Introduction Diagnosing and treating lung cancer in early stages is essential for survival outcomes. The chest X-ray (CXR) remains the primary screening tool to identify lung cancers in the UK; however, there is a shortfall of radiologists, while demand continues to increase. Image analysis by machine-learning software has the potential to support radiology workflows with a focus on immediate triage of suspicious X-rays. The RADICAL study will evaluate Qure.ai’s ‘qXR’ software in reducing reporting time for suspicious X-rays in NHS Greater Glasgow & Clyde. Methods and analysis This is a stepped-wedge cluster-randomised study consisting of a retrospective technical evaluation and prospective clinical effectiveness study alongside the assessment of acceptability via qualitative work and evaluation of cost-effectiveness via a cost utility analysis. The primary objective is to assess the clinical effectiveness of qXR to prioritise patients suspected with lung cancer on CXR for follow-up CT. Secondary objectives will look at the utility, safety, technical performance, health economics and acceptability of the intervention. The study period is 24 months, consisting of an initial 12 month data collection period and a 12 month follow-up period. All the standard care CXRs from outpatient and primary care requests will be securely transmitted to Qure.ai software ‘qXR’ for interpretation. Images with features of cancer will be flagged as ‘Urgent Suspicion of Cancer’ and be prioritised for radiologist review within the existing reporting workflow. Ethics and dissemination The study will follow the principles of Good Clinical Practice. The protocol was granted REC approval in August 2023 from North West—Greater Manchester West Research Ethics Committee (REC 23/NW/0211). This study was registered on clinicaltrials.gov (NCT06044454). An interim report will be produced for use by the Scottish Government. The results from this study will be presented at artificial intelligence, radiology and respiratory meetings and published in peer-reviewed journals. Trial registration number NCT06044454.

Background/Objectives: The precise staging of non-small cell lung cancer (NSCLC) determines its initial treatment and provides more accurate prognostic information for patients. The aim of this cohort study was to determine pre- and post-operative mediastinal nodal staging agreement and its effect on 2-year survival. Methods: A retrospective multi-centre cohort study was performed, using prospectively collected and pre-defined data from weekly lung cancer multidisciplinary team (MDT) meetings in 11 hospitals. Consecutive patients who underwent surgical resection of NSCLC between 2015 and 2017 were eligible. Pre-operative under-staging was defined as a lower pre-operative than post-operative nodal stage, and pre-operative over-staging as a higher pre-operative than post-operative nodal stage. Disparities between pre-operative nodal staging established at MDT and post-surgical nodal staging were determined and associations with subsequent lung cancer-specific 2-year mortality were identified using univariate and multivariate regression. Results: A total of 973 patients fulfilled the eligibility criteria. Concordant pre- and post-operative nodal staging was observed in 783/973 (80%), 123/973 (13%) were under-staged pre-operatively and 67/973 (7%) were over-staged. In 173 patients with clinical N1 or N2 disease (in whom invasive mediastinal staging was indicated), staging EBUS was performed in 55/173 (32%). In these patients, younger age and use of staging EBUS were independent predictors of concordant pre- and post-operative staging. In all patients, pre-operative under-staging was independently associated with increased lung cancer-specific 2-year mortality. There was no increased mortality associated with pre-operative nodal over-staging. Conclusions: Invasive mediastinal staging with EBUS was independently associated with more accurate pre-operative staging. Pre-operative nodal under-staging was associated with increased lung cancer-specific mortality. Nodal staging accuracy in potentially curable NSCLC is of fundamental importance to ensure patients receive the correct first-line treatment and to improve survival.

While deep learning has advanced the automated diagnosis of pulmonary diseases from chest X-rays, transitioning these models to treatment optimisation is fundamentally hindered by the reliance on biased observational data. In datasets, such as MIMIC, confounding factors create a "Treatment Paradox", where active interventions are statistically correlated with higher mortality simply because they are preferentially assigned to the most severely ill patients. Consequently, standard models learn clinical assignment patterns rather than true physiological efficacy. To address this, we propose a causal synthesis strategy that generates de-confounded, high-dimensional treatment counterfactuals. Guided by our experts' clinical priors, we construct a clinical transition matrix to simulate genuine physiological treatment effects. Using patient white blood cells as measure of severity, we applied a disease counterfactual model to generate the corresponding post-treatment images based on this matrix. Our longitudinal generative architecture uses both pre- and post-treatment chest X-rays to capture disease evolution over time. Furthermore, to resolve spatial misalignments caused by varying patient postures across temporal scans, we introduce an explicit lung mask constraint. This anatomy-aware mechanism confines counterfactual modifications to pulmonary regions, preventing clinically implausible alterations to background anatomy. By decoupling true treatment effects from baseline severity and posture variations, our framework successfully resolves the treatment paradox. Ultimately, this approach generates realistic treatment counterfactuals, providing clinicians with a trustworthy visual tool to evaluate patient-specific outcomes under alternative treatment scenarios and support medical decision-making.