Current Status and Risk Factors of Mild Cognitive Impairment among Older Adults in Wuhan: A Machine Learning-Based Analysis

Current Status and Risk Factors of Mild Cognitive Impairment among Older Adults in Wuhan: A Machine Learning-Based Analysis | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Current Status and Risk Factors of Mild Cognitive Impairment among Older Adults in Wuhan: A Machine Learning-Based Analysis Dajie Chen, Cen Gao, Wencai Chen, Wenzhen Li, Xiujun Liu, Qingzhou Cheng, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8248590/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Background This study seeks to understand the current situation of mild cognitive impairment (MCI) in Wuhan, explore the related risk factors, and identify high-risk groups. Methods Multistage cluster sampling was adopted to recruit a total of 2,190 adults aged 60 years and above from 30 residential (village) committees in 13 administrative districts. They were screened for MCI using the Community Screening Instrument for Dementia (CSI-D).The Least Absolute Shrinkage and Selection Operator (LASSO) was employed to screen predictive variables. A variety of machine learning classification models were integrated to analyze and identify the optimal model. Multiple evaluation indicators were utilized to compare the performance of models, including the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). Binary logistic regression was adopted to determine the effect values of risk factors, and SHapley Additive ex Planations (SHAP) was applied to interpret machine learning models. Results 35.3% participants were diagnosed with MCI. The Final model included age, occupation, sleep disorders and literacy level. Based on the AUC and DCA in the validation group, the XGBoost model demonstrated excellent performance, the most crucial features in this model and their effect values as follows: sleep disorders (OR: 1.44, 95%CI: 1.31–1.82), aged above 75 (OR: 1.52, 95%CI: 1.12–2.08), High school and above (OR: 0.39, 95%CI: 0.28–0.56), Middle school (OR: 0.48, 95%CI: 0.35–0.65), Farmers were included but without significant effect. Conclusion The current status of MCI among older adults in Wuhan is not optimistic. Therefore, early screening and intervention should be carried out for farmers and individuals with advanced age, low literacy,and sleep disorders. Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Health sciences/Risk factors Older adults MCI Screening Risk factors Prevalence Cross-sectional study Figures Figure 1 Figure 2 Figure 3 Introduction With the acceleration of population aging, China’s adult population aged ≥ 60 years reached 280.04 million by the end of 2022, accounting for 19.8% of the total population ( 1 ). A large body of research evidence suggests that the prevalence of cognitive impairment will increase with the growth of the older adult population ( 2 , 3 ). Cognitive impairment is defined as deficits in one or more cognitive functions and can be categorized based on the severity of functional impairment into mild cognitive impairment (MCI) and dementia. MCI is the preclinical stage of dementia and has a high likelihood of transitioning to dementia ( 4 ), with studies documenting that 10%–15% of patients with MCI progress to dementia each year ( 5 ). China has the largest number of dementia patients in the world, accounting for approximately 25% of the global total ( 6 ). Dementia imposes a heavy economic and social burden on China. Statistics indicate that the direct and indirect costs of treating dementia patients in China amount to trillions of dollars per year ( 2 ). Furthermore, relevant studies have indicated that factors such as gender, age, and dietary habits are associated with an increased risk of mild cognitive impairment (MCI) development ( 7 ). However, due to variations in participants, regions, and research methods, factors such as gender, smoking, alcohol consumption, and sleep disorders have not demonstrated consistent correlations ( 8 , 9 ). China has been exploring the development of dementia-specific prevention and treatment services since 2020 and has carried out cognitive function screening and early intervention for older adults in several regions. Nevertheless, comprehensive investigations on the comprehensive risk factors of large-scale mild cognitive impairment are still scarce in China. To address the inconsistencies and regional differences in previous studies and explore more potential related factors, our research aims to investigate these aspects among the elderly aged 60 and above in different districts of Wuhan. Notably, there has been no relevant research conducted at this specific location before. With a relatively high survey coverage rate, our study investigates the potential related factors of mild cognitive impairment from three aspects: demographic characteristics, behavioral lifestyles, and health status, aiming to identify the risk factors of MCI as clearly as possible and provide a reference for the prevention of MCI and dementia. Methods Study design and participants This study was based on the Basic Public Health Service Program, the Cognitive Function Screening and Early Intervention Program for Older Adults launched by the National Health Commission in 2023, and which has been implemented in hundreds of cities across China, including Wuhan. Cognitive function and health screening was performed by multistage cluster sampling in Caidian, Hanyang, Huangpi, Wuchang, and Xinzhou districts, which were randomly selected as screening areas from the 13 administrative districts of Wuhan. In each of these five districts, we randomly selected two subdistricts. In each subdistrict, we randomly selected two residential (village) committees. In each residential (village) committee, all permanent residents (including those with local household registrations and those who had lived in the city for over half a year) aged 60 and above (born before December 31, 1962) underwent cognitive function and health screening. The following exclusion criteria for MCI screening were adopted: ( 1 ) incomplete or questionable data; ( 2 ) severe hearing or vision loss preventing the completion of the cognitive assessment; and ( 3 ) confirmed diagnosis of dementia. A total of 2,402 participants from 30 residential (village) committees completed the survey. After excluding survey data with unclear primary records and incomplete information, our final analysis included 2,190 valid samples. The study protocol was approved by the Ethical Review Committee of Wuhan Mental Health Center, and all participants provided written informed consent. Screening Procedures All surveys were completed one-on-one with participants in a quiet environment through home visits by staff from subdistrict community health centers who received uniform training. Participants were first asked to fill out a Basic Information Questionnaire, which included demographic characteristics (gender, age, marital status, occupation, literacy level, monthly income, household size), behavioral lifestyle (smoking, alcohol consumption, exercise days/week), and health status (body mass index (BMI), number of chronic diseases, depression, anxiety, sleep disorders). This was followed by the Resident Mental Health Questionnaire, which used the Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder Questionnaire-7 (GAD-7), and Insomnia Severity Index (ISI) scale to assess the mental health and sleep quality of older adults. The psychiatrists then reviewed the diagnoses of participants who screened positive for depression/anxiety and 15% who screened negative. Finally, to assess their cognitive function, participants completed the Community Screening Instrument for Dementia (CSI-D), and the psychiatrists reviewed the diagnoses of those who screened positive for MCI and 15% who screened negative. Positive screening criteria Assessment of cognitive function: Researchers from various countries have developed numerous dementia screening scales applicable to different countries and groups. Among which, the CSI-D has displayed good reliability and validity when applied to the Chinese population and has been widely used in China. A total CSI-D score of ≤ 7 indicates MCI, while a score of > 7 indicates no cognitive impairment. Assessment of depression: A PHQ-9 score > 4 indicates symptoms of depression. Assessment of anxiety: A GAD-7 score of > 4 indicates symptoms of anxiety. Assessment of insomnia: An ISI score of ≥ 8 indicates clinically significant insomnia. Model development and comparison First, R software (glmnet4.1.2) was used to conduct the least absolute shrinkage and selection operator (LASSO) regression analysis and adjust the variable screening and complexity. Subsequently, the screened features were used to develop predictive models. Five ML models namely K Nearest Neighbours (KNN), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGboost) were used for predicting the occurrence of MCI. Several commonly used evaluation indexes, such as AUC, sensitivity, specificity, PPV, negative predictive value(NPV), accuracy, and F1 score, were used to evaluate the reliability of these models. Furthermore, a DCA was carried out to evaluate the utility of the decision models by quantifying the net benefit across different threshold probabilities. A binary logistic regression model was applied to analyze the risk factors for MCI, in which the dependent variable was the presence of MCI (yes/no), Model explanation The SHapley Additive exPlanations (SHAP) method offered global and local explanations for the model explanation. The global explanation could give consistent and accurate attribution values for each feature within a model to show the associations between input features and MCI. The local explanation could demonstrate a specific prediction for individual patients by inputting the specific data. Statistical analysis Statistical analyses were performed using SPSS 27.0 (IBM Corp.). and R (R version 4.5.1). Continuous variables were expressed as mean ± standard deviation (SD), and categorical variables were expressed as frequency (percentage). Statistical inference for categorical variables was performed using the χ² test. The predictive power was evaluated using the AUC, with the optimal cut-off value determined by maximizing the Youden index (sensitivity + specificity-1). All tests were two-sided, and statistical significance was set at P < 0.05. Results 1. General demographics of the screening population and distribution of MCI detected The 2,190 participants included 821 males (60–95 years; mean age: 69.75 ± 6.05 years) and 1,369 females (60–95 years; mean age: 69.35 ± 6.75 years). Among the total screening population, 1,417 participants had normal cognitive function, and 773 (detection rate: 35.3%) screened positive for MCI, including 486 women (detection rate: 35.5%) and 287 men (detection rate: 35.0%). Except for gender (χ²=0.051, p = 0.822), between-group differences in the detection rate of MCI were observed for all other demographic characteristic groups (all groups p < 0.05). The detection rate tended to increase with age, and older individuals had a higher detection rate (χ²=46.567, p < 0.001). Widowed older adults (χ²= 28.561, p < 0.001) and farmers (χ²=55.569, p < 0.001) had the highest detection rate (47.4% and 42.7%, respectively). The detection rate tended to decrease with increasing literacy (χ²=111.559, p < 0.001) and monthly income (χ²= 85.264, p < 0.001). In addition, a significant difference was observed in the detection rate among households with different sizes (χ²=10.688, p = 0.014). The distribution of positive MCI screening results among groups with different demographic characteristics is presented in Table 1 . Table 1 Demographics of the screening population and distribution of MCI detected Demographic characteristics N(%) MCI (%) p value Total population 2190 773(35.3) Gender 0.822 Female 1370(62.56) 486(35.47) Male 820(37.44) 287(35.00) Age groups (years) < 0.001 60 ~ 64 560(25.57) 167(29.82) 65 ~ 69 696(31.78) 211(30.32) 70 ~ 74 468(21.37) 173(36.97) ≥ 75 466(21.28) 222(47.64) Marital status Single‌ 30(1.37) 11(36.67) < 0.001 Married 1758(80.27) 576(32.76) Separated/Divorced 35(1.60) 12(34.29) Widowed 367(16.76) 174(47.41) Occupation < 0.001 Technical personnel 392(17.90) 99(25.26) Retirement 427(19.50) 115(26.93) Farmer 967(44.15) 413(42.71) Business/service personnel 150(6.85) 48(32.00) Others 254(11.60) 98(38.58) Literacy level < 0.001 Illiterate 530(24.20) 266(50.19) Elementary 547(24.98) 226(41.32) Middle school 591(26.99) 161(27.24) High school and above 522(23.83) 120(22.99) Monthly income < 0.001 0-1499 RMB 1196(54.61) 521(43.56) 1500–2999 RMB 326(14.89) 99(30.37) 3000–4999 RMB 541(24.70) 129(23.84) ≥ 5000 RMB 127(5.80) 24(18.90) Family size 0.014 1 298(13.60) 127(42.62) 2 881(40.23) 285(32.35) 3 ~ 7 941(42.97) 334(35.49) 8 70(3.20) 27(38.57) Smoking 0.012 Yes 459(20.96) 185(40.31) No 1731(79.04) 588(33.97) Drinking 0.301 Yes 344(15.71) 113(32.85) No 1846(84.29) 660(35.75) Exercise days/week 0.008 5 1147(52.37) 373(32.52) BMI 0.185 Underweight 126(5.75) 52(41.27) Normal 1211(55.30) 440(36.33) Overweight 628(28.68) 204(32.48) Obesity 225(10.27) 77(34.22) Number of chronic diseases 0.001 0 718(32.79) 218(30.36) 1 800(36.53) 284(35.5) ≥ 2 672(30.68) 271(40.33) Depression < 0.001 Yes 170(7.76) 81(47.65) No 2020(92.24) 692(34.26) Anxiety 0.195 Yes 136(6.21) 55(40.44) No 2054(93.79) 718(34.96) Sleep disorders < 0.001 Yes 496(22.65) 219(44.15) No 1694(77.35) 554(32.7) Among this screening population, 459 (21.96%) were smokers, and 344 (15.71%) consumed alcohol. A total of 937 (42.79%) participants exercised 5 days per week.As indicated in Table 1 , the detection rate of MCI was higher among smokers than non-smokers (χ²=6.378, p = 0.012). Alcohol consumption had no significant effect on the detection of MCI in older adults (p > 0.05). The detection rate among older adults tended to decrease with increasing exercise days/week, and between-group differences in the detection rate were observed (χ²=9.602, p = 0.008). Among this screening population, 126 (5.75%) were underweight, 1,211 (55.30%) had a normal BMI, 628 (28.68%) were overweight, and 225 (10.27%) were obese. In addition, 718 (32.78%) participants did not suffer from chronic diseases, 800 (36.53%) from one chronic disease, and 672 (30.68%) from two or more chronic diseases. The detection rates of depression, anxiety, and sleep disorders were 7.76%, 6.21%, and 22.65%, respectively. As indicated in Table 1 , the detection rate of MCI among older adults increased as the number of chronic diseases increased. The detection rate was higher among older adults with depressive symptoms than among those without such symptoms (χ²=12.309, p < 0.001). The detection rate was also higher among individuals with sleep disorders than those without (χ²=22.023, p 0.05) and anxiety (p > 0.05). Factor selection for the predictive model LASSO regression analysis was conducted on the remaining independent variables, with MCI serving as the dependent variable (Fig. 1 ). To increase the interpretability of the model and mitigate the risk of over fitting, The results showed (lambda = 0.0404, The maximum lambda within one standard error of the minimum error), that 33 independent variables were reduced to 5, including aged above 75, farmer, sleep disorders and higher literacy level (middle school and high school and above). A.Tuning parameter (λ) selection cross-validation error curve; B. Plot of the LASSO coefficient profiles. C. LASSO Selected Feature Coefficients; D. Feature Selection Statistics The best model building and external evaluation Comprehensive analysis of classified multi-model XGBoost, LR, RF, SVM, and KNN were trained and repeated 10 times. The models were evaluated using AUC values, which showed that XGBoost were highest in the validation set (Fig. 2 A). The AUC indicator focuses on the predictive accuracy of the model and does not tell whether the model is clinically usable or which one of the two is preferable. Therefore, the DCA, calibration curves, and PR curves were analyzed. (Fig. 2 B - F ). Taken together, these findings suggest that the XGBoost model was the most desirable model for this study. A. ROC Curve Comparison. B. PR Curve Comparison; C. Decision Curve Analysis; D. Calibration Curve; E. Model Performance Metrics Comparison; F. Confusion Matrix. Logistic regression analysis and tenfold cross-validation were performed on internal validation set, the results show an average AUC of 0.671 (0.619–0.725), which is slightly lower than that of the XGBoost model at 0.693 (0.642–0.745). Therefore, we employed the LR model to assess the effect sizes of the variables incorporated into the model (Fig. 3 A). The results demonstrated that sleep disorders and age over 75 years were significantly positively associated with the occurrence of MCI. with OR values of 1.44 (95%CI: 1.13–1.82) and 1.52 (95%CI: 1.12–2.08), respectively. Higher literacy level is a protective factor against MCI, with odds ratios of 0.48 for middle school and 0.39 for high school and above. Forest plot from logistic regression analysis; B. SHAP summary plot for the XGBoost model Model explanation To visually elucidate the selected variables, SHAP was utilized to illustrate how these variables predict the occurrence of MCI in the XGBoost model (Fig. 3 B). Figure 3 B depicts the four most important features (sleep disorders, age, occupation, and literacy level) in our model, the latter three are categorical variables with multiple levels and were coded as dummy variables in the model. Each feature significance line showcases all patient attributions for the outcome, represented by differently colored dots: red dots indicate high-risk values, while blue dots denote low-risk values. Figure 3 B displays the ranking of the five risk factors assessed by mean absolute SHAP value, with the x-axis SHAP value indicating the importance of the predictive model. Therefore, in the predictive model, literacy level and sleep disorders represent the most critical predictors, whereas advanced age and occupation serve as important auxiliary variables. Discussion To the best of our knowledge, this study is the first to analyze the prevalence of MCI among individuals aged 60 and above in Wuhan, and to explore the risk factors for MCI among older adults from three aspects: demographic characteristics, behavioral lifestyles, and health status. Our findings revealed that the detection rate of MCI among Wuhan residents was 35.3%, which was relatively high in China. A meta-analysis published in 2021 that included 41 observational studies documented that the prevalence of MCI among individuals in Chinese urban communities was 12.2% (95% CI: 10.6–14.2%) ( 10 ). In 2020, a large cross-sectional study involving 12 provinces in China established that the overall prevalence of MCI among Chinese adults aged 60 years and older was 15.54% (95% CI: 15.21–15.88) ( 11 ). Although the prevalence of MCI varies across different countries and regions, ranging from 4.3% to 39.1% ( 12 , 13 ), that among residents of Wuhan is still relatively high when compared with international data. For instance, a meta-analysis published in 2022 that included 66 articles involving 242,804 participants determined that the overall global prevalence of MCI among community-dwelling individuals aged 50 years and older was 15.56% (95% CI: 13.24–18.03%) ( 14 ). The significant differences in MCI detection rates across various countries and regions may be attributed not only to the inherent specificity in MCI risk that truly exists among different regions and ethnic groups, but also to the use of different screening tools in different studies (such as the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), Ascertain Dementia 8 (AD8), and CSI-D, etc.). Since MCI is an early stage of dementia, to shift the focus of prevention and treatment forward is critical. Moreover, given the high detection rate of MCI in Wuhan, analyzing the risk factors of MCI and emphasizing prevention on interventions targeting these factors is of considerable significance so as to achieve the prevention and control of MCI in Wuhan. Our findings revealed five risk factors for MCI, with advanced age being a non-modifiable risk factor. Older age was associated with a higher risk of MCI, and this finding has been confirmed in many studies ( 15 , 16 ). In a cohort study with a 12-year follow-up ( 17 ), the effect of age on cognitive impairment was associated with gray matter in the medial prefrontal cortex of the brain. The brain tissue in this region gradually atrophied with increasing age, which led to a significant decline in brain function ( 18 ), and a particularly pronounced decline in neurological function. In addition, advanced age is a risk factor for chronic diseases such as hypertension and diabetes mellitus ( 19 ), which can jeopardize the vascular and nervous systems, thus leading to cognitive decline in older adults ( 20 ). More importantly, this study identified three modifiable risk factors: literacy level, occupation and sleep disorders. Literacy and occupation are the main indicators of socioeconomic status, and individuals with higher levels of these displayed a lower risk of MCI, which is consistent with the results of numerous studies ( 11 , 21 , 22 ). According to cognitive reserve theory, a higher socioeconomic status can increase the brain’s cognitive reserve by increasing cognitive stimulation for cortical development, thereby rendering the individual less susceptible to evident cognitive decline ( 23 ); these regular and sustained stimuli also play a role in preventing the loss of neuronal connectivity and/or strengthening neuronal associations, which can compensate for neuropathological impairments related to aging, thus preventing or slowing the development of MCI ( 24 , 25 ). Health effects caused by socioeconomic inequalities have always existed ( 26 ), and have a cumulative effect, which is more prominent in old age. Early studies determined that socioeconomic factors are determinants of quality of life among older adults ( 27 ); those with low socioeconomic status are less likely to have access to appropriate nutrition and healthcare resources, frequently delaying medical consultation and thus failing to detect and intervene in MCI in time. Therefore, relevant government departments should pay more attention to older adults with low literacy and income levels, with a special emphasis on livelihood and healthcare security. This study comprehensively explores the risk factors of MCI among older adults from three aspects: demographic characteristics, behavioral lifestyle, and health status, which serves as a reference for the early identification of high-risk groups and provides evidence for the early screening of MCI. However, this study has the following limitations. First, given the cross-sectional design, no causal relationship can be established. Further prospective studies should be conducted through a cohort design to clarify the causal association. Second, all variables in the questionnaire were self-reported; hence, our findings may be affected by recall bias and social expectations. Third, our samples were selected from Wuhan, the generalizability of our findings may be somewhat constrained. Samples from more regions with varying economic development levels and different distributions of medical resources should be included in future studies. In addition, the present study used the CSI-D for detecting MCI. As a rapid screening tool, the CSI-D primarily focuses on the initial