CN114068009A - Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system - Google Patents

Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system Download PDF

Info

Publication number
CN114068009A
CN114068009A CN202010789239.7A CN202010789239A CN114068009A CN 114068009 A CN114068009 A CN 114068009A CN 202010789239 A CN202010789239 A CN 202010789239A CN 114068009 A CN114068009 A CN 114068009A
Authority
CN
China
Prior art keywords
diagnosis
treatment
information
clinical
data
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
CN202010789239.7A
Other languages
Chinese (zh)
Inventor
黄甫毅
高阳
邢润苗
万虹
郄蓓蓓
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.)
Sichuan Medical Science And Technology Co ltd
Original Assignee
Sichuan Medical Science And Technology Co ltd
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 Sichuan Medical Science And Technology Co ltd filed Critical Sichuan Medical Science And Technology Co ltd
Priority to CN202010789239.7A priority Critical patent/CN114068009A/en
Publication of CN114068009A publication Critical patent/CN114068009A/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
    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • G16H10/20—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
    • G—PHYSICS
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • 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
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/20—ICT specially adapted for the handling or processing of medical references relating to practices or guidelines
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Biomedical Technology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Medicinal Chemistry (AREA)
  • Bioethics (AREA)
  • Pharmacology & Pharmacy (AREA)
  • Toxicology (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

The invention discloses an auxiliary support method and system for clinical decision, teaching and scientific research of cervical cancer and vulvar cancer, according to the method, through a medical and pharmaceutical data storage unit, a diagnosis and treatment parameter storage unit, an information input unit, a comparison processor unit, a diagnosis and treatment result output unit and an early warning and operation recording unit in a matched system, a feasible clinical diagnosis and treatment scheme suggestion and a corresponding clinical research and real world research evidence support can be provided for relevant medical workers according to the disease specificity information parameter values of patients, the whole period of diseases such as screening diagnosis, treatment, monitoring follow-up visit, out-of-hospital management and the like is covered, a doctor is assisted to rapidly improve the clinical diagnosis and treatment level, study and update diagnosis and treatment knowledge, the research status and development direction of clinical research and real world diagnosis and treatment are mastered, the scientific research level is improved, and the contradiction that the time and energy of the medical workers are difficult to follow the clinical research progress is solved.

