Format

Send to

Choose Destination
EBioMedicine. 2018 May;31:36-46. doi: 10.1016/j.ebiom.2018.03.027. Epub 2018 Mar 30.

A Validated Clinical Risk Prediction Model for Lung Cancer in Smokers of All Ages and Exposure Types: A HUNT Study.

Author information

1
University of Crete, Department of Computer Science, Voutes Campus, Heraklion, GR 70013, Greece.
2
University of Crete, Department of Computer Science, Voutes Campus, Heraklion, GR 70013, Greece; Gnosis Data Analysis PC, Palaiokapa 64, Heraklion, GR 71305, Greece.
3
HUNT Research Centre, Department of Public Health and Nursing, Norwegian University of Science and Technology, Forskningsvegen 2, Levanger, NO 7600, Norway.
4
HUNT Research Centre, Department of Public Health and Nursing, Norwegian University of Science and Technology, Forskningsvegen 2, Levanger, NO 7600, Norway; K.G. Jebsen Center for Genetic Epidemiology, Department of Public Health an Nursing, Norwegian University of Science and Technology, NO 7491 Trondheim, Norway.
5
Norwegian University of Science and Technology, Department of Clinical Research and Molecular Medicine, Prinsesse Kristinsgt. 1, Trondheim, NO 7491, Norway; Levanger Hospital, Nord-Trøndelag Hospital Trust, Cancer Clinic, Kirkegata 2, Levanger, NO 7600, Norway; Clinical Cancer Research Center, Department of Clinical Medicine, Hobrovej 18-22, Aalborg, DK 9000, Denmark. Electronic address: oluf.roe@ntnu.no.

Abstract

Lung cancer causes >1·6 million deaths annually, with early diagnosis being paramount to effective treatment. Here we present a validated risk assessment model for lung cancer screening. The prospective HUNT2 population study in Norway examined 65,237 people aged >20years in 1995-97. After a median of 15·2years, 583 lung cancer cases had been diagnosed; 552 (94·7%) ever-smokers and 31 (5·3%) never-smokers. We performed multivariable analyses of 36 candidate risk predictors, using multiple imputation of missing data and backwards feature selection with Cox regression. The resulting model was validated in an independent Norwegian prospective dataset of 45,341 ever-smokers, in which 675 lung cancers had been diagnosed after a median follow-up of 11·6years. Our final HUNT Lung Cancer Model included age, pack-years, smoking intensity, years since smoking cessation, body mass index, daily cough, and hours of daily indoors exposure to smoke. External validation showed a 0·879 concordance index (95% CI [0·866-0·891]) with an area under the curve of 0·87 (95% CI [0·85-0·89]) within 6years. Only 22% of ever-smokers would need screening to identify 81·85% of all lung cancers within 6years. Our model of seven variables is simple, accurate, and useful for screening selection.

KEYWORDS:

All ages; All smokers; Data-driven; Early diagnosis; Ever-smokers; External validation; Feature selection; Lung cancer prediction

PMID:
29678673
PMCID:
PMC6013755
DOI:
10.1016/j.ebiom.2018.03.027
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center