Literature DB >> 33831724

A Novel Method for Identifying a Parsimonious and Accurate Predictive Model for Multiple Clinical Outcomes.

L Grisell Diaz-Ramirez1, Sei J Lee2, Alexander K Smith3, Siqi Gan4, W John Boscardin5.   

Abstract

BACKGROUND AND
OBJECTIVE: Most methods for developing clinical prognostic models focus on identifying parsimonious and accurate models to predict a single outcome; however, patients and providers often want to predict multiple outcomes simultaneously. As an example, for older adults one is often interested in predicting nursing home admission as well as mortality. We propose and evaluate a novel predictor-selection computing method for multiple outcomes and provide the code for its implementation.
METHODS: Our proposed algorithm selected the best subset of common predictors based on the minimum average normalized Bayesian Information Criterion (BIC) across outcomes: the Best Average BIC (baBIC) method. We compared the predictive accuracy (Harrell's C-statistic) and parsimony (number of predictors) of the model obtained using the baBIC method with: 1) a subset of common predictors obtained from the union of optimal models for each outcome (Union method), 2) a subset obtained from the intersection of optimal models for each outcome (Intersection method), and 3) a model with no variable selection (Full method). We used a case-study data from the Health and Retirement Study (HRS) to demonstrate our method and conducted a simulation study to investigate performance.
RESULTS: In the case-study data and simulations, the average Harrell's C-statistics across outcomes of the models obtained with the baBIC and Union methods were comparable. Despite the similar discrimination, the baBIC method produced more parsimonious models than the Union method. In contrast, the models selected with the Intersection method were the most parsimonious, but with worst predictive accuracy, and the opposite was true in the Full method. In the simulations, the baBIC method performed well by identifying many of the predictors selected in the baBIC model of the case-study data most of the time and excluding those not selected in the majority of the simulations.
CONCLUSIONS: Our method identified a common subset of variables to predict multiple clinical outcomes with superior balance between parsimony and predictive accuracy to current methods.
Copyright © 2021. Published by Elsevier B.V.

Entities:  

Keywords:  Bayesian Information Criterion; backward elimination; prognostic models; survival analysis; variable selection

Mesh:

Year:  2021        PMID: 33831724      PMCID: PMC8098121          DOI: 10.1016/j.cmpb.2021.106073

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  21 in total

1.  Internal validation of predictive models: efficiency of some procedures for logistic regression analysis.

Authors:  E W Steyerberg; F E Harrell; G J Borsboom; M J Eijkemans; Y Vergouwe; J D Habbema
Journal:  J Clin Epidemiol       Date:  2001-08       Impact factor: 6.437

2.  A new risk scheme to predict warfarin-associated hemorrhage: The ATRIA (Anticoagulation and Risk Factors in Atrial Fibrillation) Study.

Authors:  Margaret C Fang; Alan S Go; Yuchiao Chang; Leila H Borowsky; Niela K Pomernacki; Natalia Udaltsova; Daniel E Singer
Journal:  J Am Coll Cardiol       Date:  2011-07-19       Impact factor: 24.094

3.  Prognostic models with competing risks: methods and application to coronary risk prediction.

Authors:  Marcel Wolbers; Michael T Koller; Jacqueline C M Witteman; Ewout W Steyerberg
Journal:  Epidemiology       Date:  2009-07       Impact factor: 4.822

Review 4.  Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors.

Authors:  F E Harrell; K L Lee; D B Mark
Journal:  Stat Med       Date:  1996-02-28       Impact factor: 2.373

5.  Cohort Profile: the Health and Retirement Study (HRS).

Authors:  Amanda Sonnega; Jessica D Faul; Mary Beth Ofstedal; Kenneth M Langa; John W R Phillips; David R Weir
Journal:  Int J Epidemiol       Date:  2014-03-25       Impact factor: 7.196

6.  VARIABLE SELECTION FOR HIGH DIMENSIONAL MULTIVARIATE OUTCOMES.

Authors:  Tamar Sofer; Lee Dicker; Xihong Lin
Journal:  Stat Sin       Date:  2014-10       Impact factor: 1.261

7.  Guidelines abstracted from the American Geriatrics Society Guidelines for Improving the Care of Older Adults with Diabetes Mellitus: 2013 update.

Authors:  Gerardo Moreno; Carol M Mangione; Lindsay Kimbro; Ekaterina Vaisberg
Journal:  J Am Geriatr Soc       Date:  2013-11       Impact factor: 5.562

8.  Sparse Multivariate Regression With Covariance Estimation.

Authors:  Adam J Rothman; Elizaveta Levina; Ji Zhu
Journal:  J Comput Graph Stat       Date:  2010       Impact factor: 2.302

9.  Diabetes in older adults: a consensus report.

Authors:  M Sue Kirkman; Vanessa Jones Briscoe; Nathaniel Clark; Hermes Florez; Linda B Haas; Jeffrey B Halter; Elbert S Huang; Mary T Korytkowski; Medha N Munshi; Peggy Soule Odegard; Richard E Pratley; Carrie S Swift
Journal:  J Am Geriatr Soc       Date:  2012-10-25       Impact factor: 5.562

10.  A multivariate regression approach to association analysis of a quantitative trait network.

Authors:  Seyoung Kim; Kyung-Ah Sohn; Eric P Xing
Journal:  Bioinformatics       Date:  2009-06-15       Impact factor: 6.937

View more
  1 in total

1.  A Novel Method for Identifying a Parsimonious and Accurate Predictive Model for Multiple Clinical Outcomes.

Authors:  L Grisell Diaz-Ramirez; Sei J Lee; Alexander K Smith; Siqi Gan; W John Boscardin
Journal:  Comput Methods Programs Biomed       Date:  2021-03-27       Impact factor: 5.428

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.