Multidisciplinary cooperative treatment commanding and dispatching platform

Abstract

The invention relates to the technical field of multidisciplinary cooperative treatment, and discloses a multidisciplinary cooperative treatment commanding and dispatching platform, which comprises a patient information acquisition unit for acquiring patient information and storing the patient information into a patient library, and a patient classification unit for summarizing the patient information into a patient label combination, each patient label combination comprises a plurality of disease state labels with weights; the doctor information acquisition unit is used for acquiring doctor information and storing the doctor information into a doctor library; the MDT grouping module is used for calculating the complex value of each illness state label, the complex value is the sum of all weight values of the illness state labels in all patient label combinations, and the maximum illness state label combination with the accumulated complex value not exceeding a treatment label grouping threshold value serves as a treatment label combination; the patient group screening module is used for matching a corresponding patient group from a patient library through the treatment label combination, and the matched patient group is treated by a single MDT team in the same period; the technical problem that the resource utilization rate is reduced due to an MDT treatment mode is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of multidisciplinary collaborative treatment, and in particular to a multidisciplinary collaborative treatment command and dispatch platform. Background Art

[0002] MDT, or Multi-Disciplinary Treatment, is an innovative medical team work model. This model aims to provide patients with comprehensive and integrated treatment plans by integrating the knowledge and skills of medical experts from different disciplines. The MDT team is usually composed of medical experts from multiple professional departments. They hold regular meetings to discuss the patient's condition, diagnosis results, treatment plan and prognosis, so as to develop the most appropriate treatment plan for the patient.

[0003] The MDT treatment model breaks the traditional single-discipline treatment model. Through the collaboration of multidisciplinary experts, the patient's condition can be evaluated from different angles, various treatment options can be comprehensively considered, and a more comprehensive and integrated treatment plan can be formulated, thereby improving the treatment effect and avoiding misdiagnosis or missed diagnosis due to the limitations of a single department. Patients no longer need to go between multiple departments, saving time and energy, and also speeding up the treatment process. The MDT model is particularly effective in the treatment of complex diseases, cancers, and chronic diseases.

[0004] Although the MDT model is widely respected in the international medical field and has also undergone a long period of trial and exploration in my country, its overall coverage rate is still low. This is mainly due to the shortage of medical resources and uneven resource allocation in my country, the extremely uncoordinated doctor-patient ratio, and it is difficult to form an MDT team in a single hospital. In my country, the traditional expert consultation model still dominates. Compared with MDT, the consultation model lacks a standardized team structure and scientific medical guidelines, and is characterized by randomness and temporary nature. This leads to uneven consultation results and is difficult to meet the actual needs of patients. MDT requires multiple doctors to treat one patient at the same time, which is particularly difficult in the context of tight medical resources. The simultaneous participation of multiple doctors not only increases the difficulty of coordination, but may also lead to reduced resource utilization.

[0005] This results in the MDT treatment model facing problems such as low efficiency, low resource utilization and difficulty in implementation when directly implemented in the context of tight medical resources in my country. Summary of the invention

[0006] The present invention aims to provide a multidisciplinary collaborative rescue command and dispatch platform to solve the technical problem of reduced resource utilization caused by the MDT treatment model.

[0007] To achieve the above object, the present invention adopts the following technical solution: a multidisciplinary collaborative rescue command and dispatch platform, comprising:

[0008] The patient condition management module includes a patient information collection unit for collecting patient information and storing it in a patient database and a patient classification unit, wherein the patient classification unit is used to summarize the patient information into a patient label combination, wherein a single patient label combination includes a plurality of condition labels with weights;

[0009] A doctor resource management module, including a doctor information collection unit for collecting doctor information and storing it in a doctor database;

[0010] The MDT teaming module is used to calculate the complexity value of each disease label. The complexity value is the sum of all weight values ​​of the disease label in all patient label combinations. The treatment label teaming threshold is preset, and the complexity values ​​of the disease labels are accumulated in descending order of complexity value until they exceed the treatment label teaming threshold. The largest disease label combination whose accumulated complexity value does not exceed the treatment label teaming threshold is used as the treatment label combination;

[0011] The patient group screening module matches the corresponding patient groups from the patient database based on the combination of treatment labels. The matched patient groups are treated simultaneously by a single MDT team.

