Hwang Jae Kyoon, Kim Dae Hyun, Na Jae Yoon, Son Joonhyuk, Oh Yoon Ju, Jung Donggoo, Kim Chang-Ryul, Kim Tae Hyun, Park Hyun-Kyung
Department of Pediatrics, Hanyang University College of Medicine, Seoul, Republic of Korea.
Department of Artificial Intelligence, Hanyang University, Seoul, Republic of Korea.
Front Pediatr. 2023 Jun 13;11:1155921. doi: 10.3389/fped.2023.1155921. eCollection 2023.
The aim of this study is to develop an enhanced machine learning-based prediction models for bronchopulmonary dysplasia (BPD) and its severity through a two-stage approach integrated with the duration of respiratory support (RSd) using prenatal and early postnatal variables from a nationwide very low birth weight (VLBW) infant cohort.
We included 16,384 VLBW infants admitted to the neonatal intensive care unit (ICU) of the Korean Neonatal Network (KNN), a nationwide VLBW infant registry (2013-2020). Overall, 45 prenatal and early perinatal clinical variables were selected. A multilayer perceptron (MLP)-based network analysis, which was recently introduced to predict diseases in preterm infants, was used for modeling and a stepwise approach. Additionally, we applied a complementary MLP network and established new BPD prediction models (PMbpd). The performances of the models were compared using the area under the receiver operating characteristic curve (AUROC) values. The Shapley method was used to determine the contribution of each variable.
We included 11,177 VLBW infants (3,724 without BPD (BPD 0), 3,383 with mild BPD (BPD 1), 1,375 with moderate BPD (BPD 2), and 2,695 with severe BPD (BPD 3) cases). Compared to conventional machine learning (ML) models, our PMbpd and two-stage PMbpd with RSd (TS-PMbpd) model outperformed both binary (0 vs. 1,2,3; 0,1 vs. 2,3; 0,1,2 vs. 3) and each severity (0 vs. 1 vs. 2 vs. 3) prediction (AUROC = 0.895 and 0.897, 0.824 and 0.825, 0.828 and 0.823, 0.783, and 0.786, respectively). GA, birth weight, and patent ductus arteriosus (PDA) treatment were significant variables for the occurrence of BPD. Birth weight, low blood pressure, and intraventricular hemorrhage were significant for BPD ≥2, birth weight, low blood pressure, and PDA ligation for BPD ≥3. GA, birth weight, and pulmonary hypertension were the principal variables that predicted BPD severity in VLBW infants.
We developed a new two-stage ML model reflecting crucial BPD indicators (RSd) and found significant clinical variables for the early prediction of BPD and its severity with high predictive accuracy. Our model can be used as an adjunctive predictive model in the practical NICU field.
本研究旨在通过两阶段方法，结合呼吸支持持续时间（RSd），利用全国极低出生体重（VLBW）婴儿队列中的产前和出生后早期变量，开发用于支气管肺发育不良（BPD）及其严重程度的增强型机器学习预测模型。
我们纳入了韩国新生儿网络（KNN）新生儿重症监护病房（ICU）收治的16384例VLBW婴儿，KNN是一个全国性的VLBW婴儿登记处（2013 - 2020年）。总体而言，选择了45个产前和围产期早期临床变量。基于多层感知器（MLP）的网络分析最近被引入用于预测早产儿疾病，用于建模和逐步方法。此外，我们应用了互补的MLP网络并建立了新的BPD预测模型（PMbpd）。使用受试者操作特征曲线下面积（AUROC）值比较模型的性能。使用Shapley方法确定每个变量的贡献。
我们纳入了11177例VLBW婴儿（3724例无BPD（BPD 0），3383例轻度BPD（BPD 1），1375例中度BPD（BPD 2），2695例重度BPD（BPD 3）病例）。与传统机器学习（ML）模型相比，我们的PMbpd和带有RSd的两阶段PMbpd（TS - PMbpd）模型在二元（0对1,2,3；0,1对2,3；0,1,2对3）和每种严重程度（0对1对2对3）预测方面均表现更优（AUROC分别为0.895和0.897、0.824和0.825、0.828和0.823、0.783和0.786）。孕周、出生体重和动脉导管未闭（PDA）治疗是BPD发生的重要变量。出生体重、低血压和脑室内出血对BPD≥2有显著意义，出生体重、低血压和PDA结扎对BPD≥3有显著意义。孕周、出生体重和肺动脉高压是预测VLBW婴儿BPD严重程度的主要变量。
我们开发了一种反映关键BPD指标（RSd）的新的两阶段ML模型，并发现了用于早期预测BPD及其严重程度的重要临床变量，具有较高的预测准确性。我们的模型可在实际的NICU领域用作辅助预测模型。
