收藏切换
Novel combinations of plasma biomarkers for Alzheimer’s disease based on machine learning algorithms
收藏切换
Fang-yu LI, Yan WANG, Ying LI, Jian-ping JIA
Modern Preventive Medicine | 2026, 53(14) : 2518 - 2523
Less
收藏切换
Modern Preventive Medicine | 2026, 53(14): 2518-2523
• Epidemiology and Statistical Methods Advance •
Novel combinations of plasma biomarkers for Alzheimer’s disease based on machine learning algorithms
Full
Fang-yu LI, Yan WANG, Ying LI, Jian-ping JIA
Affiliations
  • Xuanwu Hospital, Capital Medical University, Beijing 100053, China
Published: 2026-07-25 doi: 10.20043/j.cnki.MPM.202511146
Outline
收藏切换
Objective

To identify a novel plasma protein biomarker panel for predicting mild cognitive impairment (MCI) and Alzheimer’s disease (AD) using machine learning algorithms, and to provide evidence for early diagnosis of AD.

Methods

A total of 566 eligible participants were enrolled from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, and baseline plasma proteomic data were collected. Random forest, Lasso regression, and support vector machine were applied to screen plasma proteins that effectively discriminate MCI and AD. Correlation analyses with cerebrospinal fluid biomarkers and cognitive scales, and Mendelian randomization analysis were conducted. The model was validated in the GEO and UK Biobank databases.

Results

Ten core plasma biomarkers, including apolipoprotein AII, apolipoprotein E, transthyretin (TTR), were consistently identified by the three algorithms and showed strong correlations with cerebrospinal fluid biomarkers and cognitive scores. Mendelian randomization indicated an inverse association between TTR and AD risk. The area under the curve (AUC) of the tenbiomarker panel was 0.929 for predicting MCI and 0.932 for AD. The panel achieved an AUC of 0.871 in the GEO dataset. When combined with age, sex and APOE ε4 status, the panel yielded an AUC of 0.856 for predicting incident AD over an average of 14 years in the UK Biobank.

Conclusion

The newly identified plasma protein panel can effectively predict the occurrence of MCI and AD, providing a noninvasive tool for early screening and prevention of AD.

Alzheimer’s disease  /  Machine learning  /  Random forest  /  Lasso regression  /  Support vector machine
李芳玉, 王彦, 李颖, 贾建平. 机器学习算法分析阿尔茨海默病血浆标志物新组合. 现代预防医学, 2026 , 53 (14) : 2518 -2523 . DOI: 10.20043/j.cnki.MPM.202511146
Fang-yu LI, Yan WANG, Ying LI, Jian-ping JIA. Novel combinations of plasma biomarkers for Alzheimer’s disease based on machine learning algorithms[J]. Modern Preventive Medicine, 2026 , 53 (14) : 2518 -2523 . DOI: 10.20043/j.cnki.MPM.202511146
Year 2026 volume 53 Issue 14
214
98
Cite this Article
BibTeX
Article Info
doi: 10.20043/j.cnki.MPM.202511146
  • Receive Date:2025-11-11
  • Online Date:2026-09-28
  • Published:2026-07-25
Article Data
Affiliations
History
  • Received:2025-11-11
Funding
Affiliations
    Xuanwu Hospital, Capital Medical University, Beijing 100053, China
References
Share
https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202511146
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT