Search

Abstract Background Diet and chronic inflammation might play a major role in the pathogenesis of mild cognitive impairment (MCI). In addition, peripheral blood leukocyte telomere length (LTL) and mitochondrial DNA copy number (mtDNAcn) might mediate the relationship between inflammation and MCI risk. The purpose of the present study is to evaluate whether inflammatory potential of diet assessed by dietary inflammatory index (DII), chronic inflammation, peripheral blood LTL, and mtDNAcn were associated with the risk of MCI. Results A population-based cohort study was conducted with a total of 2944 participants. During a median follow-up of 2 years, 438 (14.90%) individuals were new-onset MCI. After adjustment, a higher score of DII (hazard ratio [HR]: 1.056, 95% CI: 1.005, 1.109), a higher log systemic immune inflammation index (SII) (HR: 1.333, 95% CI: 1.089, 1.633) and log system inflammation response index (SIRI) (HR: 1.487, 95% CI: 1.024, 2.161) predicted elevated risk of MCI. An increased mtDNAcn (HR: 0.843, 95% CI: 0.712, 0.997), but not LTL, predicted a decreased risk of MCI. Negative associations of log SII with LTL (β:-0.359, 95% CI: -0.445, -0.273) and mtDNAcn (β:-0.048, 95% CI: -0.090, -0.006) were found. Additionally, negative associations of log SIRI with LTL (β: -0.035, 95% CI: -0.052, -0.017) and mtDNAcn (β:-0.136, 95% CI: -0.216, -0.056) were also found. Path analysis suggested that SIRI, LTL, and mtDNAcn, in series, have mediation roles in the association between DII score and MCI risk. Conclusions Higher DII, SII, and SIRI might predict a greater risk of MCI, while a longer LTL and an increased mtDNAcn were linked to a reduced risk of MCI among the older population. LTL and mtDNAcn could play mediation roles in the association between DII and MCI risk.

BackgroundCarotid plaque can progress into stroke, myocardial infarction, etc, which are major global causes of death. Evidence shows a significant increase in carotid plaque incidence among patients with fatty liver disease. However, unlike the high detection rate of fatty liver disease, screening for carotid plaque in the asymptomatic population is not yet prevalent due to cost-effectiveness reasons, resulting in a large number of patients with undetected carotid plaques, especially among those with fatty liver disease. ObjectiveThis study aimed to combine the advantages of machine learning (ML) and logistic regression to develop a straightforward prediction model among the population with fatty liver disease to identify individuals at risk of carotid plaque. MethodsOur study included 5,420,640 participants with fatty liver from Meinian Health Care Center. We used random forest, elastic net (EN), and extreme gradient boosting ML algorithms to select important features from potential predictors. Features acknowledged by all 3 models were enrolled in logistic regression analysis to develop a carotid plaque prediction model. Model performance was evaluated based on the area under the receiver operating characteristic curve, calibration curve, Brier score, and decision curve analysis both in a randomly split internal validation data set, and an external validation data set comprising 32,682 participants from MJ Health Check-up Center. Risk cutoff points for carotid plaque were determined based on the Youden index, predicted probability distribution, and prevalence rate of the internal validation data set to classify participants into high-, intermediate-, and low-risk groups. This risk classification was further validated in the external validation data set. ResultsAmong the participants, 26.23% (1,421,970/5,420,640) were diagnosed with carotid plaque in the development data set, and 21.64% (7074/32,682) were diagnosed in the external validation data set. A total of 6 features, including age, systolic blood pressure, low-density lipoprotein cholesterol (LDL-C), total cholesterol, fasting blood glucose, and hepatic steatosis index (HSI) were collectively selected by all 3 ML models out of 27 predictors. After eliminating the issue of collinearity between features, the logistic regression model established with the 5 independent predictors reached an area under the curve of 0.831 in the internal validation data set and 0.801 in the external validation data set, and showed good calibration capability graphically. Its predictive performance was comprehensively competitive compared with the single use of either logistic regression or ML algorithms. Optimal predicted probability cutoff points of 25% and 65% were determined for classifying individuals into low-, intermediate-, and high-risk categories for carotid plaque. ConclusionsThe combination of ML and logistic regression yielded a practical carotid plaque prediction model, and was of great public health implications in the early identification and risk assessment of carotid plaque among individuals with fatty liver.

