Objective  To explore the influencing factors of mild cognitive impairment (MCI) in hospitalized elderly people, construct and compare the relative risk prediction model of multi-group MCI.

Methods  A convenient sampling method was used to select the elderly hospitalized in the geriatrics department of the First Affiliated Hospital of Xinjiang Medical University from January 2023 to September 2023.  The multivariate Logistic regression, decision tree and neural network were constructed, and the influencing factors of MCI were analyzed. The area under curve (AUC) of receiver operating characteristic (ROC) was adopted to compared the performance of three sets of prediction models.

Results  A total of 992 hospitalized elderly patients were included, and the detection rate of MCI was 21.17%. The analysis results of multivariate Logistic regression model, decision tree model and neural network model all showed that age, cerebrovascular disease and education level were the main influencing factors of MCI, and the multiple Logistic regression model and neural network model also showed that the score of daily living ability below 60 was also the influencing factors of MCI. The prediction accuracy of multivariate Logistic regression prediction model was 89.1%, the AUC of ROC curve was 0.933[95%CI(0.916, 0.950)], the sensitivity was 0.881, the specificity was 0.852, and the Yoden index was 0.733. The prediction accuracy of decision tree prediction model was 86.1%, AUC was 0.908[95%CI(0.888, 0.927)], the sensitivity was 0.919, the specificity was 0.753, and the Yoden index was 0.672. The prediction accuracy of the neural network model was 88.7%, the AUC was 0.933[95%CI(0.915, 0.950)], the sensitivity was 0.876, the specificity was 0.861, and the Yoden index was 0.737. The prediction results of the three groups of models were more than 70%, and the prediction efficiency were good.

Conclusion  Increasing age, shorter years of education, cerebrovascular disease, and decreased ability to perform daily living increase the risk of MCI in older adults. Multivariate Logistic regression, decision tree and neural network models can fully explore the influencing factors of MCI from different levels, and the effective combination of multiple models can fully understand the interaction between different factors, providing references for early screening and intervention of MCI.

1.任汝静, 殷鹏, 王志会,等. 中国阿尔茨海默病报告2021[J]. 诊断学理论与实践, 2021, 20(4): 317-337.[Ren RJ, Yin P, Wang ZH, et al. Chinese Alzheimer's disease report 2021[J]. Diagnostics Theory and Practice, 2021, 20(4): 317-337.] DOI: 10.16150/j.1671-2870.2021.04.001

2.中华医学会神经病学分会痴呆与认知障碍学组. 阿尔茨海默病源性轻度认知障碍诊疗中国专家共识2021[J]. 中华神经科杂志, 2022, 55(5): 421-440. [Chinese Society of Dementia and Cognitive Impairment. Chinese expert consensus on the diagnosis and treatment of mild cognitive impairment due to Alzheimer's disease 2021[J]. Chinese Journal of Neurology, 2022, 55(5): 421-440.] DOI: 10.3760/cma.j.cn113694-20211004-00679.

3.孙晨, 拜争刚. 故事疗法延缓轻中度认知障碍老年人认知衰退的最佳证据总结[J].医学新知, 2022, 32(6): 453-462. [Sun C, Bai ZG. Summary of the best evidence for story therapy to delay cognitive decline in the elderly with mild to moderate cognitive impairment [J]. Yixue Xinzhi Zazhi, 2022, 32(6): 453-462.] DOI: 10.12173/j.issn.1004-5511.202203045.

4.史路平, 姚水洪, 王薇. 中国老年人群轻度认知障碍患病率及发展趋势的Meta分析[J]. 中国全科医学, 2022, 25(1): 109-114. [Shi LP, Yao SH, Wang W. A Meta-analysis of the prevalence and development trend of mild cognitive impairment in Chinese elderly population [J]. Chinese Journal of General Medicine, 2022, 25(1): 109-114.] DOI: 10.12114/j.issn.1007-9572.2021.00.315.

5.张筱, 袁欣瑞, 朱瑞,等. 简易智能精神状态量表和蒙特利尔认知评估量表差值在老年期痴呆鉴别诊断中的价值[J]. 中华老年医学杂志, 2015, 34(5): 494-497. [Zhang X, Yuan XR, Zhu R, et al. The value of the difference between the Simple Intelligent Mental State Scale and the Montreal Cognitive Assessment Scale in the differential diagnosis of senile dementia[J]. Chinese Journal of Gerontology, 2015, 34(5): 494-497.] DOI: 10.3760/cma.j.issn.0254-9026.2015.05.010.

