Screening Tool For Lung Cancer Research Articles

Which is a real valuable screening tool for lung cancer and measure thoracic diseases, chest radiography or low-dose computed tomography?: A review on the current status of Japan and other countries.

Chest radiography (CR) has been used as a screening tool for lung cancer and the use of low-dose computed tomography (LDCT) is not recommended in Japan. We need to reconsider whether CR really contributes to the early detection of lung cancer. In addition, we have not well discussed about other major thoracic disease detection by CR and LDCT compared with lung cancer despite of its high frequency. We review the usefulness of CR and LDCT as veridical screening tools for lung cancer and other thoracic diseases. In the case of lung cancer, many studies showed that LDCT has capability of early detection and improving outcomes compared with CR. Recent large randomized trial also supports former results. In the case of chronic obstructive pulmonary disease (COPD), LDCT contributes to early detection and leads to the implementation of smoking cessation treatments. In the case of pulmonary infections, LDCT can reveal tiny inflammatory changes that are not observed on CR, though many of these cases improve spontaneously. Therefore, LDCT screening for pulmonary infections may be less useful. CR screening is more suitable for the detection of pulmonary infections. In the case of cardiovascular disease (CVD), CR may be a better screening tool for detecting cardiomegaly, whereas LDCT may be a more useful tool for detecting vascular changes. Therefore, the current status of thoracic disease screening is that LDCT may be a better screening tool for detecting lung cancer, COPD, and vascular changes. CR may be a suitable screening tool for pulmonary infections and cardiomegaly.

175 Community lung health check as a screening tool for lung cancer: Outcomes after completing 24 months of nodule surveillance

175 Community lung health check as a screening tool for lung cancer: Outcomes after completing 24 months of nodule surveillance

Adaptation of a Tailored Lung Cancer Screening Decision Aid for People With HIV

BackgroundPeople with HIV (PWH) are both at elevated risk of lung cancer and high risk of multimorbidity, which makes shared decision-making (SDM) for lung cancer screening (LCS) in PWH complex. There are currently no tools adapted for SDM in PWH. Research QuestionCan a SDM decision aid be adapted to include HIV-specific measures with input from both PWH and their providers? Study Design and MethodsThis study utilized qualitative methods including focus groups with PWH and interviews with HIV-care providers to adapt and iterate an SDM tool for PWH. Eligible participants were PWH enrolled in an HIV primary care clinic who met age and smoking eligibility criteria for LCS and HIV care providers at the clinic. Both the focus groups and interviews included semi-structured discussions of SDM and decision aid elements for PWH. We used a framework-guided thematic analysis, mapping themes onto the Health Equity Implementation framework. ResultsForty-three PWH participated in 8 focus groups; 10 providers were interviewed. Key themes from patients included broad interest in adapting LCS SDM specifically for PWH, a preference for clear LCS recommendations, and the need for positive framing emphasizing survival. Providers were enthusiastic about personalized LCS risk assessments and point-of-care tools. Both patients and providers had mixed views on the utility of HIV-specific risk measures in patient-facing tools. Themes were utilized to adapt a personalized and flexible SDM tool for LCS in PWH. InterpretationPWH and providers were enthusiastic about specific tools for SDM which are personalized and tailored for PWH, make recommendations, and that inform LCS decision-making. Divergent views on presenting patient-facing quantitative risk assessments suggests these elements could be optional but available for review. This tool may have utility in complex decision-making for LCS in this population and is currently being evaluated in a pilot prospective trial.

How well does your e-nose detect cancer? Application of artificial breath analysis for performance assessment

Comparing electronic nose (e-nose) performance is a challenging task because of a lack of standardised method. This paper proposes a method for defining and quantifying an indicator of the effectiveness of multi-sensor systems in detecting cancers by artificial breath analysis. To build this method, an evaluation of the performances of an array of metal oxide sensors built for use as a lung cancer screening tool was conducted. Breath from 20 healthy volunteers has been sampled in fluorinated ethylene propylene sampling bags. These healthy samples were analysed with and without the addition of nine volatile organic compound (VOC) cancer biomarkers, chosen from literature. The concentration of the VOC added was done in increasing amounts. The more VOC were added, the better the discrimination between ‘healthy’ samples (breath without additives) and ‘cancer’ samples (breath with additives) was. By determining at which level of concentration the e-nose fails to reliably discriminate between the two groups, we estimate its ability to well predict the presence of the disease or not in a realistic situation. In this work, a home-made e-nose is put to the test. The results underline that the biomarkers need to be about 5.3 times higher in concentration than in real breath for the home-made nose to tell the difference between groups with a sufficient confidence.

