Literature DB >> 28550920

Neural network prediction of severe lower intestinal bleeding and the need for surgical intervention.

Tyler J Loftus1, Scott C Brakenridge1, Chasen A Croft2, Robert Stephen Smith2, Philip A Efron1, Frederick A Moore1, Alicia M Mohr1, Janeen R Jordan3.   

Abstract

BACKGROUND: The prognosis for patients with severe acute lower intestinal bleeding (ALIB) may be assessed by complex artificial neural networks (ANNs) or user-friendly regression-based models. Comparisons between these modalities are limited, and predicting the need for surgical intervention remains elusive. We hypothesized that ANNs would outperform the Strate rule to predict severe bleeding and would also predict the need for surgical intervention.
METHODS: We performed a 4-y retrospective analysis of 147 adult patients who underwent endoscopy, angiography, or surgery for ALIB. Baseline characteristics, Strate risk factors, management parameters, and outcomes were analyzed. The primary outcomes were severe bleeding and surgical intervention. ANNs were created in SPSS. Models were compared by area under the receiver operating characteristic curve (AUROC) with 95% confidence intervals.
RESULTS: The number of Strate risk factors for each patient correlated significantly with the outcome of severe bleeding (r = 0.29, P < 0.001). However, the Strate model was less accurate than an ANN (AUROC 0.66 [0.57-0.75] versus 0.98 [0.95-1.00], respectively) which incorporated six variables present on admission: hemoglobin, systolic blood pressure, outpatient prescription for Aspirin 325 mg daily, Charlson comorbidity index, base deficit ≥5 mEq/L, and international normalized ratio ≥1.5. A similar ANN including hemoglobin nadir and the occurrence of a 20% decrease in hematocrit was effective in predicting the need for surgery (AUROC 0.95 [0.90-1.00]).
CONCLUSIONS: The Strate prediction rule effectively stratified risk for severe ALIB, but was less accurate than an ANN. A separate ANN accurately predicted the need for surgery by combining risk factors for severe bleeding with parameters quantifying blood loss. Optimal prognostication may be achieved by integrating pragmatic regression-based calculators for quick decisions at the bedside and highly accurate ANNs when time and resources permit. Published by Elsevier Inc.

Entities:  

Keywords:  Gastrointestinal bleeding; Neural network; Severe bleeding; Strate; Surgery; Transfusion

Mesh:

Year:  2016        PMID: 28550920      PMCID: PMC5644023          DOI: 10.1016/j.jss.2016.12.032

Source DB:  PubMed          Journal:  J Surg Res        ISSN: 0022-4804            Impact factor:   2.192


  21 in total

Review 1.  The management of lower gastrointestinal bleeding.

Authors:  Y Marion; G Lebreton; V Le Pennec; E Hourna; S Viennot; A Alves
Journal:  J Visc Surg       Date:  2014-04-24       Impact factor: 2.043

2.  Validation of a clinical prediction rule for severe acute lower intestinal bleeding.

Authors:  Lisa L Strate; John R Saltzman; Rie Ookubo; Muthoka L Mutinga; Sapna Syngal
Journal:  Am J Gastroenterol       Date:  2005-08       Impact factor: 10.864

3.  Nutritional anaemias. Report of a WHO scientific group.

Authors: 
Journal:  World Health Organ Tech Rep Ser       Date:  1968

4.  Bleeding colonic diverticula. A reappraisal of natural history and management.

Authors:  H H McGuire
Journal:  Ann Surg       Date:  1994-11       Impact factor: 12.969

5.  Prediction of outcome in acute lower-gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model.

Authors:  Ananya Das; Tamir Ben-Menachem; Gregory S Cooper; Amitabh Chak; Michael V Sivak; Judith A Gonet; Richard C K Wong
Journal:  Lancet       Date:  2003-10-18       Impact factor: 79.321

6.  Cytotoxicity of chitosan/streptokinase nanoparticles as a function of size: An artificial neural networks study.

Authors:  Hadi Baharifar; Amir Amani
Journal:  Nanomedicine       Date:  2015-09-25       Impact factor: 5.307

