Home| About us| login/register| For authors| For reviewers |Submit a paper
(close)

(Ctrl-click to select multiple journals)


How should we address you?

Your email address


 Yes, sign up now
 Sign up for general news too

Privacy Statement
 
 
 

Biomedical Informatics Insights

Synopsis: An open access, peer reviewed electronic journal that covers all aspects of biomedical informatics and biomedical informatics supported decision-making.


Indexing: Two major databases.  Pubmed indexing for NIH-funded research.

Processing time: Decision in 2 weeks for 90% of papers.

Visibility: Most popular article read 400+ times.

View factor
for journal
29311


About this journal

ISSN: 1178-2226


Aims and scope:

Biomedical Informatics Insights is an international, open access, peer reviewed journal which considers manuscripts on all aspects of medical informatics and medical informatics supported decision making. Of particular but not exclusive interest are submissions on the use in healthcare of information management, information systems and technology, and discussions on medical decision making. The journal is particularly interested in promoting understanding on how text, genetics and clinical care integrate into stable but dynamic systems, and manuscripts addressing this topic are strongly encouraged. These articles are designated as perspectives.

Editorial standards and procedures:

Submissions, excluding editorials, letters to the editor and dedications, will be peer reviewed by two reviewers.  Reviewers are required to provide fair, balanced and constructive reports.  

Under our Fairness in Peer Review Policy authors may appeal against reviewers' recommendations which are ill-founded, unobjective or unfair.  Appeals are considered by the Editor in Chief or Associate Editor.

Papers are not sent to peer reviewers following submission of a revised manuscript. Editorial decisions on re-submitted papers are based on the author's response to the initial peer review report.

Indexing:

This journal is indexed by:

  • DOAJ 
  • OAIster

National Institutes of Health Public Access Policy compliant:

As of April 7 2008, the US NIH Public Access Policy requires that all peer reviewed articles resulting from research carried out with NIH funding be deposited in the Pubmed Central archive.

If you are an NIH employee or grantee Libertas Academica will ensure that you comply with the policy by depositing your paper at Pubmed Central on your behalf. 



 
 
 


Artificial Neural Networks for Early Prediction of Mortality in Patients with Non Variceal Upper GI Bleeding (UGIB)

Authors: Enzo Grossi, Riccardo Marmo, Marco Intraligi and Massimo Buscema
Publication Date: 24 Jun 2008
Biomedical Informatics Insights 2008:1 7-19

Enzo Grossi1, Riccardo Marmo2, Marco Intraligi3 and Massimo Buscema3

1Medical Department Bracco Milano, Italy; Centro Diagnostico Italiano, Milano, Italy. 2Division of Gastroenterology, L.Curto Hospital, Polla, Sant’Arsenio, Italy. 3Semeion Research Centre, Rome, Italy.

Abstract

Background: Mortality for non variceal upper gastrointestinal bleeding (UGIB) is clinically relevant in the first 12–24 hours of the onset of haemorrhage and therefore identification of clinical factors predictive of the risk of death before endoscopic examination may allow for early corrective therapeutic intervention.

Aim: 1) Identify simple and early clinical variables predictive of the risk of death in patients with non variceal UGIB; 2) assess previsional gain of a predictive model developed with conventional statistics vs. that developed with artificial neural networks (ANNs).

Methods and results: Analysis was performed on 807 patients with nonvariceal UGIB (527 males, 280 females), as a part of a multicentre Italian study. The mortality was considered “bleeding-related” if occurred within 30 days from the index bleeding episode. A total of 50 independent variables were analysed, 49 of which clinico-anamnestic, all collected prior to endoscopic examination plus the haemoglobin value measured on admission in the emergency department. Death occurred in 42 (5.2%). Conventional statistical techniques (linear discriminant analysis) were compared with ANNs (Twist® system-Semeion) adopting the same result validation protocol with random allocation of the sample in training and testing subsets and subsequent cross-over. ANNs resulted to be significantly more accurate than LDA with an overall accuracy rate near to 90%.

Conclusion: Artificial neural networks technology is highly promising in the development of accurate diagnostic tools designed to recognize patients at high risk of death for UGIB.



Post comment




No comments yet...Be the first to comment.

Bookmark this article

LINKEDIN FACEBOOK

Add to Mixx! MIXX YAHOO! BUZZ

PERMALINK DIGG


Sign up for free journal updates

How should we address you?
Your email address
 Yes, sign up now


Recently published in this journal

Personalizing Drug Selection Using Advanced Clinical Decision Support
- 23/Jun/2009

Current Challenge in Consumer Health Informatics: Bridging the Gap between Access to Information and Information Understanding
- 03/Apr/2009

Avoiding Pitfalls in the Statistical Analysis of Heterogeneous Tumors
- 30/Mar/2009

HIPAA, HIPAA, Hooray? Current Challenges and Initiatives in Health Informatics in the United States
- 03/Dec/2008

Planning for Hospital IT Implementation: A New Look at the Business Case
- 28/Nov/2008

Closing the Loop: Facilitating the Use of Autopsy Information in Medical Decision Making and Managed Care
- 23/Jul/2008

Artificial Neural Networks for Early Prediction of Mortality in Patients with Non Variceal Upper GI Bleeding (UGIB)
- 24/Jun/2008

Experiences from the Architectural Migration of a Joint Replacement Surgery Information System
- 20/May/2008



Related journals...