预测儿科的宏类耐药性 Mycoplasma pneumoniae肺炎:一个机器学习建模研究研究
Shuo Yang1,2, Xinying Liu1,2, Huizhe Wang1,2
1First Teaching Hospital of Tianjin University of Traditional Chinese Medicine, Tianjin, 300381, China.
概括
一个新的机器学习模型可以识别患有抗宏化物耐药Mycoplasma pneumoniae肺炎 (MRMPP) 的儿童. 这种工具有助于早期检测和指导抗生素治疗,改善临床决策.
科学领域:
- 儿童传染病 儿童传染病
- 机器学习在医学中的应用
- 临床预测建模模型
背景情况:
- 抗宏化物耐药的Mycoplasma pneumoniae肺炎 (MRMPP) 在儿科护理中构成了重大挑战.
- 早期发现MRMPP对于有效治疗和预防抗菌素耐药性至关重要.
- 目前的诊断方法可能并不总是能够及时识别耐药病例.
研究的目的:
- 开发和验证基于机器学习的临床预测模型,用于识别儿科MRMPP.
- 为了促进耐药病例的早期检测,并指导有针对性的治疗干预.
- 为儿童肺炎合理使用抗生素提供数据驱动工具.
主要方法:
- 一个回顾性,单中心的研究利用人口统计学,实验室和儿科患者的炎症数据与Mycoplasma pneumoniae肺炎 (MPP).
- 开发一个堆叠集团预测模型,使用特征选择来识别关键预测因素.
- 使用内部交叉验证和独立的外部时间队列进行验证;用于模型解释性的SHapley添加式解释 (SHAP).
主要成果:
- 堆叠组合模型表现出强的性能,AUC为0.857 (内部验证) 和0.812 (外部验证).
- 发现的关键预测因素包括IL-17A,IFN-γ,CRP,A/G比率,之前的类药物使用,以及医院前的疗程.
- 该模型可通过网页工具访问,以便快速评估抗性风险.
结论:
- 开发的机器学习模型有效地识别了患MRMPP高风险的儿童.
- 该工具是临床医生关于抗生素使用的宝贵决策辅助工具.
- 该模型在治疗儿科肺炎方面显示出显著的临床翻译价值.
相关概念视频
01:14Atypical Pneumonia
Atypical pneumonia, often caused by Mycoplasma pneumoniae, is a form of pulmonary infection that differs from the classical presentation of bacterial pneumonia in both its cause and clinical symptoms. Mycoplasma pneumoniae is a pleomorphic bacterium notable for its lack of a rigid cell wall. This structural characteristic imparts resistance to beta-lactam antibiotics and significantly influences the bacterium’s behavior within the human host.Other pathogens responsible for the disease include...
01:25Mechanism of Antibiotic Resistance in MRSA
Antibiotic resistance in bacteria arises when microorganisms evolve the ability to withstand drugs designed to kill them or inhibit their growth, rendering once-effective treatments useless. This phenomenon, driven by genetic change and selection under antibiotic exposure, poses a profound threat to modern medicine. Mechanisms include drug-inactivating enzymes (e.g., β-lactamases), efflux pumps that eject antibiotics, mutations altering antibiotic targets, decreased drug uptake, and acquisition...