Review of a large clinical series: Predicting death for patients with abdominal septic shock.

This paper reports the result of the MEDAN project that analyzes a multicenter septic shock patient data collection. The mortality prognosis based on 4 scores that are often used is compared with the prognosis of a trained neural network. We built an alarm system using the network classification results. Method. We analyzed the data of 382 patients with abdominal septic shock who were admitted to the intensive care unit (ICU) from 1998 to 2002. The analysis includes the calculation of daily sepsis-related organ failure assessment (SOFA), Acute Physiological and Chronic Health Evaluation (APACHE) II, simplified acute physiology score (SAPS) II, multiple-organ dysfunction score (MODS) scores for each patient and the training and testing of an appropriate neural network. Results. For our patients with abdominal septic shock, the analysis shows that it is not possible to predict their individual fate correctly on the day of admission to the ICU on the basis of any current score. However, when the trained network computes a score value below the threshold during the ICU stay, there is a high probability that the patient will die within 3 days. The trained neural network obtains the same outcome prediction performance as the best score, the SOFA score, using narrower confidence intervals and considering three variables only: systolic blood pressure, diastolic blood pressure and the number of thrombocytes. We conclude that the currently best available score for abdominal septic shock may be replaced by the output of a trained neural network with only 3 input variables.

Finding optimal decision scores by evolutionary strategies.

OBJECTIVE: Severeness of illness is often rated by physicians at admission time. For this purpose, medical scores have been developed as 'objective' rating methods. When considering their classification performance, it is not assumed that such an expert-driven score is an optimal one. Our aim is to design an optimized data-driven score. In particular, we compare classical scores with a new data-driven score for abdominal septic shock patients. METHODS AND MATERIAL: Medical scores are used as ratings for different aspects of a patient's health status. The medical score indicates either a more critical or a healthier condition. For example, physicians rate organ conditions for different organs. We consider four different scores, SOFA, APACHE II, SAPS II, and MODS. Beyond the use of such classical scores, we propose an evolutionary strategy, that is suitable for score design, to find optimized data-driven scores. A database of 282 patients is used to optimize a new score for abdominal septic shock patients. Classification performance is compared by a ROC analysis. RESULTS: We give a general instruction for building optimized scores, i.e. we define individuals and operators for the evolutionary score design task. We apply this instruction to abdominal septic shock patient data. When compared to the SOFA score, it has similar classification performance, but it is more performant than APACHE II, SAPS II, and MODS. It can be used as a daily bedside score. CONCLUSIONS: We argue that evolutionary strategies should be used for optimizing purposes in the medical score design process. Using abdominal septic shock patient data, we show that evolutionary score design is a feasible and performant method that can complement or replace expert knowledge, provided that qualitative data is available.

Data quality aspects of a database for abdominal septic shock patients.

Since many years, medical researchers have investigated the mechanisms that may cause a septic shock. Despite many approaches that analyzed smaller parts of the relevant data or single variables, respectively, no larger database with all the possible relevant data existed. Our work was to bridge this gap. We built a large database for abdominal septic shock patients. While building it, we were confronted with many problems concerning the database realization and the data quality. Thus, we will demonstrate how we built our database and how we assured data quality. This is of interest for all medical or computer scientists who are concerned with building medical databases with retrospective data, e.g. for data mining purposes.

Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions.

In this contribution we present an application of a knowledge-based neural network technique in the domain of medical research. We consider the crucial problem of intensive care patients developing a septic shock during their stay at the intensive care unit. Septic shock is of prime importance in intensive care medicine due to its high mortality rate. Our analysis of the patient data is embedded in a medical data analysis cycle, including preprocessing, classification, rule generation and interpretation. For classification and rule generation we chose an improved architecture based on a growing trapezoidal basis function network for our metric variables. Our results extend those of a black box classification and give a deeper insight in our patient data. We evaluate our results with classification and rule performance measures. For feature selection we introduce a new importance measure.