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

A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Abstract Text:

Adrienne Chu,Hongshik Ahn,Bhawna Halwan,Bruce Kalmin,Everson L A Artifon,Alan Barkun,Michail G Lagoudakis,Atul Kumar,

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 healthcare 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.

A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Publishing Authors By Initials

A Chu,H Ahn,B Halwan,B Kalmin,EL Artifon,A Barkun,MG Lagoudakis,A Kumar,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: Artificial intelligence in medicine

VOLUME: 42

Page Numbers: 247-59

Journal Abbreviation:

ISSN: 0933-3657

DAY: 11

MONTH: 12

YEAR: 2007

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

Number of References:

LANGUAGE: eng

NlmUniqueID: 8915031

A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: A decision support system to facilitate management of patients with acute gastrointestinal bleeding. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for A decision support system to facilitate management of patients with acute gastrointestinal bleeding.

AFFILIATION: Department of Applied Mathematics and Statistics, Stony Brook University, Stony Brook, NY 11794, United States.

Country: Netherlands

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: Artif Intell Med

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

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

• A modified Plasmodium falciparum growth inhibition assay (GIA) to assess activity of plasma from malaria endemic areas.
• A new paradigm for the treatment of high-risk prostate cancer: radiosensitization with docetaxel.
• An inherent role of microtubule network in the action of nuclear receptor.
• Antibody responses to Plasmodium falciparum vaccine candidate antigens in three areas distinct with respect to altitude.
• Breast cancer-amplified sequence 3, a target of metastasis-associated protein 1, contributes to tamoxifen resistance in premenopausal patients with breast cancer.
• Ciz1, a Novel DNA-binding coactivator of the estrogen receptor alpha, confers hypersensitivity to estrogen action.
• Cognitive function in adults with type 2 diabetes and major depression.
• Diagnosis and management of extensive vertex birth molding.
• Dynein light chain 1, a p21-activated kinase 1-interacting substrate, promotes cancerous phenotypes.
• Effect of individual and multiple antioxidant vitamins on growth and morphology of human nontumorigenic and tumorigenic parotid acinar cells in culture.
• Functional analysis of alternative isoforms of the transcription factor PAX3 in melanocytes in vitro.
• HPA axis activity and neuropathogenesis in HIV-1 clade C infection.
• How substance use differs among American secondary schools.
• Influence of Agrobacterium rhizogenes Strains on Biomass and Alkaloid Productivity in Hairy Root Lines of Hyoscyamus muticus and H. albus *.
• Letter to the editor: The suckling-micturition reflex in cows.
• Metal-binding properties of human centrin-2 determined by micro-electrospray ionization mass spectrometry and UV spectroscopy.
• Metastasis tumor antigens, an emerging family of multifaceted master coregulators.
• Metastatic tumor antigen 3 is a direct corepressor of the Wnt4 pathway.
• Modification of the expression of adenosine 3',5'-cyclic monophosphate-induced differentiated functions in neuroblastoma cells by beta-carotene and D-alpha-tocopheryl succinate.
• P21-activated kinases in human cancer.
• Pituitary abscess: Report of four cases and review of literature.
• Potential medicinal plants for CNS disorders: an overview.
• Protein disulfide isomerase assisted protein folding in malaria parasites.
• Quality of life in HIV subtype C infection among asymptomatic subjects and its association with CD4 counts and viral loads--a study from South India.
• Re-engineering cytochrome P450 2B11dH for enhanced metabolism of several substrates including the anti-cancer prodrugs cyclophosphamide and ifosfamide.
• Sexual differentiation and development in the malaria parasite.
• Standard wound coverage techniques for extremity war injury.
• Systemic, cellular and molecular analysis of chemoreflex-mediated sympathoexcitation by chronic intermittent hypoxia.
• Variable region 4 of SIV envelope correlates with rapid disease progression in morphine-exposed macaques infected with SIV/SHIV.
• p21-activated kinase signaling in breast cancer.