Description

Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system
Technical Field
The invention belongs to the field of intelligent medical treatment, and further relates to a cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system in the technical field of digital medical treatment.
Background
According to statistics, about 392.9 ten thousands of new malignant tumor cases and about 233.8 thousands of death cases occur in 2015 in China, the burden of the cancer in China still shows a continuous rising trend, and the cancer prevention and control situation is still severe. Wherein, the new cases of cervical cancer are about 11.1 ten thousand, and the diseases are released in the 6 th malignant tumor of women in China. Cervical cancer and vulvar cancer are serious diseases threatening the health of women. At present, the practical conditions of capacity, time, resources and the like limit most medical and health personnel to continuously carry out systematic medical knowledge updating, so that the clinical diagnosis and treatment standardization level and the medical service level are difficult to rapidly promote, and the requirements of people on medical service are difficult to meet.
In order to alleviate the contradiction, the existing clinical decision support system can provide clinical diagnosis and treatment scheme reference and assist doctors in making diagnosis and treatment decisions based on partial basic medical knowledge, clinical guidelines and the like. For example, chinese patent application publication No. CN103455886A, published as 12/18/2013, discloses a diagnosis and treatment decision support system based on a workflow, which establishes a workflow based on a standard clinical path for a state-authorized hospital to go out of a hospital, and outputs a diagnosis and treatment suggestion through a workflow module, a rule engine module, an inference module, and the like. Although the standardization of clinical diagnosis and treatment is considered, the actual conditions of hospitals in all regions and all levels in the country are greatly different, and the actual applicable hospital range is too narrow only by carrying out standardization through the clinical path of the national authorized hospitals. And the system can not explain what clinical research data or real world research data the given diagnosis and treatment suggestion is based on, and doctors can not judge or verify the rationality of the diagnosis and treatment suggestion by combining the clinical experience of the doctors.
Meanwhile, the invention patent application with application date of 2019, 12 and 23 and application number of 201911337942.8 describes a multi-source data-assisted clinical decision support system and method, the technical scheme combines a standard clinical path and a real world clinical path to carry out clinical decision support, enhances the operability of diagnosis and treatment suggestions, provides data such as clinical research and real world research as evidence support, and better accords with evidence-based medical principles. However, the invention only aims at the western medicine system, and cannot combine Chinese and western medicine, and Chinese patent medicines and traditional Chinese medicines are widely used in China, especially in basic medical institutions, and belong to the blind point of the existing decision assistance. In addition, the diagnosis and treatment parameter library is not independently divided, and disease-specific diagnosis and treatment parameters and weight values thereof are not systematically analyzed and utilized, so that the method is deficient in the aspects of individual decision assistance, teaching and scientific research support of specific diseases.
At present, a clinical decision support system aiming at the whole disease cycle of cervical cancer and vulvar cancer is lacked, only a few public phases are invented to relate to partial links of diagnosis and treatment of cervical cancer and vulvar cancer, for example, a clinical decision system and a method for cervical lesion disclosed in Chinese patent publication with publication number CN108565017A on the 21 st day of 9 months in 2018, and an artificial intelligent cervical cancer screening and determining method and device disclosed in Chinese patent publication with publication number CN109887561A on the 21 st day of 9 months in 2018. However, the above technical solutions do not specifically and specifically assist clinical diagnosis and treatment, support teaching and training, and support scientific research of the whole disease cycle of cervical cancer and vulvar cancer.
Disclosure of Invention
In view of the defects of the prior art, the invention aims to provide an auxiliary support method and an auxiliary support system for clinical decision, teaching and scientific research of cervical cancer and vulvar cancer, which are commonly assisted by clinical research data and real world research data, wherein the method and the system provide feasible clinical diagnosis and treatment scheme suggestions and corresponding clinical research and real world research evidence support for relevant medical workers, cover the whole period of diseases such as screening diagnosis, treatment, follow-up visit monitoring, out-of-hospital management and the like, assist the doctors to quickly improve the clinical diagnosis and treatment level, learn and update diagnosis and treatment knowledge, master the current research situation and the development direction of clinical research and real world diagnosis and solve the contradiction that the time and the energy of the medical workers are difficult to follow the clinical research progress.
The technical scheme provided by the invention is as follows:
an auxiliary support method for clinical decision, teaching and scientific research of cervical cancer and vulvar cancer is characterized by comprising the following steps:
(1) the information of the symptoms, physical signs, medical history, examination results and the like of the patient is called from an outpatient service, an emergency management subsystem, a medical record management subsystem and the like of a hospital HIS system, or the information of the patient is input by a doctor in the modes of information selection and the like under the guidance of voice, characters, images or corresponding front ends. And generating a patient information parameter value after the patient information is identified, extracted and structured.
(2) And comparing and judging whether a standard clinical path and/or a real world clinical path completely matched with the patient information parameter value exist, wherein in the judgment result:
if the data cluster exists, the completely matched standard clinical path data cluster and/or the real world clinical path data cluster are/is called, and decision support information is output and displayed; the standard clinical pathway data cluster and/or the real world clinical pathway data cluster are data sets which are paired into groups by one or more of standard clinical pathway and/or real world clinical pathway, continuing education data, medical behavior rationality early warning information, clinical research data and real world research data; the decision support information comprises a standard clinical pathway and real-world clinical pathway based clinical recommendation for assisting clinical decision making; the diagnosis and treatment suggestion is correspondingly used for clinical evidence support and real world evidence support for assisting clinical decision and scientific research, or is correspondingly used for assisting continuous education information of medicine and teaching.
If the specific information does not exist, a specific information query supplementary instruction is sent out, and then specific information is queried from a data source according to the specific information query supplementary instruction, for example, the specific information is searched from each electronic information system of a hospital or an information missing prompt is given to a user, and an information supplementary window is presented. And when the specific information is a specific inspection result, if the user confirms that the inspection is not carried out, pushing an inspection suggestion.
(3) After the specific information query supplementary result is found, secondary comparison is carried out, whether a standard clinical path and/or a real world clinical path which are completely matched with the information parameter value of the patient exist or not is judged, and the judgment result comprises the following steps:
if so, a fully matched standard clinical pathway data cluster and/or real world clinical pathway data cluster is retrieved and output.
If the standard clinical path and the real world clinical path which are completely matched with the patient information parameter values do not exist, judging whether the matching degree of the standard clinical path and/or the real world clinical path reaches a threshold value, and judging that: if the matching degree of the standard clinical path and/or the real world clinical path reaches a threshold value, outputting and displaying a corresponding standard clinical path data cluster and/or real world clinical path data cluster, and dividing the standard clinical path data cluster and/or real world clinical path data cluster into a first-choice recommendation, a second-choice recommendation and other recommendations according to the matching degree to present the recommendations to a user; and if the matching degrees of the standard clinical path and the real world clinical path do not reach the threshold value, selecting and sending the standard clinical path data cluster and the real world clinical path data cluster with the highest matching degree, presenting diagnosis and treatment references based on the similar standard clinical path and the real world clinical path to the user, prompting missing important information to the user, simultaneously providing similar real world evidence as clinical and scientific research references, and presenting continuous education information of similar medical cases as medical standardized education references. In the above process, the threshold is the optimal credit acquisition threshold of the parameter value matching degree preset according to model training, and the user can also set the threshold according to actual needs.
(4) At the moment, the user manually judges whether the diagnosis and treatment are finished or not automatically after comparing the real diagnosis and treatment path, the diagnosis and treatment ending and the diagnosis and treatment suggestion of the patient, if the diagnosis and treatment at the stage are not finished, the clinical decision support is carried out again after the information is imported through an electronic information system of the hospital or the subsequent diagnosis and treatment information of the patient is input by the user for information updating until the diagnosis and treatment at the stage are finished manually or automatically judged by the system; if the diagnosis and treatment at the stage are finished, judging whether a user adopts a diagnosis and treatment suggestion, if so, writing diagnosis and treatment options selected by the user back to a hospital HIS system, for example, writing information such as diagnosis, examination and treatment schemes back to subsystems such as medical records and prescriptions, and when the prescriptions are prescribed, carrying out real-time early warning on the diagnosis and treatment schemes or medicines selected by doctors (for example, when unreasonable diagnosis and treatment schemes or unreasonable medicines are generated), and finishing the clinical decision support; if the user chooses not to adopt the diagnosis and treatment suggestion, the user can selectively input the reason and end the clinical decision support.
