Dynamic classification using credible intervals in longitudinal discriminant analysis.
Dynamic classification using credible intervals in longitudinal discriminant analysis.
复制标题
DOI：
10.1002/sim.7397
复制
发表时间：
2017-10-30
影响因子：
2
通讯作者：
García-Fiñana M
中科院分区：
文献类型：
--
作者：
Hughes DM;Komárek A;Bonnett LJ;Czanner G;García-Fiñana M
最近发展的纵向判别分析方法允许使用连续和离散生物标志物的纵向历史将受试者分类为预先指定的预后组。分类使用贝叶斯估计每个预后组的组成员概率。这些估计来自每个组中生物标志物纵向演变的多元广义线性混合模型，并且可以在每次获得患者新数据时进行更新，提供动态（随时间推移）分配方案。然而，估计群体概率的精确度因每个病人和时间而异。这种精度可以通过查看组成员概率的可信间隔来评估。在本文中，我们提出了一种新的分配规则，该规则包含可信区间，用于动态纵向判别分析，并表明这可以减少预测测试中的假阳性数量，提高阳性预测值。我们还建立了通过让一些患者在一段时间内不分类，可以提高分类患者的分类准确性，从而增加临床医生决策的信心。最后，我们证明动态确定停止规则比指定一个确定患者状态的设定时间点更准确。我们使用癫痫患者的数据来说明我们的方法，并展示了与现有方法相比，使用可信间隔如何更准确地识别未能实现充分癫痫控制的患者。
Recently developed methods of longitudinal discriminant analysis allow for classification of subjects into prespecified prognostic groups using longitudinal history of both continuous and discrete biomarkers. The classification uses Bayesian estimates of the group membership probabilities for each prognostic group. These estimates are derived from a multivariate generalised linear mixed model of the biomarker's longitudinal evolution in each of the groups and can be updated each time new data is available for a patient, providing a dynamic (over time) allocation scheme. However, the precision of the estimated group probabilities differs for each patient and also over time. This precision can be assessed by looking at credible intervals for the group membership probabilities. In this paper, we propose a new allocation rule that incorporates credible intervals for use in context of a dynamic longitudinal discriminant analysis and show that this can decrease the number of false positives in a prognostic test, improving the positive predictive value. We also establish that by leaving some patients unclassified for a certain period, the classification accuracy of those patients who are classified can be improved, giving increased confidence to clinicians in their decision making. Finally, we show that determining a stopping rule dynamically can be more accurate than specifying a set time point at which to decide on a patient's status. We illustrate our methodology using data from patients with epilepsy and show how patients who fail to achieve adequate seizure control are more accurately identified using credible intervals compared to existing methods.
登录
查看更多内容
影响因子：
168.9
作者：
Marson, Anthony G.;Al-Kharusi, Asya M.;Alwaidh, Muna;Appleton, Richard;Baker, Gus A.;Chadwick, David W.;Cramp, Celia;Cockerell, Oliver C.;Cooper, Paul N.;Doughty, Julie;Eaton, Barbara;Gamble, Carrot;Goulding, Peter J.;Howell, Stephen J. L.;Hughes, Adrian;Jackson, Margaret;Jacoby, Ann;Kellett, Mark;Lawson, Geoffrey R.;Leach, John Paul;Nicolaides, Paola;Roberts, Richard;Shackley, Phil;Shen, Jing;Smith, David F.;Smith, Philip E. M.;Smith, Catrin Tudur;Vanoli, Alessandra;Williamson, Paula R.
通讯作者：
Williamson, Paula R.
影响因子：
1.8
作者：
Komarek, Arnost;Komarkova, Lenka
通讯作者：
Komarkova, Lenka
DOI：
10.1111/rssc.12021
发表时间：
2014-01-01
影响因子：
1.6
作者：
Guglielmi, Alessandra;Ieva, Francesca;Soriano, Jacopo
通讯作者：
Soriano, Jacopo
影响因子：
4.4
作者：
Horrocks, Julie;van Den Heuvel, Marianne J.
通讯作者：
van Den Heuvel, Marianne J.
影响因子：
1.7
作者：
Kohlmann, Mareike;Held, Leonhard;Grunert, Veit Peter
通讯作者：
Grunert, Veit Peter