Suppr超能文献

一项基于肺部超声评分和临床指标的机器学习预测新生儿呼吸窘迫综合征严重程度的研究。

A study of machine learning to predict NRDS severity based on lung ultrasound score and clinical indicators.

作者信息

Huang Chunyan, Ha Xiaoming, Cui Yanfang, Zhang Hongxia

机构信息

Department of Ultrasound, Yantaishan Hospital, Yantai, China.

Medical Impact and Nuclear Medicine Program, Binzhou Medical University, Yantai, China.

出版信息

Front Med (Lausanne). 2024 Nov 1;11:1481830. doi: 10.3389/fmed.2024.1481830. eCollection 2024.

Abstract

OBJECTIVE

To develop predictive models for neonatal respiratory distress syndrome (NRDS) using machine learning algorithms to improve the accuracy of severity predictions.

METHODS

This double-blind cohort study included 230 neonates admitted to the neonatal intensive care unit (NICU) of Yantaishan Hospital between December 2020 and June 2023. Of these, 119 neonates were diagnosed with NRDS and placed in the NRDS group, while 111 neonates with other conditions formed the non-NRDS (N-NRDS) group. All neonates underwent lung ultrasound and various clinical assessments, with data collected on the oxygenation index (OI), sequential organ failure assessment (SOFA), respiratory index (RI), and lung ultrasound score (LUS). An independent sample test was used to compare the groups' LUS, OI, RI, SOFA scores, and clinical data. Use Least Absolute Shrinkage and Selection Operator (LASSO) regression to identify predictor variables, and construct a model for predicting NRDS severity using logistic regression (LR), random forest (RF), artificial neural network (NN), and support vector machine (SVM) algorithms. The importance of predictive variables and performance metrics was evaluated for each model.

RESULTS

The NRDS group showed significantly higher LUS, SOFA, and RI scores and lower OI values than the N-NRDS group ( < 0.01). LUS, SOFA, and RI scores were significantly higher in the severe NRDS group compared to the mild and moderate groups, while OI was markedly lower ( < 0.01). LUS, OI, RI, and SOFA scores were the most impactful variables for the predictive efficacy of the models. The RF model performed best of the four models, with an AUC of 0.894, accuracy of 0.808, and sensitivity of 0.706. In contrast, the LR, NN, and SVM models have lower AUC values than the RF model with 0.841, 0.828, and 0.726, respectively.

CONCLUSION

Four predictive models based on machine learning can accurately assess the severity of NRDS. Among them, the RF model exhibits the best predictive performance, offering more effective support for the treatment and care of neonates.

摘要

目的

使用机器学习算法开发新生儿呼吸窘迫综合征(NRDS)的预测模型,以提高严重程度预测的准确性。

方法

这项双盲队列研究纳入了2020年12月至2023年6月期间在烟台山医院新生儿重症监护病房(NICU)收治的230例新生儿。其中,119例新生儿被诊断为NRDS并纳入NRDS组,111例患有其他疾病的新生儿组成非NRDS(N-NRDS)组。所有新生儿均接受了肺部超声检查和各种临床评估,收集了氧合指数(OI)、序贯器官衰竭评估(SOFA)、呼吸指数(RI)和肺部超声评分(LUS)的数据。采用独立样本检验比较两组的LUS、OI、RI、SOFA评分及临床资料。使用最小绝对收缩和选择算子(LASSO)回归识别预测变量,并使用逻辑回归(LR)、随机森林(RF)、人工神经网络(NN)和支持向量机(SVM)算法构建预测NRDS严重程度的模型。对每个模型评估预测变量的重要性和性能指标。

结果

NRDS组的LUS、SOFA和RI评分显著高于N-NRDS组,而OI值较低(<0.01)。与轻度和中度组相比,重度NRDS组的LUS、SOFA和RI评分显著更高,而OI显著更低(<0.01)。LUS、OI、RI和SOFA评分是模型预测效能最有影响的变量。四个模型中RF模型表现最佳,AUC为0.894,准确率为0.808,灵敏度为0.706。相比之下,LR、NN和SVM模型的AUC值分别为0.841、0.828和0.726,均低于RF模型。

结论

基于机器学习的四个预测模型能够准确评估NRDS的严重程度。其中,RF模型表现出最佳的预测性能,为新生儿的治疗和护理提供了更有效的支持。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1f51/11568467/01b5d0e9f673/fmed-11-1481830-g001.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验