Surveillance and Reporting, Provincial Population and Public Health, Alberta Health Services, Calgary, AB, Canada.
Surveillance and Reporting, Cancer Research and Analytics, Cancer Care Alberta, Alberta Health Services, Edmonton, AB, Canada.
Front Public Health. 2022 May 19;10:838514. doi: 10.3389/fpubh.2022.838514. eCollection 2022.
The COVID-19 pandemic has seen a large surge in case numbers over several waves, and has critically strained the health care system, with a significant number of cases requiring hospitalization and ICU admission. This study used a decision tree modeling approach to identify the most important predictors of severe outcomes among COVID-19 patients.
We identified a retrospective population-based cohort ( = 140,182) of adults who tested positive for COVID-19 between 5 March 2020 and 31 May 2021. Demographic information, symptoms and co-morbidities were extracted from a communicable disease and outbreak management information system and electronic medical records. Decision tree modeling involving conditional inference tree and random forest models were used to analyze and identify the key factors(s) associated with severe outcomes (hospitalization, ICU admission and death) following COVID-19 infection.
In the study cohort, nearly 6.37% were hospitalized, 1.39% were admitted to ICU and 1.57% died due to COVID-19. Older age (>71Y) and breathing difficulties were the top two factors associated with a poor prognosis, predicting about 50% of severe outcomes in both models. Neurological conditions, diabetes, cardiovascular disease, hypertension, and renal disease were the top five pre-existing conditions that altogether predicted 29% of outcomes. 79% of the cases with poor prognosis were predicted based on the combination of variables. Age stratified models revealed that among younger adults (18-40 Y), obesity was among the top risk factors associated with adverse outcomes.
Decision tree modeling has identified key factors associated with a significant proportion of severe outcomes in COVID-19. Knowledge about these variables will aid in identifying high-risk groups and allocating health care resources.
COVID-19 大流行期间出现了多波病例数激增，对医疗保健系统造成了严重压力，大量病例需要住院和 ICU 入院。本研究使用决策树建模方法来确定 COVID-19 患者严重结局的最重要预测因素。
我们确定了一个回顾性基于人群的队列（n=140182），其中包括 2020 年 3 月 5 日至 2021 年 5 月 31 日期间 COVID-19 检测呈阳性的成年人。从传染病和疫情管理信息系统和电子病历中提取人口统计学信息、症状和合并症。使用决策树建模涉及条件推理树和随机森林模型来分析和确定与 COVID-19 感染后严重结局（住院、ICU 入院和死亡）相关的关键因素。
在研究队列中，近 6.37%的患者住院，1.39%的患者 ICU 入院，1.57%的患者死于 COVID-19。年龄较大（>71 岁）和呼吸困难是与预后不良相关的前两个最重要的因素，在两个模型中均预测了约 50%的严重结局。神经系统疾病、糖尿病、心血管疾病、高血压和肾脏疾病是前五种预测结局的合并症，共预测了 29%的结局。79%的预后不良病例是基于变量组合预测的。分层年龄模型显示，在年轻成年人（18-40 岁）中，肥胖是与不良结局相关的最重要危险因素之一。
决策树建模已经确定了与 COVID-19 中相当一部分严重结局相关的关键因素。了解这些变量将有助于识别高风险群体并分配医疗资源。
