文献速递胸部CT

基于临床特征与胸部CT定量测量的机器学习预测住院COVID-19患者不良临床结局

Machine learning based on clinical characteristics and chest CT quantitative measurements for prediction of adverse clinical outcomes in hospitalized patients with COVID-19.
PubMed 文献 · Eur Radiol · 2021-04-15

这项回顾性多中心研究纳入424例入院时非重症COVID-19患者,用深度学习框架在胸部CT上量化肺受累程度,结合临床特征构建XGBoost模型预测住院期间重症/危重症或死亡,外部验证队列98例,主队列与验证队列AUC分别为0.959和0.953。

要点

  • CT病灶占比(lesion%)是模型纳入的影像定量特征,需在报告中准确量化肺受累范围。
  • 模型联合LDH、合并症、CT lesion%和hs-cTnI预测不良结局,主队列AUC 0.959。
  • 外部验证队列AUC 0.953,提示模型在不同中心间具有较好泛化能力。

核心结论

  • 基于临床特征和胸部CT定量测量的XGBoost模型可有效预测住院COVID-19患者不良结局,主队列AUC 0.959(95%CI 0.936-0.976),验证队列AUC 0.953(95%CI 0.891-0.986)。

研究设计与样本

  • 回顾性多中心研究,主队列纳入2020年1月17日至2月17日入院时非重症COVID-19患者424例,外部验证队列98例。
  • 采用基于深度学习的框架在胸部CT图像上量化肺受累程度,复合终点为住院期间发生重症/危重症COVID-19或死亡。
  • 选择最优机器学习分类器XGBoost和最优特征子集构建模型,特征包括LDH、合并症存在、CT病灶占比(lesion%)和hs-cTnI。

关键影像表现/征象

  • 主队列与验证队列不良结局发生率分别为8.7%和8.2%,差异无统计学意义(p=0.858)。
  • CT病灶占比(lesion%)由深度学习框架在胸部CT上量化肺受累程度获得,为模型纳入的影像定量特征。

诊断标准与关键数值

  • XGBoost模型基于LDH、合并症、CT病灶占比(lesion%)和hs-cTnI预测不良结局,主队列AUC 0.959(95%CI 0.936-0.976),验证队列AUC 0.953(95%CI 0.891-0.986)。
  • 复合终点定义为住院期间发生重症或危重症COVID-19或死亡。

临床应用与阅片要点

  • 在COVID-19住院患者胸部CT报告中应规范量化肺受累范围(lesion%),该指标被纳入预测模型。
  • 模型结合临床指标(LDH、合并症、hs-cTnI)和CT定量参数,可用于患者风险分层和医疗资源分配。
  • 外部验证显示模型在不同中心间具有较好泛化能力,但应用时需注意队列的入选条件为非重症入院患者。

局限性

  • 研究为回顾性设计,主队列与验证队列均来自特定时间段的住院患者,可能存在选择偏倚。
  • 原文未报告模型在更广泛人群或不同病毒变异株中的验证结果。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: To develop and validate a machine learning model for the prediction of adverse outcomes in hospitalized patients with COVID-19.

METHODS: We included 424 patients with non-severe COVID-19 on admission from January 17, 2020, to February 17, 2020, in the primary cohort of this retrospective multicenter study. The extent of lung involvement was quantified on chest CT images by a deep learning-based framework. The composite endpoint was the occurrence of severe or critical COVID-19 or death during hospitalization. The optimal machine learning classifier and feature subset were selected for model construction. The performance was further tested in an external validation cohort consisting of 98 patients.

RESULTS: There was no significant difference in the prevalence of adverse outcomes (8.7% vs. 8.2%, p = 0.858) between the primary and validation cohorts. The machine learning method extreme gradient boosting (XGBoost) and optimal feature subset including lactic dehydrogenase (LDH), presence of comorbidity, CT lesion ratio (lesion%), and hypersensitive cardiac troponin I (hs-cTnI) were selected for model construction. The XGBoost classifier based on the optimal feature subset performed well for the prediction of developing adverse outcomes in the primary and validation cohorts, with AUCs of 0.959 (95% confidence interval [CI]: 0.936-0.976) and 0.953 (95% CI: 0.891-0.986), respectively. Furthermore, the XGBoost classifier also showed clinical usefulness.

CONCLUSIONS: We presented a machine learning model that could be effectively used as a predictor of adverse outcomes in hospitalized patients with COVID-19, opening up the possibility for patient stratification and treatment allocation.

KEY POINTS: • Developing an individually prognostic model for COVID-19 has the potential to allow efficient allocation of medical resources. • We proposed a deep learning-based framework for accurate lung involvement quantification on chest CT images. • Machine learning based on clinical and CT variables can facilitate the prediction of adverse outcomes of COVID-19.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Feng Z, Shen H, Gao K, et al. Machine learning based on clinical characteristics and chest CT quantitative measurements for prediction of adverse clinical outcomes in hospitalized patients with COVID-19. Eur Radiol. 2021. PMID: 33856514. doi:10.1007/s00330-021-07957-z

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。