A method and system for predicting bacterial antimicrobial resistance

Through hierarchical design and rule-based monitoring separation architecture, the bacterial resistance prediction technology solves the problems of single data dimension and high computational power dependence, and achieves multi-dimensional accurate prediction and interpretability. It is suitable for use in primary healthcare institutions, improving the adaptability of prediction and clinical trust.

CN121641502BActive Publication Date: 2026-06-09NAT CENT FOR CHRONIC & NONCOMMUNICABLE DISEASE CONTROL & PREVENTION CHINESE CENT FOR DISEASE CONTROL & PREVENTION
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NAT CENT FOR CHRONIC & NONCOMMUNICABLE DISEASE CONTROL & PREVENTION CHINESE CENT FOR DISEASE CONTROL & PREVENTION
Filing Date
2025-12-05
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

Existing bacterial resistance prediction technologies suffer from problems such as reliance on a single data dimension, insufficient prediction accuracy, poor algorithm interpretability, low adaptability, and dependence on high-computing-power equipment, making them difficult to popularize in primary healthcare institutions.

Method used

The hierarchical design and rule-based monitoring separation architecture are adopted to divide the elements of drug resistance prediction into four levels: patient risk, microbial characteristics, regional prevalence, clinical rules, and drug characteristics. Data is processed independently through a set of dynamic rules specific to each level, and a dual-monitoring point linkage triggering mechanism is introduced to generate bacterial antimicrobial resistance prediction results and antimicrobial drug recommendations.

Benefits of technology

It achieves accurate predictions across multiple dimensions, improves the interpretability and adaptability of predictions, reduces reliance on high-computing-power devices, adapts to the usage scenarios of primary healthcare institutions, and increases the trust of clinicians.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121641502B_ABST
    Figure CN121641502B_ABST
Patent Text Reader

Abstract

A bacterial antimicrobial resistance prediction method and system, a hierarchical configuration unit divides resistance prediction elements into patient risk levels, microbial feature levels, regional prevalence levels, clinical rule levels and drug property levels, each level includes initial attribute values and level-specific dynamic rule sets; a data processing unit acquires real-time clinical data, each level independently processes data through its level-specific dynamic rule set, and converts initial attribute values into target attribute values; a decision superposition unit superimposes the target attribute values of each level according to the weight priority of each level to generate a bacterial antimicrobial resistance prediction result and an antibacterial drug recommendation scheme; a report output unit outputs a visual report. The present application realizes precise, interpretable and highly adaptive bacterial antimicrobial resistance prediction through hierarchical design and rule monitoring separation architecture, while reducing the dependence on high-performance equipment and adapting to the use scenarios of primary medical institutions.
Need to check novelty before this filing date? Find Prior Art