Utilizing machine learning for early screening of thyroid nodules: a dual-center cross-sectional study in China.

Background: Thyroid nodules, increasingly prevalent globally, pose a risk of malignant transformation. Early screening is crucial for management, yet current models focus mainly on ultrasound features. This study explores machine learning for screening using demographic and biochemical indicators. Methods: Analyzing data from 6,102 individuals and 61 variables, we identified 17 key variables to construct models using six machine learning classifiers: Logistic Regression, SVM, Multilayer Perceptron, Random Forest, XGBoost, and LightGBM. Performance was evaluated by accuracy, precision, recall, F1 score, specificity, kappa statistic, and AUC, with internal and external validations assessing generalizability. Shapley values determined feature importance, and Decision Curve Analysis evaluated clinical benefits. Results: Random Forest showed the highest internal validation accuracy (78.3%) and AUC (89.1%). LightGBM demonstrated robust external validation performance. Key factors included age, gender, and urinary iodine levels, with significant clinical benefits at various thresholds. Clinical benefits were observed across various risk thresholds, particularly in ensemble models. Conclusion: Machine learning, particularly ensemble methods, accurately predicts thyroid nodule presence using demographic and biochemical data. This cost-effective strategy offers valuable insights for thyroid health management, aiding in early detection and potentially improving clinical outcomes. These findings enhance our understanding of the key predictors of thyroid nodules and underscore the potential of machine learning in public health applications for early disease screening and prevention.

Reinforcement learning for individualized lung cancer screening schedules: A nested case-control study.

BACKGROUND: The current guidelines for managing screen-detected pulmonary nodules offer rule-based recommendations for immediate diagnostic work-up or follow-up at intervals of 3, 6, or 12 months. Customized visit plans are lacking. PURPOSE: To develop individualized screening schedules using reinforcement learning (RL) and evaluate the effectiveness of RL-based policy models. METHODS: Using a nested case-control design, we retrospectively identified 308 patients with cancer who had positive screening results in at least two screening rounds in the National Lung Screening Trial. We established a control group that included cancer-free patients with nodules, matched (1:1) according to the year of cancer diagnosis. By generating 10,164 sequence decision episodes, we trained RL-based policy models, incorporating nodule diameter alone, combined with nodule appearance (attenuation and margin) and/or patient information (age, sex, smoking status, pack-years, and family history). We calculated rates of misdiagnosis, missed diagnosis, and delayed diagnosis, and compared the performance of RL-based policy models with rule-based follow-up protocols (National Comprehensive Cancer Network guideline; China Guideline for the Screening and Early Detection of Lung Cancer). RESULTS: We identified significant interactions between certain variables (e.g., nodule shape and patient smoking pack-years, beyond those considered in guideline protocols) and the selection of follow-up testing intervals, thereby impacting the quality of the decision sequence. In validation, one RL-based policy model achieved rates of 12.3% for misdiagnosis, 9.7% for missed diagnosis, and 11.7% for delayed diagnosis. Compared with the two rule-based protocols, the three best-performing RL-based policy models consistently demonstrated optimal performance for specific patient subgroups based on disease characteristics (benign or malignant), nodule phenotypes (size, shape, and attenuation), and individual attributes. CONCLUSIONS: This study highlights the potential of using an RL-based approach that is both clinically interpretable and performance-robust to develop personalized lung cancer screening schedules. Our findings present opportunities for enhancing the current cancer screening system.

Acceptability of adding a non-contrast abdominal CT scan to screen for kidney cancer and other abdominal pathology within a community-based CT screening programme for lung cancer: A qualitative study.

