intelligent analysis module, a rehabilitation evaluation workstation and a storage module; the doctor workstation is used for collecting the admission medical record information of the patient and issuing an evaluation task to the rehabilitation evaluation workstation; the intelligent analysis system is used for carrying out similarity analysis on medical record information of the new patient and a historical medical record database, outputting a recommendation result and returning the recommendation result to the doctor workstation; the rehabilitation evaluation workstation is used for receiving and distributing evaluation tasks, and a rehabilitation evaluator receives the evaluation scale issued by the doctor and then carries out on-line evaluation on the patient and outputs an evaluation result; the storage module is used for carrying out persistent storage on the evaluation result evaluated by the rehabilitation evaluator.
Description
Technical Field
The invention relates to an evaluation system for diagnosis, in particular to an intelligent rehabilitation evaluation system and an intelligent rehabilitation evaluation method for a hospital rehabilitation department.
Background
Currently, most of the evaluation processes of the rehabilitation department adopt an offline evaluation mode, after an evaluation prescription is issued by a main doctor through a medical HIS system, a rehabilitation evaluator prints out the evaluation list through a printer according to an evaluation list on the evaluation prescription issued by the doctor, the evaluation list is distributed to different therapists to evaluate patients, the evaluation result is filed in a paper form, and part of hospitals scan the evaluation result into pictures and finally file the pictures in an electronic medical record system of the hospital. Although the method solves the storage of the evaluation process and the evaluation result, the evaluation result data is not effectively utilized for analysis, the evaluation table can not be quickly retrieved, the evaluation results of the patient can not be compared for many times, and effective data support can not be provided for recommendation, prediction and analysis based on the evaluation results.
Disclosure of Invention
The invention provides an intelligent rehabilitation evaluation system for a hospital rehabilitation department, which aims to solve the problems that the existing rehabilitation evaluation process cannot quickly search an evaluation table, cannot compare evaluation results of a patient for many times, cannot provide effective data support for recommendation, prediction and analysis based on the evaluation results, and the like.
Meanwhile, an intelligent rehabilitation assessment method for the hospital rehabilitation department is also provided.
The specific technical scheme of the invention is as follows:
an intelligent rehabilitation evaluation system for a hospital rehabilitation department comprises a doctor workstation, an intelligent analysis module, a rehabilitation evaluation workstation and a storage module;
the doctor workstation is used for collecting the admission medical record information of the patient and issuing an evaluation task to the rehabilitation evaluation workstation; the medical record information comprises chief complaints, current medical history, genetic history, past history, disease diagnosis, physical examination and common diseases;
the intelligent analysis system is used for carrying out similarity analysis on medical record information of the new patient and a historical medical record database, outputting a recommendation result and returning the recommendation result to the doctor workstation; the recommendation result comprises the medical record information of the previous similar patient and a plurality of evaluation scales corresponding to the medical record information of the previous similar patient;
the rehabilitation evaluation workstation is used for receiving and distributing evaluation tasks, and a rehabilitation evaluator receives the evaluation scale issued by the doctor and then carries out on-line evaluation on the patient and outputs an evaluation result;
the storage module is used for carrying out persistent storage on the evaluation result evaluated by the rehabilitation evaluator.
Furthermore, the rehabilitation evaluation workstation in the system is also used for comparing the periodic evaluation scales of a certain patient periodically so as to judge the disease rehabilitation condition of the patient.
Furthermore, the similarity analysis in the system adopts a cosine similarity algorithm;
the specific formula of the cosine similarity algorithm is as follows:
in the formula, A represents one dimension in the sample A, B represents the first dimension of the sample B, n represents n dimensions, and i represents the dimension from the ith.
Wherein, n dimensions are respectively chief complaints, current disease history, hereditary history, past history, disease diagnosis, physical examination and common diseases;
the cos theta value represents the similarity of the two samples, the calculated cos theta value ranges from [ -1,1], and the closer the cos theta value is to 1, the higher the similarity is.
Furthermore, the similarity analysis in the system adopts a Jaccard similarity algorithm;
the concrete formula of the Jaccard similarity algorithm is as follows:
assuming that the sample A and the sample B are two n-dimensional vectors, the dj value calculated by comparing the two samples represents the similarity of the two samples, the calculated dj value ranges from [0,1], and the closer the value is to 1, the higher the similarity is represented.