Background: Non-alcoholic fatty liver disease (NAFLD) is one of the most common liver diseases worldwide. Currently, most NAFLD prediction models are diagnostic models based on cross-sectional data, which failed to provide early identification or clarify causal relationships. We aimed to use time-series deep learning models with longitudinal health checkup records to predict the onset of NAFLD in the future, and update the model stepwise by incorporating new checkup records to achieve dynamic prediction. Methods: 10,493 participants with over 6 health checkup records from Beijing MJ Health Screening Center were included to conduct a retrospective cohort study, in which the constantly updated initial 5 checkup data were incorporated stepwise to predict the risk of NAFLD at and after their sixth health checkups. A total of 33 variables were considered, consisting of demographic characteristics, medical history, lifestyle, physical examinations, and laboratory tests. L1-penalized logistic regression (LR) was used for feature selection. The long short-term memory (LSTM) algorithm was introduced for model development, and five-fold cross-validation was conducted to tune and choose optimal hyperparameters. Both internal validation and external validation were conducted, using the 20% randomly divided holdout test dataset and previously unseen data from Shanghai MJ Health Screening Center, respectively, to evaluate model performance. The evaluation metrics included area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, Brier score, and decision curve. Bootstrap sampling was implemented to generate 95% confidence intervals of all the metrics. Finally, the Shapley additive explanations (SHAP) algorithm was applied in the holdout test dataset for model interpretability to obtain time-specific and sample-specific contributions of each feature. Results: Among the 10,493 participants, 1662 (15.84%) were diagnosed with NAFLD at and after their sixth health checkups. The predictive performance of the deep learning model in the internal validation dataset improved over the incorporation of the checkups, with AUROC increasing from 0.729 (95% CI: 0.698,0.760) at baseline to 0.818 (95% CI: 0.798,0.844) when consecutive 5 checkups were included. The external validation dataset, containing 1728 participants, was used to verify the results, in which AUROC increased from 0.700 (95% CI: 0.657,0.740) with only the first checkups to 0.792 (95% CI: 0.758,0.825) with all five. The results of feature significance showed that body fat percentage, alanine transaminase (ALT), and uric acid owned the greatest impact on the outcome, time-specific, individual-specific and dynamic feature contributions were also produced for model interpretability. Conclusion: A dynamic prediction model was successfully established in our study, and the prediction capability kept improving with the renewal of the latest checkup records. In addition, we identified key features associated with the onset of NAFLD, making it possible to optimize the prevention and control strategies of the disease in the general population.

BackgroundMinimal data are available on the prevalence of mild cognitive impairment (MCI) in older Chinese adults. Moreover, the current information on MCI shows important geographical variations.ObjectiveWe aimed to assess the prevalence and risk factors for MCI by age and sex among older adults in a North Chinese population.MethodsIn this population-based cross-sectional study, we enrolled a random sample of 4,943 adults aged ≥ 60 years between March 2018 and June 2019 in Tianjin, China. Of these, 312 individuals were excluded due to a lack of data (e.g., fasting blood test). As a result, 4,631 subjects were assessed. Individuals with MCI were identified using neuropsychological assessments, including the Mini-Mental State Examination and Activities of Daily Living scale, based on a modified version of the Petersen’s criteria.ResultsThe mean (SD) age of the 4,631 participants was 67.6 (4.89) years, and 2,579 (55.7%) were female. The overall age- and sex-standardized prevalence of MCI in our study population was 10.7%. There were significant associations of MCI with age [65–69 vs. 60–64 years, OR = 0.74; 95% confidence interval (CI): 0.58, 0.96], physical activity (≥23.0 vs.