CN117809823A - Medical scheme recommendation method and device based on feature analysis - Google Patents
Medical scheme recommendation method and device based on feature analysis Download PDFInfo
- Publication number
- CN117809823A CN117809823A CN202410002318.7A CN202410002318A CN117809823A CN 117809823 A CN117809823 A CN 117809823A CN 202410002318 A CN202410002318 A CN 202410002318A CN 117809823 A CN117809823 A CN 117809823A
- Authority
- CN
- China
- Prior art keywords
- medical
- information
- classification
- decision
- scheme
- 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 61
- 238000004458 analytical method Methods 0.000 title claims abstract description 57
- 238000003066 decision tree Methods 0.000 claims abstract description 42
- 238000003745 diagnosis Methods 0.000 claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000012216 screening Methods 0.000 claims abstract description 18
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 49
- 201000010099 disease Diseases 0.000 claims description 38
- 238000004891 communication Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 20
- 238000012360 testing method Methods 0.000 claims description 19
- 208000024891 symptom Diseases 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 230000000763 evoking effect Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 230000006698 induction Effects 0.000 claims description 3
- 208000015181 infectious disease Diseases 0.000 claims description 3
- 230000002458 infectious effect Effects 0.000 claims description 3
- 230000000399 orthopedic effect Effects 0.000 claims description 3
- 238000010827 pathological analysis Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 210000004556 brain Anatomy 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 8
- 239000003814 drug Substances 0.000 description 6
- 239000000243 solution Substances 0.000 description 5
- 238000007887 coronary angioplasty Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000007170 pathology Effects 0.000 description 4
- 208000031481 Pathologic Constriction Diseases 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 230000036262 stenosis Effects 0.000 description 3
- 208000037804 stenosis Diseases 0.000 description 3
- 238000001356 surgical procedure Methods 0.000 description 3
- 210000004351 coronary vessel Anatomy 0.000 description 2
- 239000008155 medical solution Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- NNJVILVZKWQKPM-UHFFFAOYSA-N Lidocaine Chemical compound CCN(CC)CC(=O)NC1=C(C)C=CC=C1C NNJVILVZKWQKPM-UHFFFAOYSA-N 0.000 description 1
- 208000007536 Thrombosis Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 238000010205 computational analysis Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001079 digestive effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000002682 general surgery Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 229960004194 lidocaine Drugs 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 210000002321 radial artery Anatomy 0.000 description 1
- ZAHRKKWIAAJSAO-UHFFFAOYSA-N rapamycin Natural products COCC(O)C(=C/C(C)C(=O)CC(OC(=O)C1CCCCN1C(=O)C(=O)C2(O)OC(CC(OC)C(=CC=CC=CC(C)CC(C)C(=O)C)C)CCC2C)C(C)CC3CCC(O)C(C3)OC)C ZAHRKKWIAAJSAO-UHFFFAOYSA-N 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000241 respiratory effect Effects 0.000 description 1
- 210000005077 saccule Anatomy 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- QFJCIRLUMZQUOT-HPLJOQBZSA-N sirolimus Chemical compound C1C[C@@H](O)[C@H](OC)C[C@@H]1C[C@@H](C)[C@H]1OC(=O)[C@@H]2CCCCN2C(=O)C(=O)[C@](O)(O2)[C@H](C)CC[C@H]2C[C@H](OC)/C(C)=C/C=C/C=C/[C@@H](C)C[C@@H](C)C(=O)[C@H](OC)[C@H](O)/C(C)=C/[C@@H](C)C(=O)C1 QFJCIRLUMZQUOT-HPLJOQBZSA-N 0.000 description 1
- 229960002930 sirolimus Drugs 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000004659 sterilization and disinfection Methods 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- 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
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a medical scheme recommending method and device based on feature analysis, which belong to the technical field of medical intelligent data analysis, and the method comprises the following steps: s1, establishing a decision tree model and a medical resource information base for storing historical medical information; s2, screening target historical medical information falling in a medical insurance range, carrying out DRG grouping processing, and training the decision tree model by utilizing the grouped target historical medical information; s3, obtaining a user portrait of a target patient, and extracting target features from the user portrait, wherein the target features comprise diagnosis and treatment features and economical features; s4, inputting the target features into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, wherein the prediction process specifically comprises the following steps: predicting a preselection scheme set according to the diagnosis and treatment characteristics; and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes, wherein the scheme recommendation accuracy is high.
