Multicenter Development and Validation of a Model for Predicting Retention in Care Among People with HIV.
Multicenter Development and Validation of a Model for Predicting Retention in Care Among People with HIV.
复制标题
DOI：
10.1007/s10461-022-03672-y
复制
发表时间：
2022-10
影响因子：
4.4
通讯作者：
Mayampurath, Anoop
中科院分区：
文献类型：
--
作者：
Ridgway, Jessica P.;Ajith, Aswathy;Friedman, Eleanor E.;Mugavero, Michael J.;Kitahata, Mari M.;Crane, Heidi M.;Moore, Richard D.;Webel, Allison;Cachay, Edward R.;Christopoulos, Katerina A.;Mayer, Kenneth H.;Napravnik, Sonia;Mayampurath, Anoop
预测分析可用于识别目前仍在护理中的艾滋病毒感染者，这些人将来有可能脱离护理，从而可以优先考虑保留干预措施。我们利用机器学习方法来开发护理保留的预测模型，定义为艾滋病研究中心综合临床系统网络（CNICS）队列中艾滋病毒护理预约之间的间隔不超过12个月。数据纵向分为推导和验证队列。我们在离散时间生存分析框架内创建了逻辑回归（LR），随机森林（RF）和梯度增强机（XGB）模型，并将其性能与仅包括人口统计学，病毒抑制和保留历史的基线模型进行了比较。纳入了2007年至2018年的21，267例患者，共507，687次访视。LR模型优于基线模型（AUC 0.68 [0.67-0.70] vs. 0.60 [0.59-0.62]，P < 0.001）。RF和XGB型号与LR型号的性能相似。LR模型中的主要特征包括保留史、年龄和病毒抑制。
Predictive analytics can be used to identify people with HIV currently retained in care who are at risk for future disengagement from care, allowing for prioritization of retention interventions. We utilized machine learning methods to develop predictive models of retention in care, defined as no more than a 12 month gap between HIV care appointments in the Center for AIDS Research Network of Integrated Clinical Systems (CNICS) cohort. Data were split longitudinally into derivation and validation cohorts. We created logistic regression (LR), random forest (RF), and gradient boosted machine (XGB) models within a discrete-time survival analysis framework and compared their performance to a baseline model that included only demographics, viral suppression, and retention history. 21,267 Patients with 507,687 visits from 2007 to 2018 were included. The LR model outperformed the baseline model (AUC 0.68 [0.67–0.70] vs. 0.60 [0.59–0.62], P < 0.001). RF and XGB models had similar performance to the LR model. Top features in the LR model included retention history, age, and viral suppression.
登录
查看更多内容
影响因子：
5
作者：
Crane, H. M.;Heckbert, S. R.;Kitahata, M. M.
通讯作者：
Kitahata, M. M.
DOI：
10.1097/qai.0b013e318273762f
发表时间：
2012-12-15
影响因子：
3.6
作者：
Mugavero, Michael J.;Westfall, Andrew O.;Giordano, Thomas P.
通讯作者：
Giordano, Thomas P.
影响因子：
1.4
作者：
Myers, Kristopher;Li, Tan;Fennie, Kristopher
通讯作者：
Fennie, Kristopher
影响因子：
11.1
作者：
Park, W. B.;Choe, P. G.;Choe, K. W.
通讯作者：
Choe, K. W.
影响因子：
11.8
作者：
Horstmann, Elizabeth;Brown, Jillian;Agins, Bruce D.
通讯作者：
Agins, Bruce D.