COVID-19 continues to be considered an endemic disease in spite of the World Health Organization's declaration that the pandemic is over. This pandemic has disrupted people's lives in unprecedented ways and caused widespread morbidity and mortality. As a result, it is important for emergency physicians to identify patients with a higher mortality risk in order to prioritize hospital equipment, especially in areas with limited medical services. The collected data from patients is beneficial to predict the outcome of COVID-19 cases, although there is a question about which data makes the most accurate predictions. Therefore, this study aims to accomplish two main objectives. First, we want to examine whether deep learning algorithms can predict a patient's morality. Second, we investigated the impact of Clinical and RT-PCR on prediction to determine which one is more reliable. We defined four stages with different feature sets and used interpretable deep learning methods to build appropriate model. Based on results, the deep neural decision forest performed the best across all stages and proved its capability to predict the recovery and death of patients. Additionally, results indicate that Clinical alone (without the use of RT-PCR) is the most effective method of diagnosis, with an accuracy of 80%. It is important to document and understand experiences from the COVID-19 pandemic in order to aid future medical efforts. This study can provide guidance for medical professionals in the event of a crisis or outbreak similar to COVID-19.

翻译：尽管世界卫生组织已宣布大流行结束，COVID-19仍被视为一种地方性流行病。这场疫情以前所未有的方式扰乱了人们的生活，并导致广泛的发病率和死亡率。因此，急诊医师需识别死亡风险较高的患者，以优先分配医院设备，尤其在医疗服务有限的地区尤为重要。收集的患者数据有助于预测COVID-19病例的结局，但何种数据能实现最准确的预测仍存疑问。为此，本研究旨在达成两个主要目标：首先，探究深度学习算法能否预测患者的死亡率；其次，分析临床数据和RT-PCR检测对预测结果的影响，以确定哪种数据更可靠。我们定义了四个具有不同特征集的阶段，并采用可解释的深度学习方法构建合适模型。结果表明，深度神经决策森林在所有阶段均表现最佳，验证了其预测患者康复与死亡的能力。此外，研究结果显示，仅使用临床数据（无需RT-PCR）即可实现80%的准确率，是最有效的诊断方法。记录和理解COVID-19疫情的经验对于助力未来医疗工作至关重要，本研究可为面临类似COVID-19危机或疫情爆发的医疗专业人员提供指导。