CN114464279A - Big data-based lung cancer full-course management system, method, equipment, medium and terminal - Google Patents
Big data-based lung cancer full-course management system, method, equipment, medium and terminal Download PDFInfo
- Publication number
- CN114464279A CN114464279A CN202111270938.1A CN202111270938A CN114464279A CN 114464279 A CN114464279 A CN 114464279A CN 202111270938 A CN202111270938 A CN 202111270938A CN 114464279 A CN114464279 A CN 114464279A
- Authority
- CN
- China
- Prior art keywords
- lung cancer
- data
- patient
- unit
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 206010058467 Lung neoplasm malignant Diseases 0.000 title claims abstract description 135
- 201000005202 lung cancer Diseases 0.000 title claims abstract description 135
- 208000020816 lung neoplasm Diseases 0.000 title claims abstract description 135
- 238000000034 method Methods 0.000 title claims description 22
- 238000007726 management method Methods 0.000 claims abstract description 140
- 238000011282 treatment Methods 0.000 claims abstract description 77
- 206010067484 Adverse reaction Diseases 0.000 claims abstract description 64
- 230000006838 adverse reaction Effects 0.000 claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 208000024891 symptom Diseases 0.000 claims abstract description 28
- 230000011218 segmentation Effects 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 11
- 230000001575 pathological effect Effects 0.000 claims abstract description 5
- 238000003745 diagnosis Methods 0.000 claims description 49
- 238000012549 training Methods 0.000 claims description 47
- 201000010099 disease Diseases 0.000 claims description 37
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 37
- 230000036541 health Effects 0.000 claims description 36
- 238000007781 pre-processing Methods 0.000 claims description 30
- 239000003814 drug Substances 0.000 claims description 26
- 238000002512 chemotherapy Methods 0.000 claims description 24
- 238000012423 maintenance Methods 0.000 claims description 23
- 238000007689 inspection Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000002347 injection Methods 0.000 claims description 10
- 239000007924 injection Substances 0.000 claims description 10
- 230000000474 nursing effect Effects 0.000 claims description 10
- 230000000007 visual effect Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000001717 pathogenic effect Effects 0.000 claims description 6
- 238000013058 risk prediction model Methods 0.000 claims description 6
- 238000009096 combination chemotherapy Methods 0.000 claims description 4
- 238000006757 chemical reactions by type Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 230000009193 crawling Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000002649 immunization Methods 0.000 claims description 3
- 230000003053 immunization Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 4
- 230000018109 developmental process Effects 0.000 abstract description 4
- 238000003672 processing method Methods 0.000 abstract description 4
- 238000007906 compression Methods 0.000 description 10
- 230000006835 compression Effects 0.000 description 10
- 229940079593 drug Drugs 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 238000012552 review Methods 0.000 description 6
- 235000005911 diet Nutrition 0.000 description 5
- 230000037213 diet Effects 0.000 description 5
- 238000001356 surgical procedure Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 210000004072 lung Anatomy 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 208000030453 Drug-Related Side Effects and Adverse reaction Diseases 0.000 description 3
- 208000002193 Pain Diseases 0.000 description 3
- 239000008280 blood Substances 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 3
- 201000011510 cancer Diseases 0.000 description 3
- 238000009169 immunotherapy Methods 0.000 description 3
- 235000003715 nutritional status Nutrition 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 238000002560 therapeutic procedure Methods 0.000 description 3
- 238000011269 treatment regimen Methods 0.000 description 3
- 206010058019 Cancer Pain Diseases 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 208000012287 Prolapse Diseases 0.000 description 2
- 230000002411 adverse Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000006694 eating habits Nutrition 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003907 kidney function Effects 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000000292 leukogenic effect Effects 0.000 description 2
- 210000004185 liver Anatomy 0.000 description 2
- 230000003908 liver function Effects 0.000 description 2
- 238000000554 physical therapy Methods 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000002980 postoperative effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 238000002636 symptomatic treatment Methods 0.000 description 2
- 238000002626 targeted therapy Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 206010065553 Bone marrow failure Diseases 0.000 description 1
- 206010011409 Cross infection Diseases 0.000 description 1
- 206010061818 Disease progression Diseases 0.000 description 1
- 206010059866 Drug resistance Diseases 0.000 description 1
- 206010052804 Drug tolerance Diseases 0.000 description 1
- 206010029803 Nosocomial infection Diseases 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 238000013276 bronchoscopy Methods 0.000 description 1
- 230000005773 cancer-related death Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 238000002651 drug therapy Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 208000026278 immune system disease Diseases 0.000 description 1
- 238000003364 immunohistochemistry Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 201000002364 leukopenia Diseases 0.000 description 1
- 231100001022 leukopenia Toxicity 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000002154 non-small cell lung carcinoma Diseases 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 208000029729 tumor suppressor gene on chromosome 11 Diseases 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
- 230000029663 wound healing Effects 0.000 description 1
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
- 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
- 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
- G16H20/17—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 delivered via infusion or injection
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention belongs to the technical field of lung cancer data processing, and discloses a big data-based lung cancer full-course management system, a big data-based lung cancer full-course management method, a big data-based lung cancer full-course management device, a big data-based lung cancer full-course management terminal, a big data-based lung cancer full-course management terminal, a big data-course management terminal, and a big data-course management terminal. The invention has accurate result, can grasp the state of illness of the patient in real time, prevent and recognize the occurrence of adverse reaction, provides a corresponding processing method according to specific conditions, improves the accuracy of recognition and detection, ensures the continuity of treatment, monitors common adverse reaction according to different treatment schemes through the detection and segmentation recognition of lung cancer parts and pathological types, accurately recognizes, treats the symptoms and continuously nurses, controls the development of the state of illness of the patient, and provides strong guarantee for the treatment.
Description
Technical Field
The invention belongs to the technical field of lung cancer data processing and whole disease course management, and particularly relates to a lung cancer whole disease course management system, method, equipment, medium and terminal based on big data. In particular to a personalized lung cancer whole-course management system based on a treatment scheme, which runs through diagnosis, treatment, adverse reaction and disease self-management.
