Machine learning algorithms to predict outcomes in children and adolescents with COVID-19: A systematic review.

BACKGROUND AND OBJECTIVES: We aimed to analyze the study designs, modeling approaches, and performance evaluation metrics in studies using machine learning techniques to develop clinical prediction models for children and adolescents with COVID-19. METHODS: We searched four databases for articles published between 01/01/2020 and 10/25/2023, describing the development of multivariable prediction models using any machine learning technique for predicting several outcomes in children and adolescents who had COVID-19. RESULTS: We included ten articles, six (60 % [95 % confidence interval (CI) 0.31 - 0.83]) were predictive diagnostic models and four (40% [95 % CI 0.170.69]) were prognostic models. All models were developed to predict a binary outcome (n= 10/10, 100 % [95 % CI 0.72-1]). The most frequently predicted outcome was disease detection (n=3/10, 30% [95 % CI 0.11-0.60]). The most commonly used machine learning models in the studies were tree-based (n=12/33, 36.3% [95 % CI 0.17-0.47]) and neural networks (n=9/27, 33.2% [95% CI 0.15-0.44]). CONCLUSION: Our review revealed that attention is required to address problems including small sample sizes, inconsistent reporting practices on data preparation, biases in data sources, lack of reporting metrics such as calibration and discrimination, hyperparameters and other aspects that allow reproducibility by other researchers and might improve the methodology.

Outcomes of SARS-CoV-2 and Seasonal Viruses Among Children Hospitalized in Brazil.

BACKGROUND AND OBJECTIVES: Understanding how severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) interacts with other respiratory viruses is crucial for developing effective public health strategies in the postpandemic era. This study aimed to compare the outcomes of SARS-CoV-2 and seasonal viruses in children and adolescents hospitalized with severe acute respiratory infection (SARI). METHODS: This population-based, retrospective cohort study included children and adolescents hospitalized with SARI from February 2020 to February 2023 in Brazil. The main exposure of interest was viral etiology. The primary outcome was in-hospital mortality. Competing risk analysis was used to account for time dependency and competing events. RESULTS: A total of 235 829 patients had available results of the viral tests, with SARS-CoV-2 predominance. According to the competing-risk survival analysis, the estimated probability of a fatal outcome at 30 days of hospitalization according to the viral strain was 6.5%, 3.4%, 2.9%, 2.3%, 2.1%, and 1.8%, for SARS-CoV-2, coinfection, adenovirus, influenza, other viruses, and respiratory syncytial virus, respectively. Individuals with a positive test for SARS-CoV-2 had hazard of death 3 times higher than subjects with a negative test (hazard ratio, 3.3; 95% confidence interval, 3.1-3.5). After adjustment by the competing-risk multivariable analysis, admission in Northeast and North regions, oxygen saturation <95%, and the presence of comorbidities were risk factors for death in all viral strains. CONCLUSIONS: SARS-CoV-2 infection had the highest hazard of in-hospital mortality in this pediatric cohort hospitalized with SARI. Regardless of viral etiology, the presence of underlying medical conditions was a risk factor for death.