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.

Asthma management and asthma control in Sao Paulo, Brazil and Uppsala, Sweden: a questionnaire-based comparison

The Global Initiative Against Asthma (GINA) was developed to meet the global challenge of asthma. GINA has been adopted in most countries and comparison of asthma management in different parts of the world may be of help when assessing the global dissemination of the guideline. The overall goals in GINA include that asthma patients should be free of symptoms, acute asthma attacks and activity limitations. The aim of the present study was to compare asthma management and asthma control in Sao Paulo, Brazil and Uppsala, Sweden. Information was collected from asthmatics in Sao Paulo and Uppsala with a questionnaire. The questionnaire dealt with the following issues: symptoms, smoking, self-management, hospital visits, effect on school/work and medication. The Sao Paulo patients were more likely to have uncontrolled asthma (36% vs 13%, P < 0.001), having made emergency room visits (57% vs 29%, P < 0.001) and having lost days at school or work because of their asthma (46% vs 28%, P = 0.03) than the asthmatics from Uppsala. There were no difference in the use of inhaled corticosteroids, but the Brazilian patients were more likely to be using theophylline (18% vs 1%, P = 0.001) and less likely to be using long-acting beta-2 agonists (18% vs 37%, P < 0.001). We conclude that the level of asthma control was lower among the patients from Sao Paulo than Uppsala. Few of the patients in either city reached the goals set up by GINA. Improved asthma management may therefore lead to health-economic benefits in both locations. Please cite this paper as: Skorup P, Rizzo LV, Machado-Boman L and Janson C. Asthma management and asthma control in Sao Paulo, Brazil and Uppsala, Sweden: a questionnaire-based comparison. The Clinical Respiratory Journal 2009; 3: 22-28.