Integrating sequencing methods with machine learning for antimicrobial susceptibility testing in pediatric infections: current advances and future insights

Abstract

Antimicrobial resistance (AMR) presents a critical challenge in clinical settings, particularly among pediatric patients with life-threatening conditions such as sepsis, meningitis, and neonatal infections. The increasing prevalence of multi- and pan-resistant pathogens is strongly associated with adverse clinical outcomes. Recent technological advances in sequencing methods, including metagenomic next-generation sequencing (mNGS), Oxford Nanopore Technologies (ONT), and targeted sequencing (TS), have significantly enhanced the detection of both pathogens and their associated resistance genes. However, discrepancies between resistance gene detection and antimicrobial susceptibility testing (AST) often hinder the direct clinical application of sequencing results. These inconsistencies may arise from factors such as genetic mutations or variants in resistance genes, differences in the phenotypic expression of resistance, and the influence of environmental conditions on resistance levels, which can lead to variations in the observed resistance patterns. Machine learning (ML) provides a promising solution by integrating large-scale resistance data with sequencing outcomes, enabling more accurate predictions of pathogen drug susceptibility. This review explores the application of sequencing technologies and ML in the context of pediatric infections, with a focus on their potential to track the evolution of resistance genes and predict antibiotic susceptibility. The goal of this review is to promote the incorporation of ML-based predictions into clinical practice, thereby improving the management of AMR in pediatric populations.

Keywords: Oxford Nanopore Technologies; antimicrobial resistance; machine learning; next-generation sequencing; pediatrics.

FIGURE 1

Overview of common pathogens implicated in pediatric infections at various anatomical sites, along with their documented resistance mechanisms and associated antibiotic resistance genes (ARGs). (H. influenzae, Haemophilus influenzae; S. pneumoniae, Streptococcus pneumoniae; M. tuberculosis, Mycobacterium tuberculosis; S. aureus, Staphylococcus aureus; E. coli, Escherichia coli).

FIGURE 2

Workflow for machine learning (ML)-based prediction of antimicrobial resistance (AMR) using sequencing methods. The process starts with collecting and preparing whole-genome sequencing (WGS) data and corresponding antimicrobial susceptibility testing (AST) results. Low-quality data are filtered to ensure accuracy. Genomic sequences are aligned with the Comprehensive Antibiotic Resistance Database (CARD) database to identify potential resistance markers. These markers train ML models, which are evaluated for their predictive accuracy. Features are weighted based on significance, and models are refined and validated with clinical samples. The results are then used to improve clinical decision-making and guide antibiotic stewardship.

FIGURE 3

Machine learning (ML)-based integrated platform for detecting antibiotic susceptibility and antibiotic resistance genes (ARGs) in pediatrics. This figure visually encapsulates the prospective advancements in research and application for detecting antibiotic susceptibility and ARGs in pediatric infections. By integrating ML with high-throughput genomic sequencing, this approach not only enhances the accuracy of detecting multiple pathogens but also supports the refinement of antibiotic treatment strategies. Such advancements are pivotal for improving clinical management and therapeutic outcomes in pediatric patients.