基于Tri-training的改进算法在辅助诊断等医学领域的应用进展

天津科技 ›› 2025, Vol. 52 ›› Issue (09): 26-28+32.

基于Tri-training的改进算法在辅助诊断等医学领域的应用进展

乔桢¹, 戚红², 罗曦³

1.天津医科大学基础医学院天津 300070;
2.天津医科大学科技成果转化中心天津 300070;
3.天津医科大学信息中心天津 300070

收稿日期:2025-08-05 出版日期:2025-09-25 发布日期:2026-01-04
基金资助:
天津市教委科研计划项目“基于大数据的集成学习在医学诊断中的应用研究”（2020KJ199）

Application progress of improved algorithm based on Tri-training in medical fields such as auxiliary diagnosis

QIAO Zhen¹, QI Hong², LUO Xi³

1. School of Basic Medical Sciences,Tianjin Medical University,Tianjin 300070,China;
2. Center for Technology Transfer,Tianjin Medical University,Tianjin 300070,China;
3. Information Centre,Tianjin Medical University,Tianjin 300070,China

Received:2025-08-05 Online:2025-09-25 Published:2026-01-04

摘要/Abstract

摘要： Tri-training算法是机器学习算法中的一种半监督学习算法,该算法自提出以来,不断被深入分析,其改进算法也日益丰富。介绍了Tri-training算法的原理及步骤,并以此为基础,对其应用于辅助诊断等医学领域的改进算法做了分类,分别进行系统介绍分析。对 Tri-training 改进算法在医学领域的未来发展方向予以展望。

关键词: Tri-training, 半监督学习, 辅助诊断, 机器学习

Abstract: The Tri-training algorithm is a type of semi-supervised learning algorithm in machine learning algorithms. Since its proposal,improvements and variants based on Tri-training have become increasingly diverse. This paper introduces the principles and procedural steps of the Tri-training algorithm,and based on this,analyzes its application status in the field of medical auxiliary diagnosis. An outlook on the future development directions of the improved Tri-training algorithm in the medical field is presented.

Key words: Tri-training, semi-supervised learning, auxiliary diagnosis, machine learning

中图分类号:

乔桢, 戚红, 罗曦. 基于Tri-training的改进算法在辅助诊断等医学领域的应用进展[J]. 天津科技, 2025, 52(09): 26-28+32.

QIAO Zhen, QI Hong, LUO Xi. Application progress of improved algorithm based on Tri-training in medical fields such as auxiliary diagnosis[J]. TIANJIN SCIENCE & TECHNOLOGY, 2025, 52(09): 26-28+32.

参考文献

[1] SINGH A,NOWAK R D,ZHU X.Unlabeled data:Now it helps,now it doesn’t[C]//22nd Annual Conference on Neural Information Processing Systems. Vancouver,British Columbia,Canada,2008:1513-1520.
[2] ZHOU Z H,LI M.Semi-supervised learning by disagreement[J]. Knowledge and Information Systems,2010,24(3):415-439.
[3] ZHOU Z H,LI M.Tri-training:Exploiting unlabeled data using three classifiers[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(11):1529-1541.
[4] 唐校辉,廖欣,陈雷霆,等. 基于改进Tri-Training算法的健康大数据分类模型研究[J]. 现代计算机(专业版),2017,23(20):21-25.
[5] 唐校辉. 基于半监督学习算法的健康大数据分类模型研究与实现[D]. 成都:电子科技大学,2018.
[6] XIE J,FENG S Q,QU Z H.Retracted:adoption of dexmedetomidine in different doses at different timing in perioperative patients[J]. BioMed Research International,2022,2022(1):4008941.
[7] FENG Q L,GUI Y Y,YANG Z H,et al.Semisupervised learning based disease-symptom and symptom-therapeutic substance relation extraction from biomedical literature[J]. BioMed Research International,2016,2016:3594937.
[8] LI Z Y,TOGO R,OGAWA T,et al.Chronic gastritis classification using gastric X-ray images with a semi-supervised learning method based on tri-training[J]. Medical & Biological Engineering & Computing,2020,58(6):1239-1250.
[9] OH M,SHEN M,LIU R B,et al.Machine learned classification of ligand intrinsic activities at human μ-opioid receptor[J]. ACS Chemical Neuroscience,2024,15(15):2842-2852.
[10] CHEN Y,ZHOU C J,LI T X,et al.Named entity recognition from Chinese adverse drug event reports with lexical feature based BiLSTM-CRF and tri-training[J]. Journal of Biomedical Informatics,2019,96:103252.
[11] YANG Y,LI X F,WANG P,et al.Multi-source transfer learning via ensemble approach for initial diagnosis of Alzheimer’s disease[J]. IEEE Journal of Translational Engineering in Health and Medicine,2020,8:1400310.