Publications by authors named "Sonia Pena-Balbuena"
Article Synopsis
- The study developed a machine-learning model to predict which hospitalized Covid-19 patients are at higher risk for severe disease, using clinical and lab data from patient admissions.
- The model was trained on 918 patients, validated internally, and then tested on 352 patients from a different hospital, achieving strong accuracy rates (AUC of 0.85 and 0.83, respectively).
- Key predictive factors included blood oxygen levels, age, kidney function, and various inflammatory markers, and the model is now available as an open-source tool for risk assessment.