OBJECTIVES: The aim of this study was to assess the applicability of knowledge discovery in database methodology, based upon data mining techniques, to the investigation of lung cancer surgery. METHODS: According to CRISP 1.0 methodology, a data mining (DM) project was developed on a data warehouse containing records for 501 patients operated on for lung cancer with curative intention. The modelling technique was logistic regression. RESULTS: The finally selected model presented the following values: sensitivity 9.68%, specificity 100%, global precision 94.02%, positive predictive value 100% and negative predictive value 93.98% for a cut-off point set at 0.5. A receiver operating characteristic (ROC) curve was constructed. The area under the curve (CI 95%) was 0.817 (0.740- 0.893) (p < 0.05). Statistical association with perioperative mortality was found for the following variables [odds ratio (CI 95%)]: age over 70 [2.3822 (1.0338-5.4891)], heart disease [2.4875 (1.0089-6.1334)], peripheral arterial disease [5.7705 (1.9296-17.2570)], pneumonectomy [3.6199 (1.4939-8.7715)] and length of surgery (min) [1.0067 (1.0008-1.0126)]. CONCLUSIONS: The CRISP-DM process model is very suitable for lung cancer surgery analysis, improving decision making as well as knowledge and quality management.
OBJECTIVES: The aim of this study was to assess the applicability of knowledge discovery in database methodology, based upon data mining techniques, to the investigation of lung cancer surgery. METHODS: According to CRISP 1.0 methodology, a data mining (DM) project was developed on a data warehouse containing records for 501 patients operated on for lung cancer with curative intention. The modelling technique was logistic regression. RESULTS: The finally selected model presented the following values: sensitivity 9.68%, specificity 100%, global precision 94.02%, positive predictive value 100% and negative predictive value 93.98% for a cut-off point set at 0.5. A receiver operating characteristic (ROC) curve was constructed. The area under the curve (CI 95%) was 0.817 (0.740- 0.893) (p < 0.05). Statistical association with perioperative mortality was found for the following variables [odds ratio (CI 95%)]: age over 70 [2.3822 (1.0338-5.4891)], heart disease [2.4875 (1.0089-6.1334)], peripheral arterial disease [5.7705 (1.9296-17.2570)], pneumonectomy [3.6199 (1.4939-8.7715)] and length of surgery (min) [1.0067 (1.0008-1.0126)]. CONCLUSIONS: The CRISP-DM process model is very suitable for lung cancer surgery analysis, improving decision making as well as knowledge and quality management.
Authors: D H Harpole; M M DeCamp; J Daley; K Hur; C A Oprian; W G Henderson; S F Khuri Journal: J Thorac Cardiovasc Surg Date: 1999-05 Impact factor: 5.209
Authors: J L Cruz-Bermúdez; C Parejo; F Martínez-Ruíz; J C Sánchez-González; A Ramos Martín-Vegue; A Royuela; A Rodríguez-González; E Menasalvas-Ruiz; M Provencio Journal: Clin Transl Oncol Date: 2019-03-12 Impact factor: 3.405
Authors: Steven Morse; Kevin Talty; Patrick Kuiper; Michael Scioletti; Steven B Heymsfield; Richard L Atkinson; Diana M Thomas Journal: PLoS One Date: 2020-06-30 Impact factor: 3.240
Authors: Beatriz Pontes; Francisco Núñez; Cristina Rubio; Alberto Moreno; Isabel Nepomuceno; Jesús Moreno; Jon Cacicedo; Juan Manuel Praena-Fernandez; German Antonio Escobar Rodriguez; Carlos Parra; Blas David Delgado León; Eleonor Rivin Del Campo; Felipe Couñago; Jose Riquelme; Jose Luis Lopez Guerra Journal: Rep Pract Oncol Radiother Date: 2021-12-30