Skip to Main Content
About this Publication
Development and Validation of a Risk Prediction Tool for Second Primary Lung Cancer.
Pubmed ID
34255071 (View this publication on the PubMed website)
Digital Object Identifier
J Natl Cancer Inst. 2021 Jul 13
Choi E, Sanyal N, Ding VY, Gardner RM, Aredo JV, Lee J, Wu JT, Hickey TP, Barrett B, Riley TL, Wilkens LR, Leung AN, Le Marchand L, Tammemägi MC, Hung RJ, Amos CI, Freedman ND, Cheng I, Wakelee HA, Han SS
  • Quantitative Sciences Unit, Stanford University School of Medicine, Stanford, CA, USA.
  • Stanford University School of Medicine, Stanford, CA, USA.
  • Information Management Services, Rockville, MD, USA.
  • Cancer Epidemiology Program, University of Hawaii Cancer Center, Honolulu, HI, USA.
  • Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA.
  • Department of Health Sciences, Brock University, St Catharines, Ontario, Canada.
  • Prosserman Centre for Population Health Research, Lunenfeld-Tanenbaum Research Institute, Sinai Health System, Toronto, Ontario, Canada.
  • Department of Medicine, Baylor College of Medicine, Houston, TX, USA.
  • Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Bethesda, MD, USA.
  • Department of Epidemiology and Biostatistics, University of California, San Francisco, CA, USA.

BACKGROUND: With advancing therapeutics, lung cancer (LC) survivors are rapidly increasing in number. While mounting evidence suggests LC survivors have high risk of second primary lung cancer (SPLC), there is no validated prediction tool available for clinical use to identify high-risk LC survivors for SPLC.

METHODS: Using data from 6,325 ever-smokers in the Multiethnic Cohort (MEC) diagnosed with initial primary lung cancer (IPLC) in 1993-2017, we developed a prediction model for 10-year SPLC risk after IPLC diagnosis using cause-specific Cox regression. We evaluated the model's clinical utility using decision curve analysis and externally validated it using two population-based data, PLCO and NLST, that included 2,963 and 2,844 IPLC (101 and 93 SPLC cases), respectively.

RESULTS: Over 14,063 person-years, 145 (2.3%) developed SPLC in MEC. Our prediction model demonstrated a high predictive accuracy (Brier score = 2.9, 95% confidence interval [CI] = 2.4-3.3) and discrimination (AUC = 81.9%, 95% CI = 78.2%-85.5%) based on bootstrap validation in MEC. Stratification by the estimated risk quartiles showed that the observed SPLC incidence was statistically significantly higher in the 4th versus 1st quartile (9.5% versus 0.2%; P < .001). Decision curve analysis indicated that in a wide range of 10-year risk thresholds from 1% to 20%, the model yielded a larger net-benefit versus hypothetical all-screening or no-screening scenarios. External validation using PLCO and NLST showed an AUC of 78.8% (95% CI = 74.6%-82.9%) and 72.7% (95% CI = 67.7%-77.7%), respectively.

CONCLUSIONS: We developed and validated a SPLC prediction model based on large population-based cohorts. The proposed prediction tool can help identify high-risk LC patients for SPLC and can be incorporated into clinical decision-making for SPLC surveillance and screening.

Related CDAS Studies
Related CDAS Projects