OBJECTIVES: The Yorkshire Kidney Screening Trial (YKST) is a feasibility study of adding non-contrast abdominal CT scanning to screen for kidney cancer and other abdominal malignancies to community-based CT screening for lung cancer within the Yorkshire Lung Screening Trial (YLST). This study explored the acceptability of the combined screening approach to participants and healthcare professionals (HCPs) involved in the trial. METHODS: We conducted semi-structured interviews with eight HCPs and 25 participants returning for the second round of scanning within YLST, 20 who had taken up the offer of the additional abdominal CT scan and five who had declined. Transcripts were analysed using thematic analysis, guided by the Theoretical Framework of Acceptability. RESULTS: Overall, combining the offer of a non-contrast abdominal CT scan alongside the low-dose thoracic CT was considered acceptable to participants, including those who had declined the abdominal scan. The offer of the additional scan made sense and fitted well within the process, and participants could see benefits in terms of efficiency, cost and convenience both for themselves as individuals and also more widely for the NHS. Almost all participants made an instant decision at the point of initial invitation based more on trust and emotions than the information provided. Despite this, there was a clear desire for more time to decide whether to accept the scan or not. HCPs also raised concerns about the burden on the study team and wider healthcare system arising from additional workload both within the screening process and downstream following findings on the abdominal CT scan. CONCLUSIONS: Adding a non-contrast abdominal CT scan to community-based CT screening for lung cancer is acceptable to both participants and healthcare professionals. Giving potential participants prior notice and having clear pathways for downstream management of findings will be important if it is to be offered more widely.

Early colorectal cancer screening-no time to lose.

In this editorial, we comment on the article entitled "Stage at diagnosis of colorectal cancer through diagnostic route: Who should be screened?" by Agatsuma et al. Colorectal cancer (CRC) is emerging as an important health issue as its incidence continues to rise globally, adversely affecting the quality of life. Although the public has become more aware of CRC prevention, most patients lack screening awareness. Some poor lifestyle practices can lead to CRC and symptoms can appear in the early stages of CRC. However, due to the lack of awareness of the disease, most of the CRC patients are diagnosed already at an advanced stage and have a poor prognosis.

Improving colorectal cancer screening programs.

In this editorial we comment on the article by Agatsuma et al published in the World Journal of Gastroenterology. They suggest policies for more effective colorectal screening. Screening is the main policy that has led to lower mortality rates in later years among the population that was eligible for screening. Colonoscopy is the gold standard tool for screening and has preventive effects by removing precancerous or early malignant polyps. However, colonoscopy is an invasive process, and fecal tests such as the current hemoglobin immunodetection were developed, followed by endoscopy, as the general tool for population screening, avoiding logistical and economic problems. Even so, participation and adherence rates are low. Different screening options are being developed with the idea that if people could choose between the ones that best suit them, participation in population-based screening programs would increase. Blood tests, such as a recent one that detects cell-free DNA shed by tumors called circulating tumor DNA, showed a similar accuracy rate to stool tests for cancer, but were less sensitive for advanced precancerous lesions. At the time when the crosstalk between the immune system and cancer was being established as a new hallmark of cancer, novel immune system-related biomarkers and information on patients' immune parameters, such as cell counts of different immune populations, were studied for the early detection of colorectal cancer, since they could be effective in asymptomatic people, appearing earlier in the adenoma-carcinoma development compared to the presence of fecal blood. sCD26, for example, detected 80.37% of advanced adenomas. To reach as many eligible people as possible, starting at an earlier age than current programs, the direction could be to apply tests based on blood, urine or salivary fluid to samples taken during routine visits to the primary health system.

A novel approach to cancer screening using the nematode Caenorhabditis elegans-based detection assays.

BACKGROUND: Early diagnosis of cancer is essential for its effective treatment. Currently, established screening tests are cancer-specific and require screening for each type of cancer separately. The primary objective of cancer research is to develop methods that can detect multiple types of tumors from a single body fluid sample. Multicancer early detection tests aim to detect fragments of circulating tumor DNA, cell-free DNA, circulating microRNAs, or proteins released by cancer cells in the patient's body fluids. However, these tests are not suitable for routine cancer prevention due to their high cost. Therefore, in recent years, cancer screening tests have been developed to detect volatile organic compounds in urine using living organisms, such as nematodes, Caenorhabditis elegans. Measuring only 1 mm in length, C. elegans has the potential to offer a new, efficient, cost-effective, quick, and painless method to detect the presence of tumor. PURPOSE: The purpose of this review is to present an overview of the literature on the development and validation of C. elegans-based cancer detection methods. The potential benefits of these assays are significant, as they could become a valuable tool for the early identification and diagnosis of cancer, even though this research is still in its initial stages of development.

[Epidemiological signatures and surveillance bias in cancer]. / Signatures épidémiologiques et biais de surveillance du cancer.

