CN114664415A - Intelligent department diagnosis guide recommendation system based on deep learning model - Google Patents

Intelligent department diagnosis guide recommendation system based on deep learning model Download PDF

Info

Publication number
CN114664415A
CN114664415A CN202210009501.0A CN202210009501A CN114664415A CN 114664415 A CN114664415 A CN 114664415A CN 202210009501 A CN202210009501 A CN 202210009501A CN 114664415 A CN114664415 A CN 114664415A
Authority
CN
China
Prior art keywords
model
data
department
deep learning
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
Application number
CN202210009501.0A
Other languages
Chinese (zh)
Inventor
李超然
刘举胜
宋美
何建佳
朱洁训
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai University of Sport
Original Assignee
Shanghai University of Sport
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai University of Sport filed Critical Shanghai University of Sport
Priority to CN202210009501.0A priority Critical patent/CN114664415A/en
Publication of CN114664415A publication Critical patent/CN114664415A/en
Pending legal-status Critical Current

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
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses an intelligent department consultation recommendation system based on a deep learning model, and particularly relates to the technical field of hospital consultation recommendation, wherein the system comprises a long-term and short-term memory neural network deep model, a webpage data collector and an online medical platform, wherein the output end of the online medical platform is connected with the input end of the webpage data collector; the long-short term memory neural network depth model acquires the chief complaint data of the patient in the online medical platform through the web data collector and performs vectorization expression and text classification on the chief complaint data of the patient during disease inquiry. The invention considers the real demand and the patient visit chief complaint data characteristic on the basis of the existing machine learning and natural language processing tool, effectively processes the context semantic association advantage of the long text by using the long and short term memory neural network depth model for reference, and carries out text classification on the patient chief complaint data by using the long and short term memory neural network depth model, thereby realizing the aim of intelligently guiding the patient.