Description
Technical Field
The invention belongs to the technical field of medical intelligent data analysis, and particularly relates to a medical scheme recommendation method and device based on feature analysis.
Background
At present, most of the existing medical recommendation systems adopt a fixed search mode or simply use the historical interaction information of doctors and patients as input so as to recommend related medical information, and the recommendation mode cannot comprehensively consider personal information of the patients, such as economic information of the patients, so that the recommended medical scheme is easy to be inaccurate, and even potential medical risks can exist.
In addition, some medical systems construct a recommendation mode based on a rule tree based on a clinical guideline, but the rule tree model constructed in the prior art mainly realizes disassembly of the clinical guideline, and then performs simulation of a doctor decision process through disassembling information, so that actual disease conditions of different patients cannot be covered accurately.
Therefore, how to accurately generate a medical recommendation scheme in a medical recommendation system becomes a technical problem to be solved. Common ways to group and generalize medical records from a clinical knowledge perspective include DRG/DIP grouping:
DRG refers to grouping according to relevant information of disease diagnosis, and dividing hospitalized patients into a certain number of disease groups according to clinical similarity and resource consumption similarity (namely according to disease severity of patients, complexity of treatment methods and resource consumption degree);
DIP refers to the use of the principle of industry division, which converts the relative price relationship between the medical cost and weight of different disease species into the score of each disease species, and then groups the disease species according to the scores;
in summary, the application provides a medical scheme recommendation method and device capable of effectively considering personal information of patients based on a DRG/DIP grouping technology.
Disclosure of Invention
In view of the above shortcomings of the prior art, an object of the present invention is to provide a medical plan recommendation method and apparatus based on feature analysis, which accurately determines a medical plan meeting a user's needs by performing comprehensive matching analysis of a user representation of a target patient and historical medical information.
In order to achieve the above object, the present invention provides the following technical solutions:
a medical protocol recommendation method based on feature analysis, comprising:
s1, establishing a decision tree model and a medical resource information base for storing historical medical information;
s2, screening target historical medical information falling in a medical insurance range, carrying out DRG grouping processing, and training the decision tree model by utilizing the grouped target historical medical information;
s3, obtaining a user portrait of a target patient, and extracting target features from the user portrait, wherein the target features comprise diagnosis and treatment features and economical features;
s4, inputting the target features into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, wherein the prediction process specifically comprises the following steps:
predicting a preselection scheme set according to the diagnosis and treatment characteristics;
and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes.
Further, the historical medical information includes medical department classification information, medical instrument classification information, and medical case information.
Further, the medical department classification information at least comprises one or more of department classification information based on treatment means, department classification information based on disease types, department classification information based on disease sites, and department classification information based on disease severity. Specifically:
the department classification information based on the treatment means comprises medical classification and surgical classification;
the department classification information based on the disease types comprises oncology classification, infectious department classification and health care department classification;
the department classification information based on the disease part comprises ophthalmic classification, stomatology classification, otorhinolaryngology classification, dermatology classification, orthopedics classification and brain classification;
the department classification information based on the severity of the symptoms comprises conventional department classification, emergency department classification and severe department classification.
Further, the medical instrument classification information at least comprises one or more of instrument classification information based on structural features and instrument classification information based on operation methods. Specifically:
the instrument classification information based on the structural features comprises passive medical instrument classification and active medical instrument classification;
the operation method-based instrument classification information comprises a contact human instrument classification and a non-contact human instrument classification.
Further, the medical case information includes at least identification information, symptom information, pathological diagnosis information, clinical treatment plan information, and treatment result information extracted from a patient medical case text.