7.  Early predictors of severe lower gastrointestinal bleeding and adverse outcomes: a prospective study.

Authors:  Fernando S Velayos; Ann Williamson; Karen H Sousa; Edward Lung; Alan Bostrom; Ellen J Weber; James W Ostroff; Jonathan P Terdiman
Journal:  Clin Gastroenterol Hepatol       Date:  2004-06       Impact factor: 11.382

8.  Risk factors for mortality in lower intestinal bleeding.

Authors:  Lisa L Strate; John Z Ayanian; Gregory Kotler; Sapna Syngal
Journal:  Clin Gastroenterol Hepatol       Date:  2008-06-16       Impact factor: 11.382

Review 9.  Minimal approach to neuro-inspired information processing.

Authors:  Miguel C Soriano; Daniel Brunner; Miguel Escalona-Morán; Claudio R Mirasso; Ingo Fischer
Journal:  Front Comput Neurosci       Date:  2015-06-02       Impact factor: 2.380

10.  Analysis of significant factors for dengue fever incidence prediction.

Authors:  Padet Siriyasatien; Atchara Phumee; Phatsavee Ongruk; Katechan Jampachaisri; Kraisak Kesorn
Journal:  BMC Bioinformatics       Date:  2016-04-16       Impact factor: 3.169

View more
  8 in total

1.  Response to Er and Tez: the use of artificial neural networks in medical prognostication.

Authors:  Tyler J Loftus; Janeen R Jordan
Journal:  J Surg Res       Date:  2017-10-27       Impact factor: 2.192

Review 2.  Machine learning in gastrointestinal surgery.

Authors:  Takashi Sakamoto; Tadahiro Goto; Michimasa Fujiogi; Alan Kawarai Lefor
Journal:  Surg Today       Date:  2021-09-24       Impact factor: 2.549

3.  Comparison of Risk Scores for Lower Gastrointestinal Bleeding: A Systematic Review and Meta-analysis.

Authors:  Majed Almaghrabi; Mandark Gandhi; Leonardo Guizzetti; Alla Iansavichene; Brian Yan; Aze Wilson; Kathryn Oakland; Vipul Jairath; Michael Sey
Journal:  JAMA Netw Open       Date:  2022-05-02

4.  Machine Learning to Predict Outcomes in Patients with Acute Gastrointestinal Bleeding: A Systematic Review.

Authors:  Dennis Shung; Michael Simonov; Mark Gentry; Benjamin Au; Loren Laine
Journal:  Dig Dis Sci       Date:  2019-05-04       Impact factor: 3.199

Review 5.  Artificial Intelligence and Surgical Decision-making.

Authors:  Tyler J Loftus; Patrick J Tighe; Amanda C Filiberto; Philip A Efron; Scott C Brakenridge; Alicia M Mohr; Parisa Rashidi; Gilbert R Upchurch; Azra Bihorac
Journal:  JAMA Surg       Date:  2020-02-01       Impact factor: 14.766

6.  Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice.

Authors:  Shungo Imai; Yoh Takekuma; Hitoshi Kashiwagi; Takayuki Miyai; Masaki Kobayashi; Ken Iseki; Mitsuru Sugawara
Journal:  PLoS One       Date:  2020-07-29       Impact factor: 3.240

7.  Nursing Value Analysis and Risk Assessment of Acute Gastrointestinal Bleeding Using Multiagent Reinforcement Learning Algorithm.

Authors:  Fang Liu; Xiaoli Liu; Changyou Yin; Hongrong Wang
Journal:  Gastroenterol Res Pract       Date:  2022-01-06       Impact factor: 2.260

8.  Combining genetic risk score with artificial neural network to predict the efficacy of folic acid therapy to hyperhomocysteinemia.

Authors:  Xiaorui Chen; Xiaowen Huang; Diao Jie; Caifang Zheng; Xiliang Wang; Bowen Zhang; Weihao Shao; Gaili Wang; Weidong Zhang
Journal:  Sci Rep       Date:  2021-11-02       Impact factor: 4.379

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.