When judging whether the user adopts the diagnosis and treatment suggestion, the user can manually judge; whether the user manually judges whether to adopt the diagnosis and treatment suggestion or not and whether the user selects to adopt the diagnosis and treatment suggestion or not, the real diagnosis and treatment path and diagnosis and treatment ending of the patient are recorded, the diagnosis and treatment path and the diagnosis and treatment ending are compared with the system diagnosis and treatment suggestion, whether the user adopts the suggestion or not is automatically judged and stored, and then corresponding diagnosis and treatment parameter storage data are continuously optimized.
Based on the method, the corresponding cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support system is characterized by comprising a medical and pharmaceutical data storage unit, a diagnosis and treatment parameter storage unit, an information input unit, a comparison processor unit, a diagnosis and treatment result output unit and an early warning and operation recording unit, wherein the specific functions of the components are as follows:
a medical and pharmaceutical data storage unit for storing: and constructing a Western medicine system and medical and pharmaceutical related data of a traditional Chinese medicine system, a standard clinical path data cluster and a real world clinical path data cluster which are required by the standard clinical path and evidence library and the real world clinical path and evidence library.
The diagnosis and treatment parameter storage unit is used for storing: parameters affecting screening diagnosis, treatment and monitoring follow-up of cervical cancer and vulvar cancer, parameter weight values and parameter values of the parameters; the user can adjust the information in the diagnosis and treatment parameter storage unit.
The information input unit is used for acquiring patient information in a mode including but not limited to calling from systems such as hospital HIS and the like and direct doctor input, performing information structuring processing according to different input forms and information structures, generating patient information parameters and sending the patient information parameters to the comparison processor unit; and the comparison processor unit is also used for automatically calling or sending a supplementary input specific information prompt to a user according to the specific information query supplementary instruction and providing corresponding specific information to the comparison processor unit. When receiving a specific information query supplement instruction sent by the comparison processor unit, the information input unit queries the specific information from a system such as a hospital HIS or sends a supplement input specific information prompt to a user, the user can check information such as associated parameters, approximate path structures and clinical significance of missing parameters of the missing parameters, and the result is sent to the comparison processor unit after the specific information query supplement.
The comparison processor unit is used for receiving the data sent by the information input unit, calling the data of the diagnosis and treatment parameter storage unit, and comparing the two data directly or after rule processing, wherein the rule processing comprises entity relationship mapping, logical relationship reasoning and the like; when parameters of missing patient information parameter values exist in the standard clinical path or the real world clinical path, the comparison processor unit sends a specific information query supplement instruction to the information input unit, secondary comparison is carried out after a specific information query supplement result fed back by the information input unit is received, and then the standard clinical path data cluster and the real world clinical path data cluster which reach a preset or user-set matching degree threshold are sent to the diagnosis and treatment result output unit.
And the diagnosis and treatment result output unit is used for receiving the result data sent by the comparison processor unit and displaying the result data in modules.
The early warning and operation recording unit is used for carrying out reasonability early warning on treatment and medication schemes and the like specifically related to a clinical path when a doctor prescribes a prescription, recording the real diagnosis and treatment path and results of a patient, comparing whether diagnosis and treatment suggestions and medical behavior reasonability early warning suggestions displayed in the diagnosis and treatment result output unit are adopted by a user or not, feeding back the recorded real diagnosis and treatment path and result information of the patient into a medical and pharmaceutical data storage unit, expanding the data quantity of the medical and pharmaceutical data storage unit, and further continuously optimizing the information in the clinical path and the evidence storage unit.
Further, the medical and pharmaceutical data storage unit comprises:
the medical and pharmaceutical database is used for storing all medical and pharmaceutical relevant data of a western medicine system and a traditional Chinese medicine system, and comprises a series of cross-modal multi-source heterogeneous data, and the series of cross-modal multi-source heterogeneous data at least comprises: medical and pharmaceutical data of western medicine system and traditional Chinese medicine system, medical policy information, structured medical record information, patient out-of-hospital management information, disease burden information, drug instruction manual, consumable information, clinical research data, real world research data, clinical guidelines, expert consensus;
the standard clinical path and evidence base is used for storing a standard clinical path data cluster, namely a data set formed by pairing one or more of standard clinical path, continuous education data, medical behavior rationality early warning information, clinical research data and real world research data generated by analyzing the medical and pharmaceutical data storage unit;
and the real-world clinical path library is used for storing a real-world clinical path data cluster, namely a data set formed by pairing one or more of real-world clinical paths, continuous education data, medical behavior rationality early warning information and real-world research data generated by analyzing the medical and pharmaceutical data storage unit.
Further, the diagnosis and treatment parameter storage unit includes:
the screening and diagnosis parameter library is used for storing parameters influencing screening and diagnosis of cervical cancer and vulvar cancer, parameter weight values and parameter values of the parameters;
the treatment parameter library is used for storing parameters influencing the treatment of the cervical cancer and the vulva cancer, parameter weight values and parameter values of the parameters;
the monitoring follow-up parameter library is used for storing parameters, parameter weight values and parameter values of the parameters, which influence the cervical cancer and vulvar cancer monitoring follow-up;
the tumor marker parameter library is used for storing markers of cervical cancer, vulvar cancer, precancerous lesion, precancerous diseases and cervical cancer and vulvar cancer related diseases, and the parameters stored in the tumor marker parameter library are derived from tumor tissues, tissues beside cancer, normal tissues or cells, blood or body fluid.
Further, the parameters stored in the screening and diagnosis parameter bank that affect screening diagnosis of cervical cancer include, but are not limited to, whether cervical cancer has been diagnosed, whether a biopsy has been performed, tumor size, tumor infiltration depth, whether the tumor is confined to the cervix, whether the tumor affects the lower third of the vagina, whether the tumor affects the pelvic wall, whether the tumor causes hydronephrosis or renal dysfunction, whether pelvic lymph node metastasis exists, whether a paraabdominal aortic lymph node metastasis exists, whether the tumor affects adjacent organs, whether the tumor spreads to distant organs, whether a chest X-ray examination has been performed, whether an abnormality is found in the chest X-ray examination result, whether other symptoms and suspected metastases have occurred, whether a hysterectomy has been performed, histological classification, histological grading, whether a sentinel lymph node biopsy has been performed; parameters which are stored in the treatment parameter library and influence the treatment of the cervical cancer comprise, but are not limited to, FIGO stages, whether the fertility function can be reserved, whether cervical conization can be performed, the incisal margin condition of conical biopsy, whether the operation can be performed, the condition of postoperative pelvic lymph node invasion, the condition of postoperative periaortic lymph node invasion, the condition of postoperative incisal margin, the condition of postoperative periuterine tissue invasion, high risk factors for adjuvant therapy, the postoperative peritoneal lymph node or peritoneal lymph node sweeping result, the recurrence condition and the previous treatment condition; parameters stored in the monitoring follow-up parameter library and influencing cervical cancer monitoring follow-up include but are not limited to FIGO stages, whether a palpable mass is found, whether lymph node enlargement is found, whether new symptoms of pelvic cavity, abdomen or lung occur, whether recurrence or metastasis is suspected; markers for cervical cancer, cervical cancer precancerous lesions, precancerous diseases and cervical cancer related diseases stored in the tumor marker parameter library include, but are not limited to, protein and metabolic markers (e.g., CA 125, CEA, SCC-Ag, CYFRA21-1, TPA, TPS, B-FABP, NCK-1, CDK4, HPV L1, p16INK4a, TOPO2A, MCM2, Ki-67, IGF-1, IGF-2, TNF- α, HIF-1, EGFR, HER2, MMR/MSI status, PD-L1, NTRK, NOTCH3, CD34, CD24, TERC, tu-M2-PK, COX-2, IL-6, etc.), nucleic acid markers, platelets (tumor-mediated microenvironment), exosomes (exosome-7 d-3p, exosome-30 d-5 p-p 5, etc.), and tumor markers (H-3-685-L634, B7-H4, CXCL-12, tumor mutational burden); the nucleic acid markers include, but are not limited to, microRNA (miR-466, miR-143, miR-21, miR-146a, miR-10a, miR-19, miR-372, miR-214, miR-218, miR-34a, miR-375, miR-181 and the like), CTC, ctDNA/cfDNA (HPV ctDNA), mRNA ctRNA (HPV E6/E7 mRNA, circulating mRNAs and the like), IncRNA (ZNF 667-AS1, CCHE1, SNHG-7, LUCAT-1, CRNDE, PC-1), DNA methylation/histone modification (DAPK 1 methylation, RAR-beta methylation, TWIST1 methylation, hX6 methylation, SOX1 methylation, PAX1 methylation, NKLMX 1 methylation, NKX6-1 methylation, WT1 methylation, ONUT 1 methylation and ECm 6A methylation.
