Design, Development and Implementation of iALERTS (Informatics Analytics for Long-term Evaluation and Repercussions Tracking of SARS-CoV-2 Infection): A Research Protocol

Introduction: The global pandemic caused by SARS-CoV-2 has led to significant morbidity and mortality, with many survivors experiencing long-term sequelae known as Post Acute Sequelae of Severe Acute Respiratory Syndrome Coronavirus-2 (SARSCoV-2) infection (PASC) or “long Coronavirus Disease (COVID).” Addressing the healthcare challenges posed by PASC requires an innovative approach to monitoring and management. Need of the study: Traditional systems are often underequipped to monitor and manage these prolonged effects comprehensively. An alert system is crucial for filling this gap, offering a data-driven approach to track, analyse, and manage the long-term repercussions of SARS-CoV-2 infection. Aim: To design, develop, and implement an informatics decision support tool that leverages data analytics to track and analyse the long-term effects of COVID-19, facilitating early identification and management of PASC. Materials and Methods: A quasi-experimental study will be conducted at Panimalar Medical College Hospital and Research Institute (PMCHRI), Chennai, Tamil Nadu, India, from December 2023 to December 2024. Primary data will be collected through a predictive survey tool from patients who have recovered from COVID-19, in addition to secondary data from hospital records, to develop a clinical decision support system. This platform employs machine learning algorithms to predict the likelihood of PASC development among Coronavirus Disease-19 (COVID-19) survivors. The project involves three phases: the creation of the predictive survey tool, the development of the iALERTS platform (Informatics Analytics for Long-term Evaluation and Repercussions Tracking of SARS-CoV-2 infection), and the implementation and evaluation of the system in clinical settings. Evaluation metrics will include user satisfaction, predictive accuracy, and the impact on clinical decision-making and patient outcomes. Statistical analysis will be conducted using multivariable regression models to identify predictors of PASC and to evaluate the association between SARS-CoV-2 infection characteristics and long-term outcomes. A p-value of <0.05 will be considered statistically significant for all analyses.