Furthermore, the similarity analysis in the system simultaneously adopts cosine similarity and Jaccard similarity calculation methods to solve the similarity, and the recommendation result corresponding to the algorithm with high similarity in the two algorithms is used as the final recommendation result.
The invention also provides a method for evaluating rehabilitation by adopting the rehabilitation evaluation system, which comprises the following implementation steps:
step 1: the medical record information of the new patient is collected by the doctor workstation and is sent to the intelligent analysis system; the medical record information comprises chief complaints, current medical history, genetic history, past history, diagnosis results, physical examination, common diseases and the like;
step 2: outputting a recommendation result according to the medical record information of the new patient;
step 2.1: the intelligent analysis system receives medical record information of a new patient, performs word segmentation according to the TF-IDF inverse document word frequency, and counts the occurrence frequency to retrieve medical record information of similar patients in the past according with conditions from a historical medical record database; wherein: the historical medical record database comprises medical record information of a plurality of previous patients;
step 2.2: taking the medical record information of the new patient and the medical record information of the previous similar patient as a sample A and a sample B, then solving the similarity of the sample A and the sample B, and if the similarity is more than 50%, outputting a recommendation result; the recommendation result comprises the medical record information of the similar previous patients and a plurality of evaluation scales corresponding to the medical record information of the previous patients;
if the similarity is less than 50%, outputting a null value which represents no recommendation result;
and 3, step 3: after the intelligent analysis system returns the recommendation result to the doctor workstation, the doctor workstation issues an evaluation task to the rehabilitation evaluation workstation, a rehabilitation therapist logs in the rehabilitation evaluation workstation after receiving the evaluation task, and carries out online rehabilitation evaluation on the patient according to the received evaluation scale;
and 4, step 4: and the storage module is used for storing the evaluation result evaluated by the rehabilitation evaluator in a lasting way.
Further, the method also comprises the step 5: and periodically comparing the staged evaluation results of a certain patient through a rehabilitation evaluation workstation, thereby judging the disease rehabilitation condition of the patient.
Further, in the method, in step 2.2, the similarity between the sample A and the sample B is solved by using a cosine similarity algorithm; the specific formula of the cosine similarity algorithm is as follows:
in the formula, A represents one dimension in the sample A, B represents the first dimension of the sample B, n represents n dimensions, and i represents the dimension from the ith.
Wherein the dimension is sex, age, chief complaint, current history, past history, and disease diagnosis.
Further, in the method, the similarity between the sample A and the sample B is solved in the step 2.2 by adopting a Jaccard similarity algorithm;
the specific formula of the Jaccard similarity algorithm is as follows:
assuming that the sample A and the sample B are two n-dimensional vectors, the dj value calculated by comparing the two samples represents the similarity of the two samples, the calculated dj value ranges from [0,1], and the closer the value is to 1, the higher the similarity is represented.
Furthermore, in the method, the similarity analysis simultaneously adopts cosine similarity and Jaccard similarity calculation methods to solve the similarity, and the recommendation result corresponding to the algorithm with high similarity in the two algorithms is used as the final recommendation result.
The invention has the beneficial effects that:
1. according to the invention, the evaluation system is constructed by adopting the doctor workstation, the intelligent analysis system, the rehabilitation evaluation workstation and the storage module, so that the traditional paper evaluation mode of the rehabilitation department at present is improved, and the problems of difficult analysis and difficult storage caused by the traditional evaluation result at present are improved; meanwhile, according to the basic data, diagnosis result and other coefficients of the patient, an assessment scale and an automatic backfill assessment result are automatically recommended in a large data analogy mode of an expert model base, so that the assessment efficiency is improved, and support is provided for assessment decision.
2. According to the invention, the TF-IDF inverse document word frequency is adopted for word segmentation, the occurrence frequency is counted, and medical record information of the previous similar patient meeting the condition is retrieved from the historical medical record database, the data is filtered in advance before the data similarity analysis, the screened data better meets the analysis standard, and meanwhile, the efficiency of mass data analysis is improved.
