RESUMEN
Background: The COVID-19 pandemic, which has impacted over 222 countries resulting in incalculable losses, has necessitated innovative solutions via machine learning (ML) to tackle the problem of overburdened healthcare systems. This study consolidates research employing ML models for COVID-19 prognosis, evaluates prevalent models and performance, and provides an overview of suitable models and features while offering recommendations for experimental protocols, reproducibility and integration of ML algorithms in clinical settings. Methods: We conducted a review following the PRISMA framework, examining ML utilisation for COVID-19 prediction. Five databases were searched for relevant studies up to 24 January 2023, resulting in 1,824 unique articles. Rigorous selection criteria led to 204 included studies. Top-performing features and models were extracted, with the area under the receiver operating characteristic curve (AUC) evaluation metric used for performance assessment. Results: This systematic review investigated 204 studies on ML models for COVID-19 prognosis across automated diagnosis (18.1%), severity classification (31.9%), and outcome prediction (50%). We identified thirty-four unique features in five categories and twenty-one distinct ML models in six categories. The most prevalent features were chest CT, chest radiographs, and advanced age, while the most frequently employed models were CNN, XGB, and RF. Top-performing models included neural networks (ANN, MLP, DNN), distance-based methods (kNN), ensemble methods (XGB), and regression models (PLS-DA), all exhibiting high AUC values. Conclusion: Machine learning models have shown considerable promise in improving COVID-19 diagnostic accuracy, risk stratification, and outcome prediction. Advancements in ML techniques and their integration with complementary technologies will be essential for expediting decision-making and informing clinical decisions, with long-lasting implications for healthcare systems globally.
Asunto(s)
COVID-19 , Discapacidades para el AprendizajeRESUMEN
Estimation of antibody development against SARS-CoV-2 is essential means for understanding the immune response against the virus. We reported IgG antibody development status against Nucleocapsid protein of the virus and compared with lifestyle (health and food habits), co-existing diseases, vaccination and COVID-19 infection status. ELISA (Enzyme Linked Immunosorbent Assay) was performed to assess IgG antibodies targeted against the Nucleocapsid protein of SARS-CoV-2 in participants (n=500). In this seroprevalence study, serological data were estimated for a period of 10 months in the participants who were aged 10 years and above. Sociodemographic and risk factors related data were collected through a written questionnaire and chi-square test was performed to determine the association with seropositivity. The overall seroprevalence of anti-SARS-CoV-2 antibodies among the study subjects was 47.8%. Estimates were highest among the participants of 21-40 years old (55.1%), and lowest in older aged (>60 years) participants (39.5%). Among the Sinopharm vaccinated individuals 81.8% had developed anti-Nucleocapsid antibody. Physical exercise and existence of comorbidities like hypertension and diabetes were the distinguishing factors between seropositive and seronegative individuals. Seropositivity rate largely varied among symptomatic (67%) and asymptomatic (33.1%) COVID-19 infected participants. The findings suggest that residents of Dhaka city had a higher prevalence of anti-nucleocapsid antibody in the second year of the pandemic. This indicates the improvement of immunological status among the population. Finally, the study emphasizes on maintaining active and healthy lifestyle to improve immunity. However, the absence of IgG antibodies in many cases of COVID-19 infected individuals suggests that antibodies wane with time.