Introduction Lung cancer screening (LCS) with low-dose CT offers a teachable moment for smoking cessation (SC), but the optimal way to implement SC within LCS is unclear. The Yorkshire Enhanced Stop Smoking (YESS) study assessed the efficacy of a personalised stop-smoking intervention delivered alongside LCS.Methods Opt-out, co-located SC support, comprising nicotine replacement therapy/e-cigarettes/pharmacotherapy and behavioural support, was offered to all individuals who currently smoked attending for LCS. Four weeks later, participants were offered recruitment to a randomised controlled trial of continued standard best practice (SBP) versus a personalised SC support package, including a booklet containing CT images of participants' own heart and lungs, annotated where appropriate to highlight emphysema or coronary artery calcification and scripted communication delivered by a smoking cessation practitioner.Results 1003 people were recruited; 52.5% were allocated to the intervention group. Validated 7-day point prevalent (PP) abstinence rates were 33.6% and 30.0% in the intervention versus SBP groups, respectively (OR 1.17, 95% CI 0.90 to 1.54) at 3 months and 29.2% versus 28.6% (OR 1.03, 95% CI 0.78 to 1.36) at 12 months post-screening. Subgroup analyses indicated a significant increase in 7-day PP abstinence at 3 months with the intervention in women (33.9% intervention, 23.1% SBP, OR 1.70, 95% CI 1.15 to 2.53) but not in men (33.3% intervention, 37.8% SBP, OR 0.82, 95% CI 0.57 to 1.19).Conclusion Around one-third of study participants were abstinent from smoking at 3 months post-screening irrespective of study arm, but adding the personalised intervention did not increase quit rates. Further research is needed exploring possible sex differences in efficacy of personalised SC support. The high overall quit rate reinforces the value of SC support delivered alongside LCS.Trial registration number ISRCRN 63825779 and NCT03750110.

Introduction Integrating smoking cessation supports into lung cancer screening can improve abstinence rates. However, healthcare decision-makers need evidence of cost-effectiveness to understand the cost/benefit of adopting this approach. Methods To evaluate the cost-effectiveness of smoking cessation interventions, and service delivery, we used a cohort-based Markov model, adapted from previous National Institute for Health and Care Excellence (NICE) guidelines on smoking cessation. This uses long-term epidemiological data to capture the prevalence of the smoking-related illnesses, updated through targeted literature searches as required from the core NICE model, with costs extracted from publicly recognised UK sources. Results All smoking cessation interventions appeared cost-effective at a threshold of £20 000 per quality-adjusted life year, compared with no intervention or behavioural support alone. Offering immediate smoking cessation as part of lung cancer screening appointments, compared with usual care (onward referral to stop smoking services), was also estimated to be cost-effective with a net monetary benefit of £2198 per person, and a saving of between £34 and £79 per person in reduced workplace absenteeism among working age attendees. Estimated healthcare cost savings were more than four times greater in the most deprived quintile compared with the least deprived, alongside a fivefold increase in quality adjusted life years accrued. Conclusions Smoking cessation interventions within lung cancer screening are cost-effective and should be integrated, so that treatment is initiated during screening visits. This is likely to reduce overall costs to the health service, and wider integrated care systems, improve quality and length of life, and may lessen health inequalities.

Prioritizing artificial intelligence (AI)-detected imaging findings may reduce the time to diagnosis of lung cancer. This prospective, multicentre, randomized controlled trial tested whether immediate AI prioritization of primary care-requested chest X-rays (CXR) influenced time to computed tomography (CT) and lung cancer diagnosis, the primary outcomes. Secondary outcomes included the number of urgent suspected lung cancer referrals, incidence and stage of lung cancer, times to urgent referral and treatment, concordance between AI and radiology reports, and algorithm accuracy. AI was available in both study arms, with AI prioritization randomized by day. Of 97,731 participant CXRs, 4,405 were excluded due to data compliance issues or failure of randomization, resulting in 93,326 CXRs analyzed (45,987 and 47,339 in the prioritization 'on' or 'off' arms, respectively). A total of 13,347 CTs were identified, with 2,766 performed within 14 days of CXR. Median (interquartile range) times to CT were 53 days (17-145) and 53 days (19-141), with and without AI prioritization, corresponding to a ratio of geometric means of 0.97 (95% confidence interval (CI) = 0.93-1.02; P = 0.31). When restricted to CTs performed within 14 days of CXR, the median time to CT was 8 days (5-11) in both groups. Lung cancer was diagnosed in 558 people (0.6% of CXRs). Median times to diagnosis were 44 days (26-90) and 46 days (24-105) respectively, with a ratio of geometric means of 0.98 (95% CI = 0.83-1.16; P = 0.84). No significant differences were observed in time to lung cancer referral (14 versus 15 days; P = 0.13), time to treatment (76 versus 72.5 days; P = 0.99) or stage at diagnosis (P = 0.34). Discordance between AI and radiology reports occurred in 28,261 CXRs (30.3%) and expert radiology review identified actionable findings in 6,750 cases (23.9%). AI prioritization of CXR requested by UK primary care has no significant impact on the lung cancer pathway. Therefore, CXR AI deployments should not include worklist prioritization in this context. Future research should differentiate between primary pathway changes and the direct impact of AI. ISRCTN registration: 78987039 .

