Search

CN-121999999-A - Tooth pulp disease department teaching hierarchical diagnosis and treatment system

CN121999999ACN 121999999 ACN121999999 ACN 121999999ACN-121999999-A

Abstract

The invention relates to the technical field of medical informatization and clinical teaching management, in particular to a dental pulp disease scientific education hierarchical diagnosis and treatment system which comprises a case difficulty evaluation module, a student ability evaluation module, a triage decision module, a task allocation and notification module, a data management and supervision module and an external system integration layer. The invention can improve the accuracy of diagnosis and treatment, ensure diagnosis and treatment safety, promote the step growth of students and improve the utilization efficiency of teaching resources.

Inventors

  • CHEN HUI
  • GU LISHA
  • WEI XI
  • WANG XINYUE

Assignees

  • 中山大学附属口腔医院

Dates

Publication Date
20260508
Application Date
20251229

Claims (10)

  1. 1. The dental pulp department teaching hierarchical diagnosis and treatment system is characterized by comprising a case difficulty evaluation module, a student ability evaluation module, a triage decision module, a task allocation and notification module, a data management and supervision module and an external system integration layer, wherein, The case difficulty evaluation module is used for receiving initial diagnosis information of a patient and outputting a case difficulty level L x, x epsilon {1,2,3,4,5} according to a preset structured evaluation rule base; The student capability assessment module is used for collecting multidimensional structured data of students and outputting student capability level C y , y epsilon {1,2,3,4}; the triage decision module executes a multi-constraint matching rule based on L x and C y to generate a recommended trainee list; the task allocation and notification module is used for pushing the structured task notification to the allocated trainees and the teacher with the education; the data management and supervision module is used for recording difficult reporting events in the treatment process and supporting re-diagnosis; the external system integration layer is used for interfacing with the electronic medical record system, the medical imaging system and the hospital information system.
  2. 2. The system of claim 1, wherein the structured evaluation rule base in the case difficulty evaluation module comprises at least a caries range score, a root canal anatomical complexity score, a dental weight coefficient, a number of revisions, and a complication risk level, wherein the system automatically extracts parameters based on the entered first-visit information and calculates a total score based on a preset weight to determine L x .
  3. 3. The system of claim 2, wherein the case difficulty assessment module supports a fully automated mode and a semi-automated mode, wherein, The full-automatic mode is used for extracting features of root tip slices, full-scenic spots or cone beam CT images provided by a medical imaging system through an AI image recognition algorithm, and grading is completed; In the semiautomatic mode, the first doctor checks or inputs key clinical parameters on a system interface, and the system finishes comprehensive grading.
  4. 4. The system of claim 1, wherein the multi-dimensional structured data collected by the learner competency assessment module includes at least a learner identity type, a historical theoretical assessment score, an operational skill score, an operational log of completed cases, a current teaching stage goal, and a current day task load status, and a weighted accumulation model is used to calculate a composite competency score for mapping to C y .
  5. 5. The system of claim 4, wherein the log of completed cases includes at least dental position, procedure, time-consuming, whether instrument separation occurred, complications, teacher score, and patient satisfaction feedback for each instance of the procedure, and wherein the learner's ability level C y triggers a review process in real-time after completion of a new case.
  6. 6. The system of claim 1, wherein the multi-constraint matching rules comprise at least: a safety boundary rule, if L x >C y +1, forbid allocation; Difficulty progressive rules, preferably selecting students meeting L x ＝C y or L x ＝C y +1; Load balancing rules, namely eliminating students with the number of cases allocated on the same day or the expected operation duration exceeding a preset threshold value; Patient fit rules reduce the priority of assigning patients labeled as low fitting or poor review compliance to class C 1 or C 2 students.
  7. 7. The system of claim 6, wherein the triage decision module implements matching calculations based on a conditional-action expert system architecture, all matching rules are stored in a database in a structured JSON format, and support for dynamic adjustment of rule weights by teaching authorities.
  8. 8. The system of claim 1, wherein the structured task notification pushed by the task allocation and notification module includes at least a patient ID, a appointment time, a complaint summary, a critical clinical findings, an imaging critical slice thumbnail, a potential operational risk prompt, and a current teaching goal, and synchronously sends a supervision initiation instruction to a band teacher, the instruction including a learner ID, a case difficulty level, and a recommended supervision intensity.
  9. 9. The system of claim 1, wherein the data management and supervision module, upon receiving a difficult report request submitted by a trainee, pushes an alert message to a teacher with education and provides operation options for remote guidance, reevaluation of case difficulty, triggering reevaluation, all intervention events are recorded as a structured event stream and fed back to the trainee's ability assessment module.
  10. 10. The system of claim 1, wherein the external system integration layer obtains patient basic information and medical history from the electronic medical record system via HL7 v2.X protocol, pulls image data of a specified dental site from the medical imaging system via DICOM protocol, and synchronizes reservation of scheduling and office occupancy status via the hospital information system.

