No abstract

No abstract

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.

Molecular fingerprint representations were compared with respect to their ability to retrieve sets of ligands by retrospective similarity searching. Twelve different biological target classes were considered, and both "holographic" fingerprint vectors containing floating-point or integer values giving the frequency of occurrence of fragment types or atom pairs, and their "binary" representations were compared. The descriptors were substructure-based or grounded on topological and spatial pharmacophore type pairs. Enrichment factors between seven and 19 were obtained for the top-scoring two percent of the reference database, depending on the target class. Although the holographic fingerprints yielded higher enrichment factors on average, only for two target classes significant differences (> 20%) between holographic and binary fingerprint representations were observed. This result demonstrates that binary fingerprint representations can be applied to rapid similarity searching for most target classes without losing significant enrichment of actives in the virtual hit lists. A comparison of the individual molecules retrieved by holographic fingerprints and their binary representation revealed that significantly different sets of actives and "inactives" were found. The intersections of two virtual hit lists ranged from zero to approximately 90% for the set of known ligands. This result demonstrates that "binarization" of continuous molecular descriptors has a significant effect on the topology of chemical space and the resulting neighborhood behavior of chemical similarity searching.

No abstract