Further, in step S2:
respectively forming a training set and a testing set by utilizing the target historical medical information after grouping processing;
extracting features of the training set based on natural semantic processing, and constructing a historical diagnosis and treatment knowledge graph through the extracted training features;
training the decision tree model by utilizing the historical diagnosis and treatment knowledge graph;
extracting features of the test set based on natural semantic processing, and inputting the extracted test features into a trained decision tree model to obtain a test result;
performing DIP (digital information processing) confidence analysis on the test result, wherein the DIP confidence analysis comprises security analysis and economic analysis; obtaining a safety score through the safety analysis and calculation, obtaining an economic score through the economic analysis and calculation, and weighting the safety score and the economic score to obtain a DIP decision score;
and judging whether the DIP decision score of the test result exceeds a DIP decision threshold, if so, finishing training and outputting the current decision tree model as an optimal decision tree model, otherwise, re-extracting training characteristics and performing optimization updating training.
Further, the diagnostic features include a symptom feature and a physiological evoked feature, and in step S4, predicting a set of pre-selected protocols from the diagnostic features includes:
matching a disorder grade and a disorder cause according to the disorder signature;
optimally screening the disease causes by the physiological evoked characteristics;
and predicting a preselection scheme set according to the disease grade and the screened disease cause, and carrying out DIP decision score value reduction sequencing on all preselection schemes in the preselection scheme set.
Further, in step S4, selecting a decision scheme from the set of pre-selected schemes according to the economic characteristics comprises:
obtaining a fee control condition according to the economical characteristics;
and taking the preselection scheme meeting the fee control condition in the preselection scheme set as a decision scheme.
In a second aspect, to achieve the above object, the present invention further provides the following technical solutions:
a medical protocol recommendation device based on feature analysis, comprising:
the construction module is used for constructing a decision tree model and a medical resource information base for storing historical medical information;
the information processing module screens target historical medical information falling in the medical insurance range and performs DRG grouping processing;
the training module is used for training the decision tree model by utilizing the target historical medical information after grouping processing;
the data acquisition module is used for acquiring a user portrait of the target patient;
the feature extraction module is used for extracting target features from the user portrait;
the prediction module is used for inputting the target characteristics into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, and the prediction process specifically comprises the following steps:
predicting a preselection scheme set according to the diagnosis and treatment characteristics;
and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes.
As a general inventive concept, the present invention also provides:
a computer readable storage medium having stored thereon a computer program which when executed by a processor implements a medical protocol recommendation method based on feature analysis as described above.
An electronic device comprising a processor, a communication interface, a memory, and a communication bus;
the processor, the communication interface and the memory realize mutual communication through a communication bus;
the memory is used for storing a computer program;
the processor is configured to execute a computer program stored on the memory, and the computer program when executed implements the medical protocol recommendation method based on the feature analysis as described above.
The invention has the following beneficial effects:
according to the invention, the decision tree model is obtained through training of the target historical medical information falling within the medical insurance range, and the user portraits of the target patients are subjected to full matching analysis through the decision tree model, so that the medical scheme meeting the user requirements is rapidly obtained, and the scheme recommendation accuracy is effectively improved;
specifically, when feature extraction is performed on a user portrait, diagnosis and treatment features and economical features are extracted respectively, the decision tree model is used for completing distribution prediction of medical links such as pathology carding, etiology confirmation, disease seed refinement, treatment process optimization and the like through comprehensive matching analysis of the diagnosis features and historical medical information, the pre-selected schemes obtained through prediction are all subjected to comprehensive confidence degree analysis based on a DRG/DIP grouping technology, and finally, a highly-reliable recommended decision scheme is obtained through screening under the condition of considering the economical features, and the decision scheme can effectively fall into a medical insurance range, so that the economical pressure of a user is reduced.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, like reference numerals being used to refer to like parts throughout the several views. It is apparent that the drawings in the following description are only some of the embodiments described in the embodiments of the present invention, and that other drawings may be obtained from these drawings by those of ordinary skill in the art.
FIG. 1 is a flow chart of a medical plan recommendation method based on feature analysis provided by the invention;
FIG. 2 is a schematic representation of a user representation of a target patient acquired in accordance with the present invention;
FIG. 3 is a schematic diagram of a historical diagnosis and treatment knowledge graph constructed according to the invention;
fig. 4 is a diagram showing a medical plan recommending apparatus based on feature analysis according to the present invention.