Surveillance bias occurs when variations in cancer incidence are the result of changes in screening or diagnostic practices rather than increases in the true occurrence of cancer. This bias is linked to the issue of overdiagnosis and can be apprehended by looking at epidemiological signatures of cancer. We explain the concept of epidemiological signatures using the examples of melanoma and of lung and prostate cancer. Accounting for surveillance bias is particularly important for assessing the true burden of cancer and for accurately communicating cancer information to the population and decision-makers.

Le biais de surveillance se produit lorsque les variations d'incidence d'un cancer sont le résultat d'un changement dans les pratiques de dépistage ou de diagnostic plutôt que d'une augmentation de la fréquence réelle de ce cancer. Ce biais est lié au concept du surdiagnostic et peut être appréhendé en examinant les signatures épidémiologiques des cancers. Nous expliquons le concept de signature épidémiologique à l'aide des exemples du mélanome et des cancers du poumon et de la prostate. La prise en compte des biais de surveillance est particulièrement importante pour évaluer le fardeau réel du cancer et communiquer avec précision l'information sur le cancer à la population et aux décideurs.

[Colorectal cancer screening program in the canton of Vaud: raising awareness]. / Programme vaudois de dépistage du cancer colorectal : évolution de la sensibilisation.

After five years of deployment, the participation rate in the Vaud colorectal cancer (CRC) screening program remains below projected targets. It was found that the communication tools made available to the population did not provide explicit recommendations regarding how to participate. To this end, Unisanté led a project between 2022 and 2023 to increase awareness and widely disseminate tools specifically designed with the target population. The intention was to provide decision-support tools (I decide to participate) and guidance in the system (in what way) to improve participation by the population targeted by the Vaud CRC screening program. This project incorporated the principles of proportionate universalism, that is to say, adapting screening methods to the specific needs of population sub-groups, such as those in a disadvantaged socio-economic position with low or very low levels of health literacy.

À l'issue de cinq années de déploiement, le taux de participation de la population au programme vaudois de dépistage du cancer colorectal (CCR) s'est révélé en dessous des objectifs souhaités Afin de faciliter une décision de participation, un projet global a été conçu par Unisanté entre 2022 et 2023, dont la finalité était de déployer des actions spécifiques de sensibilisation et de mettre à disposition de la population cible des informations d'une très large accessibilité. L'intention était de disposer d'outils d'aide à la décision (je décide à participer) et d'orientation dans le dispositif (de quelle manière) permettant d'amplifier la participation de la population ciblée par le programme vaudois de dépistage du CCR. Ce projet a permis d'adapter la sensibilisation sur les modalités de dépistage aux populations avec un niveau de littératie en santé faible, voire très faible.

[Colorectal cancer in 45-49-year-olds: systematic or targeted screening?] / Cancer du côlon chez les 45-49 ans : dépistage systématique ou ciblé ?

Principles to guide and inform population-based screening decisions cover a wide range of aspects beyond the screening test. Colorectal cancer (CRC) meets these requirements for individuals at moderate risk aged 50 to 69. In Switzerland, screening using a biennial faecal occult blood test or colonoscopy every 10 years is reimbursed free of deductible in 12 programs covering 15 cantons. This article assesses the appropriateness of systematic screening from age 45 in the Swiss context. Prioritizing measures to raise awareness among healthcare professionals and high-risk subjects rather than lowering the age of eligibility would not only be more sensible but would also benefit to the population over 50 years old.

Les critères pour proposer un dépistage organisé couvrent de nombreuses dimensions, au-delà des caractéristiques du test de dépistage. Le cancer colorectal (CCR) répond à ces exigences pour les personnes à risque modéré de 50 à 69 ans. En Suisse, un dépistage par un test biennal de détection de sang occulte dans les selles ou par coloscopie tous les 10 ans est remboursé hors franchise dans 12 programmes couvrant 15 cantons. Cet article fait le point de la situation concernant l'adéquation d'un dépistage organisé du CCR dès 45 ans dans le contexte suisse. Prioriser des mesures de sensibilisation auprès des professionnel-le-s de santé et des sujets à haut risque de CCR serait non seulement plus judicieux que d'abaisser l'âge d'éligibilité au dépistage organisé mais bénéficierait aussi à la population de plus de 50 ans.

Rapid detection of lung cancer based on serum Raman spectroscopy and a support vector machine: a case-control study.

