Risk ayarlı hastane ölüm tahmin modeli: Bir Türk eğitim ve araştırma hastanesinde uygulama örneği

In today's world, health organizations give much importance to quality and patient safety. To this end, conservation of life and prevent excessive deaths are one of the vital objectives for health services in all countries (Whalley, 2010). Although main function of hospitals is to save lives, there is a little attention to hospital mortality (Champbell et al., 2011). In this context; generating reliable mortality ratio then monitoring them are a prerequisite for improvement in care and development in patient safety. This study aimed to demonstrate the applicability of risk adjusted mortality ratio in Turkey. This is the first study conducted in this field in Turkey. To this end, various risk adjusted hospital mortality prediction models were developed by using some popular data mining techniques; logistic re-gression, decision trees, random forests and artificial neural networks. The data from 30182 inpatients of one of the Turkish training and research hospitals with 1155 beds were used. The data collected from inpatients whose discharge period was January to November in 2014. At the end, the performance of these methods were compared.