Description

Intelligent department diagnosis guide recommendation system based on deep learning model
Technical Field
The invention relates to the technical field of hospital consultation recommendation, in particular to an intelligent department consultation recommendation system based on a deep learning model.
Background
In the existing literature, the research on online medical intelligent diagnosis guidance in China is rare, and firstly, the research of medical data in China is difficult to obtain, so that certain difficulty is brought to the research of most scholars and industrial personnel; secondly, most hospitals still do not carry out digital transformation and intelligent hospitals are constructed and popularized slowly at present, most hospitals still mainly take manual diagnosis guide as a main part, and intelligent diagnosis guide development is slow. With the increase of population in China, the number of patients to be treated in a hospital is gradually increased, at the moment, the cost of manual diagnosis guide service of the hospital is increased by a large number of patients, and the increasing treatment demands of the patients cannot be met by the hospital depending on the manual service alone. In addition, with the continuous development of natural language processing models and machine learning models, an intelligent department consultation recommendation method based on a deep learning model becomes possible. Therefore, the invention provides an intelligent department consultation recommendation system based on a deep learning model aiming at industrial pain points of 'department unknown to symptoms', high hospital consultation pressure and the like of patients.
Disclosure of Invention
Therefore, the invention provides an intelligent department consultation recommendation system based on a deep learning model, which can effectively process the semantic association advantages of long text context by considering the real requirements and the patient consultation chief data characteristics on the basis of the existing machine learning and natural language processing tools and by using the long-short term memory neural network deep model for reference, and can realize the intelligent consultation guidance of the patient by performing text classification on the patient chief data by using the long-short term memory neural network deep model so as to solve the problems in the background technology.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions: the intelligent department diagnosis guide recommendation system based on the deep learning model comprises a long-short term memory neural network depth model, a webpage data collector and an online medical platform, wherein the connecting end of the long-short term memory neural network depth model is connected with the connecting end of the webpage data collector, and the output end of the online medical platform is connected with the input end of the webpage data collector;
the long-short term memory neural network depth model acquires the chief complaint data of the patient in the online medical platform through the web data collector and performs vectorization expression and text classification on the chief complaint data of the patient during disease inquiry.
Furthermore, the webpage data collector is octopus software, and the online medical platform is a doctor medical online platform.
The invention also comprises an intelligent department consultation recommendation method based on the deep learning model, which comprises the following specific steps:
step one, collecting chief complaint data and department data of a patient who finishes a diagnosis target on a doctor online medical website by using octopus software;
step two, cleaning data: the method comprises the steps that parts such as spaces and punctuation marks exist in original data, space and punctuation mark preprocessing is carried out on the data by utilizing python software, jieba word segmentation and stop word removal are further carried out on the processed data, digital assignment is carried out on department data, and the name of a department is converted into a digital form from a text form;
furthermore, word segmentation is to segment a sentence into a plurality of words, and stop words after word segmentation are filtered by using a stop word list, and the quality of data is affected by the noise such as blank space, punctuation marks and the like contained in the original data;
step three, vectorization expression of the main complaint text: pre-training a word vector model by using a genesis packet in python, selecting a proper word vector model, further performing vectorization expression on the processed chief complaint data, and converting the patient chief complaint text into a high-dimensional vector;
further, space and punctuation mark preprocessing is carried out on data by using a Skip-gram model in a genim package, a plurality of word vector models with different dimensions are trained by combining data in various medical books, and a word vector model with the best effect is selected;
step four, model learning: training, learning and testing the oppositely quantized and expressed text by utilizing a deep learning long-short term memory neural network deep model to obtain the optimal effect and learning parameters of the model;
step five, department diagnosis guide: the department classification is realized by using a long-short term memory neural network depth model constructed by the optimal parameters;
step six, evaluating the effect of the model: testing the performance and the performance of the model in the intelligent department diagnosis guide recommendation system based on the deep learning model by using a plurality of machine learning models of TextCNN, RandomForest and KNN;
further, 4 indexes of precision rate, recall rate, F1 value and accuracy rate are selected to evaluate the model, when the effect of the classification algorithm is evaluated, the sample is classified into a positive class P and a negative class N, and meanwhile, according to the classifier and the actual classification condition, the sample is further classified into a true class TP, a true negative class TN, a false positive class FP and a false negative class FN, wherein the classifier is considered as true, and the actual class is also true; the classifier considers false and actually false, and is a true and negative class; the classifier considers true and actually false as false positive; the classifier considers false and actually true as a false negative class so as to improve the accuracy and the authenticity of model evaluation.
The invention has the following advantages:
1. on the basis of the existing machine learning and natural language processing tools, the method considers the real requirements and the patient treatment chief complaint data characteristics, effectively processes the context semantic association advantages of long text by using the long and short term memory neural network depth model for reference, and performs text classification on the patient chief complaint data by using the long and short term memory neural network depth model, thereby realizing the aim of intelligent patient guide;
2. the long-short term memory neural network depth model utilizes an wor vec model to vectorize chief complaint data of patients in a doctor-patient interaction process, then utilizes the long-short term memory neural network model to train and learn a quantified text, and finally achieves the purpose of intelligently recommending departments.
3. The invention can be used for the diagnosis guidance of the offline department and the online department, and has certain practical value.
Drawings
FIG. 1 is a diagram of a system provided by the present invention;
FIG. 2 is a flow chart provided by the present invention;
FIG. 3 is a schematic representation of word vector representations of different words provided by the present invention;
fig. 4 is a schematic diagram illustrating the influence of different dimensions on the classification accuracy of a text in the KNN model provided by the present invention;
FIG. 5 is a schematic diagram of a normalized confusion matrix of the LSTM model provided by the present invention;
