ABSTRACT
Clinical evidence suggests that some patients diagnosed with coronavirus disease 2019 (COVID-19) experience a variety of complications associated with significant morbidity, especially in severe cases during the initial spread of the pandemic. To support early interventions, we propose a machine learning system that predicts the risk of developing multiple complications. We processed data collected from 3,352 patient encounters admitted to 18 facilities between April 1 and April 30, 2020, in Abu Dhabi (AD), United Arab Emirates. Using data collected during the first 24 h of admission, we trained machine learning models to predict the risk of developing any of three complications after 24 h of admission. The complications include Secondary Bacterial Infection (SBI), Acute Kidney Injury (AKI), and Acute Respiratory Distress Syndrome (ARDS). The hospitals were grouped based on geographical proximity to assess the proposed system's learning generalizability, AD Middle region and AD Western & Eastern regions, A and B, respectively. The overall system includes a data filtering criterion, hyperparameter tuning, and model selection. In test set A, consisting of 587 patient encounters (mean age: 45.5), the system achieved a good area under the receiver operating curve (AUROC) for the prediction of SBI (0.902 AUROC), AKI (0.906 AUROC), and ARDS (0.854 AUROC). Similarly, in test set B, consisting of 225 patient encounters (mean age: 42.7), the system performed well for the prediction of SBI (0.859 AUROC), AKI (0.891 AUROC), and ARDS (0.827 AUROC). The performance results and feature importance analysis highlight the system's generalizability and interpretability. The findings illustrate how machine learning models can achieve a strong performance even when using a limited set of routine input variables. Since our proposed system is data-driven, we believe it can be easily repurposed for different outcomes considering the changes in COVID-19 variants over time.
ABSTRACT
BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) was first reported in December 2019. The severity of coronavirus disease 2019 (COVID-19) ranges from asymptomatic to severe and potentially fatal. We aimed to describe the clinical and laboratory features and outcomes of hospitalised patients with COVID-19 within the Abu Dhabi Healthcare Services Facilities (SEHA). METHODS: Our retrospective analysis of patient data collected from electronic health records (EHRs) available from the SEHA health information system included all patients admitted from 1 March to 31 May 2020 with a laboratory-confirmed PCR diagnosis of SARS-CoV-2 infection. Data of clinical features, co-morbidities, laboratory markers, length of hospital stay, treatment received and mortality were analysed according to severe versus non-severe disease. RESULTS: The study included 9390 patients. Patients were divided into severe and non-severe groups. Seven hundred twenty-one (7.68%) patients required intensive care, whereas the remaining patients (92.32%) had mild or moderate disease. The mean patient age of our cohort (41.8 years) was lower than the global average. Our population had male predominance, and it included various nationalities. The major co-morbidities were hypertension, diabetes mellitus and chronic kidney disease. Laboratory tests revealed significant differences in lactate dehydrogenase, ferritin, C-reactive protein, interleukin-6 and creatinine levels and the neutrophil count between the severe and non-severe groups. The most common anti-viral therapy was the combination of Hydroxychloroquine and Favipiravir. The overall in-hospital mortality rate was 1.63%, although the rate was 19.56% in the severe group. The mortality rate was higher in adults younger than 30 years than in those older than 60 years (2.3% vs. 0.95%). CONCLUSIONS: Our analysis suggested that Abu Dhabi had lower COVID-19 morbidity and mortalities rates were less than the reported rates then in China, Italy and the US. The affected population was relatively young, and it had an international representation. Globally, Abu Dhabi had one of the highest testing rates in relation to the population volume. We believe the early identification of patients and their younger age resulted in more favourable outcomes.