Literature DB >> 26475568

A tutorial on variable selection for clinical prediction models: feature selection methods in data mining could improve the results.

Farideh Bagherzadeh-Khiabani1, Azra Ramezankhani1, Fereidoun Azizi2, Farzad Hadaegh1, Ewout W Steyerberg3, Davood Khalili4.   

Abstract

OBJECTIVES: Identifying an appropriate set of predictors for the outcome of interest is a major challenge in clinical prediction research. The aim of this study was to show the application of some variable selection methods, usually used in data mining, for an epidemiological study. We introduce here a systematic approach. STUDY DESIGN AND
SETTING: The P-value-based method, usually used in epidemiological studies, and several filter and wrapper methods were implemented to select the predictors of diabetes among 55 variables in 803 prediabetic females, aged ≥ 20 years, followed for 10-12 years. To develop a logistic model, variables were selected from a train data set and evaluated on the test data set. The measures of Akaike information criterion (AIC) and area under the curve (AUC) were used as performance criteria. We also implemented a full model with all 55 variables.
RESULTS: We found that the worst and the best models were the full model and models based on the wrappers, respectively. Among filter methods, symmetrical uncertainty gave both the best AUC and AIC.
CONCLUSION: Our experiment showed that the variable selection methods used in data mining could improve the performance of clinical prediction models. An R program was developed to make these methods more feasible and visualize the results.
Copyright © 2016 Elsevier Inc. All rights reserved.

Entities:  

Keywords:  Data mining; Feature selection; Methods; Prediction; Statistical model; Variable selection

Mesh:

Year:  2015        PMID: 26475568     DOI: 10.1016/j.jclinepi.2015.10.002

Source DB:  PubMed          Journal:  J Clin Epidemiol        ISSN: 0895-4356            Impact factor:   6.437


  28 in total

1.  Comparison of variable selection methods for clinical predictive modeling.

Authors:  L Nelson Sanchez-Pinto; Laura Ruth Venable; John Fahrenbach; Matthew M Churpek
Journal:  Int J Med Inform       Date:  2018-05-21       Impact factor: 4.046

2.  SurvBenchmark: comprehensive benchmarking study of survival analysis methods using both omics data and clinical data.

Authors:  Yunwei Zhang; Germaine Wong; Graham Mann; Samuel Muller; Jean Y H Yang
Journal:  Gigascience       Date:  2022-07-30       Impact factor: 7.658

3.  Predicting Progression Patterns of Type 2 Diabetes using Multi-sensor Measurements.

Authors:  Ramin Ramazi; Christine Perndorfer; Emily C Soriano; Jean-Philippe Laurenceau; Rahmatollah Beheshti
Journal:  Smart Health (Amst)       Date:  2021-06-12

4.  Development of Machine Learning-Based Models to Predict Treatment Response to Spinal Cord Stimulation.

Authors:  Amir Hadanny; Tessa Harland; Olga Khazen; Marisa DiMarzio; Anthony Marchese; Ilknur Telkes; Vishad Sukul; Julie G Pilitsis
Journal:  Neurosurgery       Date:  2022-05-01       Impact factor: 5.315

5.  Individual differences in the effects of the ACTION-PAC intervention: an application of personalized medicine in the prevention and treatment of obesity.

Authors:  Alena Kuhlemeier; Thomas Jaki; Elizabeth Y Jimenez; Alberta S Kong; Hope Gill; Chi Chang; Ken Resnicow; Dawn K Wilson; M Lee Van Horn
Journal:  J Behav Med       Date:  2022-01-15

6.  Identification of Affective State Change in Adults With Aphasia Using Speech Acoustics.

Authors:  Stephanie Gillespie; Jacqueline Laures-Gore; Elliot Moore; Matthew Farina; Scott Russell; Benjamin Haaland
Journal:  J Speech Lang Hear Res       Date:  2018-12-10       Impact factor: 2.297

7.  Targeted temperature management in cardiovascular disease complicated by cardiac arrest.

Authors:  M Gorecka; A Hanley; F Burke; P Nolan; J Crowley
Journal:  Ir J Med Sci       Date:  2016-05-04       Impact factor: 1.568

8.  Applying methods for personalized medicine to the treatment of alcohol use disorder.

Authors:  Alena Kuhlemeier; Yasin Desai; Alexandra Tonigan; Katie Witkiewitz; Thomas Jaki; Yu-Yu Hsiao; Chi Chang; M Lee Van Horn
Journal:  J Consult Clin Psychol       Date:  2021-04

9.  GLIMPSE: a glioblastoma prognostication model using ensemble learning-a surveillance, epidemiology, and end results study.

Authors:  Kamel A Samara; Zaher Al Aghbari; Amani Abusafia
Journal:  Health Inf Sci Syst       Date:  2021-01-12

10.  An ensemble-based feature selection framework to select risk factors of childhood obesity for policy decision making.

Authors:  Xi Shi; Gorana Nikolic; Gorka Epelde; Mónica Arrúe; Joseba Bidaurrazaga Van-Dierdonck; Roberto Bilbao; Bart De Moor
Journal:  BMC Med Inform Decis Mak       Date:  2021-07-21       Impact factor: 2.796

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.