Deep Phenotyping and Prediction of Long-term Cardiovascular Disease: Optimized by Machine Learning

BackgroundPrediction of cardiovascular disease (CVD) is important in clinical practice. Machine learning (ML) may offer an improved alternative to current CVD risk stratification in individual patients. We aim to identify important predictors and compare ML models with traditional models according to their prediction performance in a large long-term follow-up cohort.MethodsThe Atherosclerosis Risk in Communities (ARIC) study was designed to study the progression of subclinical disease to cardiovascular events over a 25-year follow-up period. All phenotypic variables at visit 1 were obtained. All-cause death, CVD, and coronary heart disease were the outcomes for analysis. The ML framework involved variable selection using the random survival forest (RSF) method, model building, and 5-fold cross-validation. Model performance was evaluated by discrimination using the Harrell concordance index (C-index), accuracy using the Brier score (BS), and interpretability using the number of variables in the model.ResultsOf the 14,842 participants in ARIC, the average age was 54.2 years, with 45.2% male and 26.2% Black participants. Thirty-eight unique variables were selected in the RSF top 20 importance ranking of all 6 outcomes. Aging, hypertension, glucose metabolism, renal function, coagulation, adiposity, and sodium retention dominated the predictions of all outcomes. The ML models outperformed the regression models and established risk scores with a higher C-index, lower BS, and varied interpretability.ConclusionsThe ML framework is useful for identifying important predictors of CVD and for developing models with robust performance compared with existing risk models.     

Severe periodontitis is associated with the serum levels of hypersensitive C reactive protein and lipoprotein-associated phospholipase A2 in the patients of acute ischemic stroke

BackgroundPeriodontitis is associated with the pathogenesis of atherosclerotic plaque, and hypersensitive C reactive protein (hs-CRP) and lipoprotein-associated phospholipase A2 (Lp-PLA2) are the serum biomarkers of the stability of atherosclerotic plaque. Whether periodontitis is associated with the serum level of hs-CRP and Lp-PLA2 of acute ischemic stroke remains unclear.Material and MethodsWe recruited 103 cases with acute ischemic stroke within 7 days after stroke onset. Pocket depth and clinical attachment loss were assessed by oral examination to define the severe periodontitis. Demographic information including gender, age and body weight index, income level, education level, past medical history include smoking history, drinking history, ischemic stroke history, coronary heart disease, hypertension, diabetes and hyperlipidemia were collected, and serum biomarkers including white blood cell (WBC), fibrinogen, total cholesterol (TC), triglyceride (TG), lower density lipoprotein (LDL-C), high density lipoprotein (HDL-C), hs-CRP, HemoglobinA1c (HbAlc), Homocysteine (HCY) and Lp-PLA2 were tested.Results65 (63.1%) cases were diagnosed as severe periodontitis. Severe periodontitis group showed more male, age, drinking history, higher levels of hs-CRP and Lp-PLA2. Multivariate logistic regression showed that severe periodontitis was were significantly associated with hs-CRP (OR = 2.367, 95%CI: 1.182–4.738; P = .015) and Lp-PLA2 (OR = 2.577, 95% CI: 1.010–6.574; P = .048).ConclusionsSevere periodontitis is independently associated with the serum Level of hs-CRP and Lp-PLA2 in patients with acute ischemic stroke. Whether the improvement of periodontitis could decrease the occurrence and re-occurrence of ischemic stroke by stablizating atherosclerotic plaque need be further studied in future.     

The Impact of Testosterone on the QT Interval: A Systematic Review

Humans and mammals have sex-specific differences in cardiac electrophysiology, linked to the action of sex hormones in the cardiac muscle. These hormones can upregulate or downregulate the expression of ionic channels modulating the cardiac cycle through genomic and non-genomic interactions. Systematic search in PubMed, Medline and EMBASE including keywords pertaining to testosterone and QT interval. Included experimental studies and observation studies and case reports presenting the results of testosterone administration, excess or deficiency in humans and animals. Testosterone has been shown to shorten the action potential duration, by enhancing the expression of K⁺ channels and downregulating I_CaL increasing the repolarization reserve of the cardiac muscle. This effect has been observed in both genders and animals. Testosterone deficient states can promote arrhythmogenesis. The evidence in this paper may be used to guide clinical considerations, such as increased clinical surveillance of patients in testosterone deficient states using ECG.     

Utility of the relative apparent diffusion coefficient for preoperative assessment of low risk endometrial carcinoma

ObjectivesLymphadenectomy is not recommended for low risk stage I endometrial carcinoma (EC) patients. This study was to investigate the predictive value of apparent diffusion coefficient (ADC) values in predicting patients with low risk EC, and to identify an optimum ADC measurement for preoperative assessment.Materials and methodsEighty-one patients with stage I EC who underwent diffusion-weighted imaging (DWI) at 1.5T were included and divided into low group and intermediate-high risk group based on the ESMO-ESGO-ESTRO classification. Clinical indexes, conventional MRI parameters, minimum ADC values (minADC), mean ADC values (meanADC) and relative ADC values (rADC) were compared between those two groups. rADC was calculated using the equation ADC (cancer)/ADC (reference) with the obturator internus muscle as reference. The optimal ADC measurement and cut-off ADC value for low risk EC were calculated using the receiver operating characteristic (ROC) curve.ResultsThe low risk group had significantly higher meanADC, minADC, and rADC values than did the intermediate-high risk group (1.095 vs. 0.902 × 10⁻³ mm²/s, 0.755 vs. 0.657 × 10⁻³ mm²/s, 0.754 vs. 0.603, respectively). In assessments of low risk EC patients, the area under the curve (AUC) values for meanADC, minADC, and rADC were 0.840 (95%CI, 0.749,0.931), 0.681 (95% CI: 0.561,0.800), and 0.876(95% CI: 0.798,0.954), respectively. The optimal cut-off rADC value for prediction was 0.669, the maximum Youden index, sensitivity, specificity, and accuracy values were 0.683, 81.8%, 86.5%, and 84.0%, respectively.ConclusionsrADC is superior to minADC and meanADC for predicting patients with low risk EC, and could potentially aid to the surgical management of these patients in avoiding unnecessary lymphadenectomy.     

2005 - 2014年中国老年人肺癌发病的时间趋势分析

目的 分析2005 - 2014年我国老年人肺癌发病的时间趋势，为我国肺癌的防控工作提供依据。方法 根据2008 - 2017年《中国肿瘤登记年报》中肺癌的相关数据，分析2005 - 2014年我国老年人肺癌的发病情况，并通过年度变化百分比（annual percentage change，APC）分析其时间变化趋势。结果 2005 - 2014年我国老年人肺癌的发病率呈上升趋势（APC = 0.71%，P＜0.05），其中农村老年人肺癌的发病率从198.9/105上升至250.7/105，上升趋势更明显（APC = 2.81%，P＜0.05），尤以农村老年女性肺癌发病率的上升趋势最为明显（APC = 5.26%，P＜0.05）。2005 - 2014年中国老年人肺癌的发病在60～64岁和65～69岁组呈上升趋势（APC分别为2.83%和2.04%，均P＜0.05），而在农村地区，老年人所有年龄组的肺癌发病率都呈明显上升趋势（APC分别为3.49%，3.86%，1.66%，2.31%，3.49%及6.37%，均P＜0.05）。结论 2005 - 2014年我国老年人肺癌发病上升趋势明显，以农村老年女性最为突出，国家应针对高危人群及早开展筛查等工作，降低我国老年人肺癌的流行水平。