A decision support system to facilitate management of patients with acute gastrointestinal bleeding

Objective: To develop a model to predict the bleeding source and identify the cohort amongst patients with acute gastrointestinal bleeding (GIB) who require urgent intervention, including endoscopy. Patients with acute GIB, an unpredictable event, are most commonly evaluated and managed by non-gastroenterologists. Rapid and consistently reliable risk stratification of patients with acute GIB for urgent endoscopy may potentially improve outcomes amongst such patients by targeting scarce health-care resources to those who need it the most. Design and methods: Using ICD-9 codes for acute GIB, 189 patients with acute GIB and all. available data variables required to develop and test models were identified from a hospital medical records database. Data on 122 patients was utilized for development of the model and on 67 patients utilized to perform comparative analysis of the models. Clinical data such as presenting signs and symptoms, demographic data, presence of co-morbidities, laboratory data and corresponding endoscopic diagnosis and outcomes were collected. Clinical data and endoscopic diagnosis collected for each patient was utilized to retrospectively ascertain optimal management for each patient. Clinical presentations and corresponding treatment was utilized as training examples. Eight mathematical models including artificial neural network (ANN), support vector machine (SVM), k-nearest neighbor, linear discriminant analysis (LDA), shrunken centroid (SC), random forest (RF), logistic regression, and boosting were trained and tested. The performance of these models was compared using standard statistical analysis and ROC curves. Results: Overall the random forest model best predicted the source, need for resuscitation, and disposition with accuracies of approximately 80% or higher (accuracy for endoscopy was greater than 75%). The area under ROC curve for RF was greater than 0.85, indicating excellent performance by the random forest model Conclusion: While most mathematical models are effective as a decision support system for evaluation and management of patients with acute GIB, in our testing, the RF model consistently demonstrated the best performance. Amongst patients presenting with acute GIB, mathematical models may facilitate the identification of the source of GIB, need for intervention and allow optimization of care and healthcare resource allocation; these however require further validation. (c) 2007 Elsevier B.V. All rights reserved.

Isolation of transcripts overexpressed in the human pathogen Trichophyton rubrum grown in lipid as carbon source

Trichophyton rubrum is the most common etiological agent of human dermatophytosis. Despite the incidence and medical importance of this dermatophyte, little is known about the mechanisms of host invasion and pathogenicity. Host invasion depends on the adaptive cellular responses of the pathogen that allow it to penetrate the skin layers, which are mainly composed of proteins and lipids. In this study, we used suppression subtractive hybridization to identify transcripts over-expressed in T rubrum cultured in lipid as carbon source. Among the subtractive cDNA clones isolated, 85 clones were positively screened by cDNA array dot blotting and were sequenced. The putative proteins encoded by the isolated transcripts showed similarities to fungal proteins involved in metabolism, signaling, defense, and virulence, such as the MDR/ABC transporter, glucan 1,3-beta-glucosidase, chitin synthase B, copper-sulfate-regulated protein, and serine/threonine phosphatase (calcineurin A). These results provide the first molecular insight into the genes differentially expressed during the adaptation of T. rubrum to a lipidic carbon source.