Article ID: JNMS.2021_88-107
Background: Coronavirus disease 2019 (COVID-19) and heat related-illness are systemic febrile diseases. In the summer during the COVID-19 pandemic, a differential diagnosis between the two conditions is important. However, no studies have compared and distinguished heat-related illness from COVID-19. We aimed to compare the data between patients with early-stage heat-related illness and those with COVID-19.
Methods: This retrospective observational study included 90 patients with early-stage heat-related illness selected from Heatstroke STUDY 2017-2019 (nationwide registries of heat-related illness in Japan) and 86 patients with laboratory-confirmed COVID-19 with complaints of fever or fatigue and were admitted to one of two hospitals in Tokyo, Japan.
Results: Amongvital signs, systolic blood pressure (119 vs. 125 mmHg, p = 0.02), oxygen saturation (98% vs. 97%, p < 0.001), and body temperature (36.6 vs. 37.6 °C, p<0.001) showed significant between-group differences for the heatstroke and COVID-19 groups, respectively. Numerous intergroup differences in laboratory findings were present, including white blood cell counts (10.8 vs. 5.2 × 103/μL, p<0.001), creatinine (2.2 vs. 0.85 mg/dL, p<0.001), and C-reactive protein (0.2 vs. 2.8 mg/dL, p<0.001), although a logistic regression model achieved an area under the curve (AUC) of 0.966 using these three factors. A Random Forest machine learning model achieved accuracy, precision, recall, and AUC of 0.908, 0.976, 0.842, and 0.978, respectively. Creatinine was the most important feature of this model.
Conclusions: Acute kidney injury was associated with heat-related illness, which could be key in distinguishing or evaluating patients with fever in the summer during the COVID-19 pandemic.