3. The invention provides more accurate recommendation of the evaluation scale by combining the similarity algorithm.
Drawings
FIG. 1 is a block diagram of an assessment system of the present invention.
FIG. 2 is a schematic diagram of the assessment method of the present invention.
FIG. 3 is a screenshot of a portion of historical medical record database content.
Fig. 4 is a schematic diagram of the evaluation process of Zhang III of the patient.
Fig. 5 is a schematic diagram of intelligent analysis of the patient three medical record information.
FIG. 6 is an evaluation representation of freehand muscle force assessment.
Detailed Description
For the understanding of the present invention, the following description will be made by referring to the accompanying drawings in the form of specific embodiments, and the drawings are not intended to limit the flow of the specific implementation of the present invention.
The embodiment provides an intelligent rehabilitation evaluation system for a hospital rehabilitation department, which comprises a doctor workstation, an intelligent analysis system, a rehabilitation evaluation workstation and a storage module, wherein the doctor workstation is connected with the intelligent analysis system;
the four modules are all operated in a server of a machine room, wherein a doctor workstation, an intelligent analysis module and a rehabilitation evaluation workstation are operated in one server, and a storage module is an independent server;
the doctor workstation is used for collecting the admission medical record information of the patient and issuing an evaluation task to the rehabilitation evaluation workstation; the medical record information includes chief complaints, current medical history, genetic history, past medical history, disease diagnosis, physical examination and common diseases.
The intelligent analysis system is used for carrying out similarity analysis on medical record information of the new patient and a historical medical record database, outputting a recommendation result and returning the recommendation result to the doctor workstation; the recommendation result comprises medical record information of the previous patient with the highest similarity and a plurality of evaluation scales corresponding to the medical record information of the previous patient;
the rehabilitation evaluation workstation is used for receiving and distributing evaluation tasks, and a rehabilitation evaluator receives the evaluation scale issued by the doctor and then carries out on-line evaluation on the patient and outputs an evaluation result;
the storage module is used for carrying out persistent storage on the evaluation result evaluated by the rehabilitation evaluator.
In addition, the rehabilitation assessment workstation also compares the periodic assessment scale of a certain patient regularly so as to judge the disease rehabilitation condition of the patient.
The evaluation system constructed by the invention realizes deep learning of historical evaluation data and forms an expert model library for guiding the evaluation process of an attending doctor and a rehabilitation evaluator, improves the business level and the working efficiency of a department and brings promotion to scientific research value.
The core of the system is to establish association between the medical record information of the past patient and the evaluation scale, so that an expert model base is formed, and the medical record of the newly admitted patient is analogized and analyzed, thereby achieving the purpose of automatic recommendation.
Based on the above description of the functioning of the rating system, a method for rating using the rating system will now be described, as shown in FIG. 2:
step 1: the medical record information of the new patient is collected by the doctor workstation and is sent to the intelligent analysis system; the medical record information comprises main complaints, current medical history, genetic history, past history, diagnosis results, physical examination, common diseases and the like;
and 2, step: outputting a recommendation result according to the medical record information of the new patient;
step 2.1: the intelligent analysis system receives medical record information of a new patient, performs word segmentation according to the TF-IDF inverse document word frequency, and counts the occurrence frequency to retrieve medical record information of similar patients in the past according with conditions from a historical medical record database; wherein: the historical medical record database comprises medical record information of a plurality of previous patients, and the content of part of the historical medical record database is shown in figure 3;
in this step, it is to be noted that: if the hospital is a specialized rehabilitation hospital for a certain disease, the word segmentation of TF-IDF document word frequency is not needed;
step 2.2: taking the medical record information of the new patient and the medical record information of the previous similar patient as a sample A and a sample B, then solving the similarity of the sample A and the sample B, and if the similarity is more than 50%, outputting a recommendation result; the recommendation result comprises the medical record information of the similar previous patients and a plurality of evaluation scales corresponding to the medical record information of the previous patients;
if the similarity is less than 50%, outputting a null value which represents no recommendation result;
the similarity solution of the sample a and the sample B in this step can have the following three ways:
the first method comprises the following steps: separately adopting a cosine similarity algorithm;
the specific formula of the cosine similarity algorithm is as follows:
in the formula, A represents one dimension in the sample A, B represents the first dimension of the sample B, n represents n dimensions, and i represents the dimension from the ith.
