Evaluating Time Influence over Performance of Machine-Learning-Based Diagnosis

Efficiently recognising severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) symptoms enables a quick and accurate diagnosis to be made, and helps in mitigating the spread of the coronavirus disease 2019. However, the emergence of new variants has caused constant changes in the symptoms associate with COVID-19. These constant changes directly impact the performance of machine-learning-based diagnose. In this context, considering the impact of these changes in symptoms over time is necessary for accurate diagnoses. Thus, in this study, we propose a machine-learning-based approach for diagnosing COVID-19 that considers the importance of time in model predictions. Our approach analyses the performance of XGBoost using two different time-based strategies for model training: month-to-month and accumulated strategies. The model was evaluated using known metrics: accuracy, precision, and recall. Furthermore, to explain the impact of feature changes on model prediction, feature importance was measured using the SHAP technique, an XAI technique. We obtained very interesting results: considering time when creating a COVID-19 diagnostic prediction model is advantageous

2019-20 coronavirus outbreak · Constant (computer programming · Context (archaeology · Coronavirus disease 2019 (COVID-19 · Disease · Feature (linguistics · Geography · Machine learning · Medical diagnosis · Pandemic · Pathology · Precision and recall · Predictive modelling · Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2 · Anomaly Detection Techniques and Applications · Computer Science · COVID-19 diagnosis using AI · Machine Learning in Healthcare · Medicine · Artificial Intelligence · Virology

• Detection of Covid-19 Patients Using Machine Learning Techniques

  Open Access•Pablo Ormeño-Arriagada, Gastón Márquez et al.•International Journal of…•2022

  Add to list