identification of abnormal cognitive function and lacks detailed assessments of specific cognitive domains. Therefore, it is difficult to precisely distinguish the subtle differences between MCI, dementia, and normal aging. Conclusion In Wuhan, the prevalence of MCI among adults aged 60 years and above is relatively high and is becoming an important public health issue that needs special attention. Wuhan’s health administrative departments and healthcare providers should formulate policies and implement measures to strengthen activities related to the early screening, diagnosis, and treatment of MCI. In addition, the key targets of such screening are individuals with advanced age, low literacy, low income, smoking habit, and sleep disorders. To ensure early detection, diagnosis, and treatment, adequate attention and care should be given to these groups to strengthen screening intervention, thereby slowing or reducing the occurrence of MCI. Abbreviations mild cognitive impairment (MCI) Community Screening Instrument for Dementia (CSI-D) body mass index (BMI) Patient Health Questionnaire-9 (PHQ-9) Generalized Anxiety Disorder Questionnaire-7 (GAD-7) Insomnia Severity Index (ISI) Declarations Supplementary Information Acknowledgment The authors are grateful to the help of staffs at subdistrict community health centers and the cooperation of participants in the screening area. Author contributions Wencai Chen, Xiujun Liu were responsible for the draft of the protocol and recruitment of participants. Dajie Chen, Qingzhou Cheng, Rong Nie and Hongping Zhang contributed to formulating the research question. Hua Hu and Cen Gao analyzed the data and wrote the initial draft of the manuscript, Wenzhen Li revised the manuscript which was commented on and edited by all co-authors. Yameng Feng produced the tables and figures. All authors had access to all data, have approved the final manuscript and accept responsibility for submission for publication. Funding The Funding for Scientific Research Projects from Wuhan Municipal Health Commission (NO.WX23B34), Science and Technology Research Project of Education Department of Hubei Province (NO. Q20221604); University Scientific Research Fund of Wuhan Polytechnic University (NO. 2022Y37). Data of Availability: The datasets generated and/or analyzed during the current study are not publicly available due to privacy and confidentiality concerns regarding sensitive personal information, but are available from the corresponding author on reasonable request. Competing interests The authors declare no competing interests. Ethics approval and consent to participate Ethical approval for this research was obtained from the Ethical Review Committee of Wuhan Mental Health Center (KY2023.0412.03), ethical standards are in accordance with the Declaration of Helsinki. Before survey initiation, informed consent was secured from all participants. Consent for publication Not applicable. References China Statistical Yearbook. (2023-04-23). (2023). Available from: https://www.stats.gov.cn/sj/ndsj/2023/indexch.htm Nichols, E. et al. Estimation of the global prevalence of dementia in 2019 and forecasted prevalence in 2050: an analysis for the Global Burden of Disease Study 2019. Lancet Public. health . 7 (2), E105–E125. 10.1016/s2468-2667(21)00249-8 (2022). Cited in: Pubmed; PMID WOS:000763474800008. Overton, M. et al. Prevalence and Incidence of Mild Cognitive Impairment across Subtypes, Age, and Sex. Dementia and geriatric cognitive disorders. ;47(4–6):219–232. eng. Epub 2019/07/17. (2019). 10.1159/000499763 . Cited in: Pubmed; PMID 31311017. Brodaty, H. et al. Progression from mild cognitive impairment to dementia: a 3-year longitudinal study. Aust. N. Z. J. Psychiatry . 48 (12), 1137–1142. 10.1177/0004867414536237 (2014). eng. Epub 2014/05/24. P SL, et al. Prevalence and distribution trends of mild cognitive impairment among Chinese older adults: a Meta-analysis. [J] Chinese General Practice, 25 (1): 109–114. 2022;25(01):109–114. (2022). Feigin, V. L. et al. Global, regional, and national burden of neurological disorders, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. Lancet Neurol. 18 (5), 459–480. 10.1016/s1474-4422(18)30499-x (2019). Cited in: Pubmed; PMID WOS:000464140400014. Campbell, N. L. et al. Risk Factors for the Progression of Mild Cognitive Impairment to Dementia. Clin. Geriatr. Med. 29 (4), 873–. 10.1016/j.cger.2013.07.009 (2013). Cited in: Pubmed; PMID WOS:000326659400009. Peltz, C. B. et al. Cognitive impairment in nondemented oldest-old: Prevalence and relationship to cardiovascular risk factors. Alzheimers Dement. 8 (2), 87–94. 10.1016/j.jalz.2011.02.008 (2012). Cited in: Pubmed; PMID WOS:000301991600001. Valenza, S. et al. Mild Cognitive Impairment Subtypes and Type 2 Diabetes in Elderly Subjects. J. Clin. Med. 9 (7). 10.3390/jcm9072055 (2020). Cited in: Pubmed; PMID WOS:000558058200001. Lu, Y. et al. Prevalence of mild cognitive impairment in community-dwelling Chinese populations aged over 55 years: a meta-analysis and systematic review. BMC geriatrics. ;21(1):10. eng. Epub 2021/01/08. (2021). 10.1186/s12877-020-01948-3 . Cited in: Pubmed; PMID 33407219. Jia, 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. Lancet Public. health . 5 (12), e661–e671. 10.1016/S2468-2667(20)30185-7 (2020). Epub 2020/12/04. Liu, L. Y. et al. Prevalence, risk and protective factors for mild cognitive impairment in a population-based study of Singaporean elderly. J. Psychiatr. Res. 145 , 111–117 (2021). Cited in: Pubmed; PMID 34894520. Sachdev, P. S. et al. Risk profiles for mild cognitive impairment vary by age and sex: the Sydney Memory and Ageing study. The American journal of geriatric psychiatry: official journal of the American Association for Geriatric Psychiatry. ;20(10):854 – 65. eng. Epub 2012/06/08. (2012). 10.1097/JGP.0b013e31825461b0 . Cited in: Pubmed; PMID 22673190. Bai, W. et al. Worldwide prevalence of mild cognitive impairment among community dwellers aged 50 years and older: a meta-analysis and systematic review of epidemiology studies. Age Ageing . 51 (8), afac173. 10.1093/ageing/afac173 (2022). Epub 2022/08/18. Xu, T. Y. et al. The prevalence and risk factors study of cognitive impairment: Analysis of the elderly population of Han nationality in Hunan province, China. Cns Neuroscience & Therapeutics. 2023 2023 Sep. 10.1111/cns.14478 . Cited in: Pubmed; PMID WOS:001071120700001. Yue-hong, Q. et al. Cognitive Characteristics and Influencing Factors of Mild Cognitive Impairment in Community Elderly. Chin. J. Clin. Psychol. 26 (02), 313–317. 10.16128/j.cnki.1005-3611.2018.02.022 (2018). Li Peng, Z. J. et al. The research on cognitive impairment of community elders in Hongkou district of Shanghai. [J]Stroke Nerv. Dis. 2019 . 26 (06), 697–701 (2019). Petersen, R. C. et al. Practice guideline update summary: Mild cognitive impairment. Neurology 90 (3), 126–135. 10.1212/wnl.0000000000004826 (2018). Siebert, J. S. et al. Attitude toward own aging as a risk factor for cognitive disorder in old age: 12-year evidence from the ILSE study. Psychol. Aging . 33 (3), 461–472. 10.1037/pag0000252 (2018). eng. Epub 2018/05/15. Zhang, Y. F. et al. [Influencing factors of mild cognitive impairment among the Chinese elderly: a meta-analysis]. Zhonghua yi xue za zhi. ; 103 (17):1340–1348. chi. Epub 2023/05/08. (2023). 10.3760/cma.j.cn112137-20220819-01765 . Cited in: Pubmed; PMID 37150685. Xiao-xia, C. et al. Current status and influencing factors of mild cognitive impairment in 1 064 elderly people in rural areas of Shanxi. J. Nurs. 30 (22), 7–12. 10.16460/j.issn1008-9969.2023.22.007 (2023). Fernandez-Blazquez, M. A. et al. Impact of individual and neighborhood dimensions of socioeconomic status on the prevalence of mild cognitive impairment over seven-year follow-up. Aging Ment. Health . 25 (5), 814–823. 10.1080/13607863.2020.1725803 (2021). Epub 2020/02/19. Godinho, F. et al. Effect of education on cognitive performance in patients with mild cognitive impairment. Appl. Neuropsychol. Adult . 29 (6), 1440–1449. 10.1080/23279095.2021.1887191 (2022 Nov-Dec). Epub 2021/03/16. Livingston, G. et al. Dementia prevention, intervention, and care: 2020 report of the Lancet Commission. Lancet (London England) . 396 (10248), 413–446. 10.1016/s0140-6736(20)30367-6 (2020). eng. Epub 2020/08/03. Svendsen, M. T. et al. Associations of health literacy with socioeconomic position, health risk behavior, and health status: a large national population-based survey among Danish adults. BMC public. health . 20 (1), 565. 10.1186/s12889-020-08498-8 (2020). eng. Epub 2020/04/30. Huisman, M. et al. Socioeconomic inequalities in mortality rates in old age in the World Health Organization Europe region. Epidemiol. Rev. 35 , 84–97. 10.1093/epirev/mxs010 (2013). Epub 2013/02/06. Rao, S. et al. Prevalence, cognitive characteristics, and influencing factors of amnestic mild cognitive impairment among older adults residing in an urban community in Chengdu, China. Front. Neurol. 15 10.3389/fneur.2024.1336385 (2024). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Feb, 2026 Reviews received at journal 16 Feb, 2026 Reviewers agreed at journal 28 Dec, 2025 Reviewers agreed at journal 26 Dec, 2025 Reviews received at journal 25 Dec, 2025 Reviewers agreed at journal 14 Dec, 2025 Reviewers invited by journal 09 Dec, 2025 Editor invited by journal 03 Dec, 2025 Editor assigned by journal 02 Dec, 2025 Submission checks completed at journal 02 Dec, 2025 First submitted to journal 01 Dec, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8248590","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":558852552,"identity":"21c488be-cffc-43e0-9d4f-80f1692c9edf","order_by":0,"name":"Dajie Chen","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Dajie","middleName":"","lastName":"Chen","suffix":""},{"id":558852553,"identity":"48ecd8ab-85dd-49fe-bcb1-607ccc81314e","order_by":1,"name":"Cen Gao","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Cen","middleName":"","lastName":"Gao","suffix":""},{"id":558852554,"identity":"f43f1438-9c11-43e2-9aa1-c17b1f4e385e","order_by":2,"name":"Wencai Chen","email":"","orcid":"","institution":"Wuhan Mental Health Center","correspondingAuthor":false,"prefix":"","firstName":"Wencai","middleName":"","lastName":"Chen","suffix":""},{"id":558852555,"identity":"021b4038-5439-4a93-ba5c-935d19e7c30d","order_by":3,"name":"Wenzhen Li","email":"","orcid":"","institution":"The Chinese University of Hong Kong","correspondingAuthor":false,"prefix":"","firstName":"Wenzhen","middleName":"","lastName":"Li","suffix":""},{"id":558852557,"identity":"947b4627-407f-48f9-ac11-647277db0462","order_by":4,"name":"Xiujun Liu","email":"","orcid":"","institution":"Wuhan Mental Health Center","correspondingAuthor":false,"prefix":"","firstName":"Xiujun","middleName":"","lastName":"Liu","suffix":""},{"id":558852558,"identity":"51246a46-de0a-409c-8663-821f876a6386","order_by":5,"name":"Qingzhou Cheng","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Qingzhou","middleName":"","lastName":"Cheng","suffix":""},{"id":558852561,"identity":"20cfa1fc-b03b-40ca-91ac-f68e6b435bb6","order_by":6,"name":"Yameng Feng","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Yameng","middleName":"","lastName":"Feng","suffix":""},{"id":558852563,"identity":"04ea9741-6847-4ec7-8563-26d8c025d69d","order_by":7,"name":"Rong Nie","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Rong","middleName":"","lastName":"Nie","suffix":""},{"id":558852565,"identity":"d526b6c6-1b65-4fa6-afa7-7604a993c287","order_by":8,"name":"Hongping