Further, the parameters stored in the screening and diagnosis parameter library that affect the vulvar cancer screening diagnosis include, but are not limited to, tumor size, shape, number, location, tumor infiltration depth, histological classification, histological grade, whether biopsy is performed, HPV screening, HIV screening, patient age, whether smoking is performed, whether tumor is confined to vulva and/or perineum, whether tumor invades adjacent tissue, whether regional lymph node metastasis is present, number of lymph node metastases, whether tumor is disseminated to distant organs; the parameters stored in the treatment parameter library and influencing the treatment of the vulvar cancer comprise but are not limited to TNM stage, FIGO stage, whether treatment is received or not, whether biopsy is carried out or not, tumor part, whether operation is feasible or not, postoperative incisional margin condition, sentinel lymph node biopsy result, whether secondary operation excision is carried out or not, inguinal lymph node biopsy result, whether residual tumor exists in primary part and/or lymph node or not, tumor bed biopsy result, recurrence condition and previous treatment condition; parameters stored in the monitoring follow-up parameter library and influencing vulvar cancer monitoring follow-up include but are not limited to disease response conditions, whether a palpable lump is found, whether lymph node swelling is found, whether new symptoms occur, whether recurrence or metastasis is suspected, follow-up time, and patient self-management conditions; markers of vulvar cancer, vulvar precancerous lesions, precancerous conditions and vulvar cancer related diseases stored in the tumor marker parameter library include, but are not limited to, protein and metabolic markers (e.g., p16, p53, CFL-1, p16Ink4a, MVD, VEGF, PTEN, ROCK1, VDR, L1CAM, Tenascin, EGFR, SCC-Ag, CA 15-3, E6 HPV, CEA, etc.), nucleic acid markers, platelets (tumor-reduced platelets), exosome and tumor microenvironment markers (PD-1/PD-L1, COX-2, tumor mutation load); the nucleic acid markers include, but are not limited to, microRNA (miR-3147, miR-17, miR-223-5p, miR-21 and the like), mRNA, CTC, ctDNA/cfDNA, ctRNA, lncRNA, DNA methylation/histone modification (RASSF 1A methylation, RASSF2A methylation, p16 methylation, TSP-1 methylation, MGMT methylation) and m6A RNA methylation.
Further, the diagnosis and treatment result output unit includes:
the diagnosis and treatment scheme module is used for displaying standard clinical paths and/or real world clinical paths, wherein the standard clinical paths and/or the real world clinical paths are classified into first-choice recommendations, second-choice recommendations and other recommendations according to the sequence from high to low after the comparison by the comparison processor unit, and one or more of the information of the whole medical process such as examination, diagnosis, treatment, rehabilitation follow-up visits and the like are used as diagnosis and treatment suggestions for assisting clinical decision;
the evidence support module is used for displaying clinical research data or real world research data matched with the standard clinical path or the real world clinical path in the diagnosis and treatment scheme module, and is specifically divided into one or more categories of research information, nano-grade standard, baseline characteristic, treatment scheme, treatment result, adverse reaction, subgroup information, other prognosis and follow-up information, reasonable medication information, guideline/expert consensus opinion, medication burden and the like for visual display, and provides scientific research suggestions for assisting clinical decision and scientific research work;
and the continuous education module is used for displaying continuous education data matched with the standard clinical path or the real world clinical path in the diagnosis and treatment scheme module, including contents such as standardized diagnosis and treatment, science popularization and patient self-management directly related to the patient condition, and displaying forms including but not limited to texts, pictures, tables, audio and videos for assisting clinical decision and teaching.
Furthermore, the diagnosis information comprises western medicine diagnosis and traditional Chinese medicine syndrome differentiation and disease differentiation, the medicine scheme suggestions in the treatment information comprise western medicines, traditional Chinese medicines and Chinese patent medicines, and a user can adjust the diagnosis and treatment suggestions on the basis of the diagnosis and treatment suggestions, wherein the diagnosis and treatment suggestions comprise item increase, item reduction, item modification and the like.
Further, the early warning and operation recording unit includes:
and the medical behavior early warning module is used for receiving the medical behavior rationality early warning information sent by the diagnosis and treatment result output unit and then carrying out real-time early warning and suggestion on unreasonable treatment and medication schemes in the diagnosis and treatment process of doctors. The medical behavior reasonability early warning information is derived from professional medical and pharmaceutical data, a drug instruction book, most authoritative and latest clinical research data at home and abroad, real world research data, reasonable medication guide consensus and the like, and the presented specific data comprises but is not limited to indications, contraindications, adverse reactions, drug interaction, medication crowd early warning, drug use early warning, reasonable medication rating and price reference;
and the operation record feedback module is used for recording the diagnosis and treatment scheme finally selected by the user and feeding back and optimizing the system. The user can manually select whether to adopt the diagnosis and treatment scheme, if the user selects to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the selected data is sent back to the relevant electronic information system of the hospital, and the functions of prescription write-back, case history write-back and the like are realized; if the user chooses not to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the reason of not adopting can be filled, and the actual diagnosis and treatment path and the diagnosis and treatment ending of the case are combined for optimizing the data of the medical and pharmaceutical data storage unit and the diagnosis and treatment parameter storage unit. The system can also compare the actual diagnosis and treatment path of the patient in each electronic information system of the hospital with the diagnosis and treatment scheme recommended by the system to judge whether the user adopts the system recommendation, and feeds the actual diagnosis and treatment path and diagnosis and treatment ending of the case back to the medical and pharmaceutical data storage unit to expand the data volume of the case and further continuously optimize the data in the diagnosis and treatment parameter storage unit.
By combining the composition and corresponding functions of the system, the system calls the comparison processor unit to compare the patient information parameter values with the data in the diagnosis and treatment parameter storage unit, so that corresponding diagnosis and treatment references can be obtained, and the diagnosis and treatment result output unit displays corresponding result data which can be used as corresponding diagnosis and treatment suggestions or auxiliary information for scientific research, learning and the like.
The invention has the following beneficial effects:
(1) the method and the system provided by the invention combine a large amount of medical/pharmaceutical related data of a western medicine system and a traditional Chinese medicine system, generate a standard clinical path through knowledge map deduction and analysis, and also combine real world research data to generate a real world clinical path as supplement. The real world clinical path and the standard clinical path can be compared to be used as diagnosis and treatment comprehensive reference, operability improvement on the standard clinical path is facilitated by combining reality, diagnosis and treatment nodes to be standardized in actual clinical work are conveniently found, and the requirements of clinical diagnosis and treatment normalization and actual operability are met. In addition, the real world clinical path can be used as a reference for special crowds and subdivision diagnosis and treatment stages, the real world clinical path established through real world data analysis can better reflect the actual development situation of clinical work and the actual diagnosis and treatment results, and clinical practice and clinical research can be better guided.
(2) The method and the system provided by the invention are used for decision support aiming at the whole disease cycle of cervical cancer and vulvar cancer, parameters influencing screening diagnosis, treatment and monitoring follow-up of the cervical cancer and the vulvar cancer, parameter weight values and parameter values of the parameters are specifically discovered through machine learning, and the standard clinical path and the real world clinical path are coded through the parameter values, so that the clinical decision support for the cervical cancer and the vulvar cancer is more accurate.
(3) According to the method and the system, the output diagnosis and treatment result suggestion integrates multi-dimensional information such as clinical diagnosis and treatment paths, evidence support, early warning of rationality of medical behaviors and the like, and systematic and multi-dimensional assistance is performed in the whole medical process from diagnosis, treatment to rational medication and rehabilitation follow-up.
(4) The method and the system provided by the invention have the advantages that the realized diagnosis and treatment assistance comprises a western medicine system and a traditional Chinese medicine system, the diagnosis suggestion comprises western medicine diagnosis and traditional Chinese medicine syndrome differentiation, and the treatment medicine recommendation comprises western medicines, traditional Chinese medicines and traditional Chinese medicines, so that the method and the system are more in line with the actual situation of China.
(5) The method and the system can give a doctor suggestions of specific diagnosis and treatment schemes in a standard clinical path and a real-world clinical path, can check clinical research evidence and real-world research data supporting the application of the diagnosis and treatment schemes, accord with the principle of evidence-based medicine, and the doctor can judge whether the diagnosis and treatment suggestions are reasonable or not by combining the clinical experience of the doctor and update the clinical knowledge of the doctor, so the method and the system can be simultaneously applied to diagnosis and treatment assistance and teaching assistance. The research evidence section is presented in a visual form, so that a user can quickly and comprehensively know the current research situation and the future development direction of a certain clinical direction to assist scientific research work.
(6) The method and the system can provide continuous education information, the information combines standard clinical paths and real world research data, and the level of clinical theory teaching and practice teaching can be rapidly and pertinently improved.
(7) The diagnosis and treatment information selected by the doctor in the system can be directly written back to subsystems such as a medical record and a prescription, and the like, so that the operation is simplified. When a doctor prescribes a prescription, the system can perform medical behavior rationality early warning based on the actual condition of a patient, prompt whether a treatment scheme in the prescription of the doctor accords with an indication, whether interaction exists, whether quantity adjustment is needed, clinical evidence intensity for the indication, rational medication evaluation and the like, synthesize individual differences of the patient and clinical paths to perform rational medication specification and early warning, ensure rationality and safety of the medication scheme based on the individual differences of the patient, improve the individualized medical service level, avoid the problem that an independent medication system inputs information again, and realize in-process multi-dimensional early warning.