fig. 6 is a schematic diagram of evaluation indexes provided by the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to the attached drawing 1 of the specification, the intelligent department consultation recommendation system based on the deep learning model comprises a long-short term memory neural network depth model, a webpage data collector and an online medical platform, wherein the connecting end of the long-short term memory neural network depth model is connected with the connecting end of the webpage data collector, and the output end of the online medical platform is connected with the input end of the webpage data collector; the long-short term memory neural network depth model acquires the chief complaint data of patients in the online medical platform through the web data collector, vectorized expression and text classification are carried out on the chief complaint data of the patients during disease inquiry, octopus software can be selected as the web data collector during actual use, and a doctor medical online platform is selected as a data capture object.
Referring to the accompanying fig. 2-5 in the specification, the intelligent department consultation recommendation method based on the deep learning model of the embodiment mainly includes the following six steps:
first, patient complaint data and department information are obtained.
And acquiring the chief complaint data and the department data of the patient in the clinic from the online medical platform of the Hakka in China.
And secondly, cleaning and processing data.
For the collected patient complaint data and department data, data cleaning and data preprocessing are performed. In the data cleaning stage, the empty characters and punctuations in the main complaint data are removed by using python software. And performing word segmentation on the processed patient chief complaint data by using a python software jieba algorithm, segmenting a sentence into a plurality of words, and filtering the stop words after word segmentation by using a Harmony large stop word list. And meanwhile, carrying out numerical assignment on department data, and converting the name of the department from a text form to a numerical form.
And thirdly, pre-training a word vector model and expressing the main complaint text vectorization.
Training a word vector model: a word vector model with the best effect is selected by training a plurality of word vector models with different dimensions by using a Skip-gram model in a true genetic package of python software and combining a plurality of medical books, and the word vector model is shown in figure 3.
As shown in fig. 4, taking the KNN algorithm as an example, according to the accuracy of text classification of the patient chief complaint data of the KNN model under different dimensions, a word vector model with an optimal description is selected for subsequent word vector expression. The 256-dimensional Skip-gram model is found to have high accuracy, so that the 256-dimensional Skip-gram word vector model is selected to carry out vectorization expression on the patient chief complaint data.
And expressing the subject text vectorized. And vectorizing and expressing the preprocessed patient complaint text by using the word vector model. The patient complaint text is converted into a high-dimensional vector.
Fourthly, model training, learning and testing.
And training, learning and testing the high-dimensional vector of the vectorization expression of the patient by using a long-short term memory neural network deep learning model (LSTM). At this time, the input variable is the high-dimensional vectorization expression of the patient's chief complaint text, and the output variable is the numerical value of the department. The principle of the LSTM model algorithm is as follows:
(1) discarding information: in the LSTM, information is first discarded and retained by the sigmod function through the forgetting gate of the LSTM.
gt＝σ(Wg[ht-1,xt]+bg) (1)，
Wherein, gtExpressing the proportion of discarded information, wherein sigma is a sigmoid function; w is a group ofgRepresenting a forgetting gate weight, bgIndicating forgetting the gate bias.
(2) Determining the updating information: the retained information is updated through the input gate, and then a new candidate vector is created by a tanh layer and added to the state. Wherein the content of the first and second substances,
it＝σ(Wi[ht-1,xt]+bi) (2)，
Figure BDA0003458436390000051
itrepresenting updated door weights, biRepresenting the updated gate bias, tanh represents the hyperbolic tangent function, WcRepresenting update candidate, bcIndicating that the candidate value bias is to be updated,
Figure BDA0003458436390000052
is a candidate value.
(3) The cell state is renewed. Associating old state with discard function gtMultiplying, discarding to the information needing discarding, and further processing each stateRow update with updated state value of Ct。
Figure BDA0003458436390000062
(4) An output state is determined. The Sigmod function determines which part of the cell state is output, the cell state is processed by the tanh function, and the processed result is multiplied by the Sigmod gate output to obtain the final output result.
Ot＝σ(Wo[ht-1,xt]+bo) (5)，
ht＝OttanhCt (6)，
Wherein, WoTo update the weight of the output weight, boFor updated output value offset, htRepresenting the final output result.
And fifthly, department leads.
And visually displaying the classification effect of the LSTM model by using the normalized confusion matrix. The value of the normalized confusion effect is the classification accuracy, the result can visualize the department diagnosis guide effect of the LSTM model, the normalization matrix can show the classification accuracy of the model, and the research finds that the diagnosis guide classification effect of the LSTM model is better, as shown in FIG. 5.
The results of the referral of the LSTM model are shown in the table below.
Figure BDA0003458436390000061
Figure BDA0003458436390000071
Sixth, model evaluation.
And selecting a deep learning model TextCNN and machine learning algorithms RandomForest and KNN as comparison algorithms to test the advantages of the method. 4 indexes of precision (precion), Recall (Recall), F1 value (F1-score) and Accuracy (Accuracy) are selected to evaluate the model. The results show that the method of the present invention performs better on multiple metrics than other algorithms, as shown in fig. 6.
When evaluating the effect of the classification algorithm, the samples will be classified into a positive class (P) and a negative class (N). Meanwhile, according to the classifier and the actual classification condition, the samples are further classified into a true class (TP), a true negative class (TN), a false positive class (FP) and a false negative class (FN). Wherein, the classifier is considered as true, and is actually true as true class; the classifier considers false and actually false, and is a true and negative class; the classifier considers true and actually false as false positive; the classifier is considered false and is actually a true false negative class. Here, P ═ TP + FN; n ═ TN + FP.
When evaluating the classification performance of the model, the accuracy rate represents the proportion of the samples which are actually in the positive class in the samples predicted to be in the positive class, and can represent the accuracy of the model prediction, and the specific calculation formula is shown as formula (7),
Figure BDA0003458436390000072
the recall rate represents the probability that the positive class in the sample is predicted to be correct, the recall ratio of the model is measured, the specific calculation formula is shown as a formula (8),
Figure BDA0003458436390000073
the F1 value is used as the harmonic average value of the precision rate and the recall rate, the index advantages of the precision rate and the recall rate can be integrated, the performance of the model can be comprehensively reflected, the specific calculation formula is shown as the formula (9),
Figure BDA0003458436390000074
the accuracy is used for measuring the correct proportion of the positive class and the negative class of the prediction result, the specific calculation formula is shown as a formula (10),
Figure BDA0003458436390000081
the method can recommend proper departments for patients, has important effects on relieving the pressure of manual diagnosis guide of hospitals, reducing the labor cost of manual diagnosis guide and improving the intelligent level and management of hospitals, can be used for off-line department diagnosis guide, and has certain practical value for on-line department diagnosis guide.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.