Wherein the dimension is sex, age, chief complaint, current history, past history, and disease diagnosis;
the cos theta value represents the similarity of the two samples, the calculated cos theta value ranges from [ -1,1], and the closer the cos theta value is to 1, the higher the similarity is;
and the second method comprises the following steps: a Jaccard similarity algorithm is independently adopted;
the concrete formula of the Jaccard similarity algorithm is as follows:
assuming that the sample A and the sample B are two n-dimensional vectors, the dj value calculated by comparing the two samples represents the similarity of the two samples, the calculated dj value ranges from [0,1], and the closer the value is to 1, the higher the similarity is represented.
And the third is that: and simultaneously solving the similarity by adopting cosine similarity and Jaccard similarity algorithms, and taking a recommendation result corresponding to the algorithm with high similarity in the two algorithms as a final recommendation result.
And step 3: after the intelligent analysis system returns the recommendation result to the doctor workstation, the doctor workstation issues an evaluation task to the rehabilitation evaluation workstation, a rehabilitation therapist logs in the rehabilitation evaluation workstation after receiving the evaluation task, and the patient is subjected to online rehabilitation evaluation according to the received evaluation scale;
and 4, step 4: and the storage module stores the evaluation result evaluated by the rehabilitation evaluator in a persistent manner.
Besides the core process, the staged evaluation results of a certain patient can be regularly compared through a rehabilitation evaluation workstation, so that the disease rehabilitation condition of the patient can be judged, and a doctor can be guided to perform subsequent treatment.
Taking Zhang III as an example to more clearly explain the evaluation method, as shown in FIG. 4, a doctor workstation collects medical record information of Zhang III of a patient, wherein the medical record information comprises chief complaints, current medical history, genetic history, past history, disease diagnosis, physical examination and common diseases of Zhang III.
The doctor workstation pushes the medical record information of Zhang III to an intelligent analysis system for recommendation analysis, the intelligent analysis system finds the historical medical record information of the prior patient meeting the conditions from a historical medical record information base by using a TF-IDF algorithm according to disease diagnosis data, then analyzes and calculates the proportion of similarity by using a cosine similarity algorithm and a jaccard similarity algorithm respectively, as shown in figure 5, and selects corresponding recommendation results with larger similarity in the two algorithms to return to the doctor workstation (for example, the optimal result similarity obtained by supposing the cosine similarity is 0.6, the corresponding evaluation table set is [ free hand muscle strength evaluation (MMT), muscle tension evaluation and balance function evaluation ], the result obtained by the jaccard similarity algorithm is 0.75, the evaluation table set is [ swallowing disorder evaluation, life self-care ability evaluation and hand muscle strength evaluation (MMT) ], where the freehand muscle force rating assessment scale is shown in fig. 6, the recommendation system employs a jaccard similarity algorithm of 0.75 to recommend the result as the final returned solution). The doctor workstation issues the evaluation task to the rehabilitation therapist, the rehabilitation therapist carries out online evaluation after receiving the online evaluation task, and then the evaluated result is stored in the storage module.
Claims (10)
1. The utility model provides a recovered evaluation system of intelligence for recovered branch of academic or vocational study of hospital which characterized in that:
comprises a doctor workstation, an intelligent analysis module, a rehabilitation evaluation workstation and a storage module;
the doctor workstation is used for collecting the admission medical record information of the patient and issuing an evaluation task to the rehabilitation evaluation workstation; the medical record information comprises chief complaints, current medical history, genetic history, past history, disease diagnosis, physical examination and common diseases;
the intelligent analysis system is used for carrying out similarity analysis on medical record information of the new patient and a historical medical record database, outputting a recommendation result and returning the recommendation result to the doctor workstation; the recommendation result comprises the medical record information of the previous similar patient and a plurality of evaluation scales corresponding to the medical record information of the previous similar patient;
the rehabilitation evaluation workstation is used for receiving and distributing evaluation tasks, and a rehabilitation evaluator receives the evaluation scale issued by the doctor and then carries out on-line evaluation on the patient and outputs an evaluation result;
the storage module is used for carrying out persistent storage on the evaluation result evaluated by the rehabilitation evaluator.