Zhang","email":"","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Hongping","middleName":"","lastName":"Zhang","suffix":""},{"id":558852566,"identity":"07a53982-b296-425c-a7d5-60de84780289","order_by":9,"name":"Hua Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYBACAwYeECkhx8/ewAYROkCUlgoLY8meAyRpOVORuGFGApFazCVyj0n8bJNg3CD5xuxxYRuDHN+NBMbPBXi0WM7IS5PsbZNgNpfOMTee2cZgLHkjgVl6Bj6H3cgxk+Btk2CznJ27TZq3jSFxw40ENmYeAlok/7ZJ8BjcPAvWUk+UFmmeMxISBjd4wVoSDAhqOfPG2FqmQsJAsif/m/SMcxKGM888bJbGq+V4juHNNwZ19f3sx9KkC8ps5PmOJx/8jE8LCmBmYJAAUowNxGoAaxkFo2AUjIJRgAkAP4hHrrAHW2EAAAAASUVORK5CYII=","orcid":"","institution":"Wuhan Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Hua","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2025-12-01 10:08:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8248590/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8248590/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98075257,"identity":"fc9722a9-3fa2-4652-8012-2425c25b62db","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4385809,"visible":true,"origin":"","legend":"","description":"","filename":"MaindocumentsBMC.docx","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/22ba732cdc90d072eb5cf33c.docx"},{"id":98075249,"identity":"d7cf8634-5606-4d5b-b3b0-d434c673d8b1","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10948,"visible":true,"origin":"","legend":"","description":"","filename":"373b9bd71e944a628bcb24c8e3b6b0d4.json","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/4205971c3dc09ca2a862ba86.json"},{"id":98428763,"identity":"380dcf87-7e50-4570-bb65-a746c6b07380","added_by":"auto","created_at":"2025-12-17 16:42:22","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93364,"visible":true,"origin":"","legend":"","description":"","filename":"373b9bd71e944a628bcb24c8e3b6b0d41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/1aa4cd56e8a8fb227d9960fb.xml"},{"id":98429700,"identity":"45d63e52-e3dd-4c0b-9def-dac304374ec5","added_by":"auto","created_at":"2025-12-17 16:44:02","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2154003,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/c2695b1fa94a2f81baf6c439.jpeg"},{"id":98075259,"identity":"6af2e049-e92d-4531-a2a4-57836717c2d0","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4931901,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/f58e4461501d5fa404725bca.jpeg"},{"id":98075253,"identity":"30e0d51d-dc01-4b65-8f1a-b0d7cad86186","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1197423,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/3d4b1661690ac57cf8328337.jpeg"},{"id":98428644,"identity":"185e647f-dcf0-4f07-b2fc-031bdfe27dca","added_by":"auto","created_at":"2025-12-17 16:42:13","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":149830,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/a9d4eff5111a0c2dc6fcc3df.png"},{"id":98430066,"identity":"92679e53-4d6d-44a9-ad01-37c53050b4ae","added_by":"auto","created_at":"2025-12-17 16:44:44","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":516591,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/2679501e0ea37ef77973435e.png"},{"id":98075255,"identity":"a19be66b-0eb4-4939-b956-6c9e44072428","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":120209,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/3edb3465b1a660136fb515ed.png"},{"id":98427054,"identity":"0769d5ba-44fe-480c-9cd9-897d34c20713","added_by":"auto","created_at":"2025-12-17 16:39:22","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92437,"visible":true,"origin":"","legend":"","description":"","filename":"373b9bd71e944a628bcb24c8e3b6b0d41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/1cd2ab92187773da37aca3de.xml"},{"id":98075260,"identity":"8c0f75b6-075b-4b80-92ed-ecc27209726f","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102573,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/8dd063de33f36dc46257d1ab.html"},{"id":98075246,"identity":"59072390-3048-4e93-b5c7-3b44a8c82815","added_by":"auto","created_at":"2025-12-12 13:31:53","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":2584431,"visible":true,"origin":"","legend":"\u003cp\u003eResults of the LASSO regression analysis.\u003c/p\u003e\n\u003cp\u003eA.Tuning parameter (λ) selection cross-validation error curve; B. Plot of the LASSO coefficient profiles. C. LASSO Selected Feature Coefficients; D. Feature Selection Statistics\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/d88848824c8b6bc35d1b67e5.png"},{"id":98429708,"identity":"d1a0393b-e675-4980-bb88-16ac3b9f3646","added_by":"auto","created_at":"2025-12-17 16:44:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":4560634,"visible":true,"origin":"","legend":"\u003cp\u003eMachine learning model performance comparison report.\u003c/p\u003e\n\u003cp\u003eA. ROC Curve Comparison. B. PR Curve Comparison; C. Decision Curve Analysis; D. Calibration Curve; E. Model Performance Metrics Comparison; F. Confusion Matrix.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/09d342477a23ab6ec593ba05.png"},{"id":98429352,"identity":"87a58581-04bf-43f5-bb9f-fb236c81df36","added_by":"auto","created_at":"2025-12-17 16:43:16","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":1187895,"visible":true,"origin":"","legend":"\u003cp\u003eThe effects of the selected variables and model interpretation.\u003c/p\u003e\n\u003cp\u003eA. Forest plot from logistic regression analysis; B. SHAP summary plot for the XGBoost model\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/a8b615dee950af527d73b55f.png"},{"id":98623101,"identity":"a68ec6a8-6528-467b-99b5-b91be6baffde","added_by":"auto","created_at":"2025-12-19 17:04:34","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9102243,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8248590/v1/79a1f75e-4de4-4c14-9d70-a05f71bd092f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Current Status and Risk Factors of Mild Cognitive Impairment among Older Adults in Wuhan: A Machine Learning-Based Analysis","fulltext":[{"header":"Introduction","content":"\u003cp\u003eWith the acceleration of population aging, China\u0026rsquo;s adult population aged\u0026thinsp;\u0026ge;\u0026thinsp;60 years reached 280.04\u0026nbsp;million by the end of 2022, accounting for 19.8% of the total population (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). A large body of research evidence suggests that the prevalence of cognitive impairment will increase with the growth of the older adult population (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). Cognitive impairment is defined as deficits in one or more cognitive functions and can be categorized based on the severity of functional impairment into mild cognitive impairment (MCI) and dementia. MCI is the preclinical stage of dementia and has a high likelihood of transitioning to dementia (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e), with studies documenting that 10%\u0026ndash;15% of patients with MCI progress to dementia each year (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eChina has the largest number of dementia patients in the world, accounting for approximately 25% of the global total (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e). Dementia imposes a heavy economic and social burden on China. Statistics indicate that the direct and indirect costs of treating dementia patients in China amount to trillions of dollars per year (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). Furthermore, relevant studies have indicated that factors such as gender, age, and dietary habits are associated with an increased risk of mild cognitive impairment (MCI) development (\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e). However, due to variations in participants, regions, and research methods, factors such as gender, smoking, alcohol consumption, and sleep disorders have not demonstrated consistent correlations (\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e). China has been exploring the development of dementia-specific prevention and treatment services since 2020 and has carried out cognitive function screening and early intervention for older adults in several regions. Nevertheless, comprehensive investigations on the comprehensive risk factors of large-scale mild cognitive impairment are still scarce in China. To address the inconsistencies and regional differences in previous studies and explore more potential related factors, our research aims to investigate these aspects among the elderly aged 60 and above in different districts of Wuhan. Notably, there has been no relevant research conducted at this specific location before. With a relatively high survey coverage rate, our study investigates the potential related factors of mild cognitive impairment from three aspects: demographic characteristics, behavioral lifestyles, and health status, aiming to identify the risk factors of MCI as clearly as possible and provide a reference for the prevention of MCI and dementia.\u003c/p\u003e"},{"header":"Methods","content":"\u003cp\u003eStudy design and participants\u003c/p\u003e\u003cp\u003eThis study was based on the Basic Public Health Service Program, the Cognitive Function Screening and Early Intervention Program for Older Adults launched by the National Health Commission in 2023, and which has been implemented in hundreds of cities across China, including Wuhan. Cognitive function and health screening was performed by multistage cluster sampling in Caidian, Hanyang, Huangpi, Wuchang, and Xinzhou districts, which were randomly selected as screening areas from the 13 administrative districts of Wuhan. In each of these five districts, we randomly selected two subdistricts. In each subdistrict, we randomly selected two residential (village) committees. In each residential (village) committee, all permanent residents (including those with local household registrations and those who had lived in the city for over half a year) aged 60 and above (born before December 31, 1962) underwent cognitive function and health screening. The following exclusion criteria for MCI screening were adopted: (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) incomplete or questionable data; (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) severe hearing or vision loss preventing the completion of the cognitive assessment; and (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e) confirmed diagnosis of dementia. A total of 2,402 participants from 30 residential (village) committees completed the survey. After excluding survey data with unclear primary records and incomplete information, our final analysis included 2,190 valid samples. The study protocol was approved by the Ethical Review Committee of Wuhan Mental Health Center, and all participants provided written informed consent.\u003c/p\u003e\u003cp\u003eScreening Procedures\u003c/p\u003e\u003cp\u003eAll surveys were completed one-on-one with participants in a quiet environment through home visits by staff from subdistrict community health centers who received uniform training. Participants were first asked to fill out a Basic Information Questionnaire, which included demographic characteristics (gender, age, marital status, occupation, literacy level, monthly income, household size), behavioral lifestyle (smoking, alcohol consumption, exercise days/week), and health status (body mass index (BMI), number of chronic diseases, depression, anxiety, sleep disorders). This was followed by the Resident Mental Health Questionnaire, which used the Patient Health Questionnaire-9 (PHQ-9), Generalized Anxiety Disorder Questionnaire-7 (GAD-7), and Insomnia Severity Index (ISI) scale to assess the mental health and sleep quality of older adults. The psychiatrists then reviewed the diagnoses of participants who screened positive for depression/anxiety and 15% who screened negative. Finally, to assess their cognitive function, participants completed the Community Screening Instrument for Dementia (CSI-D), and the psychiatrists reviewed the diagnoses of those who screened positive for MCI and 15% who screened negative.