Background
At present, the whole-course management mode refers to a whole-course collaborative management mode across regions and teams, and comprises the links of pre-hospital preparation, discharge preparation, post-hospital follow-up, remote health management and the like, and continuous health care of patients before, in and after the hospital is realized on a whole-course management platform, so that a whole-course closed-loop management mode is formed. The whole disease course management aims at taking a patient as a center, and performing a cycle management of remote health management from pre-hospital preparation, in-hospital service, discharge preparation, post-hospital follow-up, a professional team establishes a complete electronic health file for the patient, teaches the patient to perform self management, performs professional assessment on physical conditions at regular time, performs specific remote detailed guidance, provides a constructive suggestion, provides convenient and fast related services during the period, solves the problem on line during the home period, and ensures that the next treatment course can be implemented on time. The whole-course management system establishes a set of follow-up diagnosis, treatment and adverse reaction tracking treatment, enables patients to be comprehensively cared for in the whole course through specification formulation, flow establishment and information intervention, can collect health information in a data mode, establishes a database for whole-course management, and provides a basis for improvement of medical care scientific research and hospitalization procedures.
In the face of disease, humans are always very rare and, to date, medicine has not reached the point of curing cancer. Lung cancer is one of the most common malignant tumors, and the incidence and mortality of lung cancer are on the rising trend year by year and are the first cause of cancer-related death. The surgical treatment is the most important and effective treatment means for the non-small cell lung cancer, but most patients only have less than 20 percent of patients to be treated by the surgery due to late disease course or serious complications, the 5-year survival rate after the surgery is only about 30 to 60 percent, and the effect of the surgical treatment is not satisfactory. Chemotherapy is a traditional method for non-operative treatment of lung cancer, and is most widely applied to the treatment of lung cancer, but long-term chemotherapy and drug side effects cause great stress on the spirit, economy and the like of patients. With the advancement of medical technology, targeted therapy and immunotherapy approaches have proven to prolong the overall survival time of lung cancer, but adverse drug reactions often make it difficult for patients to tolerate or even abandon oral targeted drug therapy. Immunotherapy has a low incidence of adverse effects, but once it occurs, adverse effects are severe and even fatal. After the treatment scheme is determined, the patient needs to be treated for several cycles, and blood indexes such as blood routine, liver and kidney functions and the like need to be reviewed after discharge, and the review including CT enhancement, cranial magnetic resonance, bronchoscopy and the like is carried out regularly. For the patients who seek medical treatment in different places, the patients are discharged to the local and then rechecked, the rechecked result is difficult to be timely transmitted to the attending physicians, and the patients can only be admitted to the hospital in the next hospitalization. Meanwhile, the chemotherapy of the next cycle needs to be performed after the physical condition evaluation is qualified. Partial patients have poor compliance after discharge from hospital and are not subjected to reexamination; or the abnormal condition is not treated in time after the reexamination, so that the chemotherapy of the next period is delayed, the treatment effect is influenced, the average hospitalization day is prolonged, the medical cost of the patient is increased, and the medical cost which is difficult to bear is frosted. Therefore, the patient can be reviewed in time after being discharged from hospital and can be remotely transmitted to the attending doctor for consultation and symptomatic treatment, which becomes an important problem for non-operative treatment of lung cancer.
Through the above analysis, the problems and defects of the prior art are as follows:
(1) at present, the reexamination mode of the patient discharged from the lung cancer hospital is only limited to the outpatient registration reexamination, and the reexamination result or the physical sign reflection described by the patient is checked.
(2) The current technology cannot meet the demand of rest after discharge of a patient for treating lung cancer, and the patient needs to be repeatedly flushed.
(3) The current technology cannot meet the requirement of real-time detection on whether each index of the lung cancer is deteriorated or not.
(4) The prior art has poor intelligent monitoring and management efficiency and low data accuracy and can not provide a basis for specific application.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a lung cancer whole-course management system and method based on big data.
The invention is realized in such a way, and the big data-based lung cancer whole-course management method comprises the following steps:
step one, the management of the return visit: intelligently pushing related health science popularization and education information before and after different examinations by combining medical record discharge record information online and sending a re-diagnosis reminding instruction;
step two, targeted full-course management: the intelligent medicine carries out intelligent pushing of target medicine health department popularization and education and adverse reaction attention information on line, intelligent pushing of a target medicine taking patient self-management video, intelligent pushing of a re-diagnosis time instruction and examination and inspection item reminding, accurate identification of adverse reaction types and levels according to patient description symptoms and examination and inspection results, symptomatic instruction and re-diagnosis reminding instruction sending;
step three, the immune combination chemotherapy/single chemotherapy whole-course management:
the intelligent medical doctor pushes related health propaganda and guidance according to adverse reactions of different treatment schemes on line, pushes a disease self-management video intelligently, sends a time instruction for rechecking a hemogram examination intelligently, accurately identifies the type and grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to take symptoms, identifies the next treatment time in a medical record intelligently, starts a reminder to carry out hospitalization registration reservation, and sends a PICC maintenance instruction intelligently on line every week;
step four, immune maintenance overall disease course management:
the intelligent medical expert pushes related health propaganda and instruction according to the immune adverse reaction on line, pushes a disease self-management video intelligently, sends a rechecking hemogram and related examination time intelligently, accurately identifies the type and the grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to have symptoms, and sends the next injection time and the required rechecking content prompt intelligently. If the adverse reaction is aggravated, an intelligent registration and re-diagnosis and hospitalization registration appointment process is started.
Further, after the fourth step, the following steps are also required:
acquiring latest relevant data information about lung cancer in a hospital database and a network;
feeding the obtained data information into the compiled model for real-time training, and calculating to obtain a latest model for lung cancer monitoring segmentation;
the condition information of the patient is monitored in real time in a lung cancer case preprocessing module, then the monitored information is preprocessed, transferred by a microprocessor unit and uploaded to a trained monitoring segmentation model for training segmentation;
and calculating a corresponding rehabilitation treatment scheme according to the specific lung cancer information which is segmented and monitored in real time according to the model, and then displaying the corresponding rehabilitation treatment scheme through visual information.
Further, the step of the whole-course management of combined immunization chemotherapy/chemotherapy alone comprises the following steps:
and making a corresponding scheme according to the pathological type, the related indexes and the economic condition, adding different types of full-course management according to different treatment schemes, performing individualized management and establishing archives.
