Ten-year Retrospective Study of Treatment of Malignant Colonic Obstructions with Self-expandable Stents

Purpose: To describe the use of self-expandable metallic stents to manage malignant colorectal obstructions and to compare the radiation dose between fluoroscopic guidance of stent placement and combined endoscopic and fluoroscopic guidance. Materials and Methods: From January 1998 to December 2007, 467 oncology patients undergoing colorectal stent placement in a single center were included in the study. Informed consent was obtained in all cases. All procedures were performed with fluoroscopic or combined fluoroscopic and endoscopic guidance. Inclusion criteria were total or partial colorectal obstruction of neoplastic origin. Exclusion criteria were life expectancy shorter than I month, suspicion of perforation, and/or severe colonic neoplastic bleeding. Procedure time and radiation dose were recorded, and technical and clinical success were evaluated. Follow-up was performed by clinical examination and simple abdominal radiographs at 1 day and at I, 3, 6, and 12 months. Results: Of 467 procedures, technical success was achieved in 432 (92.5%). Thirty-five treatments (7.5%) were technical failures, and the patients were advised to undergo surgery. Significant differences in radiation dose and clinical success were found between the fluoroscopy and combined-technique groups (P < .001). Total decompression was achieved in 372 cases, 29 patients showed remarkable improvement, 11 showed slight improvement, and 20 showed clinical failure. Complications were recorded in 89 patients (19%), the most significant were perforation (2.3%) and stent migration (6.9%). Mean interventional time and radiation dose were 67 minutes and 3,378 dGy.cm(2), respectively. Conclusions: Treatment of colonic obstruction with stents requires a long time in the interventional room and considerable radiation dose. Nevertheless, the clinical benefits and improvement in quality of life justify the radiation risk.

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.