Literature DB >> 9819841

A comparison of statistical learning methods on the Gusto database.

M Ennis1, G Hinton, D Naylor, M Revow, R Tibshirani.   

Abstract

We apply a battery of modern, adaptive non-linear learning methods to a large real database of cardiac patient data. We use each method to predict 30 day mortality from a large number of potential risk factors, and we compare their performances. We find that none of the methods could outperform a relatively simple logistic regression model previously developed for this problem.

Entities:  

Mesh：

Year:  1998        PMID： 9819841     DOI： 10.1002/(sici)1097-0258(19981115)17:21<2501::aid-sim938>3.0.co;2-m

Source DB:  PubMed          Journal:  Stat Med        ISSN： 0277-6715            Impact factor:   2.373


  12 in total

1.  Towards better clinical prediction models: seven steps for development and an ABCD for validation.

Authors:  Ewout W Steyerberg; Yvonne Vergouwe
Journal:  Eur Heart J       Date:  2014-06-04       Impact factor: 29.983

2.  A prediction rule for selective screening of Chlamydia trachomatis infection.

Authors:  H M Götz; J E A M van Bergen; I K Veldhuijzen; J Broer; C J P A Hoebe; E W Steyerberg; A J J Coenen; F de Groot; M J C Verhooren; D T van Schaik; J H Richardus
Journal:  Sex Transm Infect       Date:  2005-02       Impact factor: 3.519

3.  Using data mining techniques in monitoring diabetes care. The simpler the better?

Authors:  Dario Gregori; Michele Petrinco; Simona Bo; Rosalba Rosato; Eva Pagano; Paola Berchialla; Franco Merletti
Journal:  J Med Syst       Date:  2009-09-10       Impact factor: 4.460

4.  Treatment of individual predictors with neural network algorithms improves Global Registry of Acute Coronary Events score discrimination.

Authors:  Raul A Borracci; Claudio C Higa; Graciana Ciambrone; Jimena Gambarte
Journal:  Arch Cardiol Mex       Date:  2021

5.  Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?

Authors:  Peter C Austin; Douglas S Lee; Ewout W Steyerberg; Jack V Tu
Journal:  Biom J       Date:  2012-07-06       Impact factor: 2.207

6.  Prediction of survival with alternative modeling techniques using pseudo values.

Authors:  Tjeerd van der Ploeg; Frank Datema; Robert Baatenburg de Jong; Ewout W Steyerberg
Journal:  PLoS One       Date:  2014-06-20       Impact factor: 3.240

7.  Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints.

Authors:  Tjeerd van der Ploeg; Peter C Austin; Ewout W Steyerberg
Journal:  BMC Med Res Methodol       Date:  2014-12-22       Impact factor: 4.615

8.  Logistic regression has similar performance to optimised machine learning algorithms in a clinical setting: application to the discrimination between type 1 and type 2 diabetes in young adults.

Authors:  Anita L Lynam; John M Dennis; Katharine R Owen; Richard A Oram; Angus G Jones; Beverley M Shields; Lauric A Ferrat
Journal:  Diagn Progn Res       Date:  2020-06-04

9.  Osteoporotic hip fracture prediction from risk factors available in administrative claims data - A machine learning approach.

Authors:  Alexander Engels; Katrin C Reber; Ivonne Lindlbauer; Kilian Rapp; Gisela Büchele; Jochen Klenk; Andreas Meid; Clemens Becker; Hans-Helmut König
Journal:  PLoS One       Date:  2020-05-19       Impact factor: 3.240

10.  Machine Learning Improves Risk Stratification After Acute Coronary Syndrome.

Authors:  Paul D Myers; Benjamin M Scirica; Collin M Stultz
Journal:  Sci Rep       Date:  2017-10-04       Impact factor: 4.379
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.