(8) The method and the system can provide feasible clinical diagnosis and treatment proposal and corresponding clinical research and real world research evidence support for relevant medical workers, cover the whole period of diseases such as screening diagnosis, treatment, monitoring follow-up visit, out-of-hospital management and the like, assist doctors to quickly improve the clinical diagnosis and treatment level, learn and update diagnosis and treatment knowledge, master the current research situation and the development direction of clinical research and real world diagnosis and treatment, and solve the contradiction that the time and the energy of the medical workers are difficult to follow the clinical research progress.
Drawings
FIG. 1 is a block diagram of the system of the present invention.
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the present invention is described below with reference to the embodiments.
Example 1
In this embodiment, the cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support system comprises a medical and pharmaceutical data storage unit, a diagnosis and treatment parameter storage unit, an information input unit, a comparison processor unit, a diagnosis and treatment result output unit and an early warning and operation recording unit. Referring to fig. 1, the specific functions of the respective constituent units are as follows:
a medical and pharmaceutical data storage unit comprising: medical and pharmaceutical repositories, standard clinical pathways and evidences repositories, real world clinical pathways and evidences repositories. The information stored in the medical and pharmaceutical database comprises, but is not limited to, medical and pharmaceutical data of western medicine system and traditional Chinese medicine system, medical policy information, structured medical record information, patient out-of-hospital management information, disease burden information, drug instruction manual, consumable information, clinical research data, real world research data, clinical guidelines, expert consensus and other cross-modal multi-source heterogeneous data; the real world research data is from real world research formed by medical data subjected to data desensitization, cleaning and system analysis in various regions, medical institutions at all levels and families at home and abroad; the information stored in the medical and pharmaceutical data storage unit is extracted through technologies such as character recognition, image recognition, voice recognition and the like, is stored after being cleaned and structured, and is subjected to machine learning knowledge graph deduction to generate standard clinical path, real world clinical path, medical behavior rationality early warning information, continuous education data, and clinical research data and real world research data which serve as the content evidence support. The standard clinical pathway and the evidence base are used for storing a standard clinical pathway data cluster, and the standard clinical pathway data cluster is formed by pairing each standard clinical pathway generated by analysis in the medical and pharmaceutical data base as a data main body with one or more data information of continuous education data, medical behavior rationality early warning information, clinical research data and real world research data. The real world clinical pathway and the evidence base are used for storing a real world clinical pathway data cluster, and the real world clinical pathway data cluster is formed by pairing each real world clinical pathway generated by analysis in the medical and pharmaceutical data base as a data main body with one or more data information of continuous education data, medical behavior rationality early warning information and real world research data.
The diagnosis and treatment parameter storage unit comprises a screening diagnosis parameter library, a treatment parameter library, a monitoring follow-up parameter library and a tumor marker parameter library, and stores: the standard clinical path and the real world clinical path are coded through the parameter values, wherein the stored parameters comprise screening diagnosis parameters, treatment parameters and monitoring follow-up parameters which are discovered through machine learning and affect the cervical cancer and the vulva cancer. The user can adjust the information in the diagnosis and treatment parameter storage unit, including increasing parameters, decreasing parameters, adjusting parameter weights and the like.
The information input unit can be directly connected with a hospital HIS system (a hospital information system for storing and comprehensively managing various information of a hospital), and cross-modal multi-source heterogeneous information such as symptoms, physical signs, medical history, examination results and the like of a patient is called through an outpatient service management subsystem, an emergency management subsystem, a medical record management subsystem and the like, and is identified, extracted and structurally processed to generate a patient information parameter value; or the doctor inputs the patient information in modes of voice, characters, images, information selection under the guidance of the front end of the system and the like. Patient information is identified, extracted and structured to generate a patient information parameter value; sending the patient information parameter values to a comparison processor unit for parameter value comparison to match a clinical pathway. When a specific information query supplement instruction sent by the comparison processor unit is received, the specific information is queried from the HIS system, or a supplement input specific information prompt is sent to a user, and the user can check information such as associated parameters, approximate path structures, clinical significance of missing parameters and the like of the missing parameters. The information input unit sends the result to the comparison processor unit after the specific information is queried and supplemented.
And the comparison processor unit is used for calling data stored in a screening and diagnosis parameter library, a treatment parameter library, a monitoring follow-up parameter library and a tumor marker parameter library in the diagnosis and treatment parameter storage unit after receiving the patient information parameter values sent by the information input unit, and comparing the patient information parameter values with the parameter values in the four databases, including direct comparison and comparison after rule processing, wherein the used comparison technology includes but is not limited to a Spark calculation engine and other various computer algorithms. When the standard clinical path or the real world clinical path has parameters with missing patient information parameter values, the comparison processor unit sends a specific information query supplement instruction to the information input unit, and secondary comparison is performed after a specific information query supplement result fed back by the information input unit is received. And when the specific information is a specific examination result, if the user confirms that the examination is not performed, pushing an examination suggestion to the diagnosis and treatment result output unit. The system presets the optimal credit acquisition threshold value of the parameter value matching degree according to model training, and a user can also set the threshold value in the system according to actual needs. And the comparison processor unit sends the standard clinical path data cluster and the real world clinical path data cluster with the matching degree reaching the threshold value to the diagnosis and treatment result output unit according to the parameter value comparison result.
And the diagnosis and treatment result output unit comprises a diagnosis and treatment scheme module, an evidence support module and a continuing education module, and is used for dividing the standard clinical path data cluster and/or the real world clinical path data cluster into a preferred recommendation, a secondary recommendation and other recommendations according to the matching degree after receiving the data sent by the comparison processor unit, so that a user can modify the recommendation division standard. And splitting and restoring the information in the standard clinical path data cluster and the real-world clinical path data cluster into a standard clinical path, a real-world clinical path, corresponding clinical research data and real-world research data, corresponding continuing education data and corresponding medical behavior rationality early warning information. The standard clinical path and the real world clinical path are presented in the diagnosis protocol module in the form of diagnosis advice, the clinical research data and the real world research data are presented in the evidence support module, and the continuing education data are presented in the continuing education module. The standard clinical path and the real world clinical path comprise information of the whole medical process such as examination, diagnosis, treatment, rehabilitation follow-up visit and the like, and one or more of the information is output as diagnosis and treatment suggestions according to the clinical diagnosis and treatment stage positioned after the information parameters of the patient are compared with the parameters in the diagnosis and treatment parameter storage unit. The diagnosis information comprises western medicine diagnosis and traditional Chinese medicine syndrome differentiation and disease differentiation. The medicine scheme suggestion in the treatment information comprises western medicines, traditional Chinese medicines and Chinese patent medicines. The user may make adjustments based on the clinical recommendations, including item additions, item reductions, and item modifications. The clinical research data and the real world research data are presented in the evidence support module and are specifically divided into one or more categories of research information, nano-ranking standards, baseline characteristics, treatment schemes, treatment results, adverse reactions, guideline/expert consensus opinions, medication burdens and the like, so that a user can quickly and comprehensively master the current research situation and the future development direction in a certain refined clinical direction, and scientific research work is assisted. The continuing education data are presented in the continuing education module in forms of texts, pictures, tables, audios and videos according to specific data structures, and are used for the standardized diagnosis and treatment teaching of the whole disease cycle of the cervical cancer and the vulvar cancer. And sending the early warning information of the rationality of the medical behavior to an early warning and operation recording unit for real-time early warning in the clinical diagnosis and treatment process of doctors.