[0012] The principle and advantages of this scheme are: through the patient condition management module, the patient information is comprehensively collected, and the patient classification unit is used to summarize the patient information into a combination of patient labels. Each label represents a certain condition characteristic of the patient and is assigned a corresponding weight to reflect the importance of the characteristic in the overall condition. In the MDT teaming module, the complexity value of each condition label is calculated, which represents the comprehensive proportion of the complexity and quantity of the condition label in the massive patient conditions. The treatment label teaming is determined according to the treatment label teaming threshold, so that patients with similar condition characteristics and condition complexity within a certain range will be classified into the same treatment label combination. The treatment label teaming threshold also avoids the high complexity of the condition leading to excessive difficulty in treatment and a long treatment cycle. Finally, the patient group screening module matches the corresponding patient groups from the patient database according to the treatment label combination. These patient groups will be treated by a single MDT team at the same time. Since the patient groups have similar condition characteristics, the MDT team can formulate and implement treatment plans more efficiently, thereby improving the utilization of medical resources.

[0013] By grouping patients with similar medical characteristics into the same treatment label combination and treating them at the same time by a single MDT team, the coordination difficulty and duplication of work of the doctor team can be significantly reduced, thereby improving the utilization rate of medical resources. Since the MDT team focuses on treating groups of patients with similar medical characteristics, they can have a deeper understanding of the characteristics and treatment needs of such patients, thereby formulating more accurate and effective treatment plans. In addition, the simultaneous occurrence of multiple similar cases also provides the doctor team with rich opportunities to accumulate experience, which helps them continuously improve their treatment level.

[0014] The treatment effects among patients provide effective data basis for doctors' subsequent treatment plans. By observing and comparing the treatment effects of patients within the same treatment label combination, doctors can more accurately evaluate the effects of different treatment plans, thereby continuously optimizing the treatment plans and improving the treatment effectiveness. Thus, the technical problem of reduced resource utilization rate caused by the MDT treatment mode is solved.

[0015] Preferably, as an improvement, for the MDT team formation module, the complex values of the condition labels are sorted in descending order as the priority order of the condition labels. The treatment label combinations composed of condition labels inherit the priority of their condition labels. Based on historical data and clinical guidelines, the expected treatment time is estimated for each treatment label combination. Based on the priority, treatment requirements, and expected treatment time of the treatment label combination, doctors are intelligently matched from the doctor library to form an MDT team.

[0016] The beneficial effect of this improvement is that the descending order of the complex values of the condition labels is set as the priority order of the condition labels, which directly reflects the urgency and intractability of the condition. The higher the priority of the condition label, it means that the number of patients with this label may be more, or the impact of this label on the patient's condition is greater. Therefore, arranging the treatment of these patients first can more effectively save the patient's life and improve the overall treatment effect.

[0017] The expected treatment time estimated for each treatment label combination based on historical data and clinical guidelines provides a scientific basis for the arrangement of the doctor team. The doctor team can reasonably plan the working hours and rhythm according to the expected treatment time, reduce the difficulty of working hour coordination, and improve work efficiency.

[0018] Taking the condition label as an intermediate quantity to match patients and doctors respectively makes the matching factors more direct and accurate. The doctor team can select the treatment label combination that matches their own professional background and expertise according to their own professional background and expertise, so as to more accurately grasp the condition characteristics and treatment requirements of patients. This precise matching helps to improve the fit between doctors and patients, enhance the treatment effect, and improve patient satisfaction.

[0019] Preferably, as an improvement, for the patient group screening module, a similarity algorithm is used to calculate the similarity between each patient label combination and the condition labels in the treatment label combination, and based on the similarity threshold and the group quantity limit of a single patient group, a clustering algorithm is used to divide patients into multiple groups.

