Liu Tai-Xiang, Zheng Jin-Xin, Chen Zheng, Zhang Zi-Chen, Li Dan, Shi Li-Ping
Department of NICU, The Children's Hospital, Zhejiang University School of Medicine, National Clinical Research Center for Child Health, Hangzhou, China.
Department of Nephrology, Ruijin Hospital, Institute of Nephrology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Front Pediatr. 2023 Apr 4;11:1097950. doi: 10.3389/fped.2023.1097950. eCollection 2023.
Nonsteroidal anti-inflammatory drugs (NSAIDs) have been widely used in the closure of ductus arteriosus in premature infants. We aimed to develop and validate an interpretable machine-learning model for predicting the efficacy of NSAIDs for closing hemodynamically significant patent ductus arteriosus (hsPDA) in preterm infants.
We assessed 182 preterm infants ≤ 30 weeks of gestational age first treated with NSAIDs to close hsPDA. According to the treatment outcome, patients were divided into a "success" group and "failure" group. Variables for analysis were demographic features, clinical features, as well as laboratory and echocardiographic parameters within 72 h before medication use. We developed the machine-learning model using random forests. Model performance was assessed by the area under the receiver operating characteristic curve (AUC). Variable-importance and marginal-effect plots were constructed to explain the predictive model. The model was validated using an external cohort of two preterm infants who received ibuprofen (p.o.) to treat hsPDA.
Eighty-three cases (45.6%) were in the success group and 99 (54.4%) in the failure group. Infants in the success group were associated with maternal chorioamnionitis ( = 0.002), multiple births ( = 0.007), gestational age at birth ( = 0.020), use of indometacin ( = 0.007), use of inotropic agents ( < 0.001), noninvasive ventilation ( = 0.001), plasma albumin level ( < 0.001), PDA size ( = 0.038) and Vmax ( = 0.013). Multivariable binary logistic regression analysis showed that maternal chorioamnionitis, multiple births, use of indomethacin, use of inotropic agents, plasma albumin level, and PDA size were independent risk factors influencing the efficacy of NSAIDs ( < 0.05). The AUC of the random forest model was 0.792. The top-three features contributing most to the model in the variable-importance plot were the plasma albumin level and platelet count 72 h before treatment and 24-h urine volume before treatment. In the external cohort, treatment succeeded in one case and failed in the other. The probabilities of success and failure predicted by the random forest model were 60.2% and 48.4%, respectively.
Based on clinical, laboratory, and echocardiographic features before first-time NSAIDs treatment, we constructed an interpretable machine-learning model, which has a certain reference value for predicting the closure of hsPDA in premature infants under 30 weeks of gestational age.
非甾体类抗炎药（NSAIDs）已广泛用于早产儿动脉导管未闭的封堵治疗。我们旨在开发并验证一种可解释的机器学习模型，用于预测NSAIDs对早产儿血流动力学显著的动脉导管未闭（hsPDA）的封堵疗效。
我们评估了182例胎龄≤30周、首次接受NSAIDs治疗以关闭hsPDA的早产儿。根据治疗结果，将患者分为“成功”组和“失败”组。分析变量包括人口统计学特征、临床特征以及用药前72小时内的实验室和超声心动图参数。我们使用随机森林开发了机器学习模型。通过受试者操作特征曲线下面积（AUC）评估模型性能。构建变量重要性图和边际效应图以解释预测模型。使用接受布洛芬（口服）治疗hsPDA的两名早产儿的外部队列对模型进行验证。
成功组83例（45.6%），失败组99例（54.4%）。成功组的婴儿与母亲绒毛膜羊膜炎（P = 0.002）、多胎妊娠（P = 0.007）、出生胎龄（P = 0.020）、使用吲哚美辛（P = 0.007）、使用强心剂（P < 0.001）、无创通气（P = 0.001）、血浆白蛋白水平（P < 0.001）、PDA大小（P = 0.038）和Vmax（P = 0.013）有关。多变量二元逻辑回归分析显示，母亲绒毛膜羊膜炎、多胎妊娠、使用吲哚美辛、使用强心剂、血浆白蛋白水平和PDA大小是影响NSAIDs疗效的独立危险因素（P < 0.05）。随机森林模型的AUC为0.792。在变量重要性图中对模型贡献最大的前三个特征是治疗前72小时的血浆白蛋白水平和血小板计数以及治疗前24小时尿量。在外部队列中，一例治疗成功，另一例失败。随机森林模型预测的成功和失败概率分别为60.2%和48.4%。
基于首次NSAIDs治疗前的临床、实验室和超声心动图特征，我们构建了一个可解释的机器学习模型，该模型对预测胎龄小于30周的早产儿hsPDA的闭合具有一定参考价值。
