Huna, São Paulo, SP, Brazil; Departamento de Ciência da Computação, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil.
Departamento de Ciência da Computação, Universidade Federal de Minas Gerais, Belo Horizonte, MG, Brazil.
Int J Med Inform. 2022 Sep;165:104835. doi: 10.1016/j.ijmedinf.2022.104835. Epub 2022 Jul 27.
Despite an extensive network of primary care availability, Brazil has suffered profoundly during the COVID-19 pandemic, experiencing the greatest sanitary collapse in its history. Thus, it is important to understand phenotype risk factors for SARS-CoV-2 infection severity in the Brazilian population in order to provide novel insights into the pathogenesis of the disease.
This study proposes to predict the risk of COVID-19 death through machine learning, using blood biomarkers data from patients admitted to two large hospitals in Brazil.
We retrospectively collected blood biomarkers data in a 24-h time window from 6,979 patients with COVID-19 confirmed by positive RT-PCR admitted to two large hospitals in Brazil, of whom 291 (4.2%) died and 6,688 (95.8%) were discharged. We then developed a large-scale exploration of risk models to predict the probability of COVID-19 severity, finally choosing the best performing model regarding the average AUROC. To improve generalizability, for each model five different testing scenarios were conducted, including two external validations.
We developed a machine learning-based panel composed of parameters extracted from the complete blood count (lymphocytes, MCV, platelets and RDW), in addition to C-Reactive Protein, which yielded an average AUROC of 0.91 ± 0.01 to predict death by COVID-19 confirmed by positive RT-PCR within a 24-h window.
Our study suggests that routine laboratory variables could be useful to identify COVID-19 patients under higher risk of death using machine learning. Further studies are needed for validating the model in other populations and contexts, since the natural history of SARS-CoV-2 infection and its consequences on the hematopoietic system and other organs is still quite recent.
尽管有广泛的初级保健网络，巴西在 COVID-19 大流行期间遭受了严重打击，经历了历史上最严重的卫生系统崩溃。因此，了解巴西人群中 SARS-CoV-2 感染严重程度的表型危险因素对于深入了解疾病的发病机制非常重要。
本研究拟通过机器学习，利用巴西两家大型医院的 COVID-19 患者的血液生物标志物数据来预测 COVID-19 死亡风险。
我们回顾性地收集了巴西两家大型医院确诊为 COVID-19 的 6979 例患者的血液生物标志物数据，这些患者在 24 小时时间窗内接受了治疗，其中 291 例（4.2%）死亡，6688 例（95.8%）出院。然后，我们开发了一种大规模的风险模型探索，以预测 COVID-19 严重程度的概率，最终选择平均 AUROC 表现最佳的模型。为了提高泛化能力，对于每个模型，我们进行了五种不同的测试场景，包括两种外部验证。
我们开发了一个基于机器学习的面板，由来自全血细胞计数（淋巴细胞、MCV、血小板和 RDW）的参数以及 C 反应蛋白组成，该面板在 24 小时窗口内预测由阳性 RT-PCR 确诊的 COVID-19 死亡的平均 AUROC 为 0.91±0.01。
我们的研究表明，使用机器学习可以从常规实验室变量中识别出 COVID-19 患者中死亡风险较高的患者。需要进一步的研究来验证该模型在其他人群和环境中的有效性，因为 SARS-CoV-2 感染的自然史及其对造血系统和其他器官的影响还相当新。
