Comparison of discriminatory power and accuracy of three lung cancer risk models

Department of Epidemiology, UT MD Anderson Cancer Center, 1155 Pressler Street - Unit 1340, Houston, Texas 77030-4009, USA.
British Journal of Cancer (Impact Factor: 4.84). 07/2010; 103(3):423-9. DOI: 10.1038/sj.bjc.6605759
Source: PubMed

ABSTRACT Three lung cancer (LC) models have recently been constructed to predict an individual's absolute risk of LC within a defined period. Given their potential application in prevention strategies, a comparison of their accuracy in an independent population is important.
We used data for 3197 patients with LC and 1703 cancer-free controls recruited to an ongoing case-control study at the Harvard School of Public Health and Massachusetts General Hospital. We estimated the 5-year LC risk for each risk model and compared the discriminatory power, accuracy, and clinical utility of these models.
Overall, the Liverpool Lung Project (LLP) and Spitz models had comparable discriminatory power (0.69), whereas the Bach model had significantly lower power (0.66; P=0.02). Positive predictive values were highest with the Spitz models, whereas negative predictive values were highest with the LLP model. The Spitz and Bach models had lower sensitivity but better specificity than did the LLP model.
We observed modest differences in discriminatory power among the three LC risk models, but discriminatory powers were moderate at best, highlighting the difficulty in developing effective risk models.

Download full-text


Available from: John K Field, Sep 26, 2015
23 Reads
  • Source
    • "[6]. Thus, lung cancer risk models using epidemiologic data have been developed and the most parsimonious models for both ever and never smokers include a family history as a lung cancer risk [7]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Genetic alterations could be responsible lung cancer, the leading cause of worldwide cancer death. This study investigated gene mutations in a Han Chinese family of lung cancer using the whole genome exome sequencing and subsequent Sanger sequencing validation and then confirmed alteration of prominin 1(PROM1) and cyclic AMP-response element binding protein-regulated transcription co-activator2(CRTC2) in blood samples of 343 sporadic lung cancer patients vs. 280 healthy controls as well as in 200 pairs of lung cancer and the corresponding normal tissues using PCR-restriction fragment length polymorphism and directed DNA sequencing of PCR products. The data showed PROM1 (p. S281R) and CRTC2 (p. R379C) mutations, in 5 and 2 cases of these 343 sporadic lung cancer patients, respectively. Notably, these mutations were absent in the healthy controls. Furthermore, in the 200 lung cancer and the matched normal tissues, PROM1 mutation occurred in 3 patients (i.e., one squamous cell carcinoma and two adenocarcinomas) with a mutation frequency of 1.5%, while CRTC2 mutation occurred in 5 patients (two squamous cell carcinomas and three adenocarcinomas) with a mutation frequency of 2.5%. The data from the current study demonstrated novel PROM1 and CRTC2 mutations, which could promote lung cancer development.
    Molecular Cancer 01/2014; 13(1):19. DOI:10.1186/1476-4598-13-19 · 4.26 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper describes a process to design and implement a cost-effective information system which meets the clinical needs of rehabilitation with initial efforts on cardiac rehabilitation. Issues of platform selection, user interface, database design, data capture and sharing, automated reasoning and decision support are addressed
    Biomedical Engineering Conference, 1997., Proceedings of the 1997 Sixteenth Southern; 05/1997
  • [Show abstract] [Hide abstract]
    ABSTRACT: Lung cancer risk prediction models hold the promise of improving patient care and streamlining research. The ultimate goal of these models is to inform clinicians as to which interventions their individual patients should receive to reduce lung cancer-associated morbidity and mortality. In this paper, we discuss the history and current state of lung cancer prediction models, focusing on three models: the Bach model, the Spitz model, and the Liverpool Lung Project (LLP) model. We also discuss the prospects for further development of improved prediction models for lung cancer risk. Although current models can identify those smokers at highest risk for lung cancer, these models are presently of limited use in the clinical setting. Nevertheless, lung cancer risk prediction models can be used during study enrollment to select more appropriate study subjects, and may eventually be useful in identifying patients for lung cancer screening or to receive chemoprevention.
    Seminars in Respiratory and Critical Care Medicine 02/2011; 32(1):3-9. DOI:10.1055/s-0031-1272864 · 2.71 Impact Factor
Show more