Claims (8)

1. Intelligent department leads a doctor recommendation system based on degree of depth learning model, its characterized in that: the system comprises a long-short term memory neural network depth model, a webpage data collector and an online medical platform, wherein the connecting end of the long-short term memory neural network depth model is connected with the connecting end of the webpage data collector, and the output end of the online medical platform is connected with the input end of the webpage data collector;
the long-short term memory neural network depth model acquires the chief complaint data of the patient in the online medical platform through the web data collector and performs vectorization expression and text classification on the chief complaint data of the patient during disease inquiry.
2. The intelligent department consultation recommendation system based on the deep learning model of claim 1, wherein: the webpage data collector is octopus software, and the online medical platform is a doctor medical online platform.
3. The recommendation method of the intelligent department consultation recommendation system based on the deep learning model as claimed in claim 2, characterized in that: the method comprises the following specific steps:
step one, collecting chief complaint data and department data of a patient who finishes a diagnosis target on a doctor online medical website by using octopus software;
step two, cleaning data: the method comprises the steps that parts such as spaces and punctuation marks exist in original data, space and punctuation mark preprocessing is carried out on the data by utilizing python software, jieba word segmentation and stop word removal are further carried out on the processed data, digital assignment is carried out on department data, and the name of a department is converted into a digital form from a text form;
step three, vectorization expression of the main complaint text: pre-training a word vector model by using a gensim packet in python, selecting a proper word vector model, and further performing vectorization expression on the processed chief complaint data;
step four, model learning: training, learning and testing the text expressed in the quantitative direction by using the deep learning long-short term memory neural network deep model to obtain the optimal effect and learning parameters of the model;
step five, department guide: the department classification is realized by using a long-short term memory neural network depth model constructed by the optimal parameters;
step six, evaluating the effect of the model: the performance and the performance of the model in the intelligent department consultation recommendation system based on the deep learning model are tested by using a plurality of machine learning models including TextCNN, RandomForest and KNN.
4. The intelligent department consultation recommendation method based on the deep learning model according to claim 3, characterized in that: in the second step, the word segmentation is to segment a sentence into a plurality of words, and the stop words after word segmentation are filtered by using the stop word list.
5. The intelligent department consultation recommendation method based on the deep learning model according to claim 3, characterized in that: in step three, the Skip-gram model in the genim package is utilized to pre-process the data by space and punctuation, and the data in various medical books is combined.
6. The intelligent department consultation recommendation method based on the deep learning model according to claim 3, characterized in that: in the third step, the result of vectorizing the processed chief complaint data is as follows: the patient complaint text is converted into a high-dimensional vector.
7. The intelligent department consultation recommendation method based on the deep learning model according to claim 3, characterized in that: and selecting 4 indexes of precision rate, recall rate, F1 value and accuracy rate to evaluate the model in the sixth step.
8. The intelligent department consultation recommendation method based on the deep learning model according to claim 3, characterized in that: when the effect of the classification algorithm is evaluated in the step six, the samples are classified into a positive class P and a negative class N, and meanwhile, the samples are classified into a true class TP, a true class TN, a false positive class FP and a false negative class FN according to the classifier and the actual classification condition, wherein the classifier is considered as true, and the actual class is also true; the classifier considers false and actually false, and is a true and negative class; the classifier considers true and actually false as false positive; the classifier is considered false and is actually a true false negative class.
CN202210009501.0A 2022-01-06 2022-01-06 Intelligent department diagnosis guide recommendation system based on deep learning model Pending CN114664415A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210009501.0A CN114664415A (en) 2022-01-06 2022-01-06 Intelligent department diagnosis guide recommendation system based on deep learning model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210009501.0A CN114664415A (en) 2022-01-06 2022-01-06 Intelligent department diagnosis guide recommendation system based on deep learning model