Detailed Description
In order to make the technical solutions of the embodiments of the present invention better understood by those skilled in the art, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. 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, shall fall within the scope of the invention.
In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of methods and systems that are consistent with aspects of the invention as detailed in the accompanying claims.
The invention aims to solve the problem of poor recommendation accuracy of the existing medical scheme, and particularly provides a medical scheme recommendation method and device based on feature analysis.
Method embodiment
As shown in fig. 1, the medical scheme recommendation method based on feature analysis mainly comprises the following steps:
s1, establishing a decision tree model and a medical resource information base;
the decision tree model specifically refers to a model capable of simulating a human decision process based on basic information, the decision tree model is specifically classified and predicted according to the shape of a tree, each internal node of the decision tree model represents a judging condition on a characteristic attribute, each branch represents a possible attribute value, and each leaf node represents a category, so that the whole decision process is conveniently and intuitively displayed;
the medical resource information base is used for storing historical medical information, and the historical medical information mainly comprises medical department classification information, medical instrument classification information and medical case information;
(11) The department classification information about medical departments, the department classifications, can be divided in different ways, the following are common classification ways:
the method is divided into the following steps: internal medicine and surgery are two general categories of departments. Internal medicine mainly treats diseases through drug treatment, including respiratory medicine, digestive medicine and the like; surgery is a way of treating diseases by surgical treatment, including general surgery, neurosurgery and the like;
dividing according to disease parts: such as ophthalmology, stomatology, otorhinolaryngology, dermatology, orthopedics, cerebology, and the like;
dividing according to disease types: such as oncology, infectious, health care, etc.;
according to the disease, the disease is divided into a light and a heavy type: such as conventional outpatient, emergency and critical departments, etc.
The above classification method is only one specific classification embodiment of medical department classification information, and the present invention includes but is not limited to the above classification information. With the continuous development of medical technology, new departments and diagnosis and treatment projects are also continuously emerging, so that in practical application, the classification information of the medical departments is also required to be continuously updated and adapted.
(12) Medical instrument classification information—medical instruments can be classified according to different characteristics:
according to structural characteristics, dividing: can be classified into passive medical devices and active medical devices;
according to the time-of-use limit classification (this classification is mainly directed to passive medical devices): the device can be divided into a disposable device, a short-term reusable device and a long-term reusable device;
dividing according to an operation method: the device can be divided into a human body contacting device and a non-human body contacting device;
according to the operation site division (this classification is mainly aimed at contacting human instruments): can be classified as skin or luminal (oral) devices, wound or tissue devices, devices of the blood circulatory system or devices of the central nervous system;
comprehensive division is performed according to structural features and operation methods: the device can be divided into a passive contact human body device, a passive non-contact human body device, an active contact human body device and an active non-contact human body device.
The above classification is only one specific classification example of medical device classification information, and the present invention includes, but is not limited to, the above classification information. For example, medical devices may be classified according to the purpose, the degree of influence on the human body, and the like.
(13) Information about medical cases
In the embodiment of the invention, through dividing text subject fields, the identification information, symptom information, pathological diagnosis information, clinical treatment scheme information, treatment result information and the like are extracted from the patient medical case text, and are stored as medical case information corresponding to the patient medical case text.
S2, screening target historical medical information falling in a medical insurance range, carrying out DRG grouping processing, and training the decision tree model by utilizing the grouped target historical medical information;
(21) Regarding the DRG grouping process, DRG means grouping according to the relevant information of disease diagnosis, so that the above-mentioned preferred target historical medical information falling within the scope of medical insurance is divided into a certain number of disease groups according to clinical similarity and resource consumption similarity (mainly referring to the disease severity of each medical case information, the complexity of treatment method and the resource consumption degree).