Cost effective quality improvement initiative in lung cancer screening: A single institutional pilot program.

458 Background: US Preventive Services Task Force (USPSTF) recommends lung cancer screening (LCS) with annual low-dose computed tomography (LDCT) screening for individuals aged 50-80 years with ≥20 pack-year smoking history. Nevertheless, only 4%-13% of eligible individuals are screened nationally. Lung cancer mortality is higher in the South where low socioeconomic status and racial minorities predominate and the screening rate in Alabama is between 4.7% - 7.7%. Thomas Hospital belongs to this catchment area and the goal of our study was to improve LCS with LDCT by embarking on a quality improvement initiative which was commenced as a pilot program for a larger healthcare system (>5 large outpatient clinics with over 12,000 visits/month). Methods: Data were obtained retrospectively by reviewing the electronic medical records of eligible patients for LCS from 01/22 to 01/23 who visited the Thomas Hospital Internal Medicine Residency Clinic (pilot study site). A multidisciplinary team was created involving Thoracic oncologists, radiologists, Thoracic surgeons, resident physicians, and PCPs to identify barriers to LCS and discuss methods on how to improve LCS. We identified areas to be improved on and utilized performance improvement tools such as a Pareto chart and a PICK chart. Data was then collected prospectively. Results: In the initial 12-month period, only 6.95% (total n=185) of patients who qualified for LCS had LDCT done for LCS. The major barriers to screening were poor smoking history documentation, lack of proper identification of screening candidates, lack of awareness of screening guidelines, infrequent follow-up, discrepancies in smoking history within the EMR, and lack of a consistent system for LDCT referral. We identified 4 main initiatives which were introduced monthly, one at a time. The interventions include Educational services/Awareness campaigns on LCS, Distribution of current LCS guidelines in the clinic rooms/offices, Patient self-reported questionnaire on smoking history, and Implementation of an EPIC flag tool for LCS. We reviewed our performance after the interventions and the total LCS after 4 interventions included 48 (47%) patients compared to 102 patients who fit the screening criteria. 5 patients had LDCT ordered but yet to be completed and 6 patients had findings that needed immediate evaluation and received appropriate referrals. Conclusions: Lung cancer screening remains suboptimal in the United States, especially in the southern region. With our approach, the screening rates have increased exponentially only within a few months compared to the previous year and this model is to be adopted by other clinics affiliated with the umbrella health system. LDCT does carry certain risks including false positive results and unnecessary biopsies; hence shared decision-making is needed before ordering the test.

B-360 Usefulness of the Ratios of CYFRA21-1 and p53 Autoantibody Immune Complexes to Their Free Antigens in Lung Cancer

Abstract Background Autoantibodies against specific cancer-associated antigens are produced in the early stages of tumorigenesis. In lung cancer, the possibility of autoantibodies as diagnostic biomarkers has been proposed. This study was to evaluate the usefulness of novel DNA-guided sandwich immunoassay detecting CYFRA21-1 and p53 autoantibody immune complexes and their free antigens in diagnosis of lung cancer. Methods In total, 100 patients with lung cancer and 119 healthy controls were analyzed with 9G testTM Lung/Cancer (Biometrix Technology, South Korea) measuring plasma autoantibody immune complexes (CYFRA21-1 with anti-CYFRA21-1 autoantibody immune complex (CIC), p53 with anti-p53 autoantibody immune complex (PIC)) and their free antigens (CYFRA 21-1 and p53). The ratios of CIC to CYFRA21-1 (CIC/CYFRA21-1) and PIC to p53 (PIC/p53), and the multiplication of the two ratios, named as LC index were calculated. Results The levels of CIC and PIC were significantly increased in lung cancer compared with those in healthy control (P = 0.0062 and P = 0.0026, respectively), while free antigens didn’t distinguish between lung cancer and healthy control. The ratios CIC/CYFRA21-1 and PIC/p53 were significantly higher in lung cancer than those in healthy control (all, P < 0.0001). Diagnostic performances expressed as area under the curve (AUC) were higher in the ratios of autoantibody immune complexes to each free antigen (PIC/p53 and CIC/CYFRA21-1) than autoantibody immune complexes (PIC and CIC) (AUC; 0.887, 0.847 vs 0.618, 0.608, respectively). The most excellent diagnostic performance was proven with LC index at diagnostic cut-off 3.60, which showed 81% sensitivity and 95% specificity with 0.945 AUC (P < 0.001). It was more sensitive to early lung cancer than to advanced lung cancer (sensitivity 87.5% vs 72.7%). Conclusion The ratios of CIC to CYFRA21-1 and PIC to p53 are useful biomarkers in lung cancer diagnosis and the combination of the ratios, LC index could be complementary tool for lung cancer screening with radiological tests.