Another object of the present invention is to provide a big-data based lung cancer overall course management system implementing the big-data based lung cancer overall course management method, the big-data based lung cancer overall course management system comprising:
the system comprises a re-diagnosis management module, a medical record and discharge management module and a medical record and discharge management module, wherein the re-diagnosis management module is used for intelligently pushing related health science popularization and education information before and after different examinations and sending a re-diagnosis reminding instruction;
the targeted full-course management module is used for intelligently pushing general propaganda and education and adverse reaction notice information of a targeted medicine health department online by an intelligent doctor, intelligently pushing a self-management video of a targeted medicine taking patient, intelligently pushing a re-diagnosis time instruction and a check and inspection item prompt, accurately identifying the type and the grade of an adverse reaction according to the description symptoms and the check and inspection result of the patient, and guiding and sending a re-diagnosis prompt instruction according to symptoms;
the immune combined chemotherapy/individual chemotherapy whole-course management module is used for intelligently pushing related health propaganda and education and guidance according to adverse reactions of different treatment schemes by an intelligent doctor on line, intelligently pushing a disease self-management video, intelligently sending a time instruction for rechecking a hemogram examination, accurately identifying the type and the grade of the adverse reaction according to the description symptoms and the examination and examination results of a patient, instructing the patient to cope with the disease, intelligently identifying the next treatment time in a medical record and starting a reminder to carry out hospitalization registration reservation, and intelligently sending a PICC maintenance instruction by the intelligent doctor on line every week;
the immune maintenance whole-course management module is used for intelligently pushing a related health propaganda and instruction according to immune adverse reactions on line by an intelligent doctor, intelligently pushing a disease self-management video, intelligently sending a rechecked hemogram and related examination time, accurately identifying the type and the grade of the adverse reactions according to the description symptoms and examination results of a patient, instructing the patient to respond to a disease, and intelligently sending the next injection time and the required rechecking content prompt. If the adverse reaction is aggravated, an intelligent registration and re-diagnosis and hospitalization registration appointment process is started.
Further, the big data-based lung cancer overall course management system further comprises:
the system comprises a lung cancer training detection module, a lung cancer case preprocessing module and a lung cancer nursing rehabilitation module; the lung cancer case preprocessing module is respectively connected with a re-diagnosis management module, a targeted whole-course management module, an immune combined chemotherapy/individual chemotherapy whole-course management module and an immune maintenance whole-course management module;
the lung cancer training and detecting module comprises a unit for receiving the latest information related data, a unit for feeding, detecting and segmenting a model, a unit for calculating the latest training and a unit for uploading and detecting the state of a patient in real time;
the lung cancer case preprocessing module comprises a unit for detecting the state of illness of a patient in real time, a unit for preprocessing the latest state of illness data, a microprocessor unit and a data information forwarding unit;
the lung cancer nursing rehabilitation module comprises a big data center computing unit, a proper treatment scheme is formulated, and the appropriate treatment scheme is summarized and displayed on a visual interface unit.
Further, the lung case preprocessing module comprises a data unit related to receiving latest information, a unit for feeding a detection segmentation model for training, a model unit for calculating the latest training and a unit for uploading and detecting the state of a patient in real time, wherein the data unit related to receiving the latest information is used for crawling the latest data information related to the lung cancer detected in the current network or hospital according to big data, then the information is transmitted back to a database for carrying out a series of operations such as cleaning, formatting and filtering on data, the related data information is obtained, then the obtained data information is fed into the detection segmentation model training unit through the feeding detection segmentation model training unit, then specific data training is carried out based on the most popular U-net network structure in the current image processing, the trained lung cancer image is detected and segmented, and then the segmented model is specifically stored and trained, and calculating a latest training model so that subsequent feeding images do not need to be retrained again, and the module is also provided with a real-time uploading patient state of illness detecting unit for receiving the data images from the lung cancer case preprocessing module for real-time uploading.
Furthermore, the lung cancer case preprocessing module comprises a real-time patient state detecting unit, a latest state detecting data preprocessing unit, a microprocessor unit and a data information forwarding unit, wherein the real-time patient state detecting unit is used for setting a certain time interval, performing real-time physical sign detection and lung cancer surface picture grabbing on a patient, preprocessing detected physical sign information data, uploading the preprocessed physical sign information data to the microprocessor unit, and sending the preprocessed physical sign information data to the lung cancer training detection model through the data information forwarding unit for detection;
in the lung cancer nursing and rehabilitation module, a large data center computing unit in the module performs data analysis on a lung cancer patient database to obtain relationship data between lung cancer and various pathogenic factors, learns and trains the relationship data to obtain a lung cancer risk prediction model, processes the detection data through the lung cancer risk prediction model to obtain reference data between various pathogenic factors and the lung cancer of a patient to be screened, then formulates a proper treatment scheme, and summarizes and displays the information to a visual interface.
It is another object of the present invention to provide a computer apparatus comprising a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to execute the big-data based lung cancer overall course management method.
It is another object of the present invention to provide a computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to execute the big-data based lung cancer overall course management method.
Another objective of the present invention is to provide an information data processing terminal for implementing the method for performing the big data-based lung cancer overall course management
In the present invention, the U-net network structure is a classic full convolutional network. The input of the network is a picture with one edge subjected to a mirroring operation, and the left-side down-convolution sampling of the network is a series of down-sampling operations formed by convolution, which can also be called a compression path. The compression path consists of 4 blocks, each block uses 3 effective volumes and 1 Max Pooling downsampling, and the number of Feature maps after each downsampling is multiplied by 2, so that the size of the Feature maps shown in the figure is changed. Finally, Feature Map with size of size is obtained. Convolution is done on the right part of the network as an extension path. And each block is multiplied by 2 by the size of the Feature Map by deconvolution before starting, the number of the blocks is halved, and the blocks are merged with the Feature maps of the left symmetrical compression path, and the U-Net is normalized by clipping the Feature maps of the compression path to the Feature maps with the same size as the extension path due to the difference in the sizes of the Feature maps of the left compression path and the right extension path. The convolution operation of the extended path still uses effective convolution operation, and the task is a binary task, so that the network has two output Feature maps, and a final data calculation model is obtained by the input and output of the image, the calculation of the loss function and the data extension and is supplied to the subsequent use.
By combining all the technical schemes, the invention has the advantages and positive effects that:
the system provides the most practical treatment scheme by utilizing the big data related technology through the detection segmentation result obtained after the well-compiled preprocessing model, the training model adopts the most popular U-net network structure of the current image processing, the training effect is best, the obtained result is accurate, the state of an illness of a patient can be mastered in real time, the occurrence of adverse reactions is prevented and recognized, a corresponding processing method is provided according to specific conditions, the recognition and detection accuracy is improved, the treatment continuity is ensured, the lung cancer part and the pathological type are detected and segmented and recognized, the common adverse reactions are monitored according to different treatment schemes, accurate recognition, symptomatic treatment and continuous nursing are realized, the development of the state of the illness of the patient is controlled, and strong guarantee is provided for treatment.
