Reliability of machine learning to diagnose pediatric obstructive sleep apnea: Systematic review and meta‐analysis

Abstract

Background Machine‐learning approaches have enabled promising results in efforts to simplify the diagnosis of pediatric obstructive sleep apnea (OSA). A comprehensive review and analysis of such studies increase the confidence level of practitioners and healthcare providers in the implementation of these methodologies in clinical practice. Objective To assess the reliability of machine‐learning‐based methods to detect pediatric OSA. Data Sources Two researchers conducted an electronic search on the Web of Science and Scopus using term, and studies were reviewed along with their bibliographic references. Eligibility Criteria Articles or reviews (Year 2000 onwards) that applied machine learning to detect pediatric OSA; reported data included information enabling derivation of true positive, false negative, true negative, and false positive cases; polysomnography served as diagnostic standard. Appraisal and Synthesis Methods Pooled sensitivities and specificities were computed for three apnea‐hypopnea index (AHI) thresholds: 1 event/hour (e/h), 5 e/h, and 10 e/h. Random‐effect models were assumed. Summary receiver‐operating characteristics (SROC) analyses were also conducted. Heterogeneity (I 2) was evaluated, and publication bias was corrected (trim and fill). Results Nineteen studies were finally retained, involving 4767 different pediatric sleep studies. Machine learning improved diagnostic performance as OSA severity criteria increased reaching optimal values for AHI = 10 e/h (0.652 sensitivity; 0.931 specificity; and 0.940 area under the SROC curve). Publication bias correction had minor effect on summary statistics, but high heterogeneity was observed among the studies.

Bispectral Analysis of Heart Rate Variability to Characterize and Help Diagnose Pediatric Sleep Apnea

“…Finally, despite the high diagnostic performance achieved here through bispectral analysis and the MLP models constructed, the promising results obtained by deep learning techniques in healthcare issues in recent years highlight the potential utility of these methods to automate the diagnosis of pediatric OSA [14]. Accordingly, in trying to increase the diagnostic performance, the inclusion of deep learning methods in the pediatric OSA context is a future research need.…”

“…Finally, although the results of the diagnostic performance from studies using physiological data from different sources must be carefully compared, it is interesting to contrast our results with the meta-analysis of a recently published systematic review [14]. In this work, Gutiérrez-Tobal et al gathered the pooled Se and Sp results from nineteen studies of machine learning methods to diagnose pediatric OSA that fulfilled their eligibility criteria [14]. A meta-analysis was performed for the same OSA severity thresholds that were employed here, which obtained an Se of 84.9%, 71.4% and 65.2% for the 1, 5 and 10 e/h cutoffs, respectively.…”

“…A recently published systematic review [14] analyzed and conducted a meta-analysis on machine learning techniques employed to automatically diagnose pediatric OSA. Among the shortcomings identified in the literature, the authors highlighted that most of the studies were exclusively based on the analysis of SpO 2 signals.…”

“…Among the shortcomings identified in the literature, the authors highlighted that most of the studies were exclusively based on the analysis of SpO 2 signals. Thus, there exists a lack of studies performing machine learning techniques using other physiological signals as alternative approaches to the gold standard PSG [14].…”

Automated analysis of the oximetry signal to simplify the diagnosis of pediatric sleep apnea: from feature-engineering to deep-learning approaches

“…MLP is the ANN-based pattern recognition algorithm most widely used in the pediatric OSA context (Gutiérrez-Tobal et al, 2021). MLP is a feed-forward neural network with an architecture consisting on several fully-connected layers (input, hidden, and output layers) composed of basic mathematical units that imitate biological neurons, called perceptrons (Bishop, 2006).…”