\u003c/p\u003e\u003cp\u003ePositive screening criteria\u003c/p\u003e\u003cp\u003eAssessment of cognitive function: Researchers from various countries have developed numerous dementia screening scales applicable to different countries and groups. Among which, the CSI-D has displayed good reliability and validity when applied to the Chinese population and has been widely used in China. A total CSI-D score of \u0026le;\u0026thinsp;7 indicates MCI, while a score of \u0026gt;\u0026thinsp;7 indicates no cognitive impairment. Assessment of depression: A PHQ-9 score\u0026thinsp;\u0026gt;\u0026thinsp;4 indicates symptoms of depression. Assessment of anxiety: A GAD-7 score of \u0026gt;\u0026thinsp;4 indicates symptoms of anxiety. Assessment of insomnia: An ISI score of \u0026ge;\u0026thinsp;8 indicates clinically significant insomnia.\u003c/p\u003e\u003cp\u003eModel development and comparison\u003c/p\u003e\u003cp\u003eFirst, R software (glmnet4.1.2) was used to conduct the least absolute shrinkage and selection operator (LASSO) regression analysis and adjust the variable screening and complexity. Subsequently, the screened features were used to develop predictive models. Five ML models namely K Nearest Neighbours (KNN), Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGboost) were used for predicting the occurrence of MCI. Several commonly used evaluation indexes, such as AUC, sensitivity, specificity, PPV, negative predictive value(NPV), accuracy, and F1 score, were used to evaluate the reliability of these models. Furthermore, a DCA was carried out to evaluate the utility of the decision models by quantifying the net benefit across different threshold probabilities. A binary logistic regression model was applied to analyze the risk factors for MCI, in which the dependent variable was the presence of MCI (yes/no),\u003c/p\u003e\u003cp\u003eModel explanation\u003c/p\u003e\u003cp\u003eThe SHapley Additive exPlanations (SHAP) method offered global and local explanations for the model explanation. The global explanation could give consistent and accurate attribution values for each feature within a model to show the associations between input features and MCI. The local explanation could demonstrate a specific prediction for individual patients by inputting the specific data.\u003c/p\u003e\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003eStatistical analysis\u003c/h2\u003e\u003cp\u003eStatistical analyses were performed using SPSS 27.0 (IBM Corp.). and R (R version 4.5.1). Continuous variables were expressed as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation (SD), and categorical variables were expressed as frequency (percentage). Statistical inference for categorical variables was performed using the χ\u0026sup2; test. The predictive power was evaluated using the AUC, with the optimal cut-off value determined by maximizing the Youden index (sensitivity\u0026thinsp;+\u0026thinsp;specificity-1). All tests were two-sided, and statistical significance was set at P\u0026thinsp;\u0026lt;\u0026thinsp;0.05.\u003c/p\u003e\u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e1. General demographics of the screening population and distribution of MCI detected\u003c/p\u003e\u003cp\u003eThe 2,190 participants included 821 males (60\u0026ndash;95 years; mean age: 69.75\u0026thinsp;\u0026plusmn;\u0026thinsp;6.05 years) and 1,369 females (60\u0026ndash;95 years; mean age: 69.35\u0026thinsp;\u0026plusmn;\u0026thinsp;6.75 years). Among the total screening population, 1,417 participants had normal cognitive function, and 773 (detection rate: 35.3%) screened positive for MCI, including 486 women (detection rate: 35.5%) and 287 men (detection rate: 35.0%).\u003c/p\u003e\u003cp\u003eExcept for gender (χ\u0026sup2;=0.051, p\u0026thinsp;=\u0026thinsp;0.822), between-group differences in the detection rate of MCI were observed for all other demographic characteristic groups (all groups p\u0026thinsp;\u0026lt;\u0026thinsp;0.05). The detection rate tended to increase with age, and older individuals had a higher detection rate (χ\u0026sup2;=46.567, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). Widowed older adults (χ\u0026sup2;= 28.561, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and farmers (χ\u0026sup2;=55.569, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) had the highest detection rate (47.4% and 42.7%, respectively). The detection rate tended to decrease with increasing literacy (χ\u0026sup2;=111.559, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001) and monthly income (χ\u0026sup2;= 85.264, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). In addition, a significant difference was observed in the detection rate among households with different sizes (χ\u0026sup2;=10.688, p\u0026thinsp;=\u0026thinsp;0.014). The distribution of positive MCI screening results among groups with different demographic characteristics is presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDemographics of the screening population and distribution of MCI detected\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDemographic characteristics\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eN(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMCI (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003ep\u003c/em\u003e value\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTotal population\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e773(35.3)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eGender\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.822\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFemale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1370(62.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e486(35.47)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMale\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e820(37.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e287(35.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge groups (years)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e60\u0026thinsp;~\u0026thinsp;64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e560(25.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e167(29.82)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e65\u0026thinsp;~\u0026thinsp;69\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e696(31.78)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e211(30.32)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e70\u0026thinsp;~\u0026thinsp;74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e468(21.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e173(36.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026ge;\u0026thinsp;75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e466(21.28)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e222(47.64)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMarital status\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSingle\u0026zwnj;\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e30(1.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11(36.67)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMarried\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1758(80.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e576(32.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSeparated/Divorced\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e35(1.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e12(34.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWidowed\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e367(16.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e174(47.41)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOccupation\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTechnical personnel\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e392(17.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e99(25.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eRetirement\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e427(19.50)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e115(26.93)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFarmer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e967(44.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e413(42.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBusiness/service personnel\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e150(6.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e48(32.00)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOthers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e254(11.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e98(38.58)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLiteracy level\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eIlliterate\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e530(24.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e266(50.19)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eElementary\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e547(24.98)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e226(41.32)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMiddle school\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e591(26.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e161(27.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHigh school and above\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e522(23.83)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e120(22.99)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMonthly income\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0-1499 RMB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1196(54.61)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e521(43.56)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1500\u0026ndash;2999 RMB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e326(14.89)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e99(30.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3000\u0026ndash;4999 RMB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e541(24.70)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e129(23.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026ge;\u0026thinsp;5000 RMB\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e127(5.80)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e24(18.90)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFamily size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.014\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e298(13.60)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e127(42.62)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e881(40.23)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e285(32.35)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u0026thinsp;~\u0026thinsp;7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e941(42.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e334(35.49)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e70(3.20)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e27(38.57)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSmoking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e459(20.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e185(40.31)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1731(79.04)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e588(33.97)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDrinking\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.301\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e344(15.71)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e113(32.85)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1846(84.29)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e660(35.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eExercise days/week\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.008\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e937(42.