Compared with the prior art, the invention has the advantages that:
the implementation of the invention provides a system and a method for managing the whole course of a lung cancer patient based on a treatment scheme, and solves the problems that the lung cancer non-operative treatment patient is in intermittent period, is in home care, self-management and difficult to see a doctor, cannot be treated according to the period due to poor body index recovery in the home period, and cannot accurately reserve the time of next hospitalization before a hospital at present, so that the patient can realize the whole course management of seeing a doctor, diagnosing, treating, rechecking, causing adverse reaction and hospitalization in a one-stop manner, and all the links are in seamless connection. Different treatment schemes are linked with different overall disease course management projects, and a proper position is accurately found, so that overall case tracking and medical humanistic care are realized, and the self health management capability of a patient is improved. The database of the whole course management is established, a favorable basis is provided for clinical scientific research, the process can be further improved day by day, the whole course management can not only improve the medical service quality, improve the hospitalizing conditions and reduce the hospitalizing cost of patients, but also alleviate the contradiction between doctors and patients, so that one trust is added to doctors and patients, one harmony is added, and a guarantee is added to happiness.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained from the drawings without creative efforts.
Fig. 1 is a flowchart of a big data-based lung cancer overall course management method according to an embodiment of the present invention.
Fig. 2 is a block diagram of a big data-based lung cancer overall course management system according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a training model for real-time lung cancer monitoring provided by the embodiment of the invention.
Fig. 4 is a flowchart of a method for managing a full course of lung cancer based on big data according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides a system and a method for managing the whole course of lung cancer based on big data, and the invention is described in detail below with reference to the accompanying drawings.
The invention provides a big data-based lung cancer whole-course management method, which comprises the following steps:
step one, the management of the return visit: intelligently pushing related health science popularization and education information before and after different examinations by combining medical record discharge record information online and sending a re-diagnosis reminding instruction;
step two, targeted full-course management: the intelligent medicine carries out intelligent pushing of target medicine health department popularization and education and adverse reaction attention information on line, intelligent pushing of a target medicine taking patient self-management video, intelligent pushing of a re-diagnosis time instruction and examination and inspection item reminding, accurate identification of adverse reaction types and levels according to patient description symptoms and examination and inspection results, symptomatic instruction and re-diagnosis reminding instruction sending;
step three, managing the whole disease course of the immune combination chemotherapy/single chemotherapy:
the intelligent medical doctor pushes related health propaganda and guidance according to adverse reactions of different treatment schemes on line, pushes a disease self-management video intelligently, sends a time instruction for rechecking a hemogram examination intelligently, accurately identifies the type and grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to take symptoms, identifies the next treatment time in a medical record intelligently, starts a reminder to carry out hospitalization registration reservation, and sends a PICC maintenance instruction intelligently on line every week;
step four, immune maintenance overall disease course management:
the intelligent medical expert pushes related health propaganda and instruction according to the immune adverse reaction on line, pushes a disease self-management video intelligently, sends a rechecking hemogram and related examination time intelligently, accurately identifies the type and the grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to have symptoms, and sends the next injection time and the required rechecking content prompt intelligently. If the adverse reaction is aggravated, an intelligent registration and re-diagnosis and hospitalization registration appointment process is started.
The fourth step is followed by:
acquiring latest relevant data information about lung cancer in a hospital database and a network;
feeding the acquired data information into a compiled model for real-time training, and calculating to obtain a latest lung cancer monitoring and segmenting model;
the condition information of the patient is monitored in real time in a lung cancer case preprocessing module, then the monitored information is preprocessed, transferred by a microprocessor unit and uploaded to a trained monitoring segmentation model for training segmentation;
and calculating a corresponding rehabilitation treatment scheme according to the specific lung cancer information which is segmented and monitored in real time according to the model, and then displaying the corresponding rehabilitation treatment scheme through visual information.
Specifically, as shown in fig. 1, the method for managing the whole course of lung cancer based on big data according to the embodiment of the present invention includes:
step one, the management of the return visit:
(A) patients with lung lesion diagnosis are admitted to hospital and evaluated, and doctors determine a diagnostic examination method according to the characteristics of lesion parts, mass properties and the like: (1) percutaneous lung puncture under CT guidance; (2) the tumor is punctured under the guidance of color ultrasound; (3) bronchoscopic tissue biopsy.
(B) After doctors give examination advice, responsibility nurses carry out psychological assessment (psychological pain scale), and psychological consultants carry out psychological intervention before puncture on high-risk persons.
(C) And obtaining pathological specimens after examination, and discharging patients to wait for results. The patients are added into the whole course management and communicated through an intelligent medical online system (an information platform). The patient is informed of the results online and is registered for a scheduled medical team for a visit.
(D) The diagnosis of the disease is confirmed as malignant tumor, and further examination such as immunohistochemistry and genetic examination is required, and the results are notified to the patient on-line by the case manager, and the patient is registered to make a scheduled diagnosis (multiple times).
(E) If the operation is needed after the face diagnosis, the thoracic surgery is scheduled to be treated. If further treatment is needed after the face diagnosis, the patients can be on-line prescribed admission.
(F) The intelligent medical doctor can combine medical record information online, intelligently pushes related health science popularization propaganda and education before and after different examinations, and reminds a double-diagnosis.
Step two, targeted full-course management:
(1) the patients needing targeted therapy are added with the whole course management, the patient targeted drug management file is established, and the management manual is issued. Assessing a psychological state and performing a psychological intervention based on the acceptance therapy. Evaluating nutritional status, and making diet guidance or recipe according to self status, diet habit and diet contraindication of targeted drug.
(2) The administration condition (administration time, dose compliance) and adverse reaction (follow-up administration according to different characteristics of targeted adverse drug reactions) of the administration case administrators are followed by the administration case administrators 1 week, 1 month and 1 month after administration, the administration manuals are perfected, the administration manuals are self-managed by the administration case administrators, registration and re-diagnosis are provided when necessary, a re-diagnosis examination order is made in advance, and the examinations are reserved.
(3) The patients with the adverse reactions can consult the intelligent medicine online at any time, and meanwhile, the reexamined examination results (blood routine, liver and kidney functions) can be sent to be evaluated and guided by a designated medical team in time.
(4) If the patient has serious adverse reaction or drug resistance and needs hospitalization, the patient can have an on-line admission card after the double-diagnosis and schedule the admission.
(5) The intelligent medical doctor can intelligently push the general propaganda and education of the target medicine health department and the attention items of the adverse reaction on line, and can remind the doctor of the re-diagnosis.