The early warning and operation recording unit comprises a medical behavior early warning module and an operation recording feedback module. And after receiving the medical behavior rationality early warning information sent by the diagnosis and treatment result output unit, the medical behavior early warning module carries out real-time early warning and suggestion on unreasonable treatment and medication schemes in the diagnosis and treatment process of doctors. The medical behavior reasonability early warning information is derived from professional medical/pharmaceutical data, a drug instruction book, most authoritative and latest clinical research data at home and abroad, real world research data, reasonable medication guide consensus and the like, and the presented specific data comprises but is not limited to indications, contraindications, adverse reactions, drug interaction, medication crowd early warning, drug use early warning, reasonable medication rating and price reference. And the operation record feedback module is used for recording the diagnosis and treatment scheme finally selected by the user and feeding back and optimizing the system. The user can manually select whether to adopt the diagnosis and treatment scheme, if the user selects to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the selected data is sent back to the relevant electronic information system of the hospital, and the functions of prescription write-back, case history write-back and the like are realized; if the user chooses not to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the reason of not adopting can be filled, and the actual diagnosis and treatment path and the diagnosis and treatment ending of the case are combined for optimizing the data of the medical and pharmaceutical data storage unit and the diagnosis and treatment parameter storage unit. The system can also compare the actual diagnosis and treatment path of the patient in each electronic information system of the hospital with the diagnosis and treatment scheme recommended by the system to judge whether the user adopts the system recommendation, and feeds the actual diagnosis and treatment path and diagnosis and treatment ending of the case back to the medical and pharmaceutical data storage unit to expand the data volume of the case and further continuously optimize the data in the diagnosis and treatment parameter storage unit.
The system combines with a corresponding auxiliary support method, as shown in fig. 2, and the specific operation steps are as follows:
(1) the information such as symptoms, physical signs, medical history and examination results of the patient is called from an outpatient service, an emergency management subsystem, a medical record management subsystem and the like of a hospital HIS system, or the information of the patient is input by a doctor in a mode of information selection under the guidance of voice, characters, images and a system front end. The patient information is identified, extracted and structured to generate patient information parameter values.
(2) The clinical decision support system starts a comparison processor unit to determine whether a standard clinical pathway and/or a real world clinical pathway completely matching the patient information parameter value exists:
if the path data cluster exists, the completely matched standard clinical path data cluster and/or the completely matched real world clinical path data cluster are/is called and sent to a diagnosis and treatment result output unit; the information presented to the user in the diagnosis and treatment result output unit comprises diagnosis and treatment suggestions (such as diagnosis results of patients at present stage, examinations to be performed, treatment scheme suggestions and rehabilitation follow-up suggestions) for auxiliary medicine based on standard clinical paths and real-world clinical paths, clinical evidence support and real-world evidence support (clinical studies or real-world studies corresponding to the diagnosis and treatment suggestions are processed by data structure and are divided into research information, nano-ranking criteria, baseline characteristics, treatment scheme, overall treatment results, adverse reactions, subgroup treatment results and adverse reactions, other prognosis and follow-up information, rational medication information, disease burden, guideline/expert consensus suggestions and the like), and continuous education information (directly related to the patient's condition) for auxiliary medicine and teaching can be correspondingly presented in the diagnosis and treatment suggestions The related contents of standardized diagnosis and treatment, science popularization, patient self management and the like are presented in the forms of texts, pictures, tables, audios, videos and the like).
If the standard clinical path and the real-world clinical path which are completely matched with the patient information parameter value do not exist, the comparison processor unit sends a specific information query supplementary instruction to the information input unit, and the information input unit queries specific information from a data source, such as searching from each electronic information system of a hospital or prompting information loss to a user and presenting an information supplementary window. And when the specific information is a specific examination result, if the user confirms that the examination is not performed, pushing an examination suggestion to the diagnosis and treatment result output unit.
And the comparison processor unit carries out secondary comparison after receiving the specific information query supplementary result fed back by the information input unit, judges whether a standard clinical path and/or a real world clinical path which are completely matched with the information parameter value of the patient exist at the moment, and calls a completely matched standard clinical path data cluster and/or a real world clinical path data cluster and sends the data cluster to the diagnosis and treatment result output unit if the standard clinical path and/or the real world clinical path data cluster exist. And if the standard clinical path and the real-world clinical path which are completely matched with the patient information parameter value do not exist, judging whether the matching degree of the standard clinical path and/or the real-world clinical path reaches a threshold value. And if the matching degree of the standard clinical path and/or the real world clinical path reaches a threshold value, sending the corresponding standard clinical path data cluster and/or the real world clinical path data cluster to a diagnosis and treatment result output unit, and dividing the decision support information into a first selection recommendation, a second selection recommendation and other recommendations according to the matching degree for presentation. If the matching degrees of the standard clinical path and the real world clinical path do not reach the threshold value, the comparison processor sends the standard clinical path data cluster and the real world clinical path data cluster with the highest matching degree to the diagnosis and treatment result output unit, diagnosis and treatment references based on the similar standard clinical path and the real world clinical path are presented to a user at the diagnosis and treatment result output unit, missing important information is prompted to the user, the diagnosis and treatment references are provided, meanwhile, similar real world evidences are provided as references, and the continuous education information of similar cases is presented to provide standardized references. In the comparison process, the threshold is the optimal confidence acquisition threshold of the system according to the parameter value matching degree preset by model training, and the user can also set the threshold in the system according to actual needs.
(3) And judging whether the diagnosis and treatment are finished by the user, if the diagnosis and treatment at the stage are not finished, calling the subsequent diagnosis and treatment information of the patient by the HIS of the hospital, importing the subsequent diagnosis and treatment information into the clinical decision support system for information updating, or manually inputting the subsequent diagnosis and treatment information of the patient by the user, and then carrying out clinical decision support again until the diagnosis and treatment at the stage are finished by the user selection. If the diagnosis and treatment at the stage are finished, whether a user adopts a diagnosis and treatment suggestion or not is judged, the diagnosis and treatment suggestion can be manually judged by the user, if the diagnosis and treatment suggestion is adopted, a diagnosis and treatment option selected by the user is written back to the HIS system, for example, information such as diagnosis, examination and treatment schemes is written back to subsystems such as a medical plan and a prescription, and when the prescription is made, the clinical decision support system can perform real-time early warning on the diagnosis and treatment scheme or medicine selected by a doctor (for example, when an unreasonable diagnosis and treatment scheme or unreasonable medicine application and other conditions occur), and the clinical decision support is finished after the completion; if the user chooses not to adopt the diagnosis and treatment suggestion, the user can selectively input the reason and end the clinical decision support. Whether the user manually judges whether to adopt the diagnosis and treatment suggestion or not and whether the user selects to adopt the diagnosis and treatment suggestion or not, the system background can record the real diagnosis and treatment path and diagnosis and treatment ending of the patient, the real diagnosis and treatment path and the diagnosis and treatment ending are compared with the diagnosis and treatment suggestion of the system, whether the user adopts the suggestion or not is automatically judged, the suggestion is fed back to the medical and pharmaceutical data storage unit, the data volume of the data storage unit is expanded, and then the data in the diagnosis and treatment parameter storage unit is continuously optimized.
Example 2
Based on the system and method implemented in embodiment 1, reference is made specifically to tables 1-2, where: table 1 lists some parameters affecting cervical cancer diagnosis and treatment, and the parameter values corresponding to the parameters are coded by different parameter values after structured processing; table 2 lists the clinical pathways of cervical cancer, expressed in part in parameter coding.
TABLE 1
Figure DEST_PATH_IMAGE002
TABLE 2
Figure DEST_PATH_IMAGE004
According to the table 1-2, the medical record information of a certain patient obtained by the information input unit at this time is 'treatment-initiated patient, 30 years old, cervical cancer confirmed in our hospital one week before, evaluated as IA1 stage by pathological biopsy, LVSI positive and unexpired', and the patient information parameter value obtained after identification, extraction, natural language processing and rule processing is 'treatment-initiated'; age 30; confirmed cervical cancer; pathology IA1 stage; LVSI positive; non-breeding; retention of fertility function ", matching the parameter value in the parameter storage unit to B0 (not receiving treatment); a1 (confirmed cervical cancer); d1 (stage IA 1); g1 (vascular infiltration positive); e1 (preservation of fertility). The clinical path matching degree is ranked from high to low as: A1-B0-D1-G1-E1 (100%); A1-B0-D1-G1-E0 (96%); A1-B0-D1-G0-E1 (90%); A1-B0-D1-G0-E0 (86%). The matching degree threshold is preset to be 95%, so the treatment recommendation part is recommended to obtain negative incisional margins for cervical conization or radical cervicitis + pelvic lymph node cleaning (considering sentinel lymph node mapping) firstly, and recommended to improve radical cervicitis + pelvic lymph node cleaning (considering sentinel lymph node mapping) or pelvic EBRT + brachytherapy secondly.
The same can be applied to vulvar cancer based on the system and method implemented in example 1. The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention.