Development of an Electronic Health Record Self-Referral Tool for Lung Cancer Screening: A Pilot Study (Preprint)

Development of an Electronic Health Record Self-Referral Tool for Lung Cancer Screening: A Pilot Study (Preprint)

R.E.A.C.T-Rapid Electro-Analytical graphitic Carbon nitride-based screening Tool for lung cancer – Case study using heptane

Early disease detection and diagnosis through breath-based chemical assessment is broadly studied as a non-invasive tool and used as a cutting-edge opportunity in health care. Breath analytics or Breathomics is based on the recognition of levels of metabolites such as Volatile Organic Compounds (VOCs) and inorganic gases in an exhaled human breath. Lung cancer, one such disease state, alters the concentrations of hydrocarbons released in breath due to oxidative stress and lipid pre-oxidation. Heptane can be utilized as a VOC biomarker for the non-invasive diagnosis of lung cancer. This work outlines the fabrication of a graphitic carbon nitride-based electrochemical sensor platform that possesses increased catalytic activity and can be used for the screening of heptane vapors in the range of 0.45–5 ppm limit of detection of 0.45 ppm with 95% confidence interval. The synthesized material is characterized and validated using various standard analytical methods. Chronoamperometry is employed as an electrochemical technique to examine the diffusion dynamics of the target analyte. We demonstrated the specific sensing responses of the system in the presence of interferants by executing a cross-reactivity study with respect to other commonly found interferants in breath. We effectively established the use of a graphitic carbon nitride-based electrochemical sensor for point-of-care screening (qualitative analysis with p < 0.05) of heptane levels by the development of a prototype device utilizing a commercial microelectronic board. We envision that the in-house fabricated modified electrode platform can aid in early screening for lung cancer, thus leading to a reduction in the mortality rate.

Biomarkers in Lung Cancer Screening: a Narrative Review.

Although when used as a lung cancer screening tool low-dose computed tomography (LDCT) has demonstrated a significant reduction in lung cancer related mortality, it is not without pitfalls. The associated high false positive rate, inability to distinguish between benign and malignant nodules, cumulative radiation exposure, and resulting patient anxiety have all demonstrated the need for adjunctive testing in lung cancer screening. Current research focuses on developing liquid biomarkers to complement imaging as non-invasive lung cancer diagnostics. Biomarkers can be useful for both the early detection and diagnosis of disease, thereby decreasing the number of unnecessary radiologic tests performed. Biomarkers can stratify cancer risk to further enrich the screening population and augment existing risk prediction. Finally, biomarkers can be used to distinguish benign from malignant nodules in lung cancer screening. While many biomarkers require further validation studies, several, including autoantibodies and blood protein profiling, are available for clinical use. This paper describes the need for biomarkers as a lung cancer screening tool, both in terms of diagnosis and risk assessment. Additionally, this paper will discuss the goals of biomarker use, describe properties of a good biomarker, and review several of the most promising biomarkers currently being studied including autoantibodies, complement fragments, microRNA, blood proteins, circulating tumor DNA, and DNA methylation. Finally, we will describe future directions in the field of biomarker development.

Implementation of a Web-Based Tool for Shared Decision-making in Lung Cancer Screening: Mixed Methods Quality Improvement Evaluation.