Step three, the immune combination chemotherapy/single chemotherapy whole-course management:
(1) after the first visit, doctors make corresponding schemes according to the types of pathology, related indexes, economic conditions and the like, add different types of overall disease course management according to different treatment schemes, and perform individualized management. And establishing a file and issuing a management manual. The psychological state of the first diagnosed lung cancer patient is first assessed and a psychological consultant performs psychological intervention based on the particular therapy. The patient who carries out adjunctie therapy follows up the postoperative wound healing condition of follow-up patient in time, and the treatment of reserving the postoperative as early as possible guarantees treatment.
(2) And (4) predicting the possible adverse reaction of the patient during hospitalization according to the medical record information and the treatment scheme of the patient, teaching self-management of the patient, and performing corresponding prevention. The dietician evaluates the nutritional status of the patient and guides or formulates a diet by combining his or her own status, dietary habits and treatment regimens.
(3) The individual case administrator takes adverse reaction follow-up visits and medication instructions 3 days after the patient is discharged from the hospital (for example, the types of the immune-related adverse reactions are many, the progress is fast, the immune disorder is easy after treatment, and the resistance to viruses and bacteria is reduced, so the patient needs to be reminded to avoid the aggregation activity, prevent infection, identify the serious adverse reactions in time and guide the patient to seek medical advice in time). The intelligent medical personnel pushes related health propaganda and education and guidance on line according to adverse reactions, and intelligently reminds the time for reexamination of examination such as hemograms.
(4) The patient will send the results of the examination after the review online and the attending physician will perform assessment guidance (e.g., the patient will review routine leukopenia after discharge, the physician will guide the treatment of leukogenic and follow up the review online). If the patient's profile suggests that myelosuppression will occur after each cycle of chemotherapy, the system will prompt the prevention of leukogenic drugs before discharge.
(5) When the patient body indexes are normal, the patient can be treated according to the schedule, online evaluation is carried out 1 week in advance, admission is made, and the patient is reserved for admission.
(6) If the patient has cancer pain and pain, the whole course management is carried out, all-round whole course guidance of medical care medicines is carried out, the medicines are taken correctly and regularly, relevant physical therapy is carried out, and the on-line evaluation, the prescription and the mailing are carried out.
(7) A patient who is placed in a PICC (peripherally inserted Central catheter) is instructed to perform maintenance at a fixed point in a hospital after the patient is discharged, and an intelligent doctor intelligently reminds the patient to perform maintenance on line every week; after the patient is maintained, the maintenance picture can be sent on line, which is beneficial for the special nurse to prevent and identify the complication in time; when the patient has complications such as blockage of the tube, prolapse and the like locally, a special nurse can conduct treatment under remote video guidance; patients with the catheter can consult on line at any time when encountering any question, correct and timely answering and guidance are provided, and the normal use of the catheter is guaranteed.
Step four, immune maintenance overall disease course management:
(1) after being evaluated by doctors, the patients who are treated by the immunotherapy add the management of the whole course of immune maintenance, establish files, issue immune maintenance manuals and teach self-management. The dietician evaluates the nutritional status of the patient and guides or formulates a diet by combining his or her own status, dietary habits and treatment regimens.
(2) The patient is on-line reserved for the immunization injection time in advance, and the case manager is on-line evaluated, provided with a relevant examination order and reserved.
(3) The case manager makes an appointment for the re-diagnosis in advance, the patient completes the relevant examination, the prescription is made, the patient is treated in the ward, and the next injection time and the content needing the re-examination are filled. The nurse administered the injection after checking.
(4) The individual case manager of the department carries out adverse reaction follow-up and guidance in a designated time period after injection and reminds the department of the administrative department of the adverse reaction follow-up and guidance of the administrative department of the adverse reaction follow-up and the guidance of the administrative department of the adverse reaction follow-up and the follow-up examination time. The patient examination results are sent online through the intelligent medical doctor, and the fixed doctor evaluates and guides. If serious adverse reaction occurs or hospitalization is needed for adjusting the treatment scheme, the on-line admission of the patient can be prescribed after the patient is subjected to the double diagnosis.
(5) If the patient has cancer pain and pain, the whole course management is carried out, all-round whole course guidance of medical care medicines is carried out, the medicines are taken correctly and regularly, relevant physical therapy is carried out, and the on-line evaluation, the prescription and the mailing are carried out.
(6) A patient who is placed in a PICC (peripherally inserted Central catheter) is instructed to perform maintenance at a fixed point in a hospital after the patient is discharged, and an intelligent doctor intelligently reminds the patient to perform maintenance on line every week; after the patient is maintained, the maintenance picture can be sent on line, which is beneficial for the special nurse to prevent and identify the complication in time; when the patient has complications such as blockage of the tube, prolapse and the like locally, a special nurse can conduct treatment under remote video guidance; patients with the catheter can consult on line at any time when encountering any question, correct and timely answering and guidance are provided, and the normal use of the catheter is guaranteed.
In a preferred embodiment of the invention, the late treatment of the patient with advanced lung cancer is a multi-cycle treatment scheme, the patient will be discharged and rest in the chemotherapy intermission period after about 3 days of treatment in hospital, and will enter the hospital again after 21 days to continue the next cycle of treatment, and the cycle is repeated and the multi-cycle is performed. Patients are periodically assessed during treatment for disease progression, systemic status, and drug tolerance, with treatment regimens being continued, modified, or suspended. The current medical system focuses more on the condition of the patient during hospitalization, but rarely intervenes and systematically manages the health condition of the patient after discharge (although the situation is important), and the lack of knowledge of the patient in the aspect of disease self-management makes the patient stay in a disease-centered rather than health-centered medical mode, and the whole-person management mode of the project effectively and systematically solves the problems related to the patient before the hospital, especially after the patient is in the hospital, effectively improves the self-management capability of the patient on the disease and the health, and is successfully applied to clinic.
The technical solution of the present invention is further described with reference to the following specific examples.
