TY -的AU -香港,草根盟——太阳,Zhoujian盟,郝Yuzhe盟——咚,Zhanghuiya盟——顾Zhaodan盟——黄、兴PY - 2022 DA - 2022/10/14 TI -识别心脏衰竭患者易受新创急性肾损伤:机器学习方法乔-地中海JMIR通知SP - e37484六世- 10 - 10 KW -心脏衰竭KW -急性肾损伤KW -非监督机器学习KW -危险分层KW -表型群AB -背景:研究表明，半数以上伴有急性肾损伤(AKI)的心力衰竭(HF)患者有新发AKI，而肾功能评估指标如估计的肾小球滤过率在住院期间通常不会反复检测。作为一个独立的危险因素，AKI识别延迟已被证明与心力衰竭患者的不良事件相关，如慢性肾脏疾病和死亡。目的:本研究的目的是开发和评估一个无监督的机器学习模型，以识别肾功能正常但易发生新生AKI的HF患者。方法:我们分析了包含5075例肾功能正常的HF患者的电子健康记录数据集，使用称为K-means聚类的无监督机器学习算法对其中的2个表型组进行分类。然后，我们通过进行生存分析、AKI预测和风险比检验来确定推断的表型指数是否有可能成为一个必要的风险指标。结果:生成表型2的AKI发生率显著高于表型1(组1:106/2823,3.75%;第二组:259/2252,11.50%;P <措施)。表型2的存活率明显低于表型1 (P<.005)。 According to logistic regression, the univariate model using the phenogroup index achieved promising performance in AKI prediction (sensitivity 0.710). The generated phenogroup index was also significant in serving as a risk indicator for AKI (hazard ratio 3.20, 95% CI 2.55-4.01). Consistent results were yielded by applying the proposed model on an external validation data set extracted from Medical Information Mart for Intensive Care (MIMIC) III pertaining to 1006 patients with HF and normal renal function. Conclusions: According to a machine learning analysis on electronic health record data, patients with HF who had normal renal function were clustered into separate phenogroups associated with different risk levels of de novo AKI. Our investigation suggests that using machine learning can facilitate patient phengrouping and stratification in clinical settings where the identification of high-risk patients has been challenging. SN - 2291-9694 UR - https://medinform.www.mybigtv.com/2022/10/e37484 UR - https://doi.org/10.2196/37484 UR - http://www.ncbi.nlm.nih.gov/pubmed/36240002 DO - 10.2196/37484 ID - info:doi/10.2196/37484 ER -