BackgroundLung cancer risk and life expectancy vary substantially across patients eligible for low-dose computed tomography lung cancer screening (LCS), which has important consequences for optimizing LCS decisions for different patients. To account for this heterogeneity during decision-making, web-based decision support tools are needed to enable quick calculations and streamline the process of obtaining individualized information that more accurately informs patient-clinician LCS discussions. We created DecisionPrecision, a clinician-facing web-based decision support tool, to help tailor the LCS discussion to a patient’s individualized lung cancer risk and estimated net benefit.ObjectiveThe objective of our study is to test two strategies for implementing DecisionPrecision in primary care at eight Veterans Affairs medical centers: a quality improvement (QI) training approach and academic detailing (AD).MethodsPhase 1 comprised a multisite, cluster randomized trial comparing the effectiveness of standard implementation (adding a link to DecisionPrecision in the electronic health record vs standard implementation plus the Learn, Engage, Act, and Process [LEAP] QI training program). The primary outcome measure was the use of DecisionPrecision at each site before versus after LEAP QI training. The second phase of the study examined the potential effectiveness of AD as an implementation strategy for DecisionPrecision at all 8 medical centers. Outcomes were assessed by comparing absolute tool use before and after AD visits and conducting semistructured interviews with a subset of primary care physicians (PCPs) following the AD visits.ResultsPhase 1 findings showed that sites that participated in the LEAP QI training program used DecisionPrecision significantly more often than the standard implementation sites (tool used 190.3, SD 174.8 times on average over 6 months at LEAP sites vs 3.5 SD 3.7 at standard sites; P<.001). However, this finding was confounded by the lack of screening coordinators at standard implementation sites. In phase 2, there was no difference in the 6-month tool use between before and after AD (95% CI −5.06 to 6.40; P=.82). Follow-up interviews with PCPs indicated that the AD strategy increased provider awareness and appreciation for the benefits of the tool. However, other priorities and limited time prevented PCPs from using them during routine clinical visits.ConclusionsThe phase 1 findings did not provide conclusive evidence of the benefit of a QI training approach for implementing a decision support tool for LCS among PCPs. In addition, phase 2 findings showed that our light-touch, single-visit AD strategy did not increase tool use. To enable tool use by PCPs, prediction-based tools must be fully automated and integrated into electronic health records, thereby helping providers personalize LCS discussions among their many competing demands. PCPs also need more time to engage in shared decision-making discussions with their patients.Trial RegistrationClinicalTrials.gov NCT02765412; https://clinicaltrials.gov/ct2/show/NCT02765412

43 - Community lung health check as a screening tool for lung cancer: the prevalence and impact of significant other findings

43 - Community lung health check as a screening tool for lung cancer: the prevalence and impact of significant other findings

Detection of antibodies against benzo[a]pyrene in blood sera of lung cancer patients by ELISA using human recombinant idiotypic and anti-idiotypic antibodies.

ELISA was developed and applied for the detection of endogenous idiotypic and anti-idiotypic antibodies against Bp in human blood sera using recombinant human idiotypic and anti-idiotypic antibodies against Bp. Serum samples of LC patients (n = 22) and healthy donors (n = 24) were analyzed by the new method. Statistical analysis showed that in sera of LC patients the levels of endogenous idiotypic and anti-idiotypic antibodies against Bp were significantly higher than in healthy donors. A logistic regression model for the LC detection utilizing such predictors as the serum levels of idiotypic and anti-idiotypic antibodies against Bp, smoking status, and age, identified LC patients with 83% specificity and 82% sensitivity. The proposed method could be further developed as additional lung cancer screening tool.

Efficacy of Low Dose Computed Tomography Using Adaptive Statistical Iterative Reconstruction in Lung Cancer Screening

