The guidelines provide more clarity in the use of further imaging, with ordinal scale reporting for PET-CT recommended to facilitate incorporation into risk models (section ‘Further imaging in management of pulmonary nodules’) and more clarity about the place of biopsy (section ‘Non-imaging tests and non-surgical biopsy’, algorithm 4). There are recommendations for the threshold for treatment without histological confirmation (sections ‘Surgical excision biopsy’ and ‘Non-surgical treatment without pathological confirmation of malignancy’, algorithm 4).

Lung cancer screening with low-dose CT can save lives. This European Union (EU) position statement presents the available evidence and the major issues that need to be addressed to ensure the successful implementation of low-dose CT lung cancer screening in Europe. This statement identified specific actions required by the European lung cancer screening community to adopt before the implementation of low-dose CT lung cancer screening. This position statement recommends the following actions: a risk stratification approach should be used for future lung cancer low-dose CT programmes; that individuals who enter screening programmes should be provided with information on the benefits and harms of screening, and smoking cessation should be offered to all current smokers; that management of detected solid nodules should use semi-automatically measured volume and volume-doubling time; that national quality assurance boards should be set up to oversee technical standards; that a lung nodule management pathway should be established and incorporated into clinical practice with a tailored screening approach; that non-calcified baseline lung nodules greater than 300 mm3, and new lung nodules greater than 200 mm3, should be managed in multidisciplinary teams according to this EU position statement recommendations to ensure that patients receive the most appropriate treatment; and planning for implementation of low-dose CT screening should start throughout Europe as soon as possible. European countries need to set a timeline for implementing lung cancer screening.

The British Thoracic Society guideline for the investigation and management of pulmonary nodules is published as a supplement to this edition of the journal. It provides recommendations for the management of an individual with single or multiple pulmonary nodules and is a comprehensive reference text.

Background Estimation of the risk of malignancy in pulmonary nodules detected by CT is central in clinical management. The use of artificial intelligence (AI) offers an opportunity to improve risk prediction. Here we compare the performance of an AI algorithm, the lung cancer prediction convolutional neural network (LCP-CNN), with that of the Brock University model, recommended in UK guidelines. Methods A dataset of incidentally detected pulmonary nodules measuring 5–15 mm was collected retrospectively from three UK hospitals for use in a validation study. Ground truth diagnosis for each nodule was based on histology (required for any cancer), resolution, stability or (for pulmonary lymph nodes only) expert opinion. There were 1397 nodules in 1187 patients, of which 234 nodules in 229 (19.3%) patients were cancer. Model discrimination and performance statistics at predefined score thresholds were compared between the Brock model and the LCP-CNN. Results The area under the curve for LCP-CNN was 89.6% (95% CI 87.6 to 91.5), compared with 86.8% (95% CI 84.3 to 89.1) for the Brock model (p≤0.005). Using the LCP-CNN, we found that 24.5% of nodules scored below the lowest cancer nodule score, compared with 10.9% using the Brock score. Using the predefined thresholds, we found that the LCP-CNN gave one false negative (0.4% of cancers), whereas the Brock model gave six (2.5%), while specificity statistics were similar between the two models. Conclusion The LCP-CNN score has better discrimination and allows a larger proportion of benign nodules to be identified without missing cancers than the Brock model. This has the potential to substantially reduce the proportion of surveillance CT scans required and thus save significant resources.