(22) Training with respect to decision tree models
Respectively forming a training set and a testing set by utilizing the target historical medical information after grouping processing;
extracting features of the training set based on natural semantic processing, and constructing a historical diagnosis and treatment knowledge graph shown in figure 3 through the extracted training features; the training feature structure comprises the aspects of medical staff team, outpatient department consultation live, department scale data, work saturation, inpatient department beds and scheduling, operating room utilization live, operating table number statistics, scheduling data and the like;
training the decision tree model by utilizing the historical diagnosis and treatment knowledge graph;
extracting features of the test set based on natural semantic processing, and inputting the extracted test features into a trained decision tree model to obtain a test result;
performing DIP (digital information processing) confidence analysis on the test result, wherein the DIP confidence analysis comprises security analysis and economic analysis; obtaining a safety score through the safety analysis and calculation, obtaining an economic score through the economic analysis and calculation, and weighting the safety score and the economic score to obtain a DIP decision score;
and judging whether the DIP decision score of the test result exceeds a DIP decision threshold, if so, finishing training and outputting the current decision tree model as an optimal decision tree model, otherwise, re-extracting training characteristics and performing optimization updating training.
S3, obtaining a user portrait of the target patient shown in fig. 2, and extracting target features from the user portrait, wherein the target features comprise diagnosis and treatment features and economy features, and the diagnosis and treatment features comprise symptom features and physiological induction features.
S4, inputting the target features into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, wherein the prediction process specifically comprises the following steps:
matching a disorder grade and a disorder cause according to the disorder signature;
optimally screening the disease causes by the physiological evoked characteristics;
predicting a preselection scheme set according to the disease grade and the screened disease cause, and performing DIP decision score value reduction sequencing on all preselection schemes in the preselection scheme set;
obtaining a fee control condition according to the economical characteristics;
and taking the preselection schemes meeting the fee control conditions in the preselection scheme set as decision schemes, and recommending the decision schemes.
In summary, taking a patient in need of percutaneous transluminal coronary angioplasty as an example, the following detailed description of the embodiments of the present invention is recommended:
a) Acquiring a user representation of a target patient through a patient visit process
If the on-line consultation exists, carrying out primary feature extraction on the consultation information, and carrying out allocation of a consultation hospital by combining the target patient address and regional medical resources based on the extracted features; whether registration type is carried out or not can also be judged according to the degree of the disease, including conventional outpatient service and emergency treatment, if no emergency treatment is needed, the specific department needing registration is judged according to the disease position;
after online or offline registration, constructing a user portrait of the target patient through the electronic case information and online consultation information of the target patient.
b) Feature extraction and depth analysis are carried out on the user image to obtain a decision scheme
Predicting a pre-selection scheme:
b1 Extracting economical features, symptom features, and physiological evoked features from the user representation;
b2 Screening and matching similar historical case cases through disorder features, and deeply splitting conventional etiology, differential etiology, disorder grade, notes and the like;
b3 Fine screening of conventional etiology and differential etiology is carried out through physiological induction characteristics, so that definite etiology and pathology are determined;
b4 Manual intervention is carried out according to different etiology and notice matters, refined analysis is carried out, clear etiology and pathology are obtained, a decision tree model is utilized to output a preselection scheme, generally, a plurality of matched preselection schemes are combined to form a preselection scheme set, and each preselection scheme comprises matched operation scheme steps, required total amount of available operation equipment, medical auxiliary equipment and the like.
For percutaneous transluminal coronary angioplasty, one of the pre-selected protocols is as follows:
(01) The operation steps are as follows:
the patient lies horizontally under DSA;
negative in the right upper limb Alln test;
conventional disinfection, and spreading of sterile towel;
2% lidocaine is locally infiltrated and anesthetized, the right radial artery is punctured, a sheath is arranged, and the whole body is heparinized.