To explore the status of low-dose CT lung cancer screening (LCS) training practices, identify existing gaps, and define key competencies to be included in LCS educational curricula. As part of the European SOLACE project, a structured cross-sectional survey consisting of 11 closed- and open-ended items, developed based on relevant literature, international guidelines, and expert input to assess LCS current practices and training needs, was administered to a panel of European LCS experts. Participants were invited to individual Zoom interviews (May–November 2025). Data were analyzed using descriptive statistics. Twenty-five LCS experts were interviewed from 14 European countries, including 10 radiologists (40

The importance of Explainable Artificial Intelligence (XAI) in medical research has become increasingly evident, especially with regulations such as the EU AI Act mandating its use. XAI techniques such as LIME and SHAP have been primarily used as tools for interpreting machine learning (ML) models used in disease risk prediction, particularly when analysing tabular Electronic Health Record (EHR) data to identify the top k important features. Although these techniques are widely adopted, their evaluation remains limited. This study uses Clinical Practice Research Datalink (CPRD) data to predict lung cancer risk, highlighting the obstacles posed by highly imbalanced datasets when applying these XAI techniques. By analysing training datasets with varying percentage of lung cancer cases, we assess the consistency of explanations generated by LIME and SHAP across different ML models relative to those trained on a balanced dataset. Our findings reveal that as class imbalance increases, the consistency of feature rankings produced by the same model across different training sets decreases. This finding highlights the practical challenges of implementing XAI techniques in healthcare, particularly in handling data imbalance and the careful application of balancing strategies in risk prediction contexts.

BACKGROUND:Low-dose CT (LDCT) lung cancer screening frequently identifies incidental findings (IFs). These have the potential to be beneficial or harmful to the participant and need to be managed effectively. We evaluated whether structured triage of IFs in a real-world screening programme led to meaningful clinical actions or benefit. METHODS:We retrospectively reviewed IFs referred according to the national protocol between January 2023 and May 2025. Outcomes included no further action, investigation, referral, surveillance, and/or treatment. Additional detailed analysis evaluated management and early outcomes of moderate or severe coronary artery calcification (CAC). RESULTS:Of 15,465 LDCT scans, 1,049 IFs in 1,030 participants were referred and reviewed by the service (6.8% of total LDCTs). Thirty-seven percent required no action after review; 23% required a single investigation. 292 (27.8%) led to new diagnoses; 51 participants (4.9%) received medical treatment, and 15 (1.4%) underwent surgery. Sixty-three incidental cancers were detected, of which 63.5% received radical treatment. Common IFs included aortic valve calcification (21.0%), thoracic aortic dilatation (10.0%), and renal abnormalities (9.9%). Among 904 participants with moderate or severe CAC, 220 were not on lipid-lowering therapy at baseline. Of these, only 35% initiated treatment within two years. All-cause mortality in this group was 4.7% at two years, with one-third due to cardiovascular causes. CONCLUSION:Structured triage enables consistent, proportionate IF management. Most IFs required no ongoing follow-up, while a minority led to diagnosis and intervention. CAC was common and undertreated, highlighting a modifiable competing risk that should be integrated into lung cancer screening pathways.

