Man-machine knowledge interaction type disease subtype diagnosis system

The human-computer knowledge-interactive disease subtype diagnostic system solves the problems of insufficient multimodal data fusion and clinical knowledge utilization, achieving high-precision and low-cost disease subtype diagnosis, improving the recall and fit of the diagnostic system, and is suitable for the accurate diagnosis of non-communicable chronic diseases.

CN122455307APending Publication Date: 2026-07-24THE AFFILIATED HOSPITAL OF XUZHOU MEDICAL UNIV +2
0 Cites 0 Cited by

Patent Information

Application Number
CN202610553603.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-24
Publication Date
2026-07-24

AI Technical Summary

Technical Problem

Existing disease subtype diagnostic systems have shortcomings in multimodal data fusion, clinical knowledge utilization, human-computer interaction mechanisms, and self-supervised learning adaptability, resulting in deviations between diagnostic results and clinical needs, low recall rates, high risk of missed diagnoses, and difficulty in meeting the needs of scenarios such as cancer screening.

Method used

A human-computer knowledge-interactive disease subtype diagnostic system is adopted, which achieves high-precision and low-training-cost disease subtype diagnosis through efficient cross-modal alignment of multimodal data, dynamic updating of structured clinical knowledge base, two-level self-supervised learning, and flexible human-computer interaction iterative optimization.

Benefits of technology

It improves the accuracy and training efficiency of multimodal fusion, ensures the dynamic reliability of the knowledge base, enhances the fit and recall of diagnoses, significantly reduces the risk of missed diagnoses, and is suitable for the accurate diagnosis of non-communicable chronic diseases.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of medical diagnosis and artificial intelligence crossing, and discloses a man-machine knowledge interaction type disease subtype diagnosis system, which comprises a data acquisition and preprocessing module used for acquiring and preprocessing multi-modal data of a to-be-diagnosed object and outputting multi-modal fusion features; the clinical knowledge base module is used for storing a structured clinical knowledge graph; the man-machine knowledge interaction module is used for providing an interaction interface to receive input of a clinical expert and quantizing the input into mathematical constraints which can be analyzed by a model; and the dual-drive diagnosis model module is used for injecting the structured knowledge in the clinical knowledge base module into a neural network, performing knowledge-guided fusion on the multi-modal fusion features, constructing a patient-feature heterogeneous graph, mining potential knowledge from multi-modal data, and generating an interpretable diagnosis result of the disease subtype. According to the invention, disease subtype diagnosis with high precision and low training cost is realized, and the method is suitable for subtype accurate diagnosis of non-infectious chronic diseases.
Need to check novelty before this filing date? Find Prior Art