BACKGROUND: Early screening and detection of lung cancer is essential for the diagnosis and prognosis of the disease. In this paper, we investigated the feasibility of serum Raman spectroscopy for rapid lung cancer screening. METHODS: Raman spectra were collected from 45 patients with lung cancer, 45 with benign lung lesions, and 45 healthy volunteers. And then the support vector machine (SVM) algorithm was applied to build a diagnostic model for lung cancer. Furthermore, 15 independent individuals were sampled for external validation, including 5 lung cancer patients, 5 benign lung lesion patients, and 5 healthy controls. RESULTS: The diagnostic sensitivity, specificity, and accuracy were 91.67%, 92.22%, 90.56% (lung cancer vs. healthy control), 92.22%,95.56%,93.33% (benign lung lesion vs. healthy) and 80.00%, 83.33%, 80.83% (lung cancer vs. benign lung lesion), repectively. In the independent validation cohort, our model showed that all the samples were classified correctly. CONCLUSION: Therefore, this study demonstrates that the serum Raman spectroscopy analysis technique combined with the SVM algorithm has great potential for the noninvasive detection of lung cancer.

Visual Inspection with Acetic Acid Positivity in Screening and Early Detection of Cervical Dysplasia in Africa, 2023: A Meta-Analysis.

Background: Visual Inspection with Acetic acid (VIA) is the best feasible method of screening and early detecting for cervical dysplasia for resource limited settings like Africa. There is no study that can represent Africa on VIA positivity. Therefore, this metaanalysis was planned to verify the best available articles to pool the visual inspection with acetic acid positivity in screening and early detection of cervical dysplasia in Africa. Methods: The Cochrane Library, Web of Science, PubMed, Scopus, free Google database search engines, Google Scholar, and Science Direct databases were used to conduct a true search of this research article. STATA version 14.0 was used to do the metaanalysis. This meta-analysis was registered in PROSPERO database under the identity pf CRD42023392197. Result: This meta-analysis analyzed data from 21,066 women who had VIA examination to estimate the pooled VIA positivity in Africa. The overall pooled effect estimate of VIA positivity in Africa was 11.93 (95%CI: 11.48-12.37). Age <16 year during first intercourse 2.58(95%CI: 1.53-3.62), lifetime sexual partner ≥2 3.92(95%CI: 2.05-5.78) and HIV positivity 2.92(95%CI: 1.72-4.12) were the significant variables which influence VIA positivity. Conclusion: Overall pooled effect estimate of VIA positivity in Africa was high compared to other continents. The main factors that affect VIA positivity are age at first sexual contact being under 16 years old, the number of lifetime sexual partners being at least two, and HIV positivity. Therefore, the WHO's goal of creating Africa free of cervical cancer is still one that requires significant effort.

Prediction-Augmented Shared Decision-Making and Lung Cancer Screening Uptake.

Importance: Addressing poor uptake of low-dose computed tomography lung cancer screening (LCS) is critical, especially for those having the most to gain-high-benefit persons with high lung cancer risk and life expectancy more than 10 years. Objective: To assess the association between LCS uptake and implementing a prediction-augmented shared decision-making (SDM) tool, which enables clinicians to identify persons predicted to be at high benefit and encourage LCS more strongly for these persons. Design, Setting, and Participants: Quality improvement interrupted time series study at 6 Veterans Affairs sites that used a standard set of clinical reminders to prompt primary care clinicians and screening coordinators to engage in SDM for LCS-eligible persons. Participants were persons without a history of LCS who met LCS eligibility criteria at the time (aged 55-80 years, smoked ≥30 pack-years, and current smoking or quit <15 years ago) and were not documented to be an inappropriate candidate for LCS by a clinician during October 2017 through September 2019. Data were analyzed from September to November 2023. Exposure: Decision support tool augmented by a prediction model that helps clinicians personalize SDM for LCS, tailoring the strength of screening encouragement according to predicted benefit. Main outcome and measure: LCS uptake. Results: In a cohort of 9904 individuals, the median (IQR) age was 64 (57-69) years; 9277 (94%) were male, 1537 (16%) were Black, 8159 (82%) were White, 5153 (52%) were predicted to be at intermediate (preference-sensitive) benefit and 4751 (48%) at high benefit, and 1084 (11%) received screening during the study period. Following implementation of the tool, higher rates of LCS uptake were observed overall along with an increase in benefit-based LCS uptake (higher screening uptake among persons anticipated to be at high benefit compared with those at intermediate benefit; primary analysis). Mean (SD) predicted probability of getting screened for a high-benefit person was 24.8% (15.5%) vs 15.8% (11.8%) for a person at intermediate benefit (mean absolute difference 9.0 percentage points; 95% CI, 1.6%-16.5%). Conclusions and Relevance: Implementing a robust approach to personalized LCS, which integrates SDM, and a decision support tool augmented by a prediction model, are associated with improved uptake of LCS and may be particularly important for those most likely to benefit. These findings are timely given the ongoing poor rates of LCS uptake.

