Department of Pathology, Division of Clinical Pathology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, Republic of China.
Department of Pathology, Division of Clinical Pathology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, Republic of China; Graduate Institute of Medical Science, National Defense Medical Center, Taipei, Taiwan, Republic of China.
J Glob Antimicrob Resist. 2024 Sep;38:173-180. doi: 10.1016/j.jgar.2024.06.004. Epub 2024 Jun 22.
The World Health Organization named Stenotrophomonas maltophilia (SM) a critical multi-drug resistant threat, necessitating rapid diagnostic strategies. Traditional culturing methods require up to 96 h, including 72 h for bacterial growth, identification with matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) through protein profile analysis, and 24 h for antibiotic susceptibility testing. In this study, we aimed at developing an artificial intelligence-clinical decision support system (AI-CDSS) by integrating MALDI-TOF MS and machine learning to quickly identify levofloxacin and trimethoprim/sulfamethoxazole resistance in SM, optimizing treatment decisions.
We selected 8,662 SM from 165,299 MALDI-TOF MS-analysed bacterial specimens, collected from a major medical centre and four secondary hospitals. We exported mass-to-charge values and intensity spectral profiles from MALDI-TOF MS .mzML files to predict antibiotic susceptibility testing results, obtained with the VITEK-2 system using machine learning algorithms. We optimized the models with GridSearchCV and 5-fold cross-validation.
We identified distinct spectral differences between resistant and susceptible SM strains, demonstrating crucial resistance features. The machine learning models, including random forest, light-gradient boosting machine, and XGBoost, exhibited high accuracy. We established an AI-CDSS to offer healthcare professionals swift, data-driven advice on antibiotic use.
MALDI-TOF MS and machine learning integration into an AI-CDSS significantly improved rapid SM resistance detection. This system reduced the identification time of resistant strains from 24 h to minutes after MALDI-TOF MS identification, providing timely and data-driven guidance. Combining MALDI-TOF MS with machine learning could enhance clinical decision-making and improve SM infection treatment outcomes.
世界卫生组织将嗜麦芽窄食单胞菌（SM）命名为关键的多重耐药威胁，这需要快速的诊断策略。传统的培养方法需要长达 96 小时，包括 72 小时的细菌生长时间、通过基质辅助激光解吸/电离飞行时间质谱（MALDI-TOF MS）进行蛋白质谱分析的鉴定，以及 24 小时的抗生素药敏试验。本研究旨在通过整合 MALDI-TOF MS 和机器学习，开发人工智能临床决策支持系统（AI-CDSS），快速识别 SM 对左氧氟沙星和复方磺胺甲噁唑的耐药性，优化治疗决策。
我们从一个主要医疗中心和四个二级医院的 165299 份 MALDI-TOF MS 分析的细菌标本中选择了 8662 株 SM。我们从 MALDI-TOF MS.mzML 文件中导出质荷比和强度光谱谱图，以使用机器学习算法预测使用 VITEK-2 系统获得的抗生素药敏试验结果。我们使用 GridSearchCV 和 5 倍交叉验证来优化模型。
我们发现耐药和敏感 SM 菌株之间存在明显的光谱差异，表明存在关键的耐药特征。包括随机森林、轻梯度提升机和 XGBoost 在内的机器学习模型具有很高的准确性。我们建立了一个 AI-CDSS，为医疗保健专业人员提供快速、数据驱动的抗生素使用建议。
MALDI-TOF MS 和机器学习集成到 AI-CDSS 中，显著提高了快速 SM 耐药检测的准确性。该系统将鉴定耐药菌株的时间从 24 小时缩短到 MALDI-TOF MS 鉴定后的几分钟，提供了及时和数据驱动的指导。将 MALDI-TOF MS 与机器学习相结合，可以增强临床决策，并改善 SM 感染的治疗效果。