[0020] The beneficial effects of this improvement are as follows: By adopting a similarity algorithm to calculate the similarity between the disease labels in the label combinations of each patient and the treatment label combination, the matching degree between the patient and the treatment label can be measured more accurately. This precise matching helps to ensure that patients are assigned to the MDT team most suitable for their disease characteristics, thereby improving the pertinence and effectiveness of treatment.

[0021] Based on the similarity threshold and the population quantity limit of a single patient population, a clustering algorithm is used to divide patients into multiple populations. This setting avoids the situation where the number of patients in a patient population is too large for a single MDT team to effectively handle. By reasonably controlling the scale of each patient population, it can be ensured that the MDT team has sufficient time and energy to provide high-quality medical services to each patient.

[0022] Through precise patient population division and reasonable control of the population scale, medical resources can be utilized more effectively. The MDT team can formulate targeted treatment plans according to the characteristics of each patient population, reducing unnecessary waste of medical resources. At the same time, due to the moderate scale of the patient population, the MDT team can carry out work more efficiently, improving the efficiency and quality of the overall medical service.

[0023] Preferably, as an improvement, the doctor resource management module further includes a doctor ability evaluation unit;

[0024] The doctor ability evaluation unit grades doctors' abilities from multi-dimensional factors, and the multi-dimensional factors include doctors' professional fields, past performance, and patient evaluations;

[0025] The treatment requirements of the treatment label combination include specialty types, participation ratios, doctor grades, and the number of doctors in each specialty type.

[0026] The beneficial effects of this improvement are as follows: By grading doctors' abilities from multi-dimensional factors, the professional level of doctors can be evaluated more accurately, so as to ensure the professionalism and pertinence of the team when matching the treatment label combination with doctors. Grading according to factors such as doctors' professional fields, past performance, and patient evaluations helps the hospital to arrange doctor resources more reasonably and avoid waste of resources.

[0027] Preferably, as an improvement, the doctor information collected by the doctor information collection unit includes doctors' scheduling situations;

[0028] In the matching process of the MDT team formation module, the scheduling situations of each doctor within the MDT team need to meet the expected treatment time of the treatment label combination, and doctors with similar scheduling situations are preferably selected as members of the same MDT team.

[0029] The beneficial effects of this improvement are as follows: Considering the doctor's schedule during the matching process can ensure that doctors within the MDT team can jointly participate in the treatment within the expected treatment time, reducing the time waste caused by scheduling conflicts. Prioritizing the selection of doctors with similar schedules as members of the same MDT team can reduce communication barriers among doctors, improve team collaboration efficiency, and thus optimize the patient's treatment experience.

[0030] Preferably, as an improvement, the doctor ability evaluation unit reviews and adjusts the doctor's ability level regularly or according to project feedback.

[0031] The beneficial effects of this improvement are as follows: Regularly reviewing and adjusting the doctor's ability level can improve the accuracy of doctor ability grading. At the same time, it can motivate doctors to continuously improve their professional skills and maintain the competitiveness of the team.

[0032] Preferably, as an improvement, the multi-disciplinary collaborative treatment command and dispatch platform further includes a remote treatment coordination module;

[0033] The remote treatment coordination module organizes remote treatment according to the mode of fixed time, fixed team, fixed patient group, and fixed treatment plan, and establishes a remote treatment monitoring system to track the treatment progress in real time, collect and analyze the feedback on treatment effects.

[0034] The beneficial effects of this improvement are as follows: Through the remote treatment coordination module, cross-regional medical resource sharing can be achieved, providing patients with a wider range of treatment options. Establishing a remote treatment monitoring system can track the treatment progress in real time, collect and analyze the feedback on treatment effects, and ensure the treatment quality.

[0035] Preferably, as an improvement, the multi-disciplinary collaborative treatment command and dispatch platform further includes an intelligent decision-making support module;

[0036] The intelligent decision-making support module uses big data analysis technology to conduct in-depth predictive analysis on patient treatment effects and doctor work efficiency, providing a scientific basis for platform decision-making.

[0037] The beneficial effects of this improvement are as follows: It can improve decision-making efficiency, optimize the allocation of medical resources, ensure that patients receive the most suitable treatment plan, and improve the overall treatment effect.