Artificial intelligence's contribution to early pulmonary lesion detection in chest X-rays: insights from two retrospective studies on a Czech population.

In recent years healthcare is undergoing significant changes due to technological innovations, with Artificial Intelligence (AI) being a key trend. Particularly in radiodiagnostics, according to studies, AI has the potential to enhance accuracy and efficiency. We focus on AI's role in diagnosing pulmonary lesions, which could indicate lung cancer, based on chest X-rays. Despite lower sensitivity in comparison to other methods like chest CT, due to its routine use, X-rays often provide the first detection of lung lesions. We present our deep learning-based solution aimed at improving lung lesion detection, especially during early-stage of illness. We then share results from our previous studies validating this model in two different clinical settings: a general hospital with low prevalence findings and a specialized oncology center. Based on a quantitative comparison with the conclusions of radiologists of different levels of experience, our model achieves high sensitivity, but lower specificity than comparing radiologists. In the context of clinical requirements and AI-assisted diagnostics, the experience and clinical reasoning of the doctor play a crucial role, therefore we currently lean more towards models with higher sensitivity over specificity. Even unlikely suspicions are presented to the doctor. Based on these results, it can be expected that in the future artificial intelligence will play a key role in the field of radiology as a supporting tool for evaluating specialists. To achieve this, it is necessary to solve not only technical but also medical and regulatory aspects. It is crucial to have access to quality and reliable information not only about the benefits but also about the limitations of machine learning and AI in medicine.

Strategic use of resources to enhance colorectal cancer screening for patients with diabetes (SURE: CRC4D) in federally qualified health centers: a protocol for hybrid type ii effectiveness-implementation trial.

BACKGROUND: Persons with diabetes have 27% elevated risk of developing colorectal cancer (CRC) and are disproportionately from priority health disparities populations. Federally qualified health centers (FQHCs) struggle to implement CRC screening programs for average risk patients. Strategies to effectively prioritize and optimize CRC screening for patients with diabetes in the primary care safety-net are needed. METHODS: Guided by the Exploration, Preparation, Implementation and Sustainment Framework, we conducted a stakeholder-engaged process to identify multi-level change objectives for implementing optimized CRC screening for patients with diabetes in FQHCs. To identify change objectives, an implementation planning group of stakeholders from FQHCs, safety-net screening programs, and policy implementers were assembled and met over a 7-month period. Depth interviews (n = 18-20) with key implementation actors were conducted to identify and refine the materials, methods and strategies needed to support an implementation plan across different FQHC contexts. The planning group endorsed the following multi-component implementation strategies: identifying clinic champions, development/distribution of patient educational materials, developing and implementing quality monitoring systems, and convening clinical meetings. To support clinic champions during the initial implementation phase, two learning collaboratives and bi-weekly virtual facilitation will be provided. In single group, hybrid type 2 effectiveness-implementation trial, we will implement and evaluate these strategies in a in six safety net clinics (n = 30 patients with diabetes per site). The primary clinical outcomes are: (1) clinic-level colonoscopy uptake and (2) overall CRC screening rates for patients with diabetes assessed at baseline and 12-months post-implementation. Implementation outcomes include provider and staff fidelity to the implementation plan, patient acceptability, and feasibility will be assessed at baseline and 12-months post-implementation. DISCUSSION: Study findings are poised to inform development of evidence-based implementation strategies to be tested for scalability and sustainability in a future hybrid 2 effectiveness-implementation clinical trial. The research protocol can be adapted as a model to investigate the development of targeted cancer prevention strategies in additional chronically ill priority populations. TRIAL REGISTRATION: This study was registered in ClinicalTrials.gov (NCT05785780) on March 27, 2023 (last updated October 21, 2023).

Patients poorly recognize lesions of concern that are malignant melanomas: is self-screening the correct advice?

