Hiren J Mehta1, James G Ravenel2, Stephanie R Shaftman3, Nichole T Tanner4, Luca Paoletti5, Katherine K Taylor5, Martin C Tammemagi6, Mario Gomez7, Paul J Nietert1, Michael K Gould8, Gerard A Silvestri9. 1. Division of Pulmonary, Critical Care, and Sleep Medicine, University of Florida College of Medicine, Gainesville, FL. 2. Department of Radiology and Radiological Sciences, Department of Medicine, Medical University of South Carolina, Charleston, SC. 3. Division of Biostatistics and Epidemiology, Department of Medicine, Medical University of South Carolina, Charleston, SC. 4. Division of Biostatistics and Epidemiology, Department of Medicine, Medical University of South Carolina, Charleston, SC; Division of Pulmonary and Critical Care Medicine, Department of Medicine, Medical University of South Carolina, Charleston, SC. 5. Division of Pulmonary and Critical Care Medicine, Department of Medicine, Medical University of South Carolina, Charleston, SC. 6. Department of Community Health Sciences, Brock University, St. Catharines, ON, Canada. 7. Pulmonary & Sleep Center of the Valley, Weslaco, TX. 8. Department of Research and Evaluation, Kaiser Permanente Southern California, Pasadena, CA. 9. Division of Pulmonary and Critical Care Medicine, Department of Medicine, Medical University of South Carolina, Charleston, SC. Electronic address: silvestri@musc.edu.
Abstract
BACKGROUND: An estimated 150,000 pulmonary nodules are identified each year, and the number is likely to increase given the results of the National Lung Screening Trial. Decision tools are needed to help with the management of such pulmonary nodules. We examined whether adding any of three novel functions of nodule volume improves the accuracy of an existing malignancy prediction model of CT scan-detected nodules. METHODS: Swensen's 1997 prediction model was used to estimate the probability of malignancy in CT scan-detected nodules identified from a sample of 221 patients at the Medical University of South Carolina between 2006 and 2010. Three multivariate logistic models that included a novel function of nodule volume were used to investigate the added predictive value. Several measures were used to evaluate model classification performance. RESULTS: With use of a 0.5 cutoff associated with predicted probability, the Swensen model correctly classified 67% of nodules. The three novel models suggested that the addition of nodule volume enhances the ability to correctly predict malignancy; 83%, 88%, and 88% of subjects were correctly classified as having malignant or benign nodules, with significant net improved reclassification for each (P<.0001). All three models also performed well based on Nagelkerke R2, discrimination slope, area under the receiver operating characteristic curve, and Hosmer-Lemeshow calibration test. CONCLUSIONS: The findings demonstrate that the addition of nodule volume to existing malignancy prediction models increases the proportion of nodules correctly classified. This enhanced tool will help clinicians to risk stratify pulmonary nodules more effectively.
BACKGROUND: An estimated 150,000 pulmonary nodules are identified each year, and the number is likely to increase given the results of the National Lung Screening Trial. Decision tools are needed to help with the management of such pulmonary nodules. We examined whether adding any of three novel functions of nodule volume improves the accuracy of an existing malignancy prediction model of CT scan-detected nodules. METHODS: Swensen's 1997 prediction model was used to estimate the probability of malignancy in CT scan-detected nodules identified from a sample of 221 patients at the Medical University of South Carolina between 2006 and 2010. Three multivariate logistic models that included a novel function of nodule volume were used to investigate the added predictive value. Several measures were used to evaluate model classification performance. RESULTS: With use of a 0.5 cutoff associated with predicted probability, the Swensen model correctly classified 67% of nodules. The three novel models suggested that the addition of nodule volume enhances the ability to correctly predict malignancy; 83%, 88%, and 88% of subjects were correctly classified as having malignant or benign nodules, with significant net improved reclassification for each (P<.0001). All three models also performed well based on Nagelkerke R2, discrimination slope, area under the receiver operating characteristic curve, and Hosmer-Lemeshow calibration test. CONCLUSIONS: The findings demonstrate that the addition of nodule volume to existing malignancy prediction models increases the proportion of nodules correctly classified. This enhanced tool will help clinicians to risk stratify pulmonary nodules more effectively.
Authors: James G Ravenel; William M Leue; Paul J Nietert; James V Miller; Katherine K Taylor; Gerard A Silvestri Journal: Radiology Date: 2008-05 Impact factor: 11.105
Authors: Ewout W Steyerberg; Andrew J Vickers; Nancy R Cook; Thomas Gerds; Mithat Gonen; Nancy Obuchowski; Michael J Pencina; Michael W Kattan Journal: Epidemiology Date: 2010-01 Impact factor: 4.822
Authors: Rob J van Klaveren; Matthijs Oudkerk; Mathias Prokop; Ernst T Scholten; Kristiaan Nackaerts; Rene Vernhout; Carola A van Iersel; Karien A M van den Bergh; Susan van 't Westeinde; Carlijn van der Aalst; Erik Thunnissen; Dong Ming Xu; Ying Wang; Yingru Zhao; Hester A Gietema; Bart-Jan de Hoop; Harry J M Groen; Geertruida H de Bock; Peter van Ooijen; Carla Weenink; Johny Verschakelen; Jan-Willem J Lammers; Wim Timens; Dik Willebrand; Aryan Vink; Willem Mali; Harry J de Koning Journal: N Engl J Med Date: 2009-12-03 Impact factor: 91.245
Authors: Johanna Uthoff; Nicholas Koehn; Jared Larson; Samantha K N Dilger; Emily Hammond; Ann Schwartz; Brian Mullan; Rolando Sanchez; Richard M Hoffman; Jessica C Sieren Journal: Eur Radiol Date: 2019-04-01 Impact factor: 5.315
Authors: Yoganand Balagurunathan; Andrew Beers; Jayashree Kalpathy-Cramer; Michael McNitt-Gray; Lubomir Hadjiiski; Bensheng Zhao; Jiangguo Zhu; Hao Yang; Stephen S F Yip; Hugo J W L Aerts; Sandy Napel; Dmitrii Cherezov; Kenny Cha; Heang-Ping Chan; Carlos Flores; Alberto Garcia; Robert Gillies; Dmitry Goldgof Journal: Med Phys Date: 2018-02-19 Impact factor: 4.071