2. The intelligent rehabilitation assessment system for hospital rehabilitation as claimed in claim 1, characterized in that: the rehabilitation evaluation workstation is also used for comparing the periodic evaluation scales of a certain patient periodically so as to judge the disease rehabilitation condition of the patient.
3. The intelligent rehabilitation assessment system for hospital rehabilitation as claimed in claim 1, characterized in that: the similarity analysis adopts a cosine similarity algorithm;
the specific formula of the cosine similarity algorithm is as follows:
in the formula, A represents one dimension in the sample A, B represents the first dimension of the sample B, n represents n dimensions, and i represents the dimension from the ith;
wherein, n dimensions are respectively chief complaints, current disease history, hereditary history, past history, disease diagnosis, physical examination and common diseases;
the cos theta value represents the similarity of the two samples, the calculated cos theta value ranges from [ -1,1], and the closer the cos theta value is to 1, the higher the similarity is.
4. The intelligent rehabilitation assessment system for hospital rehabilitation as claimed in claim 1, characterized in that: the similarity analysis adopts a Jaccard similarity algorithm;
the concrete formula of the Jaccard similarity algorithm is as follows:
assuming that the sample A and the sample B are two n-dimensional vectors, the dj value calculated by comparing the two samples represents the similarity of the two samples, the calculated dj value ranges from [0,1], and the closer the value is to 1, the higher the similarity is represented.
5. The intelligent rehabilitation assessment system for hospital rehabilitation as claimed in claim 1, characterized in that: and the similarity analysis simultaneously adopts a cosine similarity and Jaccard similarity algorithm to solve the similarity, and takes a recommendation result corresponding to an algorithm with high similarity in the two algorithms as a final recommendation result.
6. An intelligent rehabilitation assessment method for a hospital rehabilitation department is characterized by comprising the following steps: the rehabilitation assessment system of claim 1
Step 1: the medical record information of the new patient is collected by the doctor workstation and is sent to the intelligent analysis system; the medical record information comprises main complaints, current medical history, genetic history, past history, diagnosis results, physical examination, common diseases and the like;
step 2: outputting a recommendation result according to the medical record information of the new patient;
step 2.1: the intelligent analysis system receives medical record information of a new patient, performs word segmentation according to the TF-IDF inverse document word frequency, and counts the occurrence frequency to retrieve medical record information of similar patients in the past according with conditions from a historical medical record database; wherein: the historical medical record database comprises medical record information of a plurality of previous patients;
step 2.2: taking the medical record information of the new patient and the medical record information of the previous similar patient as a sample A and a sample B, then solving the similarity of the sample A and the sample B, and if the similarity is more than 50%, outputting a recommendation result; the recommendation result comprises the medical record information of the similar previous patients and a plurality of evaluation scales corresponding to the medical record information of the previous patients;
if the similarity is less than 50%, outputting a null value which represents no recommendation result;
and step 3: after the intelligent analysis system returns the recommendation result to the doctor workstation, the doctor workstation issues an evaluation task to the rehabilitation evaluation workstation, a rehabilitation therapist logs in the rehabilitation evaluation workstation after receiving the evaluation task, and carries out online rehabilitation evaluation on the patient according to the received evaluation scale;
and 4, step 4: and the storage module is used for storing the evaluation result evaluated by the rehabilitation evaluator in a lasting way.
7. The intelligent rehabilitation assessment method for hospital rehabilitation department according to claim 6, characterized in that: further comprising the step 5: and periodically comparing the staged evaluation results of a certain patient through a rehabilitation evaluation workstation, thereby judging the disease rehabilitation condition of the patient.
8. The intelligent rehabilitation assessment method for hospital rehabilitation department according to claim 6, characterized in that: in the step 2.2, the similarity of the sample A and the sample B is solved by adopting a cosine similarity algorithm; the specific formula of the cosine similarity algorithm is as follows:
in the formula, A represents one dimension in the sample A, B represents the first dimension of the sample B, n represents n dimensions, and i represents the dimension from the ith;
wherein the dimension is sex, age, chief complaint, current history, past history, and disease diagnosis.