Abstract Background: Lung cancer is the most common malignant tumor and the leading cause of cancer-related deaths all over the world. Early detection and treatment are important to increase survival rate. Therefore, screening of lung cancer should target those individuals at high risk. Aim of Study: To detect the efficacy of low dose computed tomography (LDCT) of the chest with adaptive statistical iterative reconstruction (ASIR) algorithmas a screening method in diagnosing early stages of lung cancer and thus decrease the disease related morbidity and mortality as itminimizes exposure to ionizing radiation while maintaining sufficient image quality. Material and Methods: Ninety-six high risk cases (current smokers or ex-smokers), 94 males and 2 females, withage range from 50-78 yearswere included in this study. All cases underwent CT of the chest using low dose protocol with-ASIR algorithm with different blending levels of reconstruction (40%, 60%) for lung cancer screening. All images were interpreted using the International Early Lung Cancer Action Program (I-ELCAP) diagnostic protocol for lung nodule diagnosis and management. Results: From 96 cases included in the study, 82 cases had normal chest CT and 14 cases showed abnormal findings in chest CT (4 of them showed nodular lung lesions and the other 10 cases showed other findings related to smoking as bullae, bronchial wall thickening, emphysema, honey combing and bronchiectasis). Among the 6 nodules detected in the 4 cases, one nodule was >!15mm, and 5 nodules were <15mm. According to I-ELCAP diagnostic protocol, one nodule was considered positive and 5 nodules were considered semi-positive. LDCT chest using ASIR algorithm for lung cancer screening revealed high sensitivity and specificity for detecting lesions at cut off point size 6 mm (84.9% and 100% respec-tively). The area under receiver operating characteristic (ROC) curve for prediction of nodule with cutoff point size 6mm was 0.938 with 95% confidence interval (0.887-0.990). Conclusion: LDCT of the chest using ASIR algorithm is a promising and efficient tool for lung cancer screening with significant minimization of ionizing radiation exposure as well as preserved optimum image quality.

64 - Community lung health check as a screening tool for lung cancer: initial results from a Bradford pilot

64 - Community lung health check as a screening tool for lung cancer: initial results from a Bradford pilot

Primary care and pulmonary physicians' knowledge and practice concerning screening for lung cancer in Lebanon, a middle-income country.

ABSTRACTBackgroundScreening for lung cancer with low‐dose computed tomography (LDCT) was shown to reduce lung cancer incidence and overall mortality, and it has been recently included in international guidelines. Despite the rising burden of lung cancer in low and middle‐income countries (LMICs) such as Lebanon, little is known about what primary care physicians or pulmonologists know and think about LDCT as a screening procedure for lung cancer, and if they recommend it.ObjectivesEvaluate the knowledge about LDCT and implementation of international guidelines for lung cancer screening among Lebanese primary care physicians (PCPs) and pulmonary specialists.MethodologyPCPs and PUs based in Lebanon were surveyed concerning knowledge and practices related to lung cancer screening by self‐administered paper questionnaires.Results73.8% of PCPs and 60.7% of pulmonary specialists recognized LDCT as an effective tool for lung cancer screening, with 63.6% of PCPs and 71% of pulmonary specialists having used it for screening. However, only 23.4% of PCPs and 14.5% of pulmonary specialists recognized the eligibility criteria for screening. Chest X‐ray was recognized as ineffective by only 55.8% of PCPs and 40.7% of pulmonary specialists; indeed, 30.2% of PCPs and 46% of pulmonary specialists continue using it for screening. The majority have initiated a discussion about the risks and benefits of lung cancer screening.ConclusionPCPs and pulmonary specialists are initiating discussions and ordering LDCT for lung cancer screening. However, a significant proportion of both specialties are still using a non‐recommended screening tool (chest x‐ray); only few PCPs and pulmonary specialists recognized the population at risk for which screening is recommended. Targeted provider education is needed to close the knowledge gap and promote proper implementation of guidelines for lung cancer screening.

Patient Perspectives on the Risk-Based NLST Outcomes Tool for Lung Cancer Screening.

Researchers at the NCI have developed the Risk-Based NLST Outcomes Tool (RNOT), an online tool that calculates risk of lung cancer diagnosis and death with and without lung cancer screening, and false-positive risk estimates. This tool has the potential to facilitate shared decision making for screening. The objective of this study was to examine how current heavy and former smokers understand and respond to personalized risk estimates from the RNOT. Individuals who were eligible for lung cancer screening and were visiting Walter Reed National Military Medical Center were invited to participate in a semi-structured interview to assess their experiences with and perceptions of the RNOT. Results were analyzed using template analysis. Participants found their risk of lung cancer death to be lower than anticipated and were confused by changes in risk for lung cancer diagnosis with and without screening. Most participants indicated that the RNOT would be helpful in making screening decisions, despite reporting that there was no maximum risk for a false positive that would lead them to forgo lung cancer screening. Participants provided actionable needs and recommendations to optimize this tool. Risk-based screening tools may enhance shared decision making. The RNOT is being updated to incorporate these findings.

