In simulated data and health records, latent class analysis was the optimum multimorbidity clustering algorithm.
In simulated data and health records, latent class analysis was the optimum multimorbidity clustering algorithm.
复制标题
DOI：
10.1016/j.jclinepi.2022.10.011
复制
发表时间：
2022-12
影响因子：
7.2
通讯作者：
Marshall T
中科院分区：
文献类型：
--
作者：
Nichols L;Taverner T;Crowe F;Richardson S;Yau C;Kiddle S;Kirk P;Barrett J;Nirantharakumar K;Griffin S;Edwards D;Marshall T
探讨潜在类分析（LCA）、层次聚类分析（HCA）、多重对应分析后的k-means （MCA-kmeans）和k-means （kmeans）对多病聚类的可重复性和有效性。我们首先研究了在预先确定的类中26种患病率不同的疾病的模拟数据集中的聚类算法，并使用调整后的Rand指数（aRI）将导出的类与已知的类进行比较。然后，我们调查了来自50个英国全科诊所的年龄在65至84岁之间的男性患者的医疗记录，其中有49种长期健康状况。我们使用Pearson相关系数比较了集群发病率概况，并评估了400个bootstrap样本的集群稳定性。在模拟数据集中，与已知聚类最接近（最大aRI）的是LCA算法，然后是MCA-kmeans算法。在医疗记录数据集中，所有四种算法都确定了数据集中20-25%的一个集群，其中82%的患者在所有四种算法中都是相同的。LCA和MCA-kmeans都发现了数据集的7%的第二簇。其他聚类仅由一种算法找到。LCA聚类和MCA-kmeans聚类给出了最相似的分区（aRI为0.54）。LCA取得了比其他聚类算法更高的aRI。
To investigate the reproducibility and validity of latent class analysis (LCA) and hierarchical cluster analysis (HCA), multiple correspondence analysis followed by k-means (MCA-kmeans) and k-means (kmeans) for multimorbidity clustering. We first investigated clustering algorithms in simulated datasets with 26 diseases of varying prevalence in predetermined clusters, comparing the derived clusters to known clusters using the adjusted Rand Index (aRI). We then them investigated in the medical records of male patients, aged 65 to 84 years from 50 UK general practices, with 49 long-term health conditions. We compared within cluster morbidity profiles using the Pearson correlation coefficient and assessed cluster stability was in 400 bootstrap samples. In the simulated datasets, the closest agreement (largest aRI) to known clusters was with LCA and then MCA-kmeans algorithms. In the medical records dataset, all four algorithms identified one cluster of 20–25% of the dataset with about 82% of the same patients across all four algorithms. LCA and MCA-kmeans both found a second cluster of 7% of the dataset. Other clusters were found by only one algorithm. LCA and MCA-kmeans clustering gave the most similar partitioning (aRI 0.54). LCA achieved higher aRI than other clustering algorithms.
登录
查看更多内容
影响因子：
11.1
作者：
Araujo de Carvalho I;Epping-Jordan J;Pot AM;Kelley E;Toro N;Thiyagarajan JA;Beard JR
通讯作者：
Beard JR
影响因子：
2.9
作者：
Leijten, Fenna R. M.;Hoedemakers, Maaike;Rutten-van Molken, Maureen P. M. H.
通讯作者：
Rutten-van Molken, Maureen P. M. H.
影响因子：
3.7
作者：
RAND, WM
通讯作者：
RAND, WM
影响因子：
5.7
作者：
Crowe, Francesca;Zemedikun, Dawit T.;Marshall, Tom
通讯作者：
Marshall, Tom
DOI：
10.3399/bjgp18x695465
发表时间：
2018-04
期刊：
The British journal of general practice : the journal of the Royal College of General Practitioners
影响因子：
--
作者：
Cassell A;Edwards D;Harshfield A;Rhodes K;Brimicombe J;Payne R;Griffin S
通讯作者：
Griffin S