6.马佳, 张韶伟, 刘文斌,等. 社区老年轻度认知障碍患者抑郁焦虑状况及影响因素研究 [J]. 中国全科医学, 2020, 23(33): 4246-4251. [Ma J, Zhang SW, Liu WB, et al. Study on depression and anxiety in elderly patients with mild cognitive impairment in community and its influencing factors[J]. Chinese Journal of General Medicine, 2020, 23(33): 4246-4251.] DOI: 10.12114/j.issn.1007-9572.2019.00.617.

7.Jia L, Du Y, Chu L, et al. Prevalence, risk factors, and management of dementia and mild cognitive impairment in adults aged 60 years or older in China: a cross-sectional study[J]. Lancet Public Health, 2020, 5(12): e661-e71.DOI: 10.1016/s2468-2667(20)30185-7.

8.Lee H, Wang Z, Tillekeratne A, et al. Loss of functional heterogeneity along the CA3 transverse axis in aging[J]. Curr Biol, 2022, 32(12): 2681-2693.e4. DOI: 10.1016/j.cub.2022.04.077.

9.Johnson AC. Hippocampal vascular supply and its role in vascular cognitive impairment[J]. Stroke, 2023, 54(3): 673-685. DOI: 10.1161/strokeaha.122.038263.

10.夏艳秋, 崔丽君, 魏丽萍,等. 综合医院老年住院患者轻度认知功能障碍与焦虑抑郁关系的问卷调查[J]. 中国病案, 2020, 21(3): 83-86.[Xia YQ, Cui LJ, Wei LP, et al. A questionnaire survey on the relationship between mild cognitive impairment and anxiety and depression in elderly hospitalized patients in general hospital [J]. Chinese Medical Journal, 2020, 21(3): 83-86.] DOI: 10.3969/j.issn.1672-2566.2020.03.029.

11.禹延雪, 白茹玉, 于文龙,等. ≥60岁人群认知功能障碍发生现状及影响因素研究 [J]. 中国全科医学, 2023, 26(21): 2581-2588. [Yu Yx, Bai RY, Yu WL, et al. Prevalence and influencing factors of cognitive dysfunction in ≥60 years old population[J]. Chinese Journal of General Medicine, 2023, 26(21): 2581-2588.]DOI: 10.12114/j.issn.1007-9572.2023.0004.

12.王黎, 周莲, 杨燕妮. 住院高血压患者伴发轻度认知功能障碍的风险预测模型构建[J]. 陆军军医大学学报, 2022, 44(8): 835-841. [Wang L, Zhou L, Yang YN. Construction of a risk prediction model for hospitalized hypertensive patients with mild cognitive impairment[J]. Journal of Army Medical University, 2022, 44(8): 835-841.] DOI: 10.16016/j.2097-0927.202111189.

13.陆静钰, 杨连招, 陈玲,等. 社区老年高血压患者轻度认知功能障碍风险预测模型的构建与验证[J]. 护理学报, 2021, 28(24): 42-50. [Lu JY, Yang LZ, Chen L, et al. Construction and verification of risk prediction model for mild cognitive impairment in elderly hypertensive patients in community[J]. Journal of Nursing, 2021, 28(24): 42-50.] DOI: 10.16460/j.issn1008-9969.2021.24.042.

14.陈静华. Logistic回归模型、神经网络模型和决策树模型在轻度认知功能障碍向阿尔茨海默症转归预测中的比较[D]. 南昌：南昌大学, 2021. [Chen JH. Comparison of Logistic regression model, neural network model and decision tree model in predicting the outcome of mild cognitive impairment to Alzheimer's disease[D]. Nanchang: Nanchang University, 2021.] https://xueshu.baidu.com/usercenter/paper/show?paperid=166a0jp0qm4d0a30wh2906v0xr561886.

15.Li H, Habes M, Wolk DA, et al. A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data[J]. Alzheimers Dement, 2019, 15(8): 1059-1070. DOI: 10.1016/j.jalz.2019.02.007.

16.骆文, 刘育青, 劳钰钞,等. 基于BP神经网络的阿尔茨海默病预测模型研究 [J]. 中华医学图书情报杂志, 2022, 31(1): 32-37. [Luo W, Liu YQ, Lao YC, et al. Prediction model of Alzheimer's disease based on BP neural network [J]. Chinese Journal of Medical Library and Information, 2022, 31(1): 32-37.]DOI: 10.3969/j.issn.1671-3982.2022.01.004.

17.付茸, 史艳茹, 付月仙,等. 乳腺髓样癌临床预测模型的建立和验证：基于SEER数据库[J].医学新知, 2023, 33(3): 163-172. [Fu R, Shi YR, Fu YX, et al. Establishment and verification of clinical prediction model for medullary breast cancer: based on SEER database[J]. Yixue Xinzhi Zazhi, 2023, 33(3): 163-172.] DOI: 10.12173/j.issn.1004-5511.202204049.