Claims (10)

1. An auxiliary support method for clinical decision, teaching and scientific research of cervical cancer and vulvar cancer is characterized by comprising the following steps:
(1) acquiring patient information from a hospital HIS system and a related system, or providing the patient information by a doctor, and generating a patient information parameter value after identifying, extracting and structuring the patient information;
(2) and comparing and judging whether a standard clinical path and/or a real world clinical path which are completely matched with the patient information parameter values exist or not, wherein in the judgment result:
if the completely matched standard clinical path and/or real world clinical path exist, calling a completely matched standard clinical path data cluster and/or real world clinical path data cluster, and outputting and displaying decision support information; the decision support information comprises a standard clinical pathway and real-world clinical pathway based clinical recommendation for assisting clinical decision making; the diagnosis and treatment suggestion is correspondingly used for clinical evidence support and real world evidence support for assisting clinical decision and scientific research, or is correspondingly used for continuing education information for assisting clinical decision and teaching;
if the completely matched standard clinical path and/or real world clinical path does not exist, a specific information query supplementary instruction is sent out, and then specific information is queried from a data source according to the specific information query supplementary instruction; when the specific information is a specific inspection result, if the user confirms that the inspection is not carried out, pushing an inspection suggestion;
(3) after the specific information query supplementary result is obtained, secondary comparison judgment is carried out, wherein in the secondary comparison judgment result:
if the standard clinical path and the real-world clinical path which are completely matched with the patient information parameter values exist, calling a completely matched standard clinical path data cluster and/or a completely matched real-world clinical path data cluster, and outputting and displaying decision support information;
if the standard clinical path and the real world clinical path which are completely matched with the patient information parameter values do not exist, judging whether the matching degree of the standard clinical path and/or the real world clinical path reaches a threshold value, and judging that: if the matching degree of the standard clinical path and/or the real world clinical path reaches a threshold value, outputting and displaying a corresponding standard clinical path data cluster and/or real world clinical path data cluster, and dividing the standard clinical path data cluster and/or real world clinical path data cluster into a first-choice recommendation level, a second-choice recommendation level and other recommendation levels according to the matching degree to present the levels to a user; if the matching degrees of the standard clinical path and the real world clinical path do not reach the threshold value, selecting and sending the standard clinical path data cluster and the real world clinical path data cluster with the highest matching degree, presenting diagnosis and treatment references based on the similar standard clinical path and the real world clinical path to a user, prompting missing important information to the user, simultaneously providing similar real world evidence as clinical and scientific research references, and presenting continuous education information of similar medical cases as medical standardized education references; the threshold is an optimal confidence acquisition threshold according to a parameter value matching degree preset by model training, or a threshold is set by a user according to actual needs;
(4) judging whether diagnosis and treatment are finished by the user, if the diagnosis and treatment are not finished at the stage, importing the diagnosis and treatment information through an electronic information system of the hospital or inputting subsequent diagnosis and treatment information of the patient by the user for information updating, and then carrying out clinical decision support again until the diagnosis and treatment at the stage are finished by the user; if diagnosis and treatment at the stage are finished at the moment, judging whether the user adopts diagnosis and treatment suggestions or not, wherein the judging mode comprises manual judgment of the user and automatic judgment after comparison of the real diagnosis and treatment path of the patient with the diagnosis and treatment outcome and the diagnosis and treatment suggestions: if the diagnosis and treatment options selected by the user are adopted, writing the diagnosis and treatment options back to the HIS system of the hospital, carrying out real-time early warning on the diagnosis and treatment scheme or the medicine selected by the doctor when the doctor prescribes, and ending the clinical decision support after the prescription is completed; if the user chooses not to adopt the diagnosis and treatment suggestion, the clinical decision support is ended, and the user can selectively input the reason for not adopting the diagnosis and treatment suggestion before the end.
2. The clinical decision-making, teaching and scientific research auxiliary support method for cervical cancer and vulvar cancer as claimed in claim 1, wherein in step (1), the patient information at least includes symptoms, signs, medical history and/or examination results, and the way of providing the patient information by the doctor at least includes voice, text, image and information for selecting the patient under corresponding front-end guidance information; the mode of inquiring the specific information from the data source in the step (2) comprises searching from each electronic information system of the hospital, or prompting information loss to the user and requiring the user to perform information supplement.
3. Cervical cancer and vulva cancer clinical decision, teaching, scientific research assistance support system, its characterized in that: the diagnosis and treatment system comprises a medical and pharmaceutical data storage unit, a diagnosis and treatment parameter storage unit, an information input unit, a comparison processor unit, a diagnosis and treatment result output unit and an early warning and operation recording unit;
the medical and pharmaceutical data storage unit is used for storing all medical and pharmaceutical related data of a western medicine system and a traditional Chinese medicine system, and storing a standard clinical path data cluster and a real world clinical path data cluster;
the diagnosis and treatment parameter storage unit is used for storing: parameters influencing screening diagnosis, treatment and monitoring follow-up of cervical cancer and vulvar cancer, parameter weight values and parameter values of the parameters, wherein information in the diagnosis and treatment parameter storage unit can be manually adjusted;
the information input unit is used for acquiring the patient information, performing information structuring processing according to different acquisition forms and information modes, generating patient information parameters and sending the patient information parameters to the comparison processor unit; the information input unit is used for inquiring the specific information from the hospital HIS system and related systems when receiving a specific information inquiry supplement instruction sent by the comparison processor unit, or sending a prompt for supplementing and inputting the specific information, the associated parameters of the missing parameters, the approximate path structure and the clinical significance of the missing parameters to a user and presenting an information supplement window, and sending a result to the comparison processor unit after the specific information inquiry supplement; the form of acquiring the patient information comprises: the mode of calling from the hospital HIS system and the related system and the mode of direct input by the user;
the comparison processor unit is used for receiving the data sent by the information input unit, calling the data of the diagnosis and treatment parameter storage unit and comparing the two data; when parameters of missing patient information parameter values exist in the standard clinical path or the real world clinical path, a specific information query supplement instruction is sent to the information input unit by the comparison processor unit, secondary comparison is carried out after a specific information query supplement result fed back by the information input unit is received, and then a standard clinical path data cluster and a real world clinical path data cluster which reach a preset or user-set matching degree threshold are sent to the diagnosis and treatment result output unit;
the diagnosis and treatment result output unit is used for receiving and displaying the result data sent by the comparison processor unit according to the matching degree sorting submodules so as to assist clinical decision, teaching and scientific research;
the early warning and operation recording unit is used for carrying out reasonability early warning on treatment and medication schemes and the like specifically related to a clinical path when a doctor prescribes a prescription, recording the real diagnosis and treatment path and results of a patient, comparing whether diagnosis and treatment suggestions and medical behavior reasonability early warning suggestions displayed in the diagnosis and treatment result output unit are adopted by a user or not, feeding back the recorded real diagnosis and treatment path and result information of the patient into a medical and pharmaceutical data storage unit, expanding the data quantity of the medical and pharmaceutical data storage unit, and further continuously optimizing the information in the clinical path and an evidence storage unit;
wherein, diagnosis and treatment parameter memory cell includes:
the screening and diagnosis parameter library is used for storing parameters influencing screening and diagnosis of cervical cancer and vulvar cancer, parameter weight values and parameter values of the parameters;
the treatment parameter library is used for storing parameters influencing the treatment of the cervical cancer and the vulva cancer, parameter weight values and parameter values of the parameters;
the monitoring follow-up parameter library is used for storing parameters, parameter weight values and parameter values of the parameters, which influence the cervical cancer and vulvar cancer monitoring follow-up;
the tumor marker parameter library is used for storing markers of cervical cancer, vulvar cancer, precancerous lesion, precancerous diseases and cervical cancer and vulvar cancer related diseases, and the parameters stored in the tumor marker parameter library are derived from tumor tissues, tissues beside cancer, normal tissues or cells, blood or body fluid.
4. The cervical and vulvar cancer clinical decision, education and scientific research support system of claim 3 wherein the medical and pharmaceutical data storage unit includes:
the medical and pharmaceutical database is used for storing all medical and pharmaceutical relevant data of a western medicine system and a traditional Chinese medicine system, and comprises a series of cross-modal multi-source heterogeneous data, and the series of cross-modal multi-source heterogeneous data at least comprises: medical and pharmaceutical data of western medicine system and traditional Chinese medicine system, medical policy information, structured medical record information, patient out-of-hospital management information, disease burden information, drug instruction manual, consumable information, clinical research data, real world research data, clinical guidelines, expert consensus;
the standard clinical path library is used for storing standard clinical path data clusters, namely standard clinical paths, continuing education data, medical behavior rationality early warning information, clinical research data and real world research data which are generated by analyzing the medical and pharmaceutical data storage units and are paired into groups;
and the real world clinical path library is used for storing real world clinical path data clusters, namely paired and grouped real world clinical paths, continuous education data, medical behavior rationality early warning information and real world research data which are generated by analyzing the medical and pharmaceutical data storage units.
5. The cervical and vulvar cancer clinical decision making, education, scientific research assistance support system as claimed in claim 3 wherein the parameters stored in the screening and diagnosis parameter bank that affect screening and diagnosis of cervical cancer include but are not limited to the cervical cancer that has been diagnosed, whether biopsy has been performed, tumor size, tumor infiltration depth, whether tumor is confined to cervix, whether tumor affects the lower third vagina, whether tumor affects the pelvic wall, whether tumor causes hydronephrosis or renal dysfunction, whether pelvic lymph node metastasis exists, whether there is abdominal periaortic lymph node metastasis, whether tumor invades adjacent organs, whether tumor spreads to distant organs, whether chest X-ray examination has been performed, whether abnormal results of chest X-ray examination are found, whether there are other symptoms and suspected metastases, whether hysterectomy has been performed, histological classification, whether tumor is affected by cancer, whether or not the tumor has been affected by cancer, Histology grade, whether sentinel lymph node mapping biopsy has been performed; parameters which are stored in the treatment parameter library and influence the treatment of the cervical cancer comprise, but are not limited to, FIGO stages, whether the fertility function can be reserved, whether cervical conization can be performed, the incisal margin condition of conical biopsy, whether the operation can be performed, the condition of postoperative pelvic lymph node invasion, the condition of postoperative periaortic lymph node invasion, the condition of postoperative incisal margin, the condition of postoperative periuterine tissue invasion, high risk factors for adjuvant therapy, the postoperative peritoneal lymph node or peritoneal lymph node sweeping result, the recurrence condition and the previous treatment condition; parameters stored in the monitoring follow-up parameter library and influencing cervical cancer monitoring follow-up include but are not limited to FIGO stages, whether a palpable mass is found, whether lymph node enlargement is found, whether new symptoms of pelvic cavity, abdomen or lung occur, whether recurrence or metastasis is suspected; markers of cervical cancer, cervical precancerous lesions, precancerous diseases and cervical cancer related diseases stored in the tumor marker parameter library include, but are not limited to, protein and metabolic markers, nucleic acid markers, platelets, exosomes and tumor microenvironment markers; the nucleic acid markers include, but are not limited to, microRNA, mRNA, CTC, ctDNA/cfDNA, ctRNA, lncRNA, DNA methylation/histone modification, and m6A RNA methylation.
6. The cervical and vulvar cancer clinical decision, education and scientific research support system as claimed in claim 3, wherein: parameters stored in the screening and diagnosis parameter library that affect vulvar cancer screening diagnosis include, but are not limited to, tumor size, shape, number, location, depth of tumor infiltration, histological classification, histological grade, whether biopsy is performed, HPV screening, HIV screening, patient age, whether smoking is done, whether tumor is confined to the vulva and/or perineum, whether tumor invades adjacent tissue, whether regional lymph node metastasis is present, number of lymph node metastases, whether tumor is disseminated to distant organs; the parameters stored in the treatment parameter library and influencing the treatment of the vulvar cancer comprise but are not limited to TNM stage, FIGO stage, whether treatment is received or not, whether biopsy is carried out or not, tumor part, whether operation is feasible or not, postoperative incisional margin condition, sentinel lymph node biopsy result, whether secondary operation excision is carried out or not, inguinal lymph node biopsy result, whether residual tumor exists in primary part and/or lymph node or not, tumor bed biopsy result, recurrence condition and previous treatment condition; parameters stored in the monitoring follow-up parameter library and influencing vulvar cancer monitoring follow-up include but are not limited to disease response conditions, whether a palpable lump is found, whether lymph node swelling is found, whether new symptoms occur, whether recurrence or metastasis is suspected, follow-up time, and patient self-management conditions; markers of vulvar cancer, vulvar precancerous lesion, precancerous disease and vulvar cancer related diseases stored in the tumor marker parameter library include, but are not limited to, proteins and metabolic markers, nucleic acid markers, platelets, exosomes and tumor microenvironment markers; the nucleic acid markers include, but are not limited to, microRNA, mRNA, CTC, ctDNA/cfDNA, ctRNA, lncRNA, DNA methylation/histone modification, and m6A RNA methylation.
7. The cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support system as claimed in claim 3, wherein the diagnosis and treatment result output unit comprises:
the diagnosis and treatment scheme module is used for displaying standard clinical paths and/or real world clinical paths which are divided into first-choice recommendations, second-choice recommendations and other recommendations according to the sequence from high to low after the comparison by the comparison processor unit, and at least comprises one or more of whole medical information of examination, diagnosis, treatment and rehabilitation follow-up visits as diagnosis and treatment suggestions for assisting clinical decision;
the evidence support module is used for displaying clinical research data or real world research data matched with the standard clinical path or the real world clinical path in the diagnosis and treatment scheme module, at least comprises one or more of research information, nano-grade standard, baseline characteristic, treatment scheme, treatment result, adverse reaction, subgroup information, other prognosis and follow-up information, reasonable medication information, guideline/expert consensus opinion and medication burden, visually displays the data, provides scientific research suggestions and is used for assisting clinical decision and scientific research work;
and the continuous education module is used for displaying continuous education data matched with the standard clinical path or the real-world clinical path in the diagnosis and treatment scheme module, at least comprises contents of standardized diagnosis and treatment, science popularization and patient self management directly related to the patient illness state, and the display form comprises but is not limited to texts, pictures, tables, audio and videos for assisting clinical decision and teaching.
8. The cervical and vulvar cancer clinical decision making, teaching and scientific research assistant support system as claimed in claim 7, wherein the diagnosis information of the diagnosis and treatment scheme module includes western medicine diagnosis and traditional Chinese medicine syndrome differentiation, the medical scheme suggestions in the treatment information include western medicine, traditional Chinese medicine and Chinese patent medicine, and the user selects adjustment modes including increase, decrease and modification on the basis of the diagnosis and treatment suggestions.
9. The cervical and vulvar cancer clinical decision, education and scientific research support system of claim 3 wherein the early warning and operational recording unit includes:
the medical behavior early warning module is used for receiving the medical behavior rationality early warning information sent by the diagnosis and treatment result output unit and then carrying out real-time early warning and suggestion on unreasonable treatment and medication schemes in the diagnosis and treatment process of doctors; the medical behavior rationality early warning information is derived from one or more of professional medical and pharmaceutical data, a drug instruction book, clinical research data, real world research data and a reasonable medication guide consensus, and the presented specific data comprises but is not limited to indications, contraindications, adverse reactions, drug interactions, medication crowd early warnings, drug use early warnings, reasonable medication ratings and price references;
the operation record feedback module is used for recording the diagnosis and treatment scheme finally selected by the user and feeding back and optimizing the cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support system; the user can manually select whether to adopt the diagnosis and treatment scheme, if the user selects to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the selected data is sent back to the hospital-related electronic information system, and the functions of prescription write-back and medical record write-back are realized; if the user selects not to adopt the diagnosis and treatment scheme recommended by the clinical decision support system, the reason of not adopting can be filled, and the actual diagnosis and treatment path and the diagnosis and treatment outcome of the case are combined to optimize the data of the medical and pharmaceutical data storage unit and the diagnosis and treatment parameter storage unit; meanwhile, the actual diagnosis and treatment path of the patient in each electronic information system of the hospital can be compared with the diagnosis and treatment scheme recommended by the cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support system to automatically judge whether the user adopts the system recommendation, the actual diagnosis and treatment path and diagnosis and treatment outcome of the case are fed back to the medical and pharmaceutical data storage unit, the data volume is expanded, and the data in the diagnosis and treatment parameter storage unit is continuously optimized.
10. The colorectal cancer clinical decision, teaching and scientific research auxiliary support system according to claim 3, wherein the comparison processor unit compares the two data directly with the original data according to the actual situation, or compares the data after performing rule processing; the rule processing includes at least entity relationship mapping and/or logical relationship reasoning.
CN202010789239.7A 2020-08-07 2020-08-07 Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system Pending CN114068009A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010789239.7A CN114068009A (en) 2020-08-07 2020-08-07 Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010789239.7A CN114068009A (en) 2020-08-07 2020-08-07 Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system