Biomarkers in lung cancer screening: a narrative review

: Although when used as a lung cancer screening tool low-dose computed tomography (LDCT) has demonstrated a significant reduction in lung cancer related mortality, it is not without pitfalls. The associated high false positive rate, inability to distinguish between benign and malignant nodules, cumulative radiation exposure, and resulting patient anxiety have all demonstrated the need for adjunctive testing in lung cancer screening. Current research focuses on developing liquid biomarkers to complement imaging as non-invasive lung cancer diagnostics. Biomarkers can be useful for both the early detection and diagnosis of disease, thereby decreasing the number of unnecessary radiologic tests performed. Biomarkers can stratify cancer risk to further enrich the screening population and augment existing risk prediction. Finally, biomarkers can be used to distinguish benign from malignant nodules in lung cancer screening. While many biomarkers require further validation studies, several, including autoantibodies and blood protein profiling, are available for clinical use. This paper describes the need for biomarkers as a lung cancer screening tool, both in terms of diagnosis and risk assessment. Additionally, this paper will discuss the goals of biomarker use, describe properties of a good biomarker, and review several of the most promising biomarkers currently being studied including autoantibodies, complement fragments, microRNA, blood proteins, circulating tumor DNA (ctDNA), and DNA methylation. Finally, we will describe future directions in the field of biomarker development.

Computer-Tailored Decision Support Tool for Lung Cancer Screening: Community-Based Pilot Randomized Controlled Trial

BackgroundLung cancer screening is a US Preventive Services Task Force Grade B recommendation that has been shown to decrease lung cancer-related mortality by approximately 20%. However, making the decision to screen, or not, for lung cancer is a complex decision because there are potential risks (eg, false positive results, overdiagnosis). Shared decision making was incorporated into the lung cancer screening guideline and, for the first time, is a requirement for reimbursement of a cancer screening test from Medicare. Awareness of lung cancer screening remains low in both the general and screening-eligible populations. When a screening-eligible person visits their clinician never having heard about lung cancer screening, engaging in shared decision making to arrive at an informed decision can be a challenge. Methods to effectively prepare patients for these clinical encounters and support both patients and clinicians to engage in these important discussions are needed.ObjectiveThe aim of the study was to estimate the effects of a computer-tailored decision support tool that meets the certification criteria of the International Patient Decision Aid Standards that will prepare individuals and support shared decision making in lung cancer screening decisions.MethodsA pilot randomized controlled trial with a community-based sample of 60 screening-eligible participants who have never been screened for lung cancer was conducted. Approximately half of the participants (n=31) were randomized to view LungTalk—a web-based tailored computer program—while the other half (n=29) viewed generic information about lung cancer screening from the American Cancer Society. The outcomes that were compared included lung cancer and screening knowledge, lung cancer screening health beliefs (perceived risk, perceived benefits, perceived barriers, and self-efficacy), and perception of being prepared to engage in a discussion about lung cancer screening with their clinician.ResultsKnowledge scores increased significantly for both groups with greater improvement noted in the group receiving LungTalk (2.33 vs 1.14 mean change). Perceived self-efficacy and perceived benefits improved in the theoretically expected directions.ConclusionsLungTalk goes beyond other decision tools by addressing lung health broadly, in the context of performing a low-dose computed tomography of the chest that has the potential to uncover other conditions of concern beyond lung cancer, to more comprehensively educate the individual, and extends the work of nontailored decision aids in the field by introducing tailoring algorithms and message framing based upon smoking status in order to determine what components of the intervention drive behavior change when an individual is informed and makes the decision whether to be screened or not to be screened for lung cancer.International Registered Report Identifier (IRRID)RR2-10.2196/resprot.8694

Abstract 2121: Genetic correlation between lung cancer and environmental exposures