[0038] Preferably, as an improvement, the patient group screening module calculates the similarity using the cosine similarity and Jaccard similarity algorithms, groups patients using the K-means and DBSCAN clustering algorithms, and dynamically adjusts the similarity algorithms and clustering algorithms as the treatment progresses and new information is obtained.

[0039] The beneficial effects of this improvement are as follows: As the treatment progresses and new information is obtained, the similarity algorithm and clustering algorithm are dynamically adjusted, which can ensure that the subsequent division of the patient group is more in line with the treatment needs and improve the accuracy of subsequent patient grouping.

[0040] Preferably, as an improvement, the patient information collection unit automatically captures patient information through the hospital information system, electronic medical record system, and picture archiving and communication system, and performs operations such as deduplication, format unification, and missing value processing on the information, and stores the patient information using encryption technology.

[0041] The beneficial effects of this improvement are as follows: Automatically capturing patient information through the hospital information system, electronic medical record system, etc. can reduce manual entry errors and improve information accuracy. Automatically capturing and processing patient information can greatly reduce the workload of medical staff and improve work efficiency. Storing patient information using encryption technology can ensure patient privacy and security, meeting the privacy protection requirements of the medical industry. Brief Description of the Drawings

[0042] Figure 1 It is a flowchart of an embodiment of the present invention. Detailed Description of the Specific Embodiment

[0043] The following is a further detailed description through specific embodiments:

[0044] Embodiment

[0045] Basically as shown in the Figure 1 drawings, a multi-disciplinary collaborative treatment command and dispatch platform includes: a patient condition management module, a doctor resource management module, an MDT team formation module, a patient group screening module, a remote treatment coordination module, and an intelligent decision support module.

[0046] The patient condition management module includes a patient information collection unit and a patient classification unit.

[0047] The patient information collection unit collects the basic information, medical history, diagnosis reports, etc. of patients who meet the MDT treatment conditions and stores them in the patient database. The MDT treatment conditions can be set as follows: patients who have visited 3 or more specialties but have not obtained a clear diagnosis; patients who have visited a single specialty 3 or more times and still have not been clearly diagnosed; patients whose diseases are relatively clearly diagnosed, but the condition involves multiple organs, systems, or there are many underlying diseases, and multiple specialties need to cooperate in the treatment.

[0048] Through hospital information systems (HIS), electronic medical record systems (EMR), picture archiving and communication systems (PACS), etc., automatically capture the patient's basic information (such as name, age, gender, contact information), medical history (including past medical history, surgical history, drug allergy history), current diagnosis reports (such as pathology reports, imaging reports, laboratory test results), etc. Perform operations such as deduplication, format unification, and missing value processing on the collected information to ensure the accuracy and integrity of the data. Use encryption technology to store patient information to ensure data security; during the data usage process, strictly abide by medical data protection regulations and implement access control.

[0049] Patient classification unit, summarize the patient's condition into multiple condition labels, each condition label is assigned a different weight, reflecting the treatment complexity and patient number distribution. Design a condition label system based on factors such as disease type, disease severity, complication situation, treatment needs, etc. Based on clinical experience and statistical data, set weights for each condition label to reflect its impact on treatment complexity. Apply machine learning algorithms (such as decision trees, random forests) to classify patients, and automatically generate a combination of weighted patient condition labels for each patient, facilitating subsequent team formation and resource allocation.

[0050] Doctor resource management module, including doctor information collection unit and doctor ability evaluation unit.

[0051] Doctor information collection unit, record the basic information, experience level, schedule, professional skills and interests of doctors who voluntarily participate in the MDT project to form a doctor database. Basic information: including the doctor's name, gender, age, professional background, title, education level, etc. Experience level: Evaluate the doctor's experience level based on factors such as working years, number of times participating in the MDT project, and number of successful cases. Schedule: Real-time update the doctor's schedule information, including work schedule, rest days, leave situation, etc. Professional skills and interests: Record the doctor's professional field, proficient technologies, research directions and personal interests, which helps to accurately match the team.