Description

Tooth pulp disease department teaching hierarchical diagnosis and treatment system Technical Field The invention relates to the technical field of medical informatization and clinical teaching management, in particular to a dental pulp disease science and education hierarchical diagnosis and treatment system. Background In clinical teaching practice of dental pulp department, teaching hospitals usually receive multiple layers of students such as practice students, tutoring students, study students and advanced students to participate in diagnosis and treatment work at the same time, and clinical cases matched with the skill level of the students are required to be reasonably distributed according to the actual capability of the students to ensure medical safety and teaching quality, so that the teaching target of 'from easy to difficult and progressive' is realized. However, most medical institutions still adopt a traditional manual diagnosis mode, namely, a nurse or first doctor carries out preliminary judgment on the illness state of a patient according to personal experience and manually distributes cases to corresponding students, and the whole process lacks unified and objective evaluation standards and systematic supporting tools. Although some hospitals have deployed electronic medical record systems (EMR) or Hospital Information Systems (HIS), these systems generally do not integrate intelligent diagnosis functions for teaching scenes, but can only realize basic information recording or simply mark patient disease grades, and cannot automatically associate the capability states of students with case difficulties. Disclosure of Invention The invention aims to provide a dental pulp department teaching hierarchical diagnosis and treatment system, which solves the technical problems that the case diagnosis and treatment in the existing dental pulp department clinical teaching depends on manual experience, has strong subjectivity in matching and lacks a dynamic adjustment mechanism. The invention provides a dental pulp disease department teaching hierarchical diagnosis and treatment system, which comprises a case difficulty evaluation module, a student capability evaluation module, a triage decision module, a task allocation and notification module, a data management and supervision module and an external system integration layer, The case difficulty evaluation module is used for receiving initial diagnosis information of a patient, outputting a case difficulty level L x according to a preset structured evaluation rule base, and x is {1,2,3,4,5}; The student capability assessment module is used for collecting multidimensional structured data of students and outputting student capability level C y, y epsilon {1,2,3,4}; the triage decision module executes a multi-constraint matching rule based on L x and C y to generate a recommended trainee list; the task allocation and notification module is used for pushing the structured task notification to the allocated trainees and the teacher with the education; the data management and supervision module is used for recording difficult reporting events in the treatment process and supporting re-diagnosis; the external system integration layer is used for interfacing with the electronic medical record system, the medical imaging system and the hospital information system. In some embodiments, the structured evaluation rule base in the case difficulty evaluation module at least comprises caries range score, root canal anatomical complexity score, tooth weight coefficient, revising factors of the number of re-diagnosis and complication risk level, and the system automatically extracts parameters according to the input initial diagnosis information and calculates total score according to preset weight to determine L x. It should be noted that, the system automatically extracts parameters according to the input initial diagnosis information and calculates total score according to preset weight to determine L x, which can be understood as caries range weight 0.3, root canal complexity weight 0.4, dental coefficient weight 0.2, complication risk weight 0.1, total score range 0-10 score, and map to L x, wherein L x is 0-2 score=l1, L x is 3-4 score=l2, L x is 5-6 score=l3, L x is 7-8 score=l4, L x is 9-10 score=l5. In some embodiments, the case difficulty assessment module supports a fully automatic mode as well as a semi-automatic mode, wherein, The full-automatic mode is used for extracting features of root tip slices, full-scenic spots or cone beam CT images provided by a medical imaging system through an AI image recognition algorithm, and grading is completed; In the semiautomatic mode, the first doctor checks or inputs key clinical parameters on a system interface, and the system finishes comprehensive grading. The feature extraction is carried out on the medical image through a pre-trained Convolutional Neural Network (CNN) model, the model is trained by using a mar