Publications (1)

Publication Number Publication Date
CN114664415A true CN114664415A (en) 2022-06-24

Family

ID=82026389

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210009501.0A Pending CN114664415A (en) 2022-01-06 2022-01-06 Intelligent department diagnosis guide recommendation system based on deep learning model

Country Status (1)

Country Link
CN (1) CN114664415A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376668A (en) * 2022-08-30 2022-11-22 温州城市智慧健康有限公司 Big data business analysis method and system applied to intelligent medical treatment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115376668A (en) * 2022-08-30 2022-11-22 温州城市智慧健康有限公司 Big data business analysis method and system applied to intelligent medical treatment
CN115376668B (en) * 2022-08-30 2024-03-08 温州城市智慧健康有限公司 Big data business analysis method and system applied to intelligent medical treatment

Similar Documents

Publication Publication Date Title
CN107731269B (en) Disease coding method and system based on original diagnosis data and medical record file data
CN109460473B (en) Electronic medical record multi-label classification method based on symptom extraction and feature representation
Poole et al. A method for establishing the representational validity of interaction coding systems: Do we see what they see?
CN112541056B (en) Medical term standardization method, device, electronic equipment and storage medium
CN108062978B (en) Method for predicting main adverse cardiovascular events of patients with acute coronary syndrome
CN108563626A (en) Medical text name entity recognition method and device
CN111292848A (en) Bayesian estimation-based medical knowledge map assisted reasoning method
CN113223735A (en) Triage method, device and equipment based on session representation and storage medium
CN112017744A (en) Electronic case automatic generation method, device, equipment and storage medium
CN111145903A (en) Method and device for acquiring vertigo inquiry text, electronic equipment and inquiry system
CN113539460A (en) Intelligent diagnosis guiding method and device for remote medical platform
CN114188022A (en) Clinical children cough intelligent pre-diagnosis system based on textCNN model
CN111553140A (en) Data processing method, data processing apparatus, and computer storage medium
CN111524570A (en) Ultrasonic follow-up patient screening method based on machine learning
CN113254609B (en) Question-answering model integration method based on negative sample diversity
CN114664415A (en) Intelligent department diagnosis guide recommendation system based on deep learning model
CN116050419B (en) Unsupervised identification method and system oriented to scientific literature knowledge entity
EP4273764A1 (en) Classification system
Siddiqa et al. Robust Length of Stay Prediction Model for Indoor Patients.
CN110610766A (en) Apparatus and storage medium for deriving probability of disease based on symptom feature weight
CN114822788A (en) Intelligent doctor recommendation method based on doctor-patient interaction data driving
RU2723674C1 (en) Method for prediction of diagnosis based on data processing containing medical knowledge
CN114999628A (en) Method for searching significant characteristics of degenerative knee osteoarthritis by machine learning
CN114238558A (en) Quality inspection method and device for electronic medical record, storage medium and equipment
CN114300127A (en) Method, device, equipment and storage medium for inquiry processing

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