[0052] Doctor ability evaluation unit, classify doctors into different ability levels (senior, intermediate, junior) according to factors such as the doctor's professional field, past performance, and patient evaluations. Conduct a comprehensive evaluation by combining multi-dimensional information such as the doctor's academic achievements (such as published papers, participated in research projects), clinical performance (such as surgical success rate, patient satisfaction), and peer evaluations. Regularly or according to project feedback, review and adjust the doctor's ability level to ensure the timeliness of the evaluation results. Publicize the doctor's ability level and expertise on the platform to enhance patient trust and promote internal communication within the team.

[0053] MDT team formation module. Among the used disease labels, calculate the complexity value of each disease label. The complexity value of a disease label is the sum of all weight values of this disease label in all patient label combinations. Then sort all disease labels in descending order according to the complexity value, and preferentially treat the patients corresponding to the disease labels with higher priorities.

[0054] Preset treatment label teaming threshold. According to the descending list of complexity values, cumulatively calculate the complexity values of disease labels in sequence until it exceeds the treatment label teaming threshold, that is, group the disease labels whose sum of complexity values is less than or equal to the treatment label teaming threshold according to the priority order. For example, if the complexity value of the first disease label is less than the treatment label teaming threshold, then add the complexity value of the first disease label to the complexity value of the second disease label, and then compare it with the treatment label teaming threshold until the sum of the accumulated complexity values is greater than the teaming threshold. Then remove the last disease label, and take the previously accumulated disease labels as a treatment label combination.

[0055] Based on historical data and clinical guidelines, estimate the expected treatment time for each treatment label combination.

[0056] The treatment disease label combination inherits the priorities of the disease labels it contains. From the priorities, treatment requirements, and expected treatment time of this treatment disease combination, intelligently match multiple doctors who meet the conditions from the doctor library to form an MDT team. The treatment requirements include specialty type, participation ratio, doctor level, and the number of doctors for each specialty type. The doctor scheduling situation within the MDT team needs to meet the expected treatment time of this treatment label combination. On this basis, further consider the scheduling compatibility between doctors in the same group, and preferentially select doctors with similar scheduling situations as a group. The intelligent matching algorithm for this MDT team can adopt greedy algorithms, genetic algorithms, etc.

[0057] Patient group screening module. Adopt algorithms such as cosine similarity and Jaccard similarity to calculate the similarity between each patient label combination and the disease labels in the treatment label combination. And based on the similarity threshold and the group size limit of a single patient group, use clustering algorithms such as K-means and DBSCAN to divide patients into multiple groups. Ensure that the patients within the group have similar conditions, which is convenient for efficient treatment by the same MDT team.

[0058] As the treatment progresses and new information is obtained, dynamically adjust the similarity algorithm and clustering algorithm used for patient grouping to optimize the accuracy of subsequent patient grouping.

[0059] The remote treatment coordination model organizes patients and doctors to carry out remote treatment in accordance with the four-fixed mode of fixed time, fixed team, fixed patient group, and fixed treatment plan, ensuring the continuity and consistency of treatment activities. A remote treatment monitoring system is established to track the treatment progress in real time, collect and analyze the feedback on treatment effects. This information is used for the adjustment and optimization of subsequent treatment plans, forming a closed loop of continuous improvement.

[0060] The intelligent decision-making support module uses big data analysis technology to conduct in-depth predictive analysis on patient treatment effects, doctor work efficiency, etc., providing a scientific basis for platform decision-making. Based on the analysis results, specific suggestions for optimizing resource allocation and improving treatment efficiency are automatically generated. These suggestions aim to continuously improve the platform performance and ensure efficient and high-quality MDT treatment services.

[0061] The above are only embodiments of the present invention. Specific technical solutions and / or common knowledge such as characteristics well known in the art are not described in detail herein. It should be noted that for those skilled in the art, without departing from the technical solution of the present invention, several modifications and improvements can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the implementation effect of the present invention and the practicality of the patent. The protection scope required by this application shall be subject to the content of its claims, and the specific implementation manners described in the specification can be used to interpret the content of the claims.

