基于可解释性机器学习的阿尔兹海默症痴呆风险预测

富丹; 孙悦; 郭金兴; 陈广新; 韩杨

您当前的位置：

首页 >

文章列表页 >

基于可解释性机器学习的阿尔兹海默症痴呆风险预测

更新时间：2024-05-09

- 基于可解释性机器学习的阿尔兹海默症痴呆风险预测
- Prediction of Alzheimer's dementia risk based on interpretable machine learning
- 新一代信息技术 2024年页码：1-5
- 作者机构：
  
  1.牡丹江医学院医学影像学院，黑龙江牡丹江，157011
  2.牡丹江医学院附属红旗医院，黑龙江牡丹江，157011
- 作者简介：
  
  富丹，女，讲师，1977.5-，研究方向：医学人工智能
  孙悦：女，1992.2-，初级职称，研究方向：人工智能
  郭金兴，女，1984.5-，中级职称，研究方向：人工智能
  陈广新，男，1978.3-，中级职称，研究方向：医学图像处理。
  韩杨，女，1990.12-，硕士研究生学历，实验师，研究方向：医学人工智能。E-mail：44642581@qq.com
- 基金信息：
  
  牡丹江市应用技术研究与开发计划项目(HT2022NS116)
- DOI：
  中图分类号： R195
- 网络出版日期：2024-05-09，
扫描看全文
富丹,孙悦,郭金兴等.基于可解释性机器学习的阿尔兹海默症痴呆风险预测[J].新一代信息技术,

Fu Dan,Sun Yue,Guo Jinxin,et al.Prediction of Alzheimer's dementia risk based on interpretable machine learning[J].New Generation of Information Technology,
富丹,孙悦,郭金兴等.基于可解释性机器学习的阿尔兹海默症痴呆风险预测[J].新一代信息技术, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

Fu Dan,Sun Yue,Guo Jinxin,et al.Prediction of Alzheimer's dementia risk based on interpretable machine learning[J].New Generation of Information Technology, DOI：10.3969/j.issn.2096-6091.XXXX.XX.001.

摘要

阿尔茨海默病（AD）是当今社会面临的重要挑战之一，早期诊断对于有效治疗至关重要。本研究探索了机器学习算法在预测AD风险方面的应用，并使用了多种模型进行比较。结果显示选择多种模型，由于数据集中的缺失值，预测效果并不理想。SHAP特征分析揭示了抑郁症和APOE ε4等位基因在模型预测中的关键作用。未来的研究应进一步探索这些遗传和环境因素对AD发病机制的影响，并利用先进技术优化预测模型，以提高早期诊断和干预能力，为阿尔茨海默症的预防和治疗提供更精准有效的方法。

Abstract

Alzheimer's disease (AD) is one of the important challenges facing society today

however

early diagnosis is essential for effective treatment. This study explores the application of machine learning algorithms in predicting AD risk and uses a variety of models for comparison. The results show that although the model selection is rich

the prediction effect is not ideal due to missing values in the data set. SHAP profile analysis revealed the key role of depression and APOE ε4 allele in model prediction. Future studies should further explore the influence of these genetic and environmental factors on the pathogenesis of AD

and optimize predictive models with advanced technologies to improve early diagnosis and intervention capabilities

and provide more accurate and effective methods for the prevention and treatment of Alzheimer's disease.

关键词

机器学习SHAP模型可解释性风险预测

Keywords

Machine learningSHAPModel interpretabilityRisk prediction

references

BUSH A I. The metallobiology of Alzheimer's disease[J]. Trends in neurosciences, 2003, 26(4): 207-214.

DETURE M A, DICKSON D W. The neuropathological diagnosis of Alzheimer's disease[J]. Molecular neurodegeneration, 2019, 14(1): 32.

SCHELTENS P, DE STROOPER B, KIVIPELTO M, et al. Alzheimer's disease[J]. The Lancet, 2021, 397(10284): 1577-1590.

Andrade-Guerrero J, Santiago-Balmaseda A, Jeronimo-Aguilar P, et al. Alzheimer's disease: an updated overview of its genetics[J]. International journal of molecular sciences, 2023, 24(4): 3754.

SALEH H, ELRASHIDY N, ABD ELAZIZ M, et al. Genetic algorithm-based hybrid deep learning model for explainable Alzheimer's disease prediction using temporal multimodal cognitive data[J]. International Journal of Data Science and Analytics, 2024: 1-31.

TU Y, LIN S, QIAO J, et al. Multimodal fusion diagnosis of Alzheimer's disease based on FDG-PET generation[J]. Biomedical Signal Processing and Control, 2024, 89: 105709.

YAMAZAKI Y, ZHAO N, CAULFIELD T R, et al. Apolipoprotein E and Alzheimer disease: pathobiology and targeting strategies[J]. Nature Reviews Neurology, 2019, 15(9): 501-518.

CORBO R M, SCACCHI R. Apolipoprotein E (APOE) allele distribution in the world. Is APOE* 4 a 'thrifty'allele?[J]. Annals of human genetics, 1999, 63(4): 301-310.

BOYLE P A, BUCHMAN A S, WILSON R S, et al. The APOE ε 4 allele is associated with incident mild cognitive impairment among community-dwelling older persons[J]. Neuroepidemiology, 2010, 34(1): 43-49.

ENGELBORGHS S, SLEEGERS K, CRAS P, et al. No association of CSF biomarkers with APOE ε 4, plaque and tangle burden in definite Alzheimer's disease[J]. Brain, 2007, 130(9): 2320-2326.

BERGER T, LEE H, YOUNG A H, et al. Adult hippocampal neurogenesis in major depressive disorder and Alzheimer's disease[J]. Trends in molecular medicine, 2020, 26(9): 803-818.

刘金平,吴娟娟,张荣,等.基于结构重参数化与多尺度深度监督的COVID-19胸部CT图像自动分割[J].电子学报,2023,51(05):1163-1171.

谢娟英,张凯云. SOSNet:一种非对称编码器-解码器结构的非小细胞肺癌CT图像分割模型[J]. 电子学报:1-15.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

预测COVID-19感染风险的医疗决策机器学习方法研究

基于可解释性机器学习的新冠肺炎疾病风险预测研究