Abstract Introduction: Lung cancer is the leading cause of cancer-related deaths. 10% of never-smokers develop lung cancer. Currently, no genetic-based lung cancer screening tool exists. As a substitute, phenotypic traits can serve as surrogate markers for lung cancer risk. Our study focuses on identifying novel phenotypes associated with lung cancer. Genome-wide association studies (GWAS) are useful in elucidating complex inheritance patterns and genetic architecture. Cross-trait linkage disequilibrium score regression (LDSC) specifically allows for use of GWAS summary statistics to identify genetic correlations between phenotypes of interest. This method allows for accurate calculations of genetic correlation, as it neutralizes effects from population stratification or cryptic relatedness. Methods: We used LDSC to (1) confirm prior phenotypic trait associations with lung cancer and to (2) identify novel associations. We measured pairwise genetic correlation (rg) and SNP heritability (h2) (the proportion of phenotypic variance observed in a population that can be explained genetically) between multiple phenotypes and lung cancer using summary statistics from the UK Biobank and OncoArray lung consortium. In addition, we conducted analysis after removal of genome regions related to smoking effects that enables us to correct the potential confounding effect in lung cancer. Results: Significant negative genetic correlations were found to exist between lung cancer and environmental factors. Overall alcohol use was significantly correlated with lung cancers. The effect observed was split, with a positive correlation for beer and cider intake (rg = 0.2957, p = 3.936 × 10-8) and a negative correlation with wine intake (rg = -0.3281, p = 2.251 × 10-14) for overall lung. Significant correlations existed between lung cancer and health metrics. A positive correlation was found between lung cancer and increased BMI (rg = 0.1986, p = 3.57 × 10-9). This finding was consistent across other BMI related metrics and within histological subtypes of lung cancer, including for lung adenocarcinoma (rg = 0.1059, p = 3.688 × 10-3) and lung small cell carcinoma (rg = 0.2393, p = 6.463 × 10-7). In comparison, physical conditioning metrics such as cycling to work had a negative correlation with lung cancer (rg = -0.2714, p = 5.690 × 10-5). Further, negative correlations were observed between being breastfed as a baby and lung cancer (rg = -0.320, p = 1.554 × 10-6). Each of these associations maintained its significance even after the removal of smoking-related SNPs. Conclusions: This analysis demonstrates a genetic basis for the shared genetic architecture between environmental factors and lung oncogenesis. We identify several novel associations, including a correlation between breastfeeding and lung cancer. Further studies are necessary in order to confirm these associations and investigate driving genetic mechanisms. Citation Format: Rowland West Pettit, Jinyoung Byun, Younghun Han, Jacob Edelson, Quinn Ostrom, Kyle Walsh, Melissa Bondy, James McKay, Christopher Amos, INTEGRAL Consortium. Genetic correlation between lung cancer and environmental exposures [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2121.

Feature-shared adaptive-boost deep learning for invasiveness classification of pulmonary subsolid nodules in CT images.

In clinical practice, invasiveness is an important reference indicator for differentiating the malignant degree of subsolid pulmonary nodules. These nodules can be classified as atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC). The automatic determination of a nodule's invasiveness based on chest CT scans can guide treatment planning. However, it is challenging, owing to the insufficiency of training data and their interclass similarity and intraclass variation. To address these challenges, we propose a two-stage deep learning strategy for this task: prior-feature learning followed by adaptive-boost deep learning. The adaptive-boost deep learning is proposed to train a strong classifier for invasiveness classification of subsolid nodules in chest CT images, using multiple 3D convolutional neural network (CNN)-based weak classifiers. Because ensembles of multiple deep 3D CNN models have a huge number of parameters and require large computing resources along with more training and testing time, the prior-feature learning is proposed to reduce the computations by sharing the CNN layers between all weak classifiers. Using this strategy, all weak classifiers can be integrated into a single network. Tenfold cross validation of binary classification was conducted on a total of 1357 nodules, including 765 noninvasive (AAH and AIS) and 592 invasive nodules (MIA and IAC). Ablation experimental results indicated that the proposed binary classifier achieved an accuracy of with an AUC of 81.3 . These results are superior compared to those achieved by three experienced chest imaging specialists who achieved an accuracy of , , and , respectively. About 200 additional nodules were also collected. These nodules covered 50 cases for each category (AAH, AIS, MIA, and IAC, respectively). Both binary and multiple classifications were performed on these data and the results demonstrated that the proposed method definitely achieves better performance than the performance achieved by nonensemble deep learning methods. It can be concluded that the proposed adaptive-boost deep learning can significantly improve the performance of invasiveness classification of pulmonary subsolid nodules in CT images, while the prior-feature learning can significantly reduce the total size of deep models. The promising results on clinical data show that the trained models can be used as an effective lung cancer screening tool in hospitals. Moreover, the proposed strategy can be easily extended to other similar classification tasks in 3D medical images.