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e365(38.95)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u0026thinsp;~\u0026thinsp;5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e106(4.84)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e35(33.02)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1147(52.37)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e373(32.52)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eBMI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.185\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUnderweight\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e126(5.75)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e52(41.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNormal\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1211(55.30)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e440(36.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eOverweight\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e628(28.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e204(32.48)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eObesity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e225(10.27)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e77(34.22)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNumber of chronic diseases\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e718(32.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e218(30.36)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e800(36.53)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e284(35.5)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026ge;\u0026thinsp;2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e672(30.68)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e271(40.33)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDepression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e170(7.76)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e81(47.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2020(92.24)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e692(34.26)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAnxiety\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.195\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e136(6.21)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e55(40.44)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2054(93.79)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e718(34.96)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSleep disorders\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eYes\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e496(22.65)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e219(44.15)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNo\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1694(77.35)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e554(32.7)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eAmong this screening population, 459 (21.96%) were smokers, and 344 (15.71%) consumed alcohol. A total of 937 (42.79%) participants exercised\u0026thinsp;\u0026lt;\u0026thinsp;3 days per week, 106 (4.84%) exercised 3\u0026ndash;5 days per week, and 1147 (52.37%) exercised\u0026thinsp;\u0026gt;\u0026thinsp;5 days per week.As indicated in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, the detection rate of MCI was higher among smokers than non-smokers (χ\u0026sup2;=6.378, p\u0026thinsp;=\u0026thinsp;0.012). Alcohol consumption had no significant effect on the detection of MCI in older adults (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05). The detection rate among older adults tended to decrease with increasing exercise days/week, and between-group differences in the detection rate were observed (χ\u0026sup2;=9.602, p\u0026thinsp;=\u0026thinsp;0.008).\u003c/p\u003e\u003cp\u003eAmong this screening population, 126 (5.75%) were underweight, 1,211 (55.30%) had a normal BMI, 628 (28.68%) were overweight, and 225 (10.27%) were obese. In addition, 718 (32.78%) participants did not suffer from chronic diseases, 800 (36.53%) from one chronic disease, and 672 (30.68%) from two or more chronic diseases. The detection rates of depression, anxiety, and sleep disorders were 7.76%, 6.21%, and 22.65%, respectively.\u003c/p\u003e\u003cp\u003eAs indicated in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, the detection rate of MCI among older adults increased as the number of chronic diseases increased. The detection rate was higher among older adults with depressive symptoms than among those without such symptoms (χ\u0026sup2;=12.309, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). The detection rate was also higher among individuals with sleep disorders than those without (χ\u0026sup2;=22.023, p\u0026thinsp;\u0026lt;\u0026thinsp;0.001). No significant difference was observed in the detection rate among participants with different health status in terms of BMI (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05) and anxiety (p\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e\n\u003ch3\u003eFactor selection for the predictive model\u003c/h3\u003e\n\u003cp\u003eLASSO regression analysis was conducted on the remaining independent variables, with MCI serving as the dependent variable (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). To increase the interpretability of the model and mitigate the risk of over fitting, The results showed (lambda\u0026thinsp;=\u0026thinsp;0.0404, The maximum lambda within one standard error of the minimum error), that 33 independent variables were reduced to 5, including aged above 75, farmer, sleep disorders and higher literacy level (middle school and high school and above).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eA.Tuning parameter (λ) selection cross-validation error curve; B. Plot of the LASSO coefficient profiles. C. LASSO Selected Feature Coefficients; D. Feature Selection Statistics\u003c/p\u003e\n\u003ch3\u003eThe best model building and external evaluation\u003c/h3\u003e\n\u003cp\u003eComprehensive analysis of classified multi-model XGBoost, LR, RF, SVM, and KNN were trained and repeated 10 times. The models were evaluated using AUC values, which showed that XGBoost were highest in the validation set (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eA). The AUC indicator focuses on the predictive accuracy of the model and does not tell whether the model is clinically usable or which one of the two is preferable. Therefore, the DCA, calibration curves, and PR curves were analyzed. (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003eB - F ). Taken together, these findings suggest that the XGBoost model was the most desirable model for this study.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eA. ROC Curve Comparison. B. PR Curve Comparison; C. Decision Curve Analysis; D. Calibration Curve; E. Model Performance Metrics Comparison; F. Confusion Matrix.\u003c/p\u003e\u003cp\u003eLogistic regression analysis and tenfold cross-validation were performed on internal validation set, the results show an average AUC of 0.671 (0.619\u0026ndash;0.725), which is slightly lower than that of the XGBoost model at 0.693 (0.642\u0026ndash;0.745). Therefore, we employed the LR model to assess the effect sizes of the variables incorporated into the model (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA). The results demonstrated that sleep disorders and age over 75 years were significantly positively associated with the occurrence of MCI. with OR values of 1.44 (95%CI: 1.13\u0026ndash;1.82) and 1.52 (95%CI: 1.12\u0026ndash;2.08), respectively. Higher literacy level is a protective factor against MCI, with odds ratios of 0.48 for middle school and 0.39 for high school and above.\u003c/p\u003e\u003cp\u003eForest plot from logistic regression analysis; B. SHAP summary plot for the XGBoost model\u003c/p\u003e\n\u003ch3\u003eModel explanation\u003c/h3\u003e\n\u003cp\u003eTo visually elucidate the selected variables, SHAP was utilized to illustrate how these variables predict the occurrence of MCI in the XGBoost model (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB). Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB depicts the four most important features (sleep disorders, age, occupation, and literacy level) in our model, the latter three are categorical variables with multiple levels and were coded as dummy variables in the model. Each feature significance line showcases all patient attributions for the outcome, represented by differently colored dots: red dots indicate high-risk values, while blue dots denote low-risk values. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB displays the ranking of the five risk factors assessed by mean absolute SHAP value, with the x-axis SHAP value indicating the importance of the predictive model. Therefore, in the predictive model, literacy level and sleep disorders represent the most critical predictors, whereas advanced age and occupation serve as important auxiliary variables.\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eTo the best of our knowledge, this study is the first to analyze the prevalence of MCI among individuals aged 60 and above in Wuhan, and to explore the risk factors for MCI among older adults from three aspects: demographic characteristics, behavioral lifestyles, and health status.\u003c/p\u003e\u003cp\u003eOur findings revealed that the detection rate of MCI among Wuhan residents was 35.3%, which was relatively high in China. A meta-analysis published in 2021 that included 41 observational studies documented that the prevalence of MCI among individuals in Chinese urban communities was 12.2% (95% CI: 10.6\u0026ndash;14.2%) (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). In 2020, a large cross-sectional study involving 12 provinces in China established that the overall prevalence of MCI among Chinese adults aged 60 years and older was 15.54% (95% CI: 15.21\u0026ndash;15.88) (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e). Although the prevalence of MCI varies across different countries and regions, ranging from 4.3% to 39.1% (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e), that among residents of Wuhan is still relatively high when compared with international data. For instance, a meta-analysis published in 2022 that included 66 articles involving 242,804 participants determined that the overall global prevalence of MCI among community-dwelling individuals aged 50 years and older was 15.56% (95% CI: 13.24\u0026ndash;18.03%) (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e). The significant differences in MCI detection rates across various countries and regions may be attributed not only to the inherent specificity in MCI risk that truly exists among different regions and ethnic groups, but also to the use of different screening tools in different studies (such as the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), Ascertain Dementia 8 (AD8), and CSI-D, etc.). Since MCI is an early stage of dementia, to shift the focus of prevention and treatment forward is critical. Moreover, given the high detection rate of MCI in Wuhan, analyzing the risk factors of MCI and emphasizing prevention on interventions targeting these factors is of considerable significance so as to achieve the prevention and control of MCI in Wuhan.