Claims

1. Multidisciplinary collaborative treatment command and dispatch platform, characterized by: include: The patient condition management module includes a patient information collection unit for collecting patient information and storing it in a patient database and a patient classification unit, wherein the patient classification unit is used to summarize the patient information into a patient label combination, wherein a single patient label combination includes a plurality of condition labels with weights; A doctor resource management module, including a doctor information collection unit for collecting doctor information and storing it in a doctor database; The MDT teaming module is used to calculate the complexity value of each disease label. The complexity value is the sum of all weight values ​​of the disease label in all patient label combinations. The treatment label teaming threshold is preset, and the complexity values ​​of the disease labels are accumulated in descending order of complexity value until they exceed the treatment label teaming threshold. The largest disease label combination whose accumulated complexity value does not exceed the treatment label teaming threshold is used as the treatment label combination; The patient group screening module matches the corresponding patient groups from the patient database based on the combination of treatment labels. The matched patient groups are treated simultaneously by a single MDT team.

2. The multidisciplinary collaborative rescue command and dispatch platform according to claim 1 is characterized by: The MDT team module sorts the complexity values ​​of the condition labels in descending order as the priority order of the condition labels. The treatment label combination composed of the condition labels inherits the priority of its condition label. Based on historical data and clinical guidelines, the expected treatment time is estimated for each treatment label combination. Based on the priority, treatment needs and expected treatment time of the treatment label combination, doctors are intelligently matched from the doctor database to form an MDT team.

3. The multidisciplinary collaborative rescue command and dispatch platform according to claim 2 is characterized by: The patient group screening module uses a similarity algorithm to calculate the similarity between each patient label combination and the disease condition label in the treatment label combination, and uses a clustering algorithm to divide the patients into multiple groups based on a similarity threshold and a group number limit for a single patient group.

4. The multidisciplinary collaborative rescue command and dispatch platform according to claim 3 is characterized by: The doctor resource management module also includes a doctor capability assessment unit; The doctor competency assessment unit grades doctors’ competency based on multiple factors, including their professional field, past performance, and patient evaluations; The treatment demand of the treatment label combination includes specialty type, participation ratio, physician level, and the number of physicians in each specialty type.

5. The multidisciplinary collaborative rescue command and dispatch platform according to claim 4 is characterized by: The doctor information collected by the doctor information collection unit includes the doctor's shift schedule; In the MDT teaming module, during the matching process, the scheduling of each doctor in the MDT team must be able to meet the expected treatment time of the treatment label combination, and doctors with similar scheduling situations are given priority to be selected as members of the same MDT team.

6. The multidisciplinary collaborative treatment command and dispatch platform according to claim 5 is characterized by: The physician competency assessment unit reviews and adjusts the physician's competency level periodically or based on project feedback.

7. The multidisciplinary collaborative rescue command and dispatch platform according to claim 6 is characterized by: The multidisciplinary collaborative treatment command and dispatch platform also includes a remote treatment coordination module; The remote treatment coordination module organizes remote treatment according to the model of fixed time, fixed team, fixed patient group, and fixed treatment plan, and establishes a remote treatment monitoring system to track the progress of treatment in real time and collect and analyze feedback on treatment effects.

8. The multidisciplinary collaborative rescue command and dispatch platform according to claim 7 is characterized by: The multidisciplinary collaborative treatment command and dispatch platform also includes an intelligent decision support module; The intelligent decision-making support module uses big data analysis technology to conduct in-depth predictive analysis of patient treatment effects and doctor work efficiency, providing a scientific basis for platform decision-making.

9. The multidisciplinary collaborative rescue command and dispatch platform according to claim 8 is characterized by: The patient group screening module uses cosine similarity and Jaccard similarity algorithms to calculate similarity, uses K-means and DBSCAN clustering algorithms to group patients, and dynamically adjusts the similarity algorithm and clustering algorithm as treatment progresses and new information is obtained.

10. The multidisciplinary collaborative treatment command and dispatch platform according to claim 9, characterized in that: The patient information collection unit automatically captures patient information through the hospital information system, electronic medical record system, image archiving and communication system, and performs deduplication, format unification and missing value processing operations on the information, and uses encryption technology to store patient information.

Images