🤖 AI Summary
Amid critical shortages of medical resources during the COVID-19 pandemic, rapid, interpretable, and PCR-free prognostic assessment is urgently needed—especially in resource-constrained settings.
Method: We propose a Deep Neural Decision Forest (DNDF) model that predicts patient recovery or mortality using only clinical features—without requiring RT-PCR test results. DNDF integrates decision-tree architecture with deep neural networks and is rigorously evaluated via four-stage ablation studies and comparative benchmarking against nine state-of-the-art models.
Contribution/Results: DNDF achieves superior performance across all experimental settings, attaining 80% accuracy in mortality prediction using clinical features alone—surpassing even multimodal approaches incorporating RT-PCR. This work provides the first systematic evidence that routinely collected clinical indicators are sufficient for high-accuracy prognostication. It delivers an efficient, trustworthy, and inherently interpretable AI solution for emergency triage in low-resource environments.
📝 Abstract
It is crucial for emergency physicians to identify patients at higher risk of mortality to effectively prioritize hospital resources, particularly in regions with limited medical services. This became even more critical during global pandemics, which have disrupted lives in unprecedented ways and caused widespread morbidity and mortality. The collected data from patients is beneficial to predict the outcome, although there is a question about which data makes the most accurate predictions. Therefore, this study aimed to achieve two main objectives during the pandemic, using data and experiments from the most recent global health crisis, COVID-19. 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 9 machine learning and deep learning methods to build appropriate model. Based on results, the deep neural decision forest, as an interpretable deep learning methods, 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%. This study can provide guidance for medical professionals in the event of a crisis or outbreak similar to COVID-19. Moreover, the proposed deep learning method demonstrates exceptional suitability for mortality prediction.