(02) Coronary angiography shows:
the left coronary artery is mainly not narrowed, and the anterior descending branch stent is open and is not narrowed;
the original stent of the circumflex is unobstructed and has no stenosis;
the wall of the middle section of the coronary artery is irregular, and the narrow in the original stent of the far section is 99%;
JR3.5 directs the catheter to the right coronary ostium;
the BMW guide wire reaches the distal end of the anterior descending branch, and the balloon is pre-expanded at the stenosis;
cutting the saccule to cut thrombus in the original stent, and arranging 1 rapamycin eluting stent in the far-section original stent of the right crown;
post-dilation, visualization, the disappearance of stenosis at the stent, distal T1-MI blood flow level 3;
pulling out the tube and the sheath, and pressurizing and bundling the puncture points;
(02) And (3) code searching: angioplasty—coronal-percutaneous transluminal (balloon) (single vessel) 00.66 (note further coding).
(03) Surgical coding: percutaneous transluminal coronary angioplasty 00.66.
Decision-making pre-selection scheme:
b5 For all the predicted preselection schemes, performing DIP confidence analysis on each preselect scheme in a decision tree model, specifically comprising only safety analysis and computational analysis on personnel, equipment, medicaments, medical instruments and the like related to each preselect scheme, calculating the safety score through the safety analysis, wherein the safety score is used for reflecting diagnosis and treatment factors such as operation risks, success rates, postoperative recovery and the like, calculating the economic score through the economic analysis, and mainly reflecting the economic grade, and weighting the safety score and the economic score to obtain a DIP decision score;
as shown in the following table, DIP confidence analysis results for a preselected protocol for percutaneous transluminal coronary angioplasty:
b6 Obtaining a fee control condition of the target patient according to the economic characteristics extracted from the user portrait;
b7 Taking the preselect schemes meeting the fee control conditions in the preselect scheme set as decision schemes, and recommending the decision schemes.
In the medical diagnosis and treatment process of practical application, the recommended decision scheme is faced, and further realistic communication is required to be carried out on both sides of the doctor and patient, if the secondary screening is carried out on the aspects of economy level, operation risk level and the like, the actual decision scheme is obtained through the secondary screening and the re-selection of the calculated DIP decision score.
In the whole process, patient condition data is accurately obtained through detailed analysis of user portraits of a target patient, mishanging and misregistration are reduced through means of rapid matching of departments and pathology, a decision scheme meeting the requirements of the target patient is rapidly obtained, the economic condition of the decision scheme is clarified, and economic disputes of doctors and patients are reduced.
Device embodiment
As shown in fig. 4, the medical solution recommending device based on feature analysis of the present invention mainly includes the following structures:
the construction module is used for constructing a decision tree model and a medical resource information base for storing historical medical information;
the information processing module screens target historical medical information falling in the medical insurance range and performs DRG grouping processing;
the training module is used for training the decision tree model by utilizing the target historical medical information after grouping processing;
the data acquisition module is used for acquiring a user portrait of the target patient;
the feature extraction module is used for extracting target features from the user portrait;
the prediction module is used for inputting the target characteristics into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, and the prediction process specifically comprises the following steps:
predicting a preselection scheme set according to the diagnosis and treatment characteristics;
and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes.
Specifically, the device provided in this embodiment performs feature analysis and decision recommendation of the DRG/DIP medical solution according to the method provided in the first embodiment.
In addition, in the present invention, the following embodiments are also provided based on the same inventive concept: an electronic device comprising a processor, a communication interface, a memory, and a communication bus;
the processor, the communication interface and the memory realize mutual communication through a communication bus;
the memory is used for storing a computer program;
the processor is used for executing the computer program stored on the memory, and the computer program is executed to realize the medical proposal recommending method based on the characteristic analysis.
The communication bus mentioned by the above terminal may be a peripheral component interconnect standard (Peripheral Component Interconnect, abbreviated as PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated as EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus. The communication interface is used for communication between the terminal and other devices. The memory may include random access memory (Random Access Memory, RAM) or non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage system located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
In addition, in order to achieve the above object, an embodiment of the present invention also proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the medical plan recommendation method based on feature analysis of the present invention.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable vehicles having computer-usable program code embodied therein, including but not limited to disk storage, CD-ROM, optical storage, and the like.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. "and/or" means either or both of which may be selected. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device comprising the element.
Finally, it should be noted that the above embodiments are merely for illustrating the technical solution of the embodiments of the present invention, and are not limiting. Although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the invention, and any changes and substitutions that would be apparent to one skilled in the art are intended to be included within the scope of the present invention.
