Article Text
Abstract
Background Vaccinated persons are still prone to SARS-CoV-2 breakthrough infection since vaccines do not offer 100% protection. Thus, quick decision-making on identifying high-risk persons prone to COVID-19 breakthrough infection is essential for effective medical care and cost saving. We explore how one can use Explainable Artificial Intelligence (XAI) to create a decision-making tool that can aid medical professionals in detecting patients prone of SARS-CoV-2 breakthrough in South Africa and beyond.
Methods A dataset obtained from an intervention study on volunteers with cardiovascular disease (CVD) risk factors conducted in Cape Town, South Africa, comprising symptoms and feedback from 257 persons — 203 were vaccinated and 54 not — was used for the investigation. Two machine learning algorithms: Deep Multilayer Perceptron (Deep MLP) and the XGBoost classifier were trained on the dataset. The Shapley Additive Explanations (SHAP) was used to investigate the most critical variables influencing breakthrough infection from the ML models’ results. Lastly, a decision-support tool for detecting patients prone to breakthrough infection that leverages the ML model with the best results was created.
Results The results show that the XGBoost model performed better (F1= 0.86; AUC = 0.74; G-Mean=0.71; MCC=0.49). Body temperature, total cholesterol, glucose level, blood pressure, waist circumference, body weight, body mass index (BMI), haemoglobin level, and physical activity per week are the most critical variables influencing breakthrough infection.
Conclusion We established threshold values for each of them so that we could classify every new value as either high or low, and used these to construct an XAI model that combines machine learning and rule-based reasoning to predict if a patient is prone to breakthrough and provide a rationale/justification for the prediction made.
Funding: This research was partially supported by a grant from the South African Medical Research Council (SAMRC).