Lung Cancer Risk Assessment Research Articles

High-Ambient Air Pollution Exposure Among Never Smokers Versus Ever Smokers With Lung Cancer

IntroductionAir pollution may play an important role in the development of lung cancer in people who have never smoked, especially among East Asian women. The aim of this study was to compare cumulative ambient air pollution exposure between ever and never smokers with lung cancer. MethodsA consecutive case series of never and ever smokers with newly diagnosed lung cancer were compared regarding their sex, race, and outdoor and household air pollution exposure. Using individual residential history, cumulative exposure to outdoor particulate matter (PM2.5) in a period of 20 years was quantified with a high-spatial resolution global exposure model. ResultsOf the 1005 patients with lung cancer, 56% were females and 33% were never smokers. Compared with ever smokers with lung cancer, never smokers with lung cancer were significantly younger, more frequently Asian, less likely to have chronic obstructive pulmonary disease or a family history of lung cancer, and had higher exposure to outdoor PM2.5 but lower exposure to secondhand smoke. Multivariable logistic regression analysis revealed a significant association with never-smoking patients with lung cancer and being female (OR = 4.01, 95% confidence interval [CI]: 2.76–5.82, p < 0.001), being Asian (ORAsian versus non-Asian = 6.48, 95% CI: 4.42–9.50, p < 0.001), and having greater exposure to air pollution (ORln_PM2.5 = 1.79, 95% CI: 1.10–7.2.90, p = 0.019). ConclusionsCompared with ever-smoking patients with lung cancer, never-smoking patients had strong associations with being female, being Asian, and having air pollution exposures. Our results suggest that incorporation of cumulative exposure to ambient air pollutants be considered when assessing lung cancer risk in combination with traditional risk factors.

Abstract 2536: Mutational landscape of the bronchial epithelium of individuals at high risk for lung cancer

Abstract Insights into mutational burden of the airway epithelium, the field of cancerization, may play important role in stratifying individuals at different levels of risk for lung cancer. We hypothesized that cytologically normal bronchial epithelium of patients with lung cancer and those at high risk for lung cancer harbor driver mutations. We performed next generation sequence-based targeted CAPP-Seq (CAncer Personalized Profiling by deep Sequencing) and whole exome sequencing (WES) of DNA from the bronchial epithelial cells from the bronchial brushings of individuals at-risk for lung cancer and patients with lung cancer as well as matched lung tumor tissues. We used the Tammemagi risk model to calculate the risk for lung cancer. Both CAPPSeq and WES data analyses showed higher mutation burden in lung tumor tissues compared to bronchial brushings. Using targeted CAPPSeq, a total of 129 nonsynonymous mutations were identified in bronchial brushings. Among individuals without lung cancer, 9 oncogenic driver mutations were identified in 5 out of 13 high risk and 2 out of 7 low risk individuals. Among individuals with cancer, 13 out of 22 brushings harbored 11 driver mutations, of which mutations in TP53 and PTEN were identified in both tumor and brushing matched samples. Mutations detected in the brushings of individuals with and without cancer were TP53, PIK3CA, NOTCH1, KRAS, MET, CUL3, and NF1. Using WES on the DNA from the same brushings (low risk, n=9; high risk, n=8 and lung cancer, n=17), we identified 19478 mutations total, and 90 of that were also identified by CAPPSeq. WES identified 80% of the mutations that were identified by CAPPSeq with &amp;gt;5% variant allelic frequencies (VAF). Mutations identified by CAPPSeq had VAF as low as 0.2% and vast majority of the mutations identified by WES had VAF &amp;gt;5%. Out of 9 mutations in TP53 identified in the brushings by CAPPSeq, 4 were identified by WES. Mutation in KMT2D, a histone methylation enzyme and believed to be a tumor suppressor, was identified by WES in the brushings and the tumor tissues of patients with lung cancer as well as in one high risk brushings. Mutational signature profiling identified tobacco mutational signature in the bronchial epithelium and tobacco, APOBEC and DNA-DSB repair signatures in the tumor tissues. Copy number variation (CNV) data analysis revealed significantly higher CNV levels in tumor samples than brushing samples. Genome-wide CNA profiling identified regions significantly influenced by CNV, such as deletions in chromosome region 19p13.3, which was previously reported to be related to lung cancer. We identified mutations in cancer driver genes in the bronchial brushings of individuals with and without lung cancer. This field of cancerization effect may provide a tool for risk assessment for lung cancer. This research was funded by U01CA196405 to PPM. Citation Format: SM Jamshedur Rahman, Shilin Zhao, Shih-Kai Chu, Yong Zou, Angela B. Hui, Thomas P. Stricker, Chen Heidi, Maximilian Diehn, Pierre P. Massion. Mutational landscape of the bronchial epithelium of individuals at high risk for lung cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2536.

