目的 基于随机森林方法构建甲状腺功能减退（简称甲减）患病风险预测模型。方法 从MIMIC-IV数据库纳入5 735名甲减患者为病例组,4 803名非甲减患者为对照组,基于随机森林模型进行建模。同时利用逻辑回归、贝叶斯正则化神经网络、XGBoost作为比较模型。最后用准确率、F1分数、精确率、召回率、特异性以及AUC值评价四个机器学习模型性能。结果 随机森林模型准确率为0.85,F1分数为0.84,精确率为0.84,召回率为0.84,特异性为0.86,AUC值为0.91。在该模型中,促甲状腺激素、年龄、绝对淋巴细胞计数、血液中红细胞数、中性白细胞、性别、碱性磷酸酶、丙氨酸氨基转移酶、嗜酸性粒细胞绝对计数、尿素氮为甲减患者诊断重要性排前10的指标。结论 采用随机森林方法构建的甲减患病预测模型为甲减的早期诊断有潜在应用价值。

Objective To construct a risk prediction model for hypothyroidism based on the random forest model．Methods A total of 5 735 hypothyroidism patients were included from the MIMIC-IV database as the case group, and 4 803 non-hypothyroidism patients were included as the control group．Random forest models were constructed for both groups, and logistic regression, Bayesian regularized neural network, and XGBoost were used as comparative models．The performance of the four machine learning models was evaluated using accuracy, F1 score, precision, recall, specificity, and AUC value．Results The random forest model had an accuracy of 0.85, an F1 score of 0.84, a precision of 0.84, a recall of 0.84, a specificity of 0.86, and an AUC value of 0.91．In this model, thyroid-stimulating hormone, age, absolute lymphocyte count, red blood cell count in blood, neutrophil, gender, alkaline phosphatase, aspartate aminotransferase, absolute eosinophil count, and blood urea nitrogen were the top 10 indicators for diagnosing hypothyroidism patients．Conclusions The hypothyroidism disease prediction model constructed using the random forest method has potential application value for the early diagnosis of hypothyroidism．

目的 了解新疆疏附县人民医院心脑血管疾病发病趋势和分析高血压发病相关危险因素,为高血压及其相关的心脑血管疾病的综合防治提供依据。方法 回顾性分析2007—2011年疏附县人民医院住院患者资料,按年份统计慢性非传染性疾病(以下简称慢性病)住院人数情况,并采用Logistic回归分析法分析维吾尔族人群高血压发病的相关危险因素。结果 新疆疏附县人民医院心脑血管疾病住院人数逐年增长,5年增长了约2.7倍,其中因高血压住院人数增长了3.5倍。BMI、血钠水平升高、血脂异常、年龄是维吾尔族人群高血压的危险因素。结论 新疆疏附县人民医院住院患者中以高血压为主的心脑血管疾病逐年增长。当地高血压及其相关的心脑血管疾病的防治采取生活方式干预基础上给予降压、降脂治疗的综合策略是优选。

Objective To investigate the incidence trend of cardio-cerebrovascular disease and the related risk factors about hypertension in Shufu people's hospital of Xinjiang. Moreover, to provide evidence of making prevention and controlling strategies for hypertension and the related cardio-cerebrovascular diseases.Methods A retrospective review was did on case data of the inpatients in Shufu people's hospital during 2007-2011.We counted the number of inpatients of chronic non-communicable diseases(NCDs)by year and collected the information of hypertensive inpatients and non-hypertensive inpatients to analyze the risk factors of hypertension in Uygurs using Logistic regression.Results The number of inpatients with cardio-cerebrovascular disease in Shufu people's hospital was increased by 2.7 times in 5 years, while the number of hypertensive inpatients was increased by 3.5 times. BMI, elevated blood sodium, and dyslipidemia, age are risk factors for hypertension in Uygur population.Conclusion The inpatients with cardio-cerebrovascular disease especially those with hypertension in Shufu people's hospital were increasing in recent 5 years. The strategy of lifestyle intervention combined with antihypertensive as well as lipid-lowering therapy is better to the prevention and treatment of hypertension and the related cardio-cerebrovascular diseases.

目的 研究血管紧张素转换酶(ACE)基因插入/缺失(I/D)多态性与新疆地区维吾尔族(维族)、汉族人群原发性高血压(EH)的关系。方法 采用聚合酶链反应(PCR)检测此两类人群104例原发性高血压(病例组、EH)及102例健康人群(对照组、NT)血中ACE基因16号内含子的I/D多态性。统计各基因型频率、等位基因频率,并采用Logistic回归分析剔除混杂因素后ACE基因I/D多态性与EH的关系。结果 两族人群的EH组与NT组D等位基因频率及基因型频率差异均没有统计学意义(P>0.05)。但经Logistic回归分析校正各种混杂因素后,两族人群EH的发病率与ACE基因(I/D)多态性相关(P<0.05)。结论 ACE基因I/D多态性可能为新疆地区维族、汉族EH的易感因素。

Objective To investigate whether the insertion deletion(I/D) polymorphism in the angiotensin converting enzyme(ACE) gene is associated with essential hypertension(EH) in Uighur and Han population of Xinjiang. Methods The study covered 104 hypertension patients (EH) and 102 normotensive controls (NT). The variant of ACE I/D was determined by polymorphism chain reaction (PCR). Logistic was used to analyze the ACE I/D polymorphism compared with ACE genotype. Results There was no significant difference between the EH and NT group about the genotype frequency and allele frequency(P>0.05). Using logistic regression analysis, adjusted for confounding factor, there was a relationship between EH and ACE gene I/D polymorphism(P<0.05). Conclusion The results suggest that the I/D polymorphism of ACE gene is associated with the EH in the Uighur and Han people of Xinjiang.