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.

Scientists as policy-makers: Towards a new partnership

There is an urgent need to link social science research with policy making to address many key issues confronting countries across the globe. Policy makers need the benefit of social science research which is relevant, timely, transdisciplinary, methodologically capable of capturing global and local trends, swift to respond to fundamental issues, and offering findings which are clearly articulated, effectively disseminated, and oriented to outcomes. For this a new partnership is needed between social scientists and policy makers. We can gain a clearer picture of the nature of this desired partnership by probing the dichotomy between the world of science and the world of policy making. The experience of UNESCO and its programme Management of Social Transformations provides some valuable lessons.

Lexical decision in Parkinson's disease: A reply to Brown, McDonald, and Spicer (1999)

Recent semantic priming investigations in Parkinsons disease (PD) employed variants of Neelys (1977) lexical decision paradigm to dissociate the automatic and attentional aspects of semantic activation (McDonald, Brown, Gorell, 1996; Spicer, Brown, Gorell, 1994). In our earlier review, we claimed that the results of Spicer, McDonald and colleagues normal control participants violated the two-process model of information processing (Posner Snyder, 1975) upon which their experimental paradigm had been based (Arnott Chenery, 1999). We argued that, even at the shortest SOA employed, key design modifications to Neelys original experiments biased the tasks employed by Spicer et al. and McDonald et al. towards being assessments of attention-dependent processes. Accordingly, we contended that experimental procedures did not speak to issues of automaticity and, therefore, Spicer, McDonald and colleagues claims of robust automatic semantic activation in PD must be treated with caution.