Skip to main content
. 2021 Jun 4;4:95. doi: 10.1038/s41746-021-00467-8

Fig. 4. SHapley Additive exPlanations (SHAP) force plots from an influenza and COVID-19-positive patient.

Fig. 4

SHAP plots for sample observations from a influenza A/B and b COVID-19-positive predictions. The underlying model is XGBoost. Features that are contributing to a higher and lower SHAP values are shown in red and blue, respectively, along with the size of each feature’s contribution to the classification model’s output. The influenza patient in this example shows a log-odds output of −3.92 in the rating scale, which is equal to a probability of 0.0194. The baseline—the mean of the model output (log-odds) over the training dataset—is 0.092 (translating to a probability of 0.523). The COVID-19-positive patient has a rating score of 0.61 (probability = 0.6479); Age of 75, HR of 84, BSA of 2.21, respiratory rate of 24, and a Temp of 36.5 °C increases the prediction risk, while month of march decreases the predicted risk of being COVID-19 positive.