On the explainability of hospitalization prediction on a large COVID-19 patient dataset
Published in AMIA Annual Symposium Proceedings, 2022
Multiple AI models were developed and compared for predicting hospitalization among COVID-19 positive patients, with analyses of performance robustness and variability in SHAP feature importance.
Use Google Scholar for full citation.
Recommended citation: Girardi, I., Vagenas, P., Arcos-D., D., Bessa, L., Bu, A., Furlan, L., Furlan, R., Gatti, M., Giovannini, A., Hoeven, E., Marchiori, C. (2022). "On the explainability of hospitalization prediction on a large COVID-19 patient dataset." *AMIA Annual Symposium Proceedings*, 2021, 526.
Download Paper