主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2026, Vol. 34 ›› Issue (7): 177-188.doi: 10.16381/j.cnki.issn1003-207x.2024.0608

• • 上一篇    

融合偏好学习和证据推理的疾病智能辅助诊断方法

陈希(), 窦友婍, 张文博   

  1. 西安电子科技大学经济与管理学院,陕西 西安 710126
  • 收稿日期:2024-04-19 修回日期:2025-09-11 出版日期:2026-07-25 发布日期:2026-06-18
  • 通讯作者: 陈希 E-mail:xchen@xidian.edu.cn
  • 基金资助:
    国家自然科学基金面上项目(71974154);陕西省“高层次人才特殊支持计划”青年拔尖人才项目;陕西省社会科学基金项目(2024R032);陕西省重点研发计划秦创原“科学家+工程师”队伍建设(2023KXJ-248);陕西省自然科学基金面上项目(2025JC-YBMS-798)

An Intelligent Auxiliary Diagnosis Method for Diseases Integrating Preference Learning and Evidential Reasoning

Xi Chen(), Youqi Dou, Wenbo Zhang   

  1. School of Economics & Management,Xi Dian University,Xi’an 710126,China
  • Received:2024-04-19 Revised:2025-09-11 Online:2026-07-25 Published:2026-06-18
  • Contact: Xi Chen E-mail:xchen@xidian.edu.cn

摘要:

伴随着医疗数字化转型的发展,如何利用患者在诊疗过程中生成的复杂多样诊疗信息进行智能分析,识别影响疾病的关键特征并准确诊断患者的病情,对辅助医生制订诊疗方案和提供治疗建议具有重要意义。基于此,本研究提出了一种融合偏好学习和证据推理的疾病智能辅助诊断方法。首先,考虑不同疾病特征对诊断结果影响的差异,建立了偏好学习模型获取不同特征权重,进而识别核心特征集。其次,以不同分类算法为基础构建异质基分类器,实现对患者病情的预测;进一步,为提高疾病诊断准确率,引入证据推理对基分类器的预测结果进行集成融合,辅助医生实现病情判断。最后,以实际医学数据集为例,对本文所提方法的可行性和有效性进行了验证。

关键词: 特征选择, 偏好学习, 证据推理, 集成学习, 智能诊断

Abstract:

With the development of digital transformation in healthcare, intelligently analyzing the complex and diverse diagnosis and treatment information generated during patients' diagnosis and treatment processes, identifying key features that affect diseases, and accurately predicting patients' conditions are of great significance for assisting doctors in formulating diagnosis and treatment plans and providing treatment recommendations. Based on this, an intelligent auxiliary diagnosis method for diseases is proposed that integrates preference learning and evidential reasoning. Firstly, considering the differences in the impact of various disease features on diagnosis results, a preference learning model is established to obtain the weights of different features, thereby identifying the core feature set. Secondly, heterogeneous base classifiers are constructed based on different classification algorithms to realize the prediction of patients' conditions. Furthermore, to improve the accuracy of disease diagnosis, evidential reasoning is introduced to integrate and fuse the prediction results of the base classifiers, assisting doctors in judging patients' conditions. Finally, the feasibility and effectiveness of the method proposed in this paper are verified with actual medical datasets as examples.

Key words: feature selection, preference learning, evidential reasoning, ensemble learning, intelligent diagnosis

中图分类号: