摘要
由一名新闻记者兼机器人与机器学习每日新闻-怀孕并发症的新研究-Preecla MPSIA是一篇报道的主题。根据NewsRx编辑在澳大利亚墨尔本的新闻报道，研究表明，“机器学习(ML)方法是医疗风险预测的新兴替代方法。我们旨在综合ML和经典回归研究的文献，探索潜在的公关预测因素，并比较先兆子痫的预测性能。”这项研究的财政支持来自莫纳什大学。我们的新闻记者引用了莫纳什大学的研究，“从检索到的9382项研究中，纳入了82项。66份出版物独家报道了84种预测先兆子痫发病时间的经典回归模型。另外6份出版物报道了纯ML算法，另有10篇出版物报道了同一样本的ML算法和经典回归模型，其中8篇发现ML算法优于经典回归模型。最常见的预后因素是年龄、孕前体重指数、慢性疾病、产次、先兆子痫既往史、平均动脉压、子宫动脉搏动指数、胎盘生长因子、子宫内膜异位症表现最好的ML算法是随机森林（曲线下面积(AUC)=0.94，95%置信区间(CI)0.91-0.96）和极端梯度提升（AUC=0.92，9.5%CI 0.90-0.94）。竞争风险模型表现相似（AUC=0.92，95%CI 0.90-0.94）。在ECLA前MPSIA预测中,ML算法与经典回归模型相比具有更好的预测性能,随机森林算法和boosting算法具有最好的预测性能,进一步的研究应集中在使用相同样本和评价指标的ML算法和CL回归模型的比较上,以了解它们的预测性能。性能。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Pregnancy Complications - Preecla mpsia is the subject of a report. According to news reporting out of Melbourne, Australia, by NewsRx editors, research stated, “Machine learning (ML) approaches are an emerging alternative for healthcare risk prediction. We aimed to synthes ise the literature on ML and classical regression studies exploring potential pr ognostic factors and to compare prediction performance for pre-eclampsia.” Financial support for this research came from Monash University. Our news journalists obtained a quote from the research from Monash University, “From 9382 studies retrieved, 82 were included. Sixty-six publications exclusive ly reported eighty-four classical regression models to predict variable timing o f onset of pre-eclampsia. Another six publications reported purely ML algorithms , whilst another 10 publications reported ML algorithms and classical regression models in the same sample with 8 of 10 findings that ML algorithms outperformed classical regression models. The most frequent prognostic factors were age, pre -pregnancy body mass index, chronic medical conditions, parity, prior history of pre-eclampsia, mean arterial pressure, uterine artery pulsatility index, placen tal growth factor, and pregnancy-associated plasma protein A. Top performing ML algorithms were random forest (area under the curve (AUC) = 0.94, 95% confidence interval (CI) 0.91-0.96) and extreme gradient boosting (AUC = 0.92, 9 5% CI 0.90-0.94). The competing risk model had similar performance (AUC = 0.92, 95% CI 0.91-0.92) compared with a neural network. Ca libration performance was not reported in the majority of publications. ML algor ithms had better performance compared to classical regression models in pre-ecla mpsia prediction. Random forest and boosting-type algorithms had the best predic tion performance. Further research should focus on comparing ML algorithms to cl assical regression models using the same samples and evaluation metrics to gain insight into their performance.”
NETL
NSTL