The invention provides a big data-based lung cancer whole-course management system, which comprises:
the system comprises a re-diagnosis management module, a medical record and discharge management module and a medical record and discharge management module, wherein the re-diagnosis management module is used for intelligently pushing related health science popularization and education information before and after different examinations and sending a re-diagnosis reminding instruction;
the targeted full-course management module is used for intelligently pushing general propaganda and education and adverse reaction notice information of a targeted medicine health department online by an intelligent doctor, intelligently pushing a self-management video of a targeted medicine taking patient, intelligently pushing a re-diagnosis time instruction and a check and inspection item prompt, accurately identifying the type and the grade of an adverse reaction according to the description symptoms and the check and inspection result of the patient, and guiding and sending a re-diagnosis prompt instruction according to symptoms;
the immune combined chemotherapy/individual chemotherapy whole-course management module is used for intelligently pushing related health propaganda and education and guidance according to adverse reactions of different treatment schemes by an intelligent doctor on line, intelligently pushing a disease self-management video, intelligently sending a time instruction for rechecking a hemogram examination, accurately identifying the type and the grade of the adverse reaction according to the description symptoms and the examination and examination results of a patient, instructing the patient to cope with the disease, intelligently identifying the next treatment time in a medical record and starting a reminder to carry out hospitalization registration reservation, and intelligently sending a PICC maintenance instruction by the intelligent doctor on line every week;
the immune maintenance whole-course management module is used for intelligently pushing a disease self-management video according to immune adverse reaction promotion and guidance, intelligently sending a review hemogram and related examination time, accurately identifying the type and grade of the adverse reaction according to patient description symptoms and examination results, performing symptomatic guidance, and intelligently sending next injection time and required review content reminding by an intelligent doctor. If the adverse reaction is aggravated, an intelligent registration and re-diagnosis and hospitalization registration appointment process is started.
As shown in fig. 2-3, the present invention provides a lung cancer full-course management system based on big data, further comprising a lung cancer training and detecting module, a lung cancer case preprocessing module and a lung cancer nursing and rehabilitation module. The lung cancer training and detecting module comprises a unit for receiving latest information related data, a unit for feeding, detecting and segmenting a model, a unit for calculating the latest training and a unit for uploading and detecting the state of a patient in real time, the lung cancer case preprocessing module comprises a unit for detecting the state of the patient in real time, a unit for preprocessing the latest state of the patient, a microprocessor unit and a data information forwarding unit, and the lung cancer nursing and recovering module comprises a large data center calculating unit, a proper treatment scheme and a summarizing display visual interface unit. The system utilizes big data related technology to provide the most practical treatment scheme through the detection segmentation result obtained after the well-compiled preprocessing model, the training model uses the most popular U-net network structure of the current image processing, the training effect is best, the obtained result is accurate, the state of illness of a patient can be mastered in real time, the occurrence of accidents is prevented, a corresponding processing method is provided according to specific conditions, the accuracy of recognition and detection is improved, the development of the state of illness of the patient is controlled through the detection and segmentation recognition of lung cancer parts, and great guarantee is provided for treatment.
In a preferred embodiment of the present invention, the lung case preprocessing module comprises a unit for receiving data related to the latest information, a unit for feeding a detection segmentation model for training, a unit for calculating the latest training model, and a unit for uploading a detection patient's condition in real time, wherein the unit for receiving data related to the latest information is used for crawling data information related to the latest lung cancer detected in a current network or a hospital according to big data, then the information is transmitted back to a database for a series of operations such as data cleaning, formatting, filtering, etc., the related data information is acquired, then the data information acquired in the past is fed into the detection segmentation model training unit through the feeding detection segmentation model training unit, then specific data training is performed based on the most popular U-net network structure in the current image processing, and the lung cancer image of the training is detected and segmented, and then, specifically storing and training the segmented model, and calculating a latest training model so as to avoid retraining subsequent feeding images, thereby saving a large amount of time and memory overhead.
In a preferred embodiment of the present invention, the lung cancer case preprocessing module includes a real-time patient condition detecting unit, a latest condition data preprocessing unit, a microprocessor unit and a data information forwarding unit, wherein the real-time patient condition detecting unit sets a certain time interval, performs real-time physical sign detection and lung cancer surface image capture on a patient, preprocesses detected physical sign information data, uploads the processed physical sign information data to the microprocessor unit, and then the microprocessor unit sends the processed physical sign information data to the lung cancer training detection model through the data information forwarding unit for detection.
In a preferred embodiment of the present invention, in the lung cancer nursing and rehabilitation module, the large data center computing unit in the module performs data analysis on the lung cancer patient database to obtain relationship data between lung cancer and each pathogenic factor, learns and trains the relationship data to obtain a lung cancer risk prediction model, processes the detection data through the lung cancer risk prediction model to obtain reference data between each pathogenic factor of a patient to be screened and lung cancer, and then makes a proper treatment scheme, and then summarizes and displays the information on a visual interface.
In a preferred embodiment of the present invention, the U-net network structure is a classic full convolutional network. The input of the network is a picture with one edge subjected to a mirroring operation, and the left-side down-convolution sampling of the network is a series of down-sampling operations formed by convolution, which can also be called compression paths. The compression path consists of 4 blocks, each block uses 3 effective volumes and 1 Max Pooling downsampling, and the number of Feature maps after each downsampling is multiplied by 2, so that the size of the Feature maps shown in the figure is changed. Finally, Feature Map with size of size is obtained. Convolution is done on the right part of the network as an extension path. And each block is multiplied by 2 by the size of the Feature Map by deconvolution before starting, the number of the blocks is halved, and the blocks are merged with the Feature maps of the left symmetrical compression path, and the U-Net is normalized by clipping the Feature maps of the compression path to the Feature maps with the same size as the extension path due to the difference in the sizes of the Feature maps of the left compression path and the right extension path. The convolution operation of the extended path still uses effective convolution operation, and the task is a binary task, so that the network has two output Feature maps, and a final data calculation model is obtained by the input and output of the image, the calculation of the loss function and the data extension and is supplied to the subsequent use.
As shown in fig. 4, the method workflow provided by the present invention further includes:
s101: and acquiring latest relevant data information about the lung cancer in a hospital database and a network.
S102: and feeding the acquired data information into the compiled model for real-time training, and calculating to obtain the latest lung cancer monitoring and segmentation model.
S103: the condition information of the patient is monitored in real time in the lung cancer case preprocessing module, then the monitored information is preprocessed, transferred by the microprocessor unit and uploaded to a trained monitoring segmentation model for training segmentation.
S104: and calculating a corresponding rehabilitation treatment scheme according to the specific lung cancer information which is segmented and monitored in real time according to the model, and then displaying the corresponding rehabilitation treatment scheme through visual information.
The invention solves the problems of difficult diagnosis, difficult registration and difficult reexamination of the lung cancer patients at present, shortens the time from examination evaluation, diagnosis to treatment of the lung cancer patients, tracks and improves the physical conditions and adverse reactions of the patients in the treatment intermission period to ensure the normal operation of the treatment in the next period, teaches self health management of the patients, avoids repeated wave running of the patients, reduces cross infection in a hospital, complements a technical short board for remote reexamination evaluation of the lung cancer patients in the treatment intermission period during discharge, meets the requirement of monitoring whether each index of the patients deteriorates in real time in the follow-up patient examination, and greatly ensures the treatment and rehabilitation of the patients.
