Improving ECG-based COVID-19 diagnosis and mortality predictions using pre-pandemic medical records at population-scale
This incremental approach addresses the need for timely AI solutions in pandemic outbreaks by leveraging historical health records to enhance prediction accuracy for COVID-19 diagnosis and mortality.
The study tackled the problem of insufficient clinical data for accurate COVID-19 prediction models during early pandemic phases by pre-training deep learning models on pre-pandemic ECG records and fine-tuning them with limited pandemic data, resulting in substantial performance improvements across three diagnostic and prognostic tasks.
Pandemic outbreaks such as COVID-19 occur unexpectedly, and need immediate action due to their potential devastating consequences on global health. Point-of-care routine assessments such as electrocardiogram (ECG), can be used to develop prediction models for identifying individuals at risk. However, there is often too little clinically-annotated medical data, especially in early phases of a pandemic, to develop accurate prediction models. In such situations, historical pre-pandemic health records can be utilized to estimate a preliminary model, which can then be fine-tuned based on limited available pandemic data. This study shows this approach -- pre-train deep learning models with pre-pandemic data -- can work effectively, by demonstrating substantial performance improvement over three different COVID-19 related diagnostic and prognostic prediction tasks. Similar transfer learning strategies can be useful for developing timely artificial intelligence solutions in future pandemic outbreaks.