Do Hyun Jeong, Moon Kyoung Min, Jin Hyun-Seung
Department of Pediatrics, Gangneung Asan Hospital, University of Ulsan College of Medicine, 38, Bangdong-gil, Sacheon-myeon, Gangneung-si 25440, Korea.
Department of Pulmonary, Allergy and Critical Care Medicine, Gangneung Asan Hospital, University of Ulsan College of Medicine, 38, Bangdong-gil, Sacheon-myeon, Gangneung-si 25440, Korea.
Diagnostics (Basel). 2022 Mar 3;12(3):625. doi: 10.3390/diagnostics12030625.
Statistical and analytical methods using artificial intelligence approaches such as machine learning (ML) are increasingly being applied to the field of pediatrics, particularly to neonatology. This study compared the representative ML analysis and the logistic regression (LR), which is a traditional statistical analysis method, using them to predict mortality of very low birth weight infants (VLBWI). We included 7472 VLBWI data from a nationwide Korean neonatal network. Eleven predictor variables (neonatal factors: male sex, gestational age, 5 min Apgar scores, body temperature, and resuscitation at birth; maternal factors: diabetes mellitus, hypertension, chorioamnionitis, premature rupture of membranes, antenatal steroid, and cesarean delivery) were selected based on clinical impact and statistical analysis. We compared the predicted mortality between ML methods—such as artificial neural network (ANN), random forest (RF), and support vector machine (SVM)—and LR with a randomly selected training set (80%) and a test set (20%). The model performances of area under the receiver operating curve (95% confidence interval) equaled LR 0.841 (0.811−0.872), ANN 0.845 (0.815−0.875), and RF 0.826 (0.795−0.858). The exception was SVM 0.631 (0.578−0.683). No statistically significant differences were observed between the performance of LR, ANN, and RF (i.e., p > 0.05). However, the SVM model was lower (p < 0.01). We suggest that VLBWI mortality prediction using ML methods would yield the same prediction rate as the traditional statistical LR method and may be suitable for predicting mortality. However, low prediction rates are observed in certain ML methods; hence, further research is needed on these limitations and selecting an appropriate method.
使用机器学习（ML）等人工智能方法的统计和分析方法越来越多地应用于儿科学领域，尤其是新生儿学。本研究比较了代表性的ML分析方法和传统统计分析方法逻辑回归（LR），用它们来预测极低出生体重儿（VLBWI）的死亡率。我们纳入了来自韩国全国新生儿网络的7472例VLBWI数据。基于临床影响和统计分析，选择了11个预测变量（新生儿因素：男性、胎龄、5分钟阿氏评分、体温和出生时复苏；母亲因素：糖尿病、高血压、绒毛膜羊膜炎、胎膜早破、产前类固醇使用和剖宫产）。我们将ML方法（如人工神经网络（ANN）、随机森林（RF）和支持向量机（SVM））与LR的预测死亡率进行了比较，随机选择了训练集（80%）和测试集（20%）。受试者工作特征曲线下面积（95%置信区间）的模型性能为：LR为0.841（0.811−0.872），ANN为0.845（0.815−0.875），RF为0.826（0.795−0.858）。例外的是SVM为0.631（0.578−0.683）。LR、ANN和RF的性能之间未观察到统计学显著差异（即p>0.05）。然而，SVM模型较低（p<0.01）。我们认为，使用ML方法预测VLBWI死亡率将产生与传统统计LR方法相同的预测率，并且可能适用于预测死亡率。然而，在某些ML方法中观察到预测率较低；因此，需要对这些局限性进行进一步研究并选择合适的方法。