The invention trains the latest lung cancer related data model by using the most advanced network computing model, trains according to various parameters of the lung cancer detected in real time, detects and segments the focus area, determines whether the disease condition deteriorates, can detect in real time, effectively masters the progress of the disease condition of a patient, greatly ensures the safety of the patient, provides a scheme for subsequent treatment, and also provides a great guarantee for the subsequent treatment of the patient.
The invention provides the most practical treatment scheme by utilizing the big data related technology through the detection segmentation result obtained after the well-compiled preprocessing model, the training model uses the most popular U-net network structure of the current image processing, the training effect is best, the obtained result is accurate, the state of the patient can be mastered in real time, the occurrence of accidents is prevented, the corresponding processing method is provided according to the specific situation, the accuracy of identification and detection is improved, the development of the patient's state of illness is controlled through the detection and segmentation identification of the lung cancer part, and the strong guarantee is provided for the treatment.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. The big data-based lung cancer overall course management method is characterized by comprising the following steps of:
step one, the management of the return visit: intelligently pushing related health science popularization and education information before and after different examinations by combining medical record discharge record information online and sending a re-diagnosis reminding instruction;
step two, targeted full-course management: the intelligent medicine carries out intelligent pushing of target medicine health department popularization and education and adverse reaction attention information on line, intelligent pushing of a target medicine taking patient self-management video, intelligent pushing of a re-diagnosis time instruction and examination and inspection item reminding, accurate identification of adverse reaction types and levels according to patient description symptoms and examination and inspection results, symptomatic instruction and re-diagnosis reminding instruction sending;
step three, managing the whole disease course of the immune combination chemotherapy/single chemotherapy:
the intelligent medical doctor pushes related health propaganda and guidance according to adverse reactions of different treatment schemes on line, pushes a disease self-management video intelligently, sends a time instruction for rechecking a hemogram examination intelligently, accurately identifies the type and grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to take symptoms, identifies the next treatment time in a medical record intelligently, starts a reminder to carry out hospitalization registration reservation, and sends a PICC maintenance instruction intelligently on line every week;
step four, immune maintenance overall disease course management:
the intelligent medical online health diagnosis system pushes related health propaganda and guidance according to the immune adverse reaction, intelligently pushes a disease self-management video, intelligently sends a rechecked hemogram and related examination time, accurately identifies the type and the grade of the adverse reaction according to the description symptoms and examination results of a patient, guides the patient to have symptoms, and intelligently sends the next injection time and the required rechecking content prompt; adverse reactions worsen, and intelligent registration and re-diagnosis and hospitalization registration reservation procedures are started.
2. The big data based lung cancer overall course management method according to claim 1, wherein the fourth step is followed by:
acquiring latest relevant data information about lung cancer in a hospital database and a network;
feeding the acquired data information into a compiled model for real-time training, and calculating to obtain a latest lung cancer monitoring and segmenting model;
the condition information of a patient is monitored in real time in a lung cancer case preprocessing module, then the monitored information is preprocessed and transferred by a microprocessor unit and then uploaded to a trained monitoring segmentation model for training segmentation;
and calculating a corresponding rehabilitation treatment scheme according to the specific lung cancer information which is segmented and monitored in real time according to the model, and then displaying the corresponding rehabilitation treatment scheme through visual information.
3. The big data based lung cancer overall course management method of claim 1, wherein the step of combined immunization chemotherapy/chemotherapy alone overall course management comprises:
and making a corresponding scheme according to the pathological type, the related indexes and the economic condition, adding different types of full-course management according to different treatment schemes, performing individualized management and establishing archives.
4. A big-data-based lung cancer overall course management system for implementing the big-data-based lung cancer overall course management method according to any one of claims 1 to 3, wherein the big-data-based lung cancer overall course management system comprises:
the system comprises a re-diagnosis management module, a medical record and discharge management module and a medical record and discharge management module, wherein the re-diagnosis management module is used for intelligently pushing related health science popularization and education information before and after different examinations and sending a re-diagnosis reminding instruction;
the targeted full-course management module is used for intelligently pushing general propaganda and education and adverse reaction notice information of a targeted medicine health department online by an intelligent doctor, intelligently pushing a self-management video of a targeted medicine taking patient, intelligently pushing a re-diagnosis time instruction and a check and inspection item prompt, accurately identifying the type and the grade of an adverse reaction according to the description symptoms and the check and inspection result of the patient, and guiding and sending a re-diagnosis prompt instruction according to symptoms;
the immune combined chemotherapy/individual chemotherapy whole-course management module is used for intelligently pushing related health propaganda and education and guidance according to adverse reactions of different treatment schemes by an intelligent doctor on line, intelligently pushing a disease self-management video, intelligently sending a time instruction for rechecking a hemogram examination, accurately identifying the type and the grade of the adverse reaction according to the description symptoms and the examination and examination results of a patient, instructing the patient to cope with the disease, intelligently identifying the next treatment time in a medical record and starting a reminder to carry out hospitalization registration reservation, and intelligently sending a PICC maintenance instruction by the intelligent doctor on line every week;
the immune maintenance whole-course management module is used for intelligently pushing a related health propaganda and instruction according to immune adverse reactions on line by an intelligent doctor, intelligently pushing a disease self-management video, intelligently sending a rechecked hemogram and related examination time, accurately identifying the type and the grade of the adverse reactions according to the description symptoms and examination results of a patient, instructing the patient to respond to a disease, and intelligently sending the next injection time and the required rechecking content prompt. If the adverse reaction is aggravated, an intelligent registration and re-diagnosis and hospitalization registration appointment flow is started.
5. The big-data based lung cancer overall course management system of claim 4, wherein the big-data based lung cancer overall course management system further comprises:
the system comprises a lung cancer training detection module, a lung cancer case preprocessing module and a lung cancer nursing rehabilitation module; the lung cancer case preprocessing module is respectively connected with a re-diagnosis management module, a targeted whole-course management module, an immune combined chemotherapy/individual chemotherapy whole-course management module and an immune maintenance whole-course management module;
the lung cancer training and detecting module comprises a unit for receiving the latest information related data, a unit for feeding, detecting and segmenting a model, a unit for calculating the latest training and a unit for uploading and detecting the state of a patient in real time;
the lung cancer case preprocessing module comprises a unit for detecting the state of illness of a patient in real time, a unit for preprocessing the latest state of illness data, a microprocessor unit and a data information forwarding unit;
the lung cancer nursing and rehabilitation module comprises a big data center computing unit, a proper treatment scheme making unit, a summarizing unit and a visual interface unit.
