Mori Martina, Palumbo Diego, De Lorenzo Rebecca, Broggi Sara, Compagnone Nicola, Guazzarotti Giorgia, Giorgio Esposito Pier, Mazzilli Aldo, Steidler Stephanie, Pietro Vitali Giordano, Del Vecchio Antonella, Rovere Querini Patrizia, De Cobelli Francesco, Fiorino Claudio
Medical Physics, San Raffaele Scientific Institute, Milano, Italy.
Radiology, San Raffaele Scientific Institute, Milano, Italy.
Phys Med. 2021 May;85:63-71. doi: 10.1016/j.ejmp.2021.04.022. Epub 2021 Apr 30.
To train and validate a predictive model of mortality for hospitalized COVID-19 patients based on lung densitometry.
Two-hundred-fifty-one patients with respiratory symptoms underwent CT few days after hospitalization. "Aerated" (AV), "consolidated" (CV) and "intermediate" (IV) lung sub-volumes were quantified by an operator-independent method based on individual HU maximum gradient recognition. AV, CV, IV, CV/AV, IV/AV, and HU of the first peak position were extracted. Relevant clinical parameters were prospectively collected. The population was composed by training (n = 166) and validation (n = 85) consecutive cohorts, and backward multi-variate logistic regression was applied on the training group to build a CT_model. Similarly, models including only clinical parameters (CLIN_model) and both CT/clinical parameters (COMB_model) were developed. Model's performances were assessed by goodness-of-fit (H&L-test), calibration and discrimination. Model's performances were tested in the validation group.
Forty-three patients died (25/18 in training/validation). CT_model included AVmax (i.e. maximum AV between lungs), CV and CV/AE, while CLIN_model included random glycemia, C-reactive protein and biological drugs (protective). Goodness-of-fit and discrimination were similar (H&L:0.70 vs 0.80; AUC:0.80 vs 0.80). COMB_model including AVmax, CV, CV/AE, random glycemia, biological drugs and active cancer, outperformed both models (H&L:0.91; AUC:0.89, 95%CI:0.82-0.93). All models showed good calibration (R:0.77-0.97). Despite several patient's characteristics were different between training and validation cohorts, performances in the validation cohort confirmed good calibration (R:0-70-0.81) and discrimination for CT_model/COMB_model (AUC:0.72/0.76), while CLIN_model performed worse (AUC:0.64).
Few automatically extracted densitometry parameters with clear functional meaning predicted mortality of COVID-19 patients. Combined with clinical features, the resulting predictive model showed higher discrimination/calibration.
基于肺部密度测定法训练并验证住院COVID-19患者的死亡预测模型。
251例有呼吸道症状的患者在住院几天后接受了CT检查。通过基于个体HU最大梯度识别的独立于操作者的方法对“充气”（AV）、“实变”（CV）和“中间”（IV）肺子体积进行量化。提取AV、CV、IV、CV/AV、IV/AV以及第一个峰值位置的HU。前瞻性收集相关临床参数。该人群由连续的训练队列（n = 166）和验证队列（n = 85）组成，并对训练组应用向后多变量逻辑回归来构建CT模型。同样，开发了仅包括临床参数的模型（CLIN模型）以及包括CT/临床参数的模型（COMB模型）。通过拟合优度（H&L检验）、校准和鉴别来评估模型的性能。在验证组中测试模型的性能。
43例患者死亡（训练组/验证组分别为25/18例）。CT模型包括AVmax（即两肺之间的最大AV）、CV和CV/AE，而CLIN模型包括随机血糖、C反应蛋白和生物药物（具有保护作用）。拟合优度和鉴别能力相似（H&L：0.70对0.80；AUC：0.80对0.80）。包括AVmax、CV、CV/AE、随机血糖、生物药物和活动性癌症的COMB模型优于其他两个模型（H&L：0.91；AUC：0.89，95%CI：0.82 - 0.93）。所有模型均显示出良好的校准（R：0.77 - 0.97）。尽管训练队列和验证队列之间有几个患者特征不同，但验证队列中的性能证实了CT模型/COMB模型具有良好的校准（R：0.70 - 0.81）和鉴别能力（AUC：0.72/0.76），而CLIN模型表现较差（AUC：0.64）。
少数具有明确功能意义的自动提取的密度测定参数可预测COVID-19患者的死亡率。结合临床特征，所得预测模型显示出更高的鉴别能力/校准度。