OBJECTIVE:Invitations to participate in screening programmes are predominantly distributed through traditional paper-based methods. More tailored approaches - incorporating both socioeconomic status- (SES) and sex-specific preferences - may improve programme uptake. This study aims to optimize the recruitment strategy for high-risk individuals in lung cancer screening: the 4-IN-THE-LUNG-RUN trial. METHODS:A total of 336,860 Dutch individuals, aged 60-79 years, were randomised to receive one of three recruitment methods: (1) standard paper, (2) standard online, or (3) tailored online, and invited to participate if they considered themselves eligible. Additionally, there was the option to self-enrol (online). Inclusion criteria for participation were: 1) People who currently smoke or have quit smoking within the past 10 years with ≥ 35 pack-years or 2) a PLCOm2012NoRace risk ≥ 2.60%. RESULTS:Out of 35,755 respondents (10.6%), 15,840 individuals (44.3%) were eligible to participate. While the absolute number of eligibles was highest in the paper-based group (N = 5079), exceeding the online groups by 13.1% and 17.0%, the proportion of eligible was significantly lower (37.8%) compared with both online groups (ONLINE: N = 4412, 45.0%; TAILORED: N = 4214, 45.0%; p < 0.001). Overall, a significantly larger proportion of individuals from the low SES group (40.0%) were eligibles relative to the middle (26.5%) and high (33.5%) SES (p < 0.001). The proportion of low SES eligibles was significantly higher in the paper-based group (42.8%) compared to both online groups (ONLINE: 37.0% and TAILORED: 38.6%; p < 0.001). Self-registered eligibles had a similar low SES participant proportion (42.6%) as the paper-based group. Gender distributions were comparable across recruitment methods (p = 0.137). CONCLUSION:Online recruitment strategies may effectively recruit high-risk individuals for low-dose CT screening, including older elderly and those from lower SES, and may be associated with lower resource requirements compared with paper-based approaches. Nevertheless, retaining a paper-based option is essential to ensure inclusive and equitable access to lung cancer screening.

The 5th edition of the European Code Against Cancer (ECAC5) recommends sustainable, organised screening programmes for: (a) colorectal cancer using biennial quantitative faecal immunochemical test (FIT) for individuals aged 50–74 years. As an alternative strategy, once‐only endoscopy may be considered within the same age range; (b) breast cancer using biennial digital mammography for women aged 50–69 years. Implementing this strategy for women aged 45–49 years and 70–74 years can be considered. Other screening strategies or additional examinations could be considered for women with high mammographic density; (c) cervical cancer using human papillomavirus (HPV) screening at intervals no shorter than 5 years for women aged 30–65 years. It is recommended to adapt policies according to vaccination status and screening history; and (d) lung cancer using annual low‐dose computed tomography (LDCT) for individuals considered to be at increased risk of lung cancer based on age, history of smoking or validated risk models, with biennial screening as an alternative. Screening should incorporate smoking cessation interventions.

Lung cancer screening with low-dose computed tomography has been proven to reduce lung-cancer-specific and all-cause mortality. The UK launched the NHS England Targeted Lung Health Check Programme in 2019, which has now become the national Lung Cancer Screening Programme, with full coverage expected by 2030. Here we present the progress and outcomes of the program. People aged 55-74 were offered low-dose computed tomography of the thorax if they had ever smoked and if risk thresholds, as determined by multivariable models, were met. Delivery of the program is through regionally federated clinical infrastructure and leadership, with national strategic, clinical and economic frameworks. The program has invited over two million people, with 7,193 lung cancers diagnosed-63.1% at tumor, node, metastasis stage 1 and 12.6% stage 2-to March 2025. This has increased the early-stage proportion of lung cancer in England over 5 years, particularly in socioeconomically deprived regions. The NHS England Programme exemplifies how large-scale implementation can be achieved at speed through centralized protocols and effective project management. The program has demonstrated feasibility and scalability in reaching high-risk and underserved populations, but needs to further address inequalities in participation. These findings support adoption of lung cancer screening across the UK and globally, and offer practical tools for international adaptation.

BACKGROUND:Stage III-N2 non-small cell lung cancer (NSCLC) accounts for ∼ 6% of NSCLC cases in the UK. Despite decades of research, no clear survival advantage has been demonstrated between surgical and non-surgical treatment strategies in cases considered resectable. The impact of these regimens on health-related quality of life (HRQoL) remains poorly understood. The PIONEER trial aimed to assess the feasibility of a future phase III randomised controlled trial (RCT) comparing surgical versus non-surgical multimodality treatment with HRQoL as a potential primary outcome. METHODS:PIONEER was a UK-based, 8-centre feasibility RCT recruiting patients with resectable stage III-N2 NSCLC. Patients were randomised 1:1 to surgical multimodality treatment or non-surgical treatment. Feasibility outcomes included recruitment rate, treatment adherence, and completion of HRQoL questionnaires (EORTC QLQ-C30). RESULTS:Of 276 screened patients, 52 (19%) were eligible, and 28 (54%) of these consented and were randomised. Uptake of randomised treatment was high (93%), but only 50% and 57% completed HRQoL questionnaires at 3 and 6 months, respectively. Completion of planned multimodality treatment occurred in 50% (surgery arm) and 65% (non-surgical arm). Central review showed 12% of "unresectable" patients were potentially eligible and highlighted variability between multi-disciplinary teams. CONCLUSIONS:A future phase III trial is unlikely to be feasible. We suggest future work in this area considers leveraging high-quality, real-world data to offer valuable insights into treatment patterns and outcomes in unselected populations.