Background: Australia is known for its outdoor culture, with a large percentage of its population engaging in outdoor recreational activities, aquatic, non-aquatic and outdoor occupational activities. However, these outdoor enthusiasts face increased exposure to ultraviolet radiation (UVR), leading to a higher risk of skin cancer, including malignant melanoma (MM). Over the past 40 years, there has been a significant rise in skin cancer rates in Australia, with two out of three Australians expected to develop some form of skin cancer by age 70. Currently, skin cancer examinations are not endorsed in asymptomatic or low-risk individuals in Australia, with only high-risk individuals recommended to undergo regular skin examinations. Notably, the Melanoma Institute Australia suggests that one-half of patients identify MMs themselves, although this claim appears to be based on limited Australian data which may not reflect contemporary practice. Therefore this study sought to determine the percentage of patients who were able to self-identify MMs as lesions of concern when presenting for a skin cancer examination. Methods: Multi-site, cross-sectional study design incorporating a descriptive survey and total body skin cancer screening, including artificial intelligence by a skin cancer doctor. Results: A total of 260 participants with suspect MM lesions were biopsied, with 83 (31.9%) found to be melanomas. Of the true positive MMs only a small percentage of participants (21.7% specificity) correctly had concerns about the suspect lesion being a MM. These MMs were located primarily on the back (44.4%), shoulder (11.1%) and upper leg (11.1%). There was no significant difference in the size between those participants aware of a MM versus those who were not (P = 0.824, 24.6 vs 23.4 mm2). Significantly more males identified lesions of concern that were MMs as compared to females (P = 0.008, 61.1% vs 38.9%, respectively). With regard to true negatives males and females were similar (52.1% vs 47.9%, respectively). With regard to false negatives (n = 65), a greater percentage of males than females did not recognize the MM as a lesion of concern (66.2% vs 33.8%, respectively). Participants were more likely to correctly identify an invasive MM as opposed to an in situ MM (27.3% versus 21.3%). Conclusions: Only a small percentage of participants in this study were able to self-identify either in situ or invasive MM as a lesion of concern with a tendency to identify the more advanced, thicker MMs. Given that MM is associated with a high mortality and cost of treatment, particularly when invasive, the inability of lay persons to identify these cancerous lesions will likely lead to delayed treatment and a possible adverse outcome. We believe the current melanoma screening practices in Australian general practice should be revisited to improve patient outcomes with regard to MM. Additionally, prevention campaigns should include images and primary risk factors for MM.

How COVID-19 Impacted Colonoscopy Utilization and Colorectal Cancer Detection in Hawai'i in 2020.

The Coronavirus Disease of 2019 (COVID-19) pandemic had a profound impact on colorectal cancer (CRC) screening and diagnostic testing. During the initial months of the pandemic, there was a sharp decline in colonoscopies performed as many areas were on lockdown and elective procedures could not be performed. In later months, even when routine procedures started being scheduled again, some patients became fearful of contracting COVID during colonoscopy or lost their health insurance, leading to further delays in CRC diagnosis by colonoscopy. Previous studies have reported the dramatic decrease in colonoscopy rates and CRC detection at various institutions across the country, but no previous study has been performed to determine rates of colorectal screening by colonoscopy in Hawai'i where the demographics of CRC differ. The team investigated the pandemic's impact on colonoscopy services and colorectal neoplasia detection at several large outpatient endoscopy centers in Hawai'i and also classified new CRC cases by patient demographics of age, sex, and ethnicity. There were fewer colonoscopies performed in these endoscopy centers in 2020 than in 2019 and a disproportionate decrease in CRC cases diagnosed. Elderly males as well as Native Hawaiians/Pacific Islanders were most impacted by this decrease in CRC detection. It is possible there will be an increase in later stage presentation of CRC and eventual CRC related mortality among these patients.

ALINA: Another stepping stone toward a future of LDCT lung cancer screening in never-smokers?

The ALINA trial1 demonstrated that 2 years of adjuvant alectinib achieved statistically significantly improved 2-year overall and central nervous system (CNS) disease-free survival over platinum-doublet chemotherapy in resected early-stage (IB ≥ 4 cm to IIIA) ALK+ non-small cell lung cancer (NSCLC). Identifying early-stage ALK+ NSCLC patients (60% were never-smokers in the ALINA trial) may require low-dose computed tomography (LDCT) lung cancer screening in never-smokers.