6. The big-data based lung cancer overall course management system of claim 5,
the lung cancer case preprocessing module comprises a unit for receiving latest information related data, a unit for feeding detection segmentation model training, a unit for calculating latest training model and a unit for uploading and detecting patient state of illness in real time, wherein the unit for receiving latest information related data is used for crawling the latest lung cancer related data information detected in the current network or hospital according to big data, then the information is transmitted back to a database, a series of operations such as cleaning, formatting and filtering of data are carried out, the related data information is obtained, then the obtained data information is fed into the detection segmentation model training unit through the feeding detection segmentation model training unit, then specific data training is carried out based on the most popular U-net network structure in the current image processing, the trained lung cancer image is detected and segmented, and then the segmented model is stored and trained specifically, and calculating a latest training model so that subsequent feeding images do not need to be retrained again, and the module is also provided with a real-time uploading patient state of illness detecting unit for receiving the data images from the lung cancer case preprocessing module for real-time uploading.
7. The big-data-based lung cancer whole-course management system according to claim 5, wherein the lung cancer case preprocessing module comprises a real-time patient condition detection unit, a latest condition preprocessing data unit, a microprocessor unit and a data information forwarding unit, wherein the real-time patient condition detection unit is set at a certain time interval, carries out real-time sign detection and lung cancer surface image capture on a patient, preprocesses detected sign information data, uploads the processed sign information data to the microprocessor unit, and then the microprocessor unit sends the processed sign information data to the lung cancer training detection model through the data information forwarding unit for detection;
in the lung cancer nursing and rehabilitation module, a large data center computing unit in the module performs data analysis on a lung cancer patient database to obtain relationship data between lung cancer and various pathogenic factors, learns and trains the relationship data to obtain a lung cancer risk prediction model, processes the detection data through the lung cancer risk prediction model to obtain reference data between various pathogenic factors and the lung cancer of a patient to be screened, then formulates a proper treatment scheme, and summarizes and displays the information to a visual interface.
8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the computer program, when executed by the processor, causes the processor to perform the big-data based lung cancer overall course management method according to any one of claims 1 to 3.
9. A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to execute the big-data based lung cancer overall course management method according to any one of claims 1 to 3.
10. An information data processing terminal, characterized in that the information data processing terminal is used for implementing the big data-based lung cancer overall course management method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111270938.1A CN114464279A (en) | 2021-10-29 | 2021-10-29 | Big data-based lung cancer full-course management system, method, equipment, medium and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111270938.1A CN114464279A (en) | 2021-10-29 | 2021-10-29 | Big data-based lung cancer full-course management system, method, equipment, medium and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114464279A true CN114464279A (en) | 2022-05-10 |
Family
ID=81406499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111270938.1A Pending CN114464279A (en) | 2021-10-29 | 2021-10-29 | Big data-based lung cancer full-course management system, method, equipment, medium and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114464279A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118230925A (en) * | 2024-05-23 | 2024-06-21 | 南京纳实医学科技有限公司 | Intelligent analysis management system for chronic disease course queue |
-
2021
- 2021-10-29 CN CN202111270938.1A patent/CN114464279A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118230925A (en) * | 2024-05-23 | 2024-06-21 | 南京纳实医学科技有限公司 | Intelligent analysis management system for chronic disease course queue |
| CN118230925B (en) * | 2024-05-23 | 2024-08-06 | 南京纳实医学科技有限公司 | Intelligent analysis management system for chronic disease course queue |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200321119A1 (en) | Methods and systems for an artificial intelligence support network for vibrant constitutional guidance | |
| US20190096534A1 (en) | Apparatus and method for providing healthcare services remotely or virtually with or using an electronic healthcare record and/or a communication network | |
| US11393590B2 (en) | Methods and systems for an artificial intelligence alimentary professional support network for vibrant constitutional guidance | |
| CN100366211C (en) | diagnostic information system | |
| US20150112702A1 (en) | Apparatus and method for processing and/or for providing healthcare information and/or healthcare-related information with or using an electronic healthcare record and genetic information and/or genetic-related information | |
| US20140081667A1 (en) | Apparatus and method for processing and/or providing healthcare information and/or healthcare-related information with or using an electronic healthcare record or electronic healthcare records | |
| US20150278453A1 (en) | Apparatus and method for providing healthcare services remotely or virtually with or using an electronic healthcare record and/or a communication network | |
| US11393589B2 (en) | Methods and systems for an artificial intelligence support network for vibrant constitutional guidance | |
| EP3077933A1 (en) | Computational medical treatment plan method and system with mass medical analysis | |
| CN112820369B (en) | Anorectal surgery information management system based on big data | |
| Bailon et al. | Continuous subcutaneous insulin infusion (insulin pump) therapy can be safely used in the hospital in select patients | |
| Schoenfeld et al. | Integrated care models: optimizing adult ambulatory care in inflammatory bowel disease | |
| CN115732058A (en) | Artificial intelligence-based automatic intervention and adjustment method and system for surgical rehabilitation | |
| Biernacki et al. | Transformation of care: integrating the registered nurse care coordinator into the patient-centered medical home | |
| US20140067423A1 (en) | Apparatus and method for processing and/or providing healthcare information and/or healthcare-related information with or using an electronic healthcare record or electronic healthcare records | |
| CN112102956A (en) | Method and system for improving compliance of diabetic patient | |
| CN114334129A (en) | Medical diagnosis system based on Internet of things | |
| CN114464279A (en) | Big data-based lung cancer full-course management system, method, equipment, medium and terminal | |
| CN114974530A (en) | Post-diagnosis follow-up method, system and storage medium | |
| WO2014164474A1 (en) | Systems and methods for interpreting medical information | |
| Fraenkel et al. | The use of radiographs to evaluate shoulder pain in the ED | |
| Tan et al. | Validation of a retrospective computing model for mortality risk in the intensive care unit | |
| Arnold et al. | Cost, work, reimbursement, and the pediatric nephrologist in the United States Medicare/End-stage Renal Disease Program | |
| Alguwaie et al. | Integrated Healthcare Approaches: Contributions of Nursing, Laboratories, Radiology, Nutrition, and Psychology to Holistic Patient Well-being | |
| Huang | A framework for quality improvement and evaluation of a clinical decision support system in NICU environment in cross-cultural settings. |
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 |