Alessandro Brunelli1, Gaetano Rocco. 1. Unit of Thoracic Surgery, Umberto I Regional Hospital, Ancona, Italy. alexit_2000@yahoo.com
Abstract
OBJECTIVE: The objective of the present analysis was to compare the performance of a lung resection mortality model developed by means of logistic regression and bootstrap analysis with that of multiple mortality models developed by using the traditional training-and-test method from the same dataset. METHODS: Eleven mortality models (1 developed by means of logistic regression and bootstrap validation and the other 10 developed by means of the traditional training-and-test random splitting of the dataset) were generated by the data of unit A (571 patients submitted to major lung resection). The performances of each of the 11 mortality models were then evaluated by assessing the distribution of the respective c-statistics in 1000 bootstrap samples derived from unit B (224 patients). RESULTS: The first model (logistic regression and bootstrap analysis) had good discrimination among the 1000 bootstrap external samples (c-statistics >0.7 in 80% of samples and >0.8 in 38% of samples). Among the 10 training-and-test models, only one model had a similar performance, whereas the others had a poorer discrimination. CONCLUSIONS: The traditional training-and-test method for risk model building proved to be unreliable across multiple external populations and was generally inferior to bootstrap analysis for variable selection in regression analysis. Therefore the use of bootstrap analysis must be recommended for every future model-building process.
OBJECTIVE: The objective of the present analysis was to compare the performance of a lung resection mortality model developed by means of logistic regression and bootstrap analysis with that of multiple mortality models developed by using the traditional training-and-test method from the same dataset. METHODS: Eleven mortality models (1 developed by means of logistic regression and bootstrap validation and the other 10 developed by means of the traditional training-and-test random splitting of the dataset) were generated by the data of unit A (571 patients submitted to major lung resection). The performances of each of the 11 mortality models were then evaluated by assessing the distribution of the respective c-statistics in 1000 bootstrap samples derived from unit B (224 patients). RESULTS: The first model (logistic regression and bootstrap analysis) had good discrimination among the 1000 bootstrap external samples (c-statistics >0.7 in 80% of samples and >0.8 in 38% of samples). Among the 10 training-and-test models, only one model had a similar performance, whereas the others had a poorer discrimination. CONCLUSIONS: The traditional training-and-test method for risk model building proved to be unreliable across multiple external populations and was generally inferior to bootstrap analysis for variable selection in regression analysis. Therefore the use of bootstrap analysis must be recommended for every future model-building process.
Authors: David A Zisman; David J Ross; John A Belperio; Rajan Saggar; Joseph P Lynch; Abbas Ardehali; Arun S Karlamangla Journal: Respir Med Date: 2007-07-02 Impact factor: 3.415
Authors: Adam Attaar; Daniel G Winger; James D Luketich; Matthew J Schuchert; Inderpal S Sarkaria; Neil A Christie; Katie S Nason Journal: J Thorac Cardiovasc Surg Date: 2016-10-14 Impact factor: 5.209
Authors: Luuk Wieske; Esther Witteveen; Camiel Verhamme; Daniela S Dettling-Ihnenfeldt; Marike van der Schaaf; Marcus J Schultz; Ivo N van Schaik; Janneke Horn Journal: PLoS One Date: 2014-10-27 Impact factor: 3.240
Authors: Enora Laas; Cécile Poilroux; Corinne Bézu; Charles Coutant; Serge Uzan; Roman Rouzier; Elisabeth Chéreau Journal: Int J Breast Cancer Date: 2012-12-19