所有项目
临床路径
预测模型
临床路径模型
冠心病临床路径模型(非用药医嘱)

模型简介:用2020年5月-2020年12月出院诊断为冠心病的4909例患者,根据《稳定性冠心病临床路径2016》将住院时间划分成入院第1天,入院第2天,入院第3-4天,入院第5天这四个时期,分别计算其非用药医嘱支持度,各医嘱使用频率较符合《稳定性冠心病临床路径2016》。

4909

总病例/人

查看详情

临床路径模型
胆总管结石伴胆管炎临床路径

模型简介:本项目采用基于Apriori算法的胆总管结石伴胆管炎诊疗临床路径挖掘,利用1762个患者医嘱数据进行挖掘,其主要包括诊疗数据、用药以及护理数据。依照现实诊疗数据,分析挖掘住院时间、诊疗阶段的划分、临床路径候选集筛查、以及时序路径的构造。

1762

总病例/人

查看详情

预测模型
基于XGboost的脑梗90天再入院

模型简介:摘要 目的:缺血性脑卒中患者出院后90天内再入院是一项重要的质量指标 缺血性中风的再入院率通常高于其他慢性疾病。我们的目的是确定缺血性中风复发的危险因素,并建立缺血性中风患者90天再入院预测模型。 方法:采用江西省医学大数据工程技术研究中心的病人数据。再入院预测模型是采用极端梯度推进(XGboost)方法建立的,该方法可以生成一组分类树,并为每个特征分配一个预测风险分数。用受试者操作特征曲线(ROC)和时间相关ROC评价预测结果,并与Logistic回归(LR)模型的结果进行比较。 结果:本研究共选择6070例无IS病史的成人患者,其中520例(8.6%)在90天内再次入院。媒介年龄67岁,其中女性2404人(39.6%)。患者数据分为训练集(5159)和验证集(911)。基于XGboost的预测模型在54天内的标准AUC(曲线下面积)分别为0.782(0.729-0.834)和0.808。相比之下,LR模型的标准AUC为0.771(0.714-0.828),时间相关AUC为0.797。 结论:XGboost对首次卒中患者90天再入院的风险预测优于LR模型。该模型还可以揭示脑卒中患者复发和再入院的高危因素。 Abstract Object: Ischemic stroke readmission within 90 days of hospital discharge is an important quality of care metric The readmission rates of ischemic stroke are usually higher than other chronic diseases Our aim was to identify ischemic stroke recurrent risk factors and establish a 90-day readmission prediction model for ischemic stroke patients . Methods: This study used patient data from the Jiang Xi Province Medical Big Data Engineering & Technology Research Center. The readmission prediction model was developed using Extreme Gradient Boosting (XGboost), which can generate an ensemble of classification trees and assign a predictive risk score to each feature. Prediction results were evaluated with receiver operating characteristic curve (ROC) and time-dependent ROC,compared with the outputs from the Logistic Regression (LR) model. Result: Totally, 6,070 adult patients without IS history were selected in this study, of which 520 (8.6%) were readmitted within 90 days . The media age was 67 years and 2,404 (39.6%) of them were female. Patients data was split into a training set (5,159) and a validate set (911). The XGboost based prediction model achieved a standard AUC(Area Under Curve)of 0.782 (0.729-0.834) and the time-dependent AUC is 0.808 in 54 days for the validate set, respectively. In contrast, the LR model yielded a standard AUC of 0.771 (0.714-0.828) and time-dependent AUC of 0.797 . Conclusions: XGboost performed better risk prediction for 90-day readmission in first ever stroke patients than the LR model. This model can also reveal the high risk factors of stroke recurrence and readmission hazards in stroke patients.

6070

总病例/人

查看详情

预测模型
基于XGboost脑卒中肺部感染预测

模型简介:利用临床常规指标并结合XGboost算法构建缺血性脑卒中合并肺部感染预测模型,并分析模型在合并肺部感染中的影响因子。

3766

总病例/人

查看详情