\u003c/p\u003e\u003cp\u003eOur findings revealed five risk factors for MCI, with advanced age being a non-modifiable risk factor. Older age was associated with a higher risk of MCI, and this finding has been confirmed in many studies (\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e). In a cohort study with a 12-year follow-up (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e), the effect of age on cognitive impairment was associated with gray matter in the medial prefrontal cortex of the brain. The brain tissue in this region gradually atrophied with increasing age, which led to a significant decline in brain function (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e), and a particularly pronounced decline in neurological function. In addition, advanced age is a risk factor for chronic diseases such as hypertension and diabetes mellitus (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e), which can jeopardize the vascular and nervous systems, thus leading to cognitive decline in older adults (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eMore importantly, this study identified three modifiable risk factors: literacy level, occupation and sleep disorders. Literacy and occupation are the main indicators of socioeconomic status, and individuals with higher levels of these displayed a lower risk of MCI, which is consistent with the results of numerous studies (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e). According to cognitive reserve theory, a higher socioeconomic status can increase the brain\u0026rsquo;s cognitive reserve by increasing cognitive stimulation for cortical development, thereby rendering the individual less susceptible to evident cognitive decline (\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e); these regular and sustained stimuli also play a role in preventing the loss of neuronal connectivity and/or strengthening neuronal associations, which can compensate for neuropathological impairments related to aging, thus preventing or slowing the development of MCI (\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e). Health effects caused by socioeconomic inequalities have always existed (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e), and have a cumulative effect, which is more prominent in old age. Early studies determined that socioeconomic factors are determinants of quality of life among older adults (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e); those with low socioeconomic status are less likely to have access to appropriate nutrition and healthcare resources, frequently delaying medical consultation and thus failing to detect and intervene in MCI in time. Therefore, relevant government departments should pay more attention to older adults with low literacy and income levels, with a special emphasis on livelihood and healthcare security.\u003c/p\u003e\u003cp\u003eThis study comprehensively explores the risk factors of MCI among older adults from three aspects: demographic characteristics, behavioral lifestyle, and health status, which serves as a reference for the early identification of high-risk groups and provides evidence for the early screening of MCI. However, this study has the following limitations. First, given the cross-sectional design, no causal relationship can be established. Further prospective studies should be conducted through a cohort design to clarify the causal association. Second, all variables in the questionnaire were self-reported; hence, our findings may be affected by recall bias and social expectations. Third, our samples were selected from Wuhan, the generalizability of our findings may be somewhat constrained. Samples from more regions with varying economic development levels and different distributions of medical resources should be included in future studies. In addition, the present study used the CSI-D for detecting MCI. As a rapid screening tool, the CSI-D primarily focuses on the initial identification of abnormal cognitive function and lacks detailed assessments of specific cognitive domains. Therefore, it is difficult to precisely distinguish the subtle differences between MCI, dementia, and normal aging.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn Wuhan, the prevalence of MCI among adults aged 60 years and above is relatively high and is becoming an important public health issue that needs special attention. Wuhan\u0026rsquo;s health administrative departments and healthcare providers should formulate policies and implement measures to strengthen activities related to the early screening, diagnosis, and treatment of MCI. In addition, the key targets of such screening are individuals with advanced age, low literacy, low income, smoking habit, and sleep disorders. To ensure early detection, diagnosis, and treatment, adequate attention and care should be given to these groups to strengthen screening intervention, thereby slowing or reducing the occurrence of MCI.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003emild cognitive impairment (MCI)\u003c/p\u003e\n\u003cp\u003eCommunity Screening Instrument for Dementia (CSI-D)\u003c/p\u003e\n\u003cp\u003ebody mass index (BMI)\u003c/p\u003e\n\u003cp\u003ePatient Health Questionnaire-9 (PHQ-9)\u003c/p\u003e\n\u003cp\u003eGeneralized Anxiety Disorder Questionnaire-7 (GAD-7)\u003c/p\u003e\n\u003cp\u003eInsomnia Severity Index (ISI)\u003c/p\u003e\n"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eSupplementary Information\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgment\u003c/strong\u003e\u0026nbsp; \u0026nbsp; The authors are grateful to the help of staffs at subdistrict community health centers and the cooperation of participants in the screening area.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor contributions\u0026nbsp;\u003c/strong\u003e\u0026nbsp; Wencai Chen, Xiujun Liu were responsible for the draft of the protocol and recruitment of participants. Dajie Chen, Qingzhou Cheng, Rong Nie and Hongping Zhang contributed to formulating the research question. Hua Hu and Cen Gao analyzed the data and wrote the initial draft of the manuscript, Wenzhen Li revised the manuscript which was commented on and edited by all co-authors. Yameng Feng produced the tables and figures. All authors had access to all data, have approved the final manuscript and accept responsibility for submission for publication.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u0026nbsp;\u003c/strong\u003e\u0026nbsp; The Funding for Scientific Research Projects from Wuhan Municipal Health Commission (NO.WX23B34), Science and Technology Research Project of Education Department of Hubei Province (NO. Q20221604); University Scientific Research Fund of Wuhan Polytechnic University (NO. 2022Y37).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData of Availability:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets generated and/or analyzed during the current study are not publicly available due to privacy and confidentiality concerns regarding sensitive personal information, but are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eEthical approval for this research was obtained from the Ethical Review Committee of Wuhan Mental Health Center (KY2023.0412.03), ethical standards are in accordance with the Declaration of Helsinki. Before survey initiation, informed consent was secured from all participants.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u0026nbsp; \u0026nbsp; Not applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eChina Statistical Yearbook. (2023-04-23). (2023). Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.stats.gov.cn/sj/ndsj/2023/indexch.htm\u003c/span\u003e\u003cspan address=\"https://www.stats.gov.cn/sj/ndsj/2023/indexch.htm\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eNichols, E. et al. Estimation of the global prevalence of dementia in 2019 and forecasted prevalence in 2050: an analysis for the Global Burden of Disease Study 2019. \u003cem\u003eLancet Public. health\u003c/em\u003e. \u003cb\u003e7\u003c/b\u003e (2), E105\u0026ndash;E125. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s2468-2667(21)00249-8\u003c/span\u003e\u003cspan address=\"10.1016/s2468-2667(21)00249-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022). Cited in: Pubmed; PMID WOS:000763474800008.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eOverton, M. et al. Prevalence and Incidence of Mild Cognitive Impairment across Subtypes, Age, and Sex. Dementia and geriatric cognitive disorders. ;47(4\u0026ndash;6):219\u0026ndash;232. eng. Epub 2019/07/17. (2019). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1159/000499763\u003c/span\u003e\u003cspan address=\"10.1159/000499763\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited in: Pubmed; PMID 31311017.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBrodaty, H. et al. Progression from mild cognitive impairment to dementia: a 3-year longitudinal study. \u003cem\u003eAust. N. Z. J. Psychiatry\u003c/em\u003e. \u003cb\u003e48\u003c/b\u003e (12), 1137\u0026ndash;1142. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1177/0004867414536237\u003c/span\u003e\u003cspan address=\"10.1177/0004867414536237\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2014). eng. Epub 2014/05/24.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eP SL, et al. Prevalence and distribution trends of mild cognitive impairment among Chinese older adults: a Meta-analysis. [J] Chinese General Practice, 25 (1): 109\u0026ndash;114. 2022;25(01):109\u0026ndash;114. (2022).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFeigin, V. L. et al. Global, regional, and national burden of neurological disorders, 1990\u0026ndash;2016: a systematic analysis for the Global Burden of Disease Study 2016. \u003cem\u003eLancet Neurol.\u003c/em\u003e \u003cb\u003e18\u003c/b\u003e (5), 459\u0026ndash;480. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s1474-4422(18)30499-x\u003c/span\u003e\u003cspan address=\"10.1016/s1474-4422(18)30499-x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2019). Cited in: Pubmed; PMID WOS:000464140400014.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCampbell, N. L. et al. Risk Factors for the Progression of Mild Cognitive Impairment to Dementia. \u003cem\u003eClin. Geriatr. Med.\u003c/em\u003e \u003cb\u003e29\u003c/b\u003e (4), 873\u0026ndash;. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cger.2013.07.009\u003c/span\u003e\u003cspan address=\"10.1016/j.cger.2013.07.009\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013). Cited in: Pubmed; PMID WOS:000326659400009.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePeltz, C. B. et al. Cognitive impairment in nondemented oldest-old: Prevalence and relationship to cardiovascular risk factors. \u003cem\u003eAlzheimers Dement.\u003c/em\u003e \u003cb\u003e8\u003c/b\u003e (2), 87\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.jalz.2011.02.008\u003c/span\u003e\u003cspan address=\"10.1016/j.jalz.2011.02.008\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2012). Cited in: Pubmed; PMID WOS:000301991600001.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eValenza, S. et al. Mild Cognitive Impairment Subtypes and Type 2 Diabetes in Elderly Subjects. \u003cem\u003eJ. Clin. Med.\u003c/em\u003e \u003cb\u003e9\u003c/b\u003e (7). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jcm9072055\u003c/span\u003e\u003cspan address=\"10.3390/jcm9072055\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020). Cited in: Pubmed; PMID WOS:000558058200001.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLu, Y. et al. Prevalence of mild cognitive impairment in community-dwelling Chinese populations aged over 55 years: a meta-analysis and systematic review. BMC geriatrics. ;21(1):10. eng. Epub 2021/01/08. (2021). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12877-020-01948-3\u003c/span\u003e\u003cspan address=\"10.1186/s12877-020-01948-3\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited in: Pubmed; PMID 33407219.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJia, 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. \u003cem\u003eLancet Public. health\u003c/em\u003e. \u003cb\u003e5\u003c/b\u003e (12), e661\u0026ndash;e671. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S2468-2667(20)30185-7\u003c/span\u003e\u003cspan address=\"10.1016/S2468-2667(20)30185-7\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020). Epub 2020/12/04.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLiu, L. Y. et al. Prevalence, risk and protective factors for mild cognitive impairment in a population-based study of Singaporean elderly. \u003cem\u003eJ. Psychiatr. Res.\u003c/em\u003e \u003cb\u003e145\u003c/b\u003e, 111\u0026ndash;117 (2021). Cited in: Pubmed; PMID 34894520.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSachdev, P. S. et al. Risk profiles for mild cognitive impairment vary by age and sex: the Sydney Memory and Ageing study. The American journal of geriatric psychiatry: official journal of the American Association for Geriatric Psychiatry. ;20(10):854\u0026thinsp;\u0026ndash;\u0026thinsp;65. eng. Epub 2012/06/08. (2012). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/JGP.0b013e31825461b0\u003c/span\u003e\u003cspan address=\"10.1097/JGP.0b013e31825461b0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited in: Pubmed; PMID 22673190.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBai, W. et al. Worldwide prevalence of mild cognitive impairment among community dwellers aged 50 years and older: a meta-analysis and systematic review of epidemiology studies. \u003cem\u003eAge Ageing\u003c/em\u003e. \u003cb\u003e51\u003c/b\u003e (8), afac173. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/ageing/afac173\u003c/span\u003e\u003cspan address=\"10.1093/ageing/afac173\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022). Epub 2022/08/18.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXu, T. Y. et al. The prevalence and risk factors study of cognitive impairment: Analysis of the elderly population of Han nationality in Hunan province, China. Cns Neuroscience \u0026amp; Therapeutics. 2023 2023 Sep. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1111/cns.14478\u003c/span\u003e\u003cspan address=\"10.1111/cns.14478\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited in: Pubmed; PMID WOS:001071120700001.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eYue-hong, Q. et al. Cognitive Characteristics and Influencing Factors of Mild Cognitive Impairment in Community Elderly. \u003cem\u003eChin. J. Clin. Psychol.\u003c/em\u003e \u003cb\u003e26\u003c/b\u003e (02), 313\u0026ndash;317. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.16128/j.cnki.1005-3611.2018.02.022\u003c/span\u003e\u003cspan address=\"10.16128/j.cnki.1005-3611.2018.02.022\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLi Peng, Z. J. et al. The research on cognitive impairment of community elders in Hongkou district of Shanghai. \u003cem\u003e[J]Stroke Nerv. Dis. 2019\u003c/em\u003e. \u003cb\u003e26\u003c/b\u003e (06), 697\u0026ndash;701 (2019).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePetersen, R. C. et al. Practice guideline update summary: Mild cognitive impairment. \u003cem\u003eNeurology\u003c/em\u003e \u003cb\u003e90\u003c/b\u003e (3), 126\u0026ndash;135. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1212/wnl.0000000000004826\u003c/span\u003e\u003cspan address=\"10.1212/wnl.0000000000004826\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSiebert, J. S. et al. Attitude toward own aging as a risk factor for cognitive disorder in old age: 12-year evidence from the ILSE study. \u003cem\u003ePsychol. Aging\u003c/em\u003e. \u003cb\u003e33\u003c/b\u003e (3), 461\u0026ndash;472. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1037/pag0000252\u003c/span\u003e\u003cspan address=\"10.1037/pag0000252\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2018). eng. Epub 2018/05/15.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eZhang, Y. F. et al. [Influencing factors of mild cognitive impairment among the Chinese elderly: a meta-analysis]. Zhonghua yi xue za zhi. ;\u003cb\u003e103\u003c/b\u003e(17):1340\u0026ndash;1348. chi. Epub 2023/05/08. (2023). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3760/cma.j.cn112137-20220819-01765\u003c/span\u003e\u003cspan address=\"10.3760/cma.j.cn112137-20220819-01765\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. Cited in: Pubmed; PMID 37150685.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eXiao-xia, C. et al. Current status and influencing factors of mild cognitive impairment in 1 064 elderly people in rural areas of Shanxi. \u003cem\u003eJ. Nurs.\u003c/em\u003e \u003cb\u003e30\u003c/b\u003e (22), 7\u0026ndash;12. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.16460/j.issn1008-9969.2023.22.007\u003c/span\u003e\u003cspan address=\"10.16460/j.issn1008-9969.2023.22.007\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2023).\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFernandez-Blazquez, M. A. et al. Impact of individual and neighborhood dimensions of socioeconomic status on the prevalence of mild cognitive impairment over seven-year follow-up. \u003cem\u003eAging Ment. Health\u003c/em\u003e. \u003cb\u003e25\u003c/b\u003e (5), 814\u0026ndash;823. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/13607863.2020.1725803\u003c/span\u003e\u003cspan address=\"10.1080/13607863.2020.1725803\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2021). Epub 2020/02/19.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eGodinho, F. et al. Effect of education on cognitive performance in patients with mild cognitive impairment. \u003cem\u003eAppl. Neuropsychol. Adult\u003c/em\u003e. \u003cb\u003e29\u003c/b\u003e (6), 1440\u0026ndash;1449. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1080/23279095.2021.1887191\u003c/span\u003e\u003cspan address=\"10.1080/23279095.2021.1887191\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2022 Nov-Dec). Epub 2021/03/16.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLivingston, G. et al. Dementia prevention, intervention, and care: 2020 report of the Lancet Commission. \u003cem\u003eLancet (London England)\u003c/em\u003e. \u003cb\u003e396\u003c/b\u003e (10248), 413\u0026ndash;446. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/s0140-6736(20)30367-6\u003c/span\u003e\u003cspan address=\"10.1016/s0140-6736(20)30367-6\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020). eng. Epub 2020/08/03.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSvendsen, M. T. et al. Associations of health literacy with socioeconomic position, health risk behavior, and health status: a large national population-based survey among Danish adults. \u003cem\u003eBMC public. health\u003c/em\u003e. \u003cb\u003e20\u003c/b\u003e (1), 565. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12889-020-08498-8\u003c/span\u003e\u003cspan address=\"10.1186/s12889-020-08498-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2020). eng. Epub 2020/04/30.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eHuisman, M. et al. Socioeconomic inequalities in mortality rates in old age in the World Health Organization Europe region. \u003cem\u003eEpidemiol. Rev.\u003c/em\u003e \u003cb\u003e35\u003c/b\u003e, 84\u0026ndash;97. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/epirev/mxs010\u003c/span\u003e\u003cspan address=\"10.1093/epirev/mxs010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2013). Epub 2013/02/06.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRao, S. et al. Prevalence, cognitive characteristics, and influencing factors of amnestic mild cognitive impairment among older adults residing in an urban community in Chengdu, China. \u003cem\u003eFront. Neurol.\u003c/em\u003e \u003cb\u003e15\u003c/b\u003e \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fneur.2024.1336385\u003c/span\u003e\u003cspan address=\"10.3389/fneur.2024.1336385\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Older adults, MCI Screening, Risk factors, Prevalence, Cross-sectional study","lastPublishedDoi":"10.21203/rs.3.rs-8248590/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8248590/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e\u003cp\u003eThis study seeks to understand the current situation of mild cognitive impairment (MCI) in Wuhan, explore the related risk factors, and identify high-risk groups.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e\u003cp\u003e Multistage cluster sampling was adopted to recruit a total of 2,190 adults aged 60 years and above from 30 residential (village) committees in 13 administrative districts. They were screened for MCI using the Community Screening Instrument for Dementia (CSI-D).The Least Absolute Shrinkage and Selection Operator (LASSO) was employed to screen predictive variables. A variety of machine learning classification models were integrated to analyze and identify the optimal model. Multiple evaluation indicators were utilized to compare the performance of models, including the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA). Binary logistic regression was adopted to determine the effect values of risk factors, and SHapley Additive ex Planations (SHAP) was applied to interpret machine learning models.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e\u003cp\u003e35.3% participants were diagnosed with MCI. The Final model included age, occupation, sleep disorders and literacy level. Based on the AUC and DCA in the validation group, the XGBoost model demonstrated excellent performance, the most crucial features in this model and their effect values as follows: sleep disorders (OR: 1.44, 95%CI: 1.31\u0026ndash;1.82), aged above 75 (OR: 1.52, 95%CI: 1.12\u0026ndash;2.08), High school and above (OR: 0.39, 95%CI: 0.28\u0026ndash;0.56), Middle school (OR: 0.48, 95%CI: 0.35\u0026ndash;0.65), Farmers were included but without significant effect.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e\u003cp\u003eThe current status of MCI among older adults in Wuhan is not optimistic. Therefore, early screening and intervention should be carried out for farmers and individuals with advanced age, low literacy,and sleep disorders.\u003c/p\u003e","manuscriptTitle":"Current Status and Risk Factors of Mild Cognitive Impairment among Older Adults in Wuhan: A Machine Learning-Based Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-12 13:31:48","doi":"10.21203/rs.3.rs-8248590/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-20T07:39:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-16T07:19:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"162506994653319046675020497916284044273","date":"2025-12-28T19:51:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"63322586430993794972807106215306352131","date":"2025-12-26T14:47:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-25T08:12:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"221056605792270467773971443494797186462","date":"2025-12-14T13:48:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-09T13:03:40+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-12-03T06:50:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-02T12:13:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-02T12:08:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-12-01T09:20:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4bcce99b-8009-42e4-8803-bbb9679eff8a","owner":[],"postedDate":"December 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":59492961,"name":"Health sciences/Diseases"},{"id":59492962,"name":"Health sciences/Health care"},{"id":59492963,"name":"Health sciences/Medical research"},{"id":59492964,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-05-20T04:23:27+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-12 13:31:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8248590","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8248590","identity":"rs-8248590","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}