9. The intelligent rehabilitation assessment method for hospital rehabilitation department according to claim 6, characterized in that: in the step 2.2, the similarity of the sample A and the sample B is solved by adopting a Jaccard similarity algorithm;
the concrete formula of the Jaccard similarity algorithm is as follows:
assuming that the sample A and the sample B are two n-dimensional vectors, the dj value calculated by comparing the two samples represents the similarity of the two samples, the calculated dj value ranges from [0,1], and the closer the value is to 1, the higher the similarity is represented.
10. The intelligent rehabilitation assessment method for hospital rehabilitation department according to claim 6, characterized in that: and the similarity analysis simultaneously adopts cosine similarity and Jaccard similarity algorithms to solve the similarity, and takes the recommendation result corresponding to the algorithm with high similarity in the two algorithms as the final recommendation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072620.0A CN114429820A (en) | 2022-01-21 | 2022-01-21 | Intelligent rehabilitation evaluation system and method for hospital rehabilitation department |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210072620.0A CN114429820A (en) | 2022-01-21 | 2022-01-21 | Intelligent rehabilitation evaluation system and method for hospital rehabilitation department |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114429820A true CN114429820A (en) | 2022-05-03 |
Family
ID=81312501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210072620.0A Pending CN114429820A (en) | 2022-01-21 | 2022-01-21 | Intelligent rehabilitation evaluation system and method for hospital rehabilitation department |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114429820A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052378A (en) * | 2023-04-03 | 2023-05-02 | 中航创世机器人(西安)有限公司 | Alarm analysis method and system based on multi-stage user adaptation |
-
2022
- 2022-01-21 CN CN202210072620.0A patent/CN114429820A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116052378A (en) * | 2023-04-03 | 2023-05-02 | 中航创世机器人(西安)有限公司 | Alarm analysis method and system based on multi-stage user adaptation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112256828B (en) | Medical entity relation extraction method, device, computer equipment and readable storage medium | |
| US20080120267A1 (en) | Systems and methods for analyzing data to predict medical outcomes | |
| CN106934235A (en) | Patient's similarity measurement migratory system between a kind of disease areas based on transfer learning | |
| Sharara et al. | Active surveying: A probabilistic approach for identifying key opinion leaders | |
| CN109935337B (en) | Medical record searching method and system based on similarity measurement | |
| CN108986907A (en) | A kind of tele-medicine based on KNN algorithm divides the method for examining automatically | |
| CN111710364B (en) | Method, device, terminal and storage medium for acquiring flora marker | |
| US11636411B2 (en) | Apparatus for determining role fitness while eliminating unwanted bias | |
| CN117290462B (en) | Intelligent decision system and method for large data model | |
| CN110543594B (en) | Knowledge base-based personalized evidence-based correction recommendation method for prisoners | |
| CN114429820A (en) | Intelligent rehabilitation evaluation system and method for hospital rehabilitation department | |
| CN113284627B (en) | Medication recommendation method based on patient characterization learning | |
| CN111950840A (en) | Intelligent operation and maintenance knowledge retrieval method and system for metrological verification device | |
| Nababan et al. | Implementation of K-Nearest Neighbors (KNN) algorithm in classification of data water quality | |
| CN113407700A (en) | Data query method, device and equipment | |
| CN110634565A (en) | Regression analysis method for medical big data | |
| Kaur et al. | A review on Naive Baye’s (NB), J48 and K-means based mining algorithms for medical data mining | |
| CN117435648B (en) | Method, device, equipment and storage medium for associating college teacher with scientific research result | |
| CN117033584B (en) | Method and device for determining case text and electronic equipment | |
| Xie et al. | Research on assistant diagnostic method of TCM based on multi classifier integration | |
| CN115440330A (en) | Chinese electronic medical record named entity identification method based on active learning | |
| Anirudh et al. | A Hybrid Model for Accurate Prediction of Progression in Parkinson’s Disease | |
| CN117909466A (en) | Domain question-answering system, construction method, electronic device and storage medium | |
| Nezhad-Afrasiabi et al. | Discovering profitable customers by data mining approach | |
| CN112966161A (en) | Public opinion category determination method, device and equipment |
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 |