Dynamic Data Analysis and Data Mining for Prediction of Clinical Stability
Van Loon Kristien, Fabián Güiza, Geert Meyfroidt, Jean‐Marie Aerts, Jan Ramon, Hendrik Blockeel, Maurice Bruynooghe, Greet Van den Berghe, Daniël Berckmans · Studies in health technology and informatics · 2009
This work studies the impact of using dynamic information as features in a machine learning algorithm for the prediction task of classifying critically ill patients in two classes according to the time they need to reach a stable state after coronary bypass surgery: less or more than nine hours. On the basis of five physiological variables different dynamic features were extracted. These sets of features served subsequently as inputs for a Gaussian process and the prediction results were compared with the case where only admission data was used for the classification. The dynamic features, especially the cepstral coefficients (aROC: 0.749, Brier score: 0.206), resulted in higher performances when compared to static admission data (aROC: 0.547, Brier score: 0.247). In all cases, the Gaussian process classifier outperformed logistic regression.