Claims (10)
1. The medical scheme recommending method based on the feature analysis is characterized by comprising the following steps of:
s1, establishing a decision tree model and a medical resource information base for storing historical medical information;
s2, screening target historical medical information falling in a medical insurance range, carrying out DRG grouping processing, and training the decision tree model by utilizing the grouped target historical medical information;
s3, obtaining a user portrait of a target patient, and extracting target features from the user portrait, wherein the target features comprise diagnosis and treatment features and economical features;
s4, inputting the target features into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, wherein the prediction process specifically comprises the following steps:
predicting a preselection scheme set according to the diagnosis and treatment characteristics;
and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes.
2. The feature analysis-based medical protocol recommendation method according to claim 1, wherein: the historical medical information comprises medical department classification information, medical instrument classification information and medical case information; and is also provided with
The medical department classification information at least comprises one or more of department classification information based on treatment means, department classification information based on disease types, department classification information based on disease parts and department classification information based on disease severity;
the medical instrument classification information at least comprises one or more of instrument classification information based on structural characteristics and instrument classification information based on operation methods;
the medical case information includes at least identity information, symptom information, pathological diagnosis information, clinical treatment plan information, and treatment result information extracted from a patient medical case text.
3. The medical scenario recommendation method based on feature analysis according to claim 2, wherein:
the department classification information based on the treatment means comprises medical classification and surgical classification;
the department classification information based on the disease types comprises oncology classification, infectious department classification and health care department classification;
the department classification information based on the disease part comprises ophthalmic classification, stomatology classification, otorhinolaryngology classification, dermatology classification, orthopedics classification and brain classification;
the department classification information based on the severity of the symptoms comprises conventional department classification, emergency department classification and severe department classification.
4. The medical scenario recommendation method based on feature analysis according to claim 2, wherein:
the instrument classification information based on the structural features comprises passive medical instrument classification and active medical instrument classification;
the operation method-based instrument classification information comprises a contact human instrument classification and a non-contact human instrument classification.
5. The medical scenario recommendation method based on feature analysis according to claim 2, wherein in step S2:
respectively forming a training set and a testing set by utilizing the target historical medical information after grouping processing;
extracting features of the training set based on natural semantic processing, and constructing a historical diagnosis and treatment knowledge graph through the extracted training features;
training the decision tree model by utilizing the historical diagnosis and treatment knowledge graph;
extracting features of the test set based on natural semantic processing, and inputting the extracted test features into a trained decision tree model to obtain a test result;
performing DIP (digital information processing) confidence analysis on the test result, wherein the DIP confidence analysis comprises security analysis and economic analysis; obtaining a safety score through the safety analysis and calculation, obtaining an economic score through the economic analysis and calculation, and weighting the safety score and the economic score to obtain a DIP decision score;
and judging whether the DIP decision score of the test result exceeds a DIP decision threshold, if so, finishing training and outputting the current decision tree model as an optimal decision tree model, otherwise, re-extracting training characteristics and performing optimization updating training.
6. The feature analysis-based medical protocol recommendation method according to claim 5, wherein: the diagnosis and treatment characteristics comprise symptom characteristics and physiological induction characteristics, and in step S4, the prediction and pre-selection scheme set according to the diagnosis and treatment characteristics comprises:
matching a disorder grade and a disorder cause according to the disorder signature;
optimally screening the disease causes by the physiological evoked characteristics;
and predicting a preselection scheme set according to the disease grade and the screened disease cause, and carrying out DIP decision score value reduction sequencing on all preselection schemes in the preselection scheme set.
7. The feature analysis-based medical protocol recommendation method according to claim 6, wherein: in step S4, selecting a decision scheme from the set of pre-selected schemes according to the economic characteristic comprises:
obtaining a fee control condition according to the economical characteristics;
and taking the preselection scheme meeting the fee control condition in the preselection scheme set as a decision scheme.
