Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis.
Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis.
复制标题
多变量Logistic回归和其他机器学习算法在妊娠护理预后预测研究中的比较：系统综述和荟萃分析。
DOI：
10.2196/16503
复制
发表时间：
2020-11-17
影响因子：
3.2
通讯作者：
Su EC
中科院分区：
文献类型：
--
作者：
Sufriyana H;Husnayain A;Chen YL;Kuo CY;Singh O;Yeh TY;Wu YW;Su EC
怀孕护理的预测是复杂的，因为多种因素之间的相互作用。因此，妊娠结局不容易通过仅使用一种算法或建模方法的单个预测因子来预测。本研究旨在审查和比较逻辑回归（LR）和其他机器学习算法之间的预测性能，以开发或验证妊娠护理的多变量预后预测模型，为临床医生的决策提供信息。根据预后预测研究的几个指南，包括偏倚风险（ROB）评估，对来自MEDLINE、Scopus、Web of Science和Google Scholar的研究文章进行了审查。我们根据PRISMA（系统评价和荟萃分析的首选报告项目）指南报告结果。研究主要是作为PICOTS框架（人群、指数、比较者、结局、时间和环境）：人群：生殖管理中的男性或女性、孕妇、胎儿或新生儿;指数：使用非LR算法进行风险分类以告知临床医生决策的多变量预后预测模型;比较者：应用LR的模型;结局：妊娠相关的生育结局或妊娠妇女和胎儿或新生儿的妊娠结局;时间：孕前、孕间和围孕期（预测因素），在妊娠、分娩、产后或新生儿期（结局），以及短期或长期妊娠（时间间隔）;和设置：初级保健或医院。通过报告研究特征和ROB以及对相同妊娠结局的每个非LR模型与LR模型的受试者工作特征曲线下对数面积差异进行随机效应建模，对结果进行综合。我们还使用τ2和I2报告了研究间异质性。在2093份记录中，我们纳入了142项系统综述研究和62项荟萃分析研究。在非LR算法中，大多数预测模型使用LR（92/142，64.8%）和人工神经网络（20/142，14.1%）。只有16.9%（24/142）的研究的ROB较低。来自低ROB研究的总共2种非LR算法显著优于LR。第一种算法是早产（logit AUROC 2.51，95% CI 1.49-3.53; I2=86%; τ2=0.77）和先兆子痫（logit AUROC 1.2，95% CI 0.72-1.67; I2=75%; τ2=0.09）的随机森林。第二种算法是剖宫产（logit AUROC 2.26，95% CI 1.39-3.13; I2=75%; τ2=0.43）和妊娠期糖尿病（logit AUROC 1.03，95% CI 0.69-1.37; I2=83%; τ2=0.07）的梯度增强。在研究中表现最好的预测模型不一定是那些使用LR的模型，但也使用了随机森林和梯度提升，这些模型也表现良好。我们建议重新分析现有的LR模型的几个怀孕的结果，通过比较它们与那些算法，适用于标准的指南。PROSPERO（国际系统性综述前瞻性登记系统）CRD 42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?记录ID =136106
Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method. This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making. Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ2 and I2. Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I2=86%; τ2=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I2=75%; τ2=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I2=75%; τ2=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I2=83%; τ2=0.07). Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines. PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106
登录
查看更多内容
影响因子：
3.1
作者：
Berntorp K;Anderberg E;Claesson R;Ignell C;Källén K
通讯作者：
Källén K
影响因子：
3.1
作者：
Al-Rubaie, Ziad T. A.;Hudson, H. Malcolm;Lord, Sarah J.
通讯作者：
Lord, Sarah J.
使用 GnRH 拮抗剂方案进行受控卵巢刺激时卵巢反应高低的预后模型。
DOI：
10.1093/humrep/deu090
发表时间：
2014-08
期刊：
Human reproduction (Oxford, England)
影响因子：
--
作者：
Broekmans FJ;Verweij PJ;Eijkemans MJ;Mannaerts BM;Witjes H
通讯作者：
Witjes H
影响因子：
3.7
作者：
Chen, Lili;Hao, Yaru;Hu, Xue
通讯作者：
Hu, Xue
影响因子：
4.3
作者：
Amini P;Maroufizadeh S;Samani RO;Hamidi O;Sepidarkish M
通讯作者：
Sepidarkish M