Multicentre external validation of the BIMC model for solid solitary pulmonary nodule malignancy prediction
- 276 Downloads
To provide multicentre external validation of the Bayesian Inference Malignancy Calculator (BIMC) model by assessing diagnostic accuracy in a cohort of solitary pulmonary nodules (SPNs) collected in a clinic-based setting. To assess model impact on SPN decision analysis and to compare findings with those obtained via the Mayo Clinic model.
Clinical and imaging data were retrospectively collected from 200 patients from three centres. Accuracy was assessed by means of receiver-operating characteristic (ROC) areas under the curve (AUCs). Decision analysis was performed by adopting both the American College of Chest Physicians (ACCP) and the British Thoracic Society (BTS) risk thresholds.
ROC analysis showed an AUC of 0.880 (95 % CI, 0.832-0.928) for the BIMC model and of 0.604 (95 % CI, 0.524-0.683) for the Mayo Clinic model. Difference was 0.276 (95 % CI, 0.190-0.363, P < 0.0001). Decision analysis showed a slightly reduced number of false-negative and false-positive results when using ACCP risk thresholds.
The BIMC model proved to be an accurate tool when characterising SPNs. In a clinical setting it can distinguish malignancies from benign nodules with minimal errors by adopting current ACCP or BTS risk thresholds and guiding lesion-tailored diagnostic and interventional procedures during the work-up.
• The BIMC model can accurately discriminate malignancies in the clinical setting
• The BIMC model showed ROC AUC of 0.880 in this multicentre study
• The BIMC model compares favourably with the Mayo Clinic model
KeywordsLung cancer Solid pulmonary nodule Decision analysis Computed tomography
The authors would like to thank Prof. MC Tammemägi for his valuable suggestions during the writing of this paper and L Brandon for language editing. The scientific guarantor of this publication is Simone Perandini. The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article. The authors state that this work has not received any funding. One of the authors has significant statistical expertise (S.P.). Institutional Review Board approval was not required because the research involved collection and analysis of existing data. Data and diagnostic specimens were recorded by the investigator in such a manner that subjects cannot be identified. Written informed consent was not required for this study because the research involved collection and analysis of existing data. Data and diagnostic specimens were recorded by the investigator in such a manner that subjects cannot be identified. Methodology:
Retrospective, diagnostic or prognostic study, multicentre study. One hundred fifty-three SPNs are part of a larger data set, which was analysed in a manuscript investigating SPN 18-FDG-PET characterisation and is currently under review.
- 2.Gould MK, Donington J, Lynch WR et al (2013) Evaluation of individuals with pulmonary nodules: when is it lung cancer?: Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians Evidence-Based Clinical Practice Guidelines. Chest 143:e93S–e120SCrossRefPubMedPubMedCentralGoogle Scholar