8. The medical scheme recommending device based on the feature analysis is characterized by comprising the following structure:
the construction module is used for constructing a decision tree model and a medical resource information base for storing historical medical information;
the information processing module screens target historical medical information falling in the medical insurance range and performs DRG grouping processing;
the training module is used for training the decision tree model by utilizing the target historical medical information after grouping processing;
the data acquisition module is used for acquiring a user portrait of the target patient;
the feature extraction module is used for extracting target features from the user portrait;
the prediction module is used for inputting the target characteristics into a trained optimal decision tree model to predict a diagnosis and treatment decision scheme, and the prediction process specifically comprises the following steps:
predicting a preselection scheme set according to the diagnosis and treatment characteristics;
and screening decision schemes from the pre-selected scheme set according to the economical characteristics, and recommending the decision schemes.
9. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program, when executed by a processor, implements the medical protocol recommendation method based on feature analysis according to any one of claims 1-7.
10. An electronic device, characterized in that: comprises a processor, a communication interface, a memory and a communication bus;
the processor, the communication interface and the memory realize mutual communication through a communication bus;
the memory is used for storing a computer program;
the processor is configured to execute a computer program stored on a memory, and the computer program when executed implements the medical protocol recommendation method based on feature analysis as claimed in any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410002318.7A CN117809823A (en) | 2024-01-02 | 2024-01-02 | Medical scheme recommendation method and device based on feature analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410002318.7A CN117809823A (en) | 2024-01-02 | 2024-01-02 | Medical scheme recommendation method and device based on feature analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117809823A true CN117809823A (en) | 2024-04-02 |
Family
ID=90428212
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410002318.7A Pending CN117809823A (en) | 2024-01-02 | 2024-01-02 | Medical scheme recommendation method and device based on feature analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117809823A (en) |
-
2024
- 2024-01-02 CN CN202410002318.7A patent/CN117809823A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3234823B1 (en) | Differential medical diagnosis apparatus adapted in order to determine an optimal sequence of diagnostic tests for identifying a pathology by adopting diagnostic appropriateness criteria | |
US20200315518A1 (en) | Apparatus for processing data for predicting dementia through machine learning, method thereof, and recording medium storing the same | |
Riganello et al. | Heart rate variability: an index of brain processing in vegetative state? An artificial intelligence, data mining study | |
CN108780663A (en) | Digital personalized medicine platform and system | |
CN107785057B (en) | Medical data processing method, device, storage medium and computer equipment | |
CN109256212A (en) | Bone health assessment models construction method, device, equipment, medium and appraisal procedure | |
US20160259899A1 (en) | Clinical decision support system for diagnosing and monitoring of a disease of a patient | |
Aljawarneh et al. | Particularities of data mining in medicine: lessons learned from patient medical time series data analysis | |
JP2018060529A (en) | Method and apparatus of context-based patient similarity | |
KR102025315B1 (en) | Information processing device, information processing method, program, and database system | |
CN111899837A (en) | Operation report coordination method and system based on digital operating room | |
US20180211730A1 (en) | Health information (data) medical collection, processing and feedback continuum systems and methods | |
CN110046757B (en) | Outpatient clinic volume prediction system and prediction method based on LightGBM algorithm | |
CN114652311A (en) | Fine nursing method and system based on stepped nursing intervention | |
CN113506625A (en) | Diagnosis and treatment suggestion scoring system based on csco guide | |
Thandi et al. | Mapping frailty concepts to SNOMED CT | |
Chiang et al. | On the qi deficiency in traditional Chinese medicine | |
CN117809823A (en) | Medical scheme recommendation method and device based on feature analysis | |
Iliyas et al. | Prediction of heart disease using decision tree | |
CN113257416B (en) | COPD patient personalized management and optimization device and equipment based on deep learning | |
CN115295110A (en) | Postoperative complication prediction system and method | |
EP2645273A1 (en) | System for differentiation and analysis of recorded clinical data | |
Li et al. | Normative modeling for personalized clinical pathway using organizational semiotics methods | |
Almeida et al. | Information, reality and epistemology: an ontological take | |
CN117688226B (en) | Intelligent pre-diagnosis self-service bill making method and system based on similar child patient matching |
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 |