The 3rd Annual Lung Cancer Symposium (Oslo Cancer Cluster, 25 September 2025) gathered experts from all the Nordic countries, Norway, Finland, Iceland, Denmark, Sweden, as well as Germany, the UK and the USA to present new evidence and implementation experiences in low-dose chest tomography lung cancer screening, with cross-cutting attention to risk stratification, health economics, AI-enabled workflows, and equity. The symposium was organized by Oslo Cancer Cluster, Levanger Hospital and the Norwegian University of Science and Technology, as a continuation of previous years´ annual efforts to gather and showcase the experiences and the progress of the Nordic countries with lung cancer screening. Across settings, LDCT screening is associated with stage shift and potential mortality reduction, consistent with large trials (NLST, NELSON) and maturing real-world experience (HANSE pilot study, programs in Croatia, Taiwan, the UK, and the US). Emerging Nordic pilots demonstrate feasibility, early-stage detection, and high adherence, while European coordination (SOLACE) is accelerating guideline harmonization and implementation pilots. Key themes included: (1) superiority of multivariable risk models over categorical criteria; (2) the necessity of integrating smoking cessation; (3) program economics that are likely acceptable under Nordic decision thresholds; (4) capacity and downstream pathway planning; and (5) equity-by-design to avoid widening disparities. This report synthesizes country updates and implications for Nordic and European scale-up.

Randomised controlled trials have shown that early detection of lung cancer by low-dose computed tomography (LDCT) reduces lung cancer and all-cause mortality. This, and a detailed health economics evaluation, led to a recommendation in September 2022 by the UK National Screening Committee (UKNSC) that all four UK nations move towards implementation of a targeted lung cancer screening programme. The National Health Service England (NHSE) Targeted Lung Health Check (TLHC) programme launched in 2019 and has been adopted as the national screening programme in England with national rollout expected to be complete in 2030. Given the complexities of lung cancer screening, a comprehensive protocol and linked quality assurance standard were developed to provide a mechanism to ensure uniform and regulated implementation of a high-quality programme. This review will describe the importance of quality assurance and show how this works in a national programme.

PURPOSE:Lung cancer is the leading global cause of cancer mortality with substantial evidence of inequity, disparity in process and outcomes, and unwarranted clinical variation. Over the last decades, there has been major evolution and discovery in best evidence-based practice (EBP), enhancing diagnostics, management, and the delivery of precision medicine. However, questions remain about the completeness of translation of best EBP into delivered care. DESIGN:Learning health systems (LHSs) have been defined as improvement environments where knowledge generation processes are embedded into daily clinical practice to continually improve the quality, safety, and outcomes of health care delivery. Lung cancer clinical quality registries (CQRs) provide a rigorous infrastructure supporting LHS function through the collection, analysis, and reporting of care process and outcome information delivered by health service organizations. CQRs measure the appropriateness and effectiveness of delivered care and report on the degree of best EBP delivery by stakeholder providers. The provision of risk-adjusted, benchmark reporting to stakeholders describes equity, disparity, and unwarranted clinical variation and is a fundamental driver of improvement in the safety and quality of care provided to consumers. RESULTS:There is mounting international evidence of the positive impacts of CQR reporting on management processes, health care infrastructure, survival, quality improvement, and education within lung cancer communities. The use of implementation science approaches including the Knowledge to Action framework targets bridging the gaps between evidence-based knowledge and practice. CONCLUSION:Registry evolution is exampled by the Danish Lung Cancer Registry, National Lung Cancer Audit (United Kingdom), Dutch Lung Cancer Audit, and Victorian Lung Cancer Registry (Australia), which identify innovation opportunities to close the evidence-practice gap, overcome service deficits, and lead to better decision making for health care improvement.