跨院区病理质量风险协同预警方法及其应用

Through vertical federated learning and homomorphic encryption technology, the cross-hospital pathology quality control system has achieved full-chain risk sharing and traceability with privacy compliance, solving the data privacy barriers and traceability difficulties in cross-hospital pathology quality control, and improving the efficiency of risk identification and handling.

CN122114392BActive Publication Date: 2026-07-17SHENZHEN SHENGQIANG TECH
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN SHENGQIANG TECH
Filing Date
2026-04-27
Publication Date
2026-07-17

Smart Images

  • Figure CN122114392B_ABST
    Figure CN122114392B_ABST
Patent Text Reader

Abstract

本发明提出了一种跨院区病理质量风险协同预警方法及其应用，属于医疗数据处理技术领域。针对跨院区病理质控中的数据隐私壁垒及全链路风险溯源难题，本方案采用纵向联邦学习架构，各本地节点提取质量特征并加密上传梯度，实现数据不出域的全局模型训练；利用非敏感属性哈希映射实现跨院流转样本的全链路特征关联；结合贝叶斯网络与边际贡献算法定量计算各环节风险贡献度并定位根因，进而触发分级协同预警。本发明主要用于医联体场景下病理诊断全链路的隐私合规质控、风险实时预警与责任溯源。
Need to check novelty before this filing date? Find Prior Art