A method, device, and storage medium for predicting the risk of diabetes in patients with periodontal disease.

By detecting the expression levels of core mediator proteins and clinical data in patients with periodontal disease, a diabetes risk prediction model was constructed using the XGBoost algorithm. This solved the problem of insufficient accuracy in existing studies on the causal relationship between periodontal disease and diabetes, and achieved high-precision risk prediction and early intervention.

CN122135984APending Publication Date: 2026-06-02SICHUAN UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SICHUAN UNIV
Filing Date
2026-03-04
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

In existing technologies, studies on the causal relationship between periodontal disease and diabetes rely on cross-sectional design and small sample size, making it difficult to achieve high-precision clinical prediction and intervention.

Method used

By obtaining biological samples from patients with periodontal disease, detecting the expression levels of core mediator proteins and clinical covariate data, and using the XGBoost algorithm to construct a diabetes risk prediction model, the model is used to make predictions by combining the expression levels of key proteins such as C1S, PSAP, and CFP.

Benefits of technology

It achieves high-precision prediction of the future risk of diabetes in patients with periodontal disease, provides objective quantitative risk assessment basis, and supports early identification and intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122135984A_ABST
    Figure CN122135984A_ABST
Patent Text Reader

Abstract

This invention discloses a method, device, and storage medium for predicting the risk of diabetes in patients with periodontal disease, relating to the field of smart healthcare technology. The method includes: acquiring biological samples from patients with periodontal disease; detecting the expression levels of core mediator proteins in the biological samples, including C1S, PSAP, and CFP; acquiring clinical covariate data from patients with periodontal disease; inputting the expression levels of the core mediator proteins and the clinical covariate data into a pre-trained diabetes risk prediction model to obtain a prediction of the risk of developing diabetes in patients with periodontal disease within a predetermined time window; wherein, the diabetes risk prediction model is based on the XGBoost algorithm, using the expression levels of the core mediator proteins and the clinical covariate data as input features, and using the outcome of diabetes as a label for training. This invention provides a solution that can systematically elucidate the causal relationship between periodontal disease and diabetes, achieving high-precision prediction of the future risk of developing diabetes in patients with periodontal disease.
Need to check novelty before this filing date? Find Prior Art