Elinor Nemlander1,2, Andreas Rosenblad1,3,4, Eliya Abedi1,2, Simon Ekman5, Jan Hasselström1,2, Lars E Eriksson6,7,8, Axel C Carlsson1,2. 1. Division of Family Medicine and Primary Care, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Solna, Sweden. 2. Academic Primary Health Care Centre, Region Stockholm, Stockholm, Sweden. 3. Regional Cancer Centre Stockholm-Gotland, Region Stockholm, Stockholm, Sweden. 4. Division of Clinical Diabetology and Metabolism, Department of Medical Sciences, Uppsala University, Uppsala, Sweden. 5. Thoracic Oncology Centre, Karolinska University Hospital, Dept of Oncology-Pathology, Karolinska Institutet, Stockholm, Sweden. 6. Division of Nursing, Department of Neurobiology, Care Sciences and Society, Karolinska Institutet, Huddinge, Sweden. 7. School of Health and Psychological Sciences, City, University of London, London, United Kingdom. 8. Medical Unit Infectious Diseases, Karolinska University Hospital, Huddinge, Sweden.
Abstract
PURPOSE: The aim of the present study was to investigate the predictive ability for lung cancer of symptoms reported in an adaptive e-questionnaire, separately for never smokers, former smokers, and current smokers. PATIENTS AND METHODS: Consecutive patients referred for suspected lung cancer were recruited between September 2014 and November 2015 from the lung clinic at the Karolinska University Hospital, Stockholm, Sweden. A total of 504 patients were later diagnosed with lung cancer (n = 310) or no cancer (n = 194). All participants answered an adaptive e-questionnaire with a maximum of 342 items, covering background variables and symptoms/sensations suspected to be associated with lung cancer. Stochastic gradient boosting, stratified on smoking status, was used to train and test a model for predicting the presence of lung cancer. RESULTS: Among never smokers, 17 predictors contributed to predicting lung cancer with 82% of the patients being correctly classified, compared with 26 predictors with an accuracy of 77% among current smokers and 36 predictors with an accuracy of 63% among former smokers. Age, sex, and education level were the most important predictors in all models. CONCLUSION: Methods or tools to assess the likelihood of lung cancer based on smoking status and to prioritize investigative and treatment measures among all patients seeking care with diffuse symptoms are much needed. Our study presents risk assessment models for patients with different smoking status that may be developed into clinical risk assessment tools that can help clinicians in assessing a patient's risk of having lung cancer.
PURPOSE: The aim of the present study was to investigate the predictive ability for lung cancer of symptoms reported in an adaptive e-questionnaire, separately for never smokers, former smokers, and current smokers. PATIENTS AND METHODS: Consecutive patients referred for suspected lung cancer were recruited between September 2014 and November 2015 from the lung clinic at the Karolinska University Hospital, Stockholm, Sweden. A total of 504 patients were later diagnosed with lung cancer (n = 310) or no cancer (n = 194). All participants answered an adaptive e-questionnaire with a maximum of 342 items, covering background variables and symptoms/sensations suspected to be associated with lung cancer. Stochastic gradient boosting, stratified on smoking status, was used to train and test a model for predicting the presence of lung cancer. RESULTS: Among never smokers, 17 predictors contributed to predicting lung cancer with 82% of the patients being correctly classified, compared with 26 predictors with an accuracy of 77% among current smokers and 36 predictors with an accuracy of 63% among former smokers. Age, sex, and education level were the most important predictors in all models. CONCLUSION: Methods or tools to assess the likelihood of lung cancer based on smoking status and to prioritize investigative and treatment measures among all patients seeking care with diffuse symptoms are much needed. Our study presents risk assessment models for patients with different smoking status that may be developed into clinical risk assessment tools that can help clinicians in assessing a patient's risk of having lung cancer.
Authors: Harry J de Koning; Carlijn M van der Aalst; Pim A de Jong; Ernst T Scholten; Kristiaan Nackaerts; Marjolein A Heuvelmans; Jan-Willem J Lammers; Carla Weenink; Uraujh Yousaf-Khan; Nanda Horeweg; Susan van 't Westeinde; Mathias Prokop; Willem P Mali; Firdaus A A Mohamed Hoesein; Peter M A van Ooijen; Joachim G J V Aerts; Michael A den Bakker; Erik Thunnissen; Johny Verschakelen; Rozemarijn Vliegenthart; Joan E Walter; Kevin Ten Haaf; Harry J M Groen; Matthijs Oudkerk Journal: N Engl J Med Date: 2020-01-29 Impact factor: 91.245
Authors: Barbara Iyen-Omofoman; Laila J Tata; David R Baldwin; Chris J P Smith; Richard B Hubbard Journal: Thorax Date: 2013-01-15 Impact factor: 9.139
Authors: Adrian Levitsky; Britt-Marie Bernhardson; Carol Tishelman; Lars E Eriksson; Ingela Henoch; Maria Olin; Karl Kölbeck; Nadja Rystedt Journal: BMC Cancer Date: 2021-05-13 Impact factor: 4.430
Authors: F M Walter; G Rubin; C Bankhead; H C Morris; N Hall; K Mills; C Dobson; R C Rintoul; W Hamilton; J Emery Journal: Br J Cancer Date: 2015-03-31 Impact factor: 7.640
Authors: Silvano Gallus; Alessandra Lugo; Carlo La Vecchia; Paolo Boffetta; Frank J Chaloupka; Paolo Colombo; Laura Currie; Esteve Fernandez; Colin Fischbacher; Anna Gilmore; Fiona Godfrey; Luk Joossens; Maria E Leon; David T Levy; Lien Nguyen; Gunnar Rosenqvist; Hana Ross; Joy Townsend; Luke Clancy Journal: Eur J Cancer Prev Date: 2014-05 Impact factor: 2.497
Authors: Adrian Levitsky; Maria Pernemalm; Britt-Marie Bernhardson; Jenny Forshed; Karl Kölbeck; Maria Olin; Roger Henriksson; Janne Lehtiö; Carol Tishelman; Lars E Eriksson Journal: Sci Rep Date: 2019-11-11 Impact factor: 4.379