Development of a Robust Multicriteria Classification Model for Monitoring the Postoperative Behaviour of Heart Patients

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia occurring in 2% of the general population, while the assuming projected incidence in 2050 will rise to 4.3%. This paper presents a multicriteria methodology for the development of a model for monitoring the post‐operative behaviour of patients who have received treatment for AF. The model classifies the patients in seven categories according to their relapse risk, on the basis of seven criteria related to the AF type and pathology conditions, the treatment received by the patients and their medical history. The analysis is based on an extension of the UTilités Additives DIScriminantes (UTADIS) method, through the introduction of a two‐stage model development procedure that minimizes the number and the magnitude of the misclassifications. The analysis is based on a sample of 116 patients who had pulmonary veins isolation in a Greek public hospital. The classification accuracy of the best fitted models scores between 71% and 84%.