Ardila Carlos M, González-Arroyave Daniel, Tobón Sergio
Basic Sciences Department, Biomedical Stomatology Research Group, Faculty of Dentistry, Universidad de Antioquia U de A, Medellín Colombia.
Postdoctoral Program, CIFE University Center, Cuernavaca, México.
PLoS One. 2025 Feb 25;20(2):e0319460. doi: 10.1371/journal.pone.0319460. eCollection 2025.
Antimicrobial resistance (AMR) poses a worldwide health threat; quick and accurate identification of AMR enhances patient outcomes and reduces inappropriate antibiotic usage. The objective of this systematic review is to evaluate the efficacy of machine learning (ML) approaches in predicting AMR in critical and high-priority pathogens (CHPP), considering antimicrobial susceptibility tests in real-world healthcare settings.
The search methodology encompassed the examination of several databases, such as PubMed/MEDLINE, EMBASE, Web of Science, SCOPUS, and SCIELO. An extensive electronic database search was conducted from the inception of these databases until November 2024.
After completing the final step of the eligibility assessment, the systematic review ultimately included 21 papers. All included studies were cohort observational studies assessing 688,107 patients and 1,710,867 antimicrobial susceptibility tests. GBDT, Random Forest, and XGBoost were the top-performing ML models for predicting antibiotic resistance in CHPP infections. GBDT exhibited the highest AuROC values compared to Logistic Regression (LR), with a mean value of 0.80 (range 0.77-0.90) and 0.68 (range 0.50-0.83), respectively. Similarly, Random Forest generally showed better AuROC values compared to LR (mean value 0.75, range 0.58-0.98 versus mean value 0.71, range 0.61-0.83). However, some predictors selected by these algorithms align with those suggested by LR.
ML displays potential as a technology for predicting AMR, incorporating antimicrobial susceptibility tests in CHPP in real-world healthcare settings. However, limitations such as retrospective methodology for model development, nonstandard data processing, and lack of validation in randomized controlled trials must be considered before applying these models in clinical practice.
抗菌药物耐药性（AMR）对全球健康构成威胁；快速准确地识别AMR可改善患者预后并减少不恰当的抗生素使用。本系统评价的目的是评估机器学习（ML）方法在预测危急和高优先级病原体（CHPP）的AMR方面的有效性，同时考虑现实医疗环境中的抗菌药物敏感性试验。
检索方法包括对多个数据库进行检索，如PubMed/MEDLINE、EMBASE、科学引文索引（Web of Science）、Scopus和拉丁美洲及加勒比地区卫生科学数据库（SCIELO）。从这些数据库建立之初至2024年11月进行了广泛的电子数据库检索。
在完成资格评估的最后一步后，本系统评价最终纳入了21篇论文。所有纳入研究均为队列观察性研究，共评估了688,107例患者和1,710,867次抗菌药物敏感性试验。梯度提升决策树（GBDT）、随机森林和极端梯度提升（XGBoost）是预测CHPP感染中抗生素耐药性的表现最佳的ML模型。与逻辑回归（LR）相比，GBDT的曲线下面积（AuROC）值最高，其平均值分别为0.80（范围0.77 - 0.90）和0.68（范围0.50 - 0.83）。同样，与LR相比，随机森林通常显示出更好的AuROC值（平均值0.75，范围0.58 - 0.98；而LR平均值为0.71，范围0.61 - 0.83）。然而，这些算法选择的一些预测因子与LR所建议的预测因子一致。
在现实医疗环境中，ML在结合CHPP的抗菌药物敏感性试验来预测AMR方面显示出作为一种技术的潜力。然而，在将这些模型应用于临床实践之前，必须考虑诸如模型开发的回顾性方法、非标准数据处理以及缺乏随机对照试验验证等局限性。
