Predicting Death for Abdominal Septic Shock Patients- The Results of the MEDAN Project

This contribution reviews the results of the MEDAN project – an analysis of a multi-center septic shock patient data collection. Since the description of sepsis by Schottmüller in 1914 [1], the amount on knowledge available on sepsis and its underlying pathophysiology has substantially increased. Epidemiologic examinations of abdominal septic shock patients show the potential for high risk posed by and the extensive therapy situation in the intensive care unit (ICU) [2]. Unfortunately, until now it has not been possible to significantly reduce the mortality rate of septic shock, which is as high as 50-60% worldwide, although PROWESS' results [3] are encouraging. The heterogeneity of patients groups and the variations in therapy strategies is seen as one of the main problems for sepsis trials. Therefore, commonly available scoring systems are used for comparing critical ill patient groups. Moreover, one of the main objectives of scores is giving information with respect to outcome prediction. The task of the MEDAN project was the development of a septic shock diagnosis by self-learning systems, especially neural networks, and compare its performance to those of several established scores (SOFA, APACHE II, SAPS II, MODS). For this purpose, a group of 382 patients made up exclusively of abdominal septic shock patients for the first time in Germany was investigated by using scores and a multivariate neural network analysis. The classification results provided the basis for creating a reliable alarm system for abdominal septic shock patients.