Risk of malignancy in pulmonary nodules: A validation study of four prediction models

Solid pulmonary nodule risk assessment and decision analysis: comparison of four prediction models in 285 cases

“…These models have been sometimes proposed to characterize SPNs in a more clinical scenario, and they have been validated to some extent. In the recent work by Al-Ameri and co-workers [18], the Brock model [19], which was developed using data from the PanCanadian Early Detection of Lung Cancer Study, was considered to have Bgood accuracy^. Unluckily the study did not focus on decision analysis.…”

“…The screening population has a prevalence of cancer that is much lower than a clinic-based population, in which physicians are often requested to characterize larger, incidentally discovered SPNs. As a matter of fact the Brock model was developed from 7008 nodules of which only 102 were cancers (1.45 %) [19], whereas reported prevalence of malignancy in a clinic-based population ranges typically between 23 % and 58 % [5,7,8,18]. For this reason we believe that this kind of model should not be taken into account for comparison when dealing with SPNs detected in clinical practice.…”

Segmental 18F-FDG-PET/CT in a single pulmonary nodule: a better cost/effectiveness strategy

“…In a recent assessment of the likelihood of malignancy in pulmonary nodules, a diagnostic model including PET/CT showed a significantly higher diagnostic efficacy than models including CT alone [14].…”

Prediction of risk of lung cancer in populations and in pulmonary nodules: Significant progress to drive changes in paradigms

“…It is therefore essential to validate prediction models, if possible in a different clinical setting and ideally in a population similar to that in which the model is being used clinically. The paper by Al-Ameri et al, in this issue, has done just that [8]. The four models they validated were those of the Mayo Clinic [2], Veterans Administration (VA) [3], Herder et al [9] and Brock University [7] (see Table 1).…”