Publications (1)

Publication Number Publication Date
CN114068009A true CN114068009A (en) 2022-02-18

Family

ID=80232683

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010789239.7A Pending CN114068009A (en) 2020-08-07 2020-08-07 Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system

Country Status (1)

Country Link
CN (1) CN114068009A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115612744A (en) * 2022-12-14 2023-01-17 中国医学科学院肿瘤医院 Human papilloma virus typing and related gene methylation integrated detection model and construction method thereof
CN116219012A (en) * 2022-12-15 2023-06-06 华中科技大学同济医学院附属同济医院 System and method for predicting cervical cancer neoadjuvant chemotherapy effect or recurrent high-risk classification based on plasma cfDNA fragment distribution characteristics

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115612744A (en) * 2022-12-14 2023-01-17 中国医学科学院肿瘤医院 Human papilloma virus typing and related gene methylation integrated detection model and construction method thereof
CN116219012A (en) * 2022-12-15 2023-06-06 华中科技大学同济医学院附属同济医院 System and method for predicting cervical cancer neoadjuvant chemotherapy effect or recurrent high-risk classification based on plasma cfDNA fragment distribution characteristics

Similar Documents

Publication Publication Date Title
Azami-Aghdash et al. Prevalence and causes of cesarean section in Iran: systematic review and meta-analysis
US7844560B2 (en) Personalized prognosis modeling in medical treatment planning
CN114068003A (en) Clinical decision, teaching and scientific research auxiliary support system and method for urinary system tumor
Shen et al. Global research trends and foci of artificial intelligence-based tumor pathology: a scientometric study
CN114067999A (en) Lung cancer clinical decision, teaching and scientific research auxiliary support system and method
WO2007123914A2 (en) Prognosis modeling from one or more sources of information
EP2435940B1 (en) A method and device for side-effect prognosis and monitoring
CN108520778A (en) A kind of screening lung cancer system and method based on big data
WO2015066421A1 (en) Integrated virtual patient framework
CN114067998A (en) Lymphoma clinical decision, teaching and scientific research auxiliary support system and method
CN114068009A (en) Cervical cancer and vulvar cancer clinical decision, teaching and scientific research auxiliary support method and system
CN114068002A (en) Auxiliary support system and method for clinical decision, teaching and scientific research of breast and thyroid tumors
CN114068006A (en) Leukemia clinical decision, teaching and scientific research auxiliary support system and method
CN114068001A (en) Auxiliary support system and method for clinical decision, teaching and scientific research of head and neck tumors
KR101295785B1 (en) Apparatus and Method for Constructing Gene-Disease Relation Database
CN116259396A (en) Treatment expense prediction method, system, equipment and storage medium based on machine learning
WO2009148803A2 (en) Methods and systems for integrated health systems
CN114067997A (en) Ovarian cancer clinical decision, teaching and scientific research auxiliary support system and method
CN117711552A (en) Radiotherapy clinical auxiliary decision-making method and system based on artificial intelligence knowledge base
CN114068000A (en) Auxiliary support system and method for clinical decision, teaching and scientific research of uterine body cancer
CN114068004A (en) Colorectal cancer clinical decision, teaching and scientific research auxiliary support system and method
CN114068007A (en) Auxiliary support system and method for clinical decision, teaching and scientific research of gastric cancer
CN114067996A (en) Nasopharyngeal carcinoma clinical decision, teaching and scientific research auxiliary support system and method
Xiao Towards evidence-based argumentation graph for clinical decision support
CN114068008A (en) Esophagus cancer clinical decision, teaching and scientific research auxiliary support system and method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination