Department of Pulmonary and Critical Care Medicine, Loudi Central Hospital, No. 51, Changqing Middle Street, Loudi, 417000, People's Republic of China.
Department of Pulmonary and Critical Care Medicine, Xiangtan Central Hospital, No. 120, Road Heping, Distract Yuhu, Xiangtan, 411100, People's Republic of China.
BMC Pulm Med. 2022 May 12;22(1):188. doi: 10.1186/s12890-022-01986-0.
Most severe, critical, or mortal COVID-19 cases often had a relatively stable period before their status worsened. We developed a deterioration risk model of COVID-19 (DRM-COVID-19) to predict exacerbation risk and optimize disease management on admission.
We conducted a multicenter retrospective cohort study with 239 confirmed symptomatic COVID-19 patients. A combination of the least absolute shrinkage and selection operator (LASSO), change-in-estimate (CIE) screened out independent risk factors for the multivariate logistic regression model (DRM-COVID-19) from 44 variables, including epidemiological, demographic, clinical, and lung CT features. The compound study endpoint was progression to severe, critical, or mortal status. Additionally, the model's performance was evaluated for discrimination, accuracy, calibration, and clinical utility, through internal validation using bootstrap resampling (1000 times). We used a nomogram and a network platform for model visualization.
In the cohort study, 62 cases reached the compound endpoint, including 42 severe, 18 critical, and two mortal cases. DRM-COVID-19 included six factors: dyspnea [odds ratio (OR) 4.89;confidence interval (95% CI) 1.53-15.80], incubation period (OR 0.83; 95% CI 0.68-0.99), number of comorbidities (OR 1.76; 95% CI 1.03-3.05), D-dimer (OR 7.05; 95% CI, 1.35-45.7), C-reactive protein (OR 1.06; 95% CI 1.02-1.1), and semi-quantitative CT score (OR 1.50; 95% CI 1.27-1.82). The model showed good fitting (Hosmer-Lemeshow goodness, X(8) = 7.0194, P = 0.53), high discrimination (the area under the receiver operating characteristic curve, AUROC, 0.971; 95% CI, 0.949-0.992), precision (Brier score = 0.051) as well as excellent calibration and clinical benefits. The precision-recall (PR) curve showed excellent classification performance of the model (AUC = 0.934). We prepared a nomogram and a freely available online prediction platform ( https://deterioration-risk-model-of-covid-19.shinyapps.io/DRMapp/ ).
We developed a predictive model, which includes the including incubation period along with clinical and lung CT features. The model presented satisfactory prediction and discrimination performance for COVID-19 patients who might progress from mild or moderate to severe or critical on admission, improving the clinical prognosis and optimizing the medical resources.
大多数严重、危急或致命的 COVID-19 病例在病情恶化前通常有一个相对稳定的时期。我们开发了一种 COVID-19 恶化风险模型（DRM-COVID-19），以预测入院时的恶化风险并优化疾病管理。
我们进行了一项多中心回顾性队列研究，纳入了 239 例确诊的有症状 COVID-19 患者。最小绝对收缩和选择算子（LASSO）和变化估计（CIE）的组合从 44 个变量中筛选出多变量逻辑回归模型（DRM-COVID-19）的独立危险因素，这些变量包括流行病学、人口统计学、临床和肺部 CT 特征。复合研究终点是进展为严重、危急或致命状态。此外，通过使用 bootstrap 重采样（1000 次）进行内部验证，评估模型的判别能力、准确性、校准和临床实用性。我们使用了一个列线图和一个网络平台来可视化模型。
在队列研究中，62 例达到复合终点，包括 42 例严重、18 例危急和 2 例死亡。DRM-COVID-19 包括六个因素：呼吸困难[比值比（OR）4.89；95%置信区间（95%CI）1.53-15.80]、潜伏期（OR 0.83；95%CI 0.68-0.99）、合并症数量（OR 1.76；95%CI 1.03-3.05）、D-二聚体（OR 7.05；95%CI，1.35-45.7）、C 反应蛋白（OR 1.06；95%CI 1.02-1.1）和半定量 CT 评分（OR 1.50；95%CI 1.27-1.82）。该模型具有良好的拟合度（Hosmer-Lemeshow 良好度，X(8) = 7.0194，P = 0.53）、高判别能力（受试者工作特征曲线下面积，AUROC，0.971；95%CI，0.949-0.992）、精确性（Brier 评分= 0.051）以及出色的校准和临床获益。精确召回（PR）曲线显示模型具有出色的分类性能（AUC = 0.934）。我们制作了一个列线图和一个免费的在线预测平台（https://deterioration-risk-model-of-covid-19.shinyapps.io/DRMapp/）。
我们开发了一种预测模型，包括潜伏期以及临床和肺部 CT 特征。该模型对入院时可能从轻症或中度进展为重症或危重症的 COVID-19 患者具有令人满意的预测和判别性能，改善了临床预后并优化了医疗资源。
