Statistical approaches using longitudinal biomarkers for disease early detection: A comparison of methodologies.
Statistical approaches using longitudinal biomarkers for disease early detection: A comparison of methodologies.
复制标题
使用纵向生物标志物进行疾病早期检测的统计方法：方法学比较。
DOI：
10.1002/sim.8731
复制
发表时间：
2020-12-20
影响因子：
2
通讯作者：
Liu, Danping
中科院分区：
文献类型：
--
作者：
Han, Yongli;Albert, Paul S.;Berg, Christine D.;Wentzensen, Nicolas;Katki, Hormuzd A.;Liu, Danping
关键词：
可以使用纵向生物标记物测量来预测临床结果的早期检测，例如癌症。追踪纵向生物标记物作为识别早期疾病发病的一种方式，可能有助于降低卵巢癌等疾病的死亡率，如果及早发现，这些疾病更容易治疗。共享随机效应模型(SREM)和模式混合模型(PMM)两种疾病风险预测框架可用于评估疾病早期发现的纵向生物标志物。本文通过在卵巢癌中的应用，研究了SREM和PMM在疾病早期检测中的区分和校准性能，并对卵巢癌风险算法(ROCA)的早期检测进行了评估。以上三种方法的比较是通过分析前列腺癌、肺癌、结直肠癌和卵巢癌筛查试验的卵巢癌数据进行的。辨别力通过随时间变化的受试者工作特征曲线及其面积来评估，而校准则通过校准图和观察到的患病人数与预期患病人数的比率来评估。样本外绩效的计算采用留一法交叉验证，目的是最小化潜在的模型过度拟合。对使用生物标记物癌抗原125进行卵巢癌早期检测的仔细分析表明，与SREM和ROCA相比，PMM的鉴别性能显著提高，但所有方法总体上都得到了很好的校准。在广泛的仿真研究中，进一步研究了所有方法的稳健性。PMM相对于ROCA的表现有所改善，部分原因是生物标志物测量每隔一年进行一次，这不够频繁，无法可靠地估计ROCA下的变点或变点后的斜率。
Early detection of clinical outcomes such as cancer may be predicted using longitudinal biomarker measurements. Tracking longitudinal biomarkers as a way to identify early disease onset may help to reduce mortality from diseases like ovarian cancer that are more treatable if detected early. Two disease risk prediction frameworks, the shared random effects model (SREM) and the pattern mixture model (PMM) could be used to assess longitudinal biomarkers on disease early detection. In this article, we studied the discrimination and calibration performances of SREM and PMM on disease early detection through an application to ovarian cancer, where early detection using the risk of ovarian cancer algorithm (ROCA) has been evaluated. Comparisons of the above three approaches were performed via analyses of the ovarian cancer data from the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial. Discrimination was evaluated by the time-dependent receiver operating characteristic curve and its area, while calibration was assessed using calibration plot and the ratio of observed to expected number of diseased subjects. The out-of-sample performances were calculated via using leave-one-out cross-validation, aiming to minimize potential model overfitting. A careful analysis of using the biomarker cancer antigen 125 for ovarian cancer early detection showed significantly improved discrimination performance of PMM as compared with SREM and ROCA, nevertheless all approaches were generally well calibrated. Robustness of all approaches was further investigated in extensive simulation studies. The improved performance of PMM relative to ROCA is in part due to the fact that the biomarker measurements were taken at a yearly interval, which is not frequent enough to reliably estimate the changepoint or the slope after changepoint in cases under ROCA.
登录
查看更多内容
DOI：
10.1158/1078-0432.ccr-15-2750
发表时间：
2017-07-15
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Skates SJ;Greene MH;Buys SS;Mai PL;Brown P;Piedmonte M;Rodriguez G;Schorge JO;Sherman M;Daly MB;Rutherford T;Brewster WR;O'Malley DM;Partridge E;Boggess J;Drescher CW;Isaacs C;Berchuck A;Domchek S;Davidson SA;Edwards R;Elg SA;Wakeley K;Phillips KA;Armstrong D;Horowitz I;Fabian CJ;Walker J;Sluss PM;Welch W;Minasian L;Horick NK;Kasten CH;Nayfield S;Alberts D;Finkelstein DM;Lu KH
通讯作者：
Lu KH
影响因子：
2
作者：
Albert, Paul S.
通讯作者：
Albert, Paul S.
影响因子：
--
作者：
Russell MR;D'Amato A;Graham C;Crosbie EJ;Gentry-Maharaj A;Ryan A;Kalsi JK;Fourkala EO;Dive C;Walker M;Whetton AD;Menon U;Jacobs I;Graham RL
通讯作者：
Graham RL
影响因子：
158.5
作者：
Barry, MJ
通讯作者：
Barry, MJ
影响因子：
45.3
作者：
Menon, U;Skates, SJ;Jacobs, IJ
通讯作者：
Jacobs, IJ