机器学习在检测小儿癫痫发作中的准确性：系统评价与荟萃分析

Accuracy of Machine Learning in Detecting Pediatric Epileptic Seizures: Systematic Review and Meta-Analysis.

作者信息

Zou Zhuan, Chen Bin, Xiao Dongqiong, Tang Fajuan, Li Xihong

机构信息

Department of Emergency, West China Second University Hospital, Sichuan University, Chengdu, China.

Key Laboratory of Birth Defects and Related Diseases of Women and Children, Ministry of Education, Sichuan University, Chengdu, China.

出版信息

J Med Internet Res. 2024 Dec 11;26:e55986. doi: 10.2196/55986.

DOI:10.2196/55986

PMID:39661965

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11669868/

Abstract

BACKGROUND

Real-time monitoring of pediatric epileptic seizures poses a significant challenge in clinical practice. In recent years, machine learning (ML) has attracted substantial attention from researchers for diagnosing and treating neurological diseases, leading to its application for detecting pediatric epileptic seizures. However, systematic evidence substantiating its feasibility remains limited.

OBJECTIVE

This systematic review aimed to consolidate the existing evidence regarding the effectiveness of ML in monitoring pediatric epileptic seizures with an effort to provide an evidence-based foundation for the development and enhancement of intelligent tools in the future.

METHODS

We conducted a systematic search of the PubMed, Cochrane, Embase, and Web of Science databases for original studies focused on the detection of pediatric epileptic seizures using ML, with a cutoff date of August 27, 2023. The risk of bias in eligible studies was assessed using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2). Meta-analyses were performed to evaluate the C-index and the diagnostic 4-grid table, using a bivariate mixed-effects model for the latter. We also examined publication bias for the C-index by using funnel plots and the Egger test.

RESULTS

This systematic review included 28 original studies, with 15 studies on ML and 13 on deep learning (DL). All these models were based on electroencephalography data of children. The pooled C-index, sensitivity, specificity, and accuracy of ML in the training set were 0.76 (95% CI 0.69-0.82), 0.77 (95% CI 0.73-0.80), 0.74 (95% CI 0.70-0.77), and 0.75 (95% CI 0.72-0.77), respectively. In the validation set, the pooled C-index, sensitivity, specificity, and accuracy of ML were 0.73 (95% CI 0.67-0.79), 0.88 (95% CI 0.83-0.91), 0.83 (95% CI 0.71-0.90), and 0.78 (95% CI 0.73-0.82), respectively. Meanwhile, the pooled C-index of DL in the validation set was 0.91 (95% CI 0.88-0.94), with sensitivity, specificity, and accuracy being 0.89 (95% CI 0.85-0.91), 0.91 (95% CI 0.88-0.93), and 0.89 (95% CI 0.86-0.92), respectively.

CONCLUSIONS

Our systematic review demonstrates promising accuracy of artificial intelligence methods in epilepsy detection. DL appears to offer higher detection accuracy than ML. These findings support the development of DL-based early-warning tools in future research.

TRIAL REGISTRATION

PROSPERO CRD42023467260; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023467260.

摘要

背景

在临床实践中，对小儿癫痫发作进行实时监测是一项重大挑战。近年来，机器学习（ML）在神经疾病的诊断和治疗方面引起了研究人员的广泛关注，从而被应用于小儿癫痫发作的检测。然而，证实其可行性的系统证据仍然有限。

目的

本系统评价旨在整合关于ML在监测小儿癫痫发作有效性方面的现有证据，以便为未来智能工具的开发和改进提供循证基础。

方法

我们对PubMed、Cochrane、Embase和Web of Science数据库进行了系统检索，以查找专注于使用ML检测小儿癫痫发作的原始研究，截止日期为2023年8月27日。使用QUADAS-2（诊断准确性研究质量评估-2）对符合条件的研究中的偏倚风险进行评估。进行荟萃分析以评估C指数和诊断四格表，后者使用双变量混合效应模型。我们还通过漏斗图和Egger检验检查了C指数的发表偏倚。

结果

本系统评价纳入了28项原始研究，其中15项关于ML，13项关于深度学习（DL）。所有这些模型均基于儿童的脑电图数据。ML在训练集中的合并C指数、敏感性、特异性和准确性分别为0.76（95%CI 0.69-0.82）、0.77（95%CI 0.73-0.80）、0.74（95%CI 0.70-0.77）和0.75（95%CI 0.72-0.77）。在验证集中，ML的合并C指数、敏感性、特异性和准确性分别为0.73（95%CI 0.67-0.79）、0.88（95%CI 0.83-0.91）、0.83（95%CI 0.71-0.90）和0.78（95%CI 0.73-0.82）。同时，DL在验证集中的合并C指数为0.91（95%CI 0.88-0.94），敏感性、特异性和准确性分别为0.89（95%CI 0.85-0.91）、0.91（95%CI 0.88-0.93）和0.89（95%CI 0.86-0.92）。