Abstract 2614: A deep learning model-based lung cancer risk assessment for incidental pulmonary nodules

Abstract Lung cancer is the leading cause of cancer death among both men and women. The solitary pulmonary nodule (SPN) is frequently seen on radiographs and computed tomography (CT) and often provokes additional clinical and imaging activities as an SPN alerts possible early stage lung cancer. However, reliable diagnosis of malignant lung nodules in the workup of SPN is challenging, making it difficult for early stage cancer management to avoid morbidity due to malignant cancer, patient distress, and increased costs caused by more invasive and unwarranted procedures for benign cases. We developed a deep learning model based on convolutional neural networks (CNNs) to predict lung cancer risk for incidental SPN. The model can help better management of incidental lung cancer by providing a reliable characterization of SPNs. Deep learning models currently are applied to nodule detection in low-dose CT scans of lung cancer screening for at-risk population. Our work aims to investigate whether deep learning can differentiate benign from malignant incidental SPN during normal dose CT exams, where the number of patients with SPN is an order more than that of lung screening population. We collected an incidental SPN dataset containing 139 CT scans to generate the nodule malignancy prediction model using 3D CNN. This dataset was collected from either contrast or non-contrast CT scans with regular doses. All 139 patients went through surgeries to remove the tumors. CT images were collected within one year before the surgery. 90 cases are malignant and the rest are benign. Ground truth labels were obtained from biopsies. Data were preprocessed by resampling, normalization, and cropping to unique volume around the SPN. The radiologists annotated the SPN location. Since the two nodule classes are imbalanced, we did online data augmentation to increase the variety of lung nodule images and balance the two classes. We used 80% of the data for training and 20% for testing. The deep learning structure adapted is a 3D Resnet with 68 layers and 33M parameters. The area under the receiving operating characteristics curve (AUC) of the prediction result was 0.81 while the accuracy was 79.6%. Applying GradCam to visualize important regions in CT scans contributing to the final predictions, we found that our trained ResNet model focuses on meaningful areas in lung nodules and detects malignant SPNs in most cases. Our preliminary results shows the feasibility of using deep learning to predict incidental lung nodules and improve diagnostic speed and accuracy. Citation Format: Pengyu Yuan, Tiancheng He, Hien Nguyen, Stephen T. Wong. A deep learning model-based lung cancer risk assessment for incidental pulmonary nodules [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2614.

Utility of incorporating a gene-based lung cancer risk test on uptake and adherence in a community-based lung cancer screening pilot study.

Based on the results of randomized control trials, screening for lung cancer using computed tomography (CT) is now widely recommended. However, adherence to screening remains an issue outside the clinical trial setting. This study examines the utility of biomarker-based risk assessment on uptake and subsequent adherence in a community screening study.In a single arm pilot study, current or former smokers > 50 years old with 20 + pack year history were recruited following local advertising. One hundred and fifty seven participants volunteered to participate in the study that offered an optional gene-based lung cancer risk assessment followed by low-dose CT according to a standardised screening protocol.All 157 volunteers who attended visit 1 underwent the gene-based risk assessment comprising of a clinical questionnaire and buccal swab. Of this group, 154 subsequently attended for CT screening (98%) and were followed prospectively for a median of 2.7 years. A participant’s adherence to screening was influenced by their baseline lung cancer risk category, with overall adherence in those with a positive scan being significantly greater in the “very high” risk group compared to “moderate” and “high” risk categories (71% vs 52%, Odds ratio = 2.27, 95% confidence interval of 1.02–5.05, P = 0.047). Those in the “moderate” risk group were not different to those in the “high” risk group (52% and 52%, P > 0.05).In this proof-of-concept study, personalised gene-based lung cancer risk assessment was well accepted, associated with a 98% uptake for screening and increased adherence for those in the highest risk group.

Reduction in total and major cause-specific mortality from tobacco smoking cessation: a pooled analysis of 16 population-based cohort studies in Asia.

Little is known about the time course of mortality reduction following smoking cessation in Asians who have smoking behaviours distinct from their Western counterparts. We evaluated the level of reduction in all-cause, cardiovascular disease (CVD) and lung cancer mortality by years since quitting smoking, in Asia. Using Cox regression, we analysed individual participant data (n = 709 151) from 16 prospective cohorts conducted in China, Japan, Korea/Singapore, and India/Bangladesh, separately by cohorts. Cohort-specific hazard ratios (HRs) were combined using a random-effects meta-analysis. During a mean follow-up of 12.0 years, 108 287 deaths were ascertained-35 658 from CVD and 7546 from lung cancer. Among Asian men, a dose-response relationship of risk reduction in deaths from all causes, CVD and lung cancer was observed with an increase in years after smoking cessation. Compared with never smokers, however, all-cause and CVD mortality among former smokers remained elevated 10-14 years after quitting [multivariable-adjusted HR (95% confidence interval (CI) = 1.25 (1.13-1.37) and 1.20 (1.02-1.41), respectively]. Lung cancer mortality stayed almost 2-fold higher than among never smokers 15-19 years after smoking cessation [1.97 (1.41-2.73)], particularly among former heavy smokers [2.62 (1.71-4.00)]. Women who quitted for ≥5 years retained a significantly elevated mortality from all causes, CVD and lung cancer. Overall patterns of the cessation-mortality associations were similar across countries. Our findings suggest that adverse effects of tobacco smoking persist for an extended time period, even for more than two decades, which is beyond the time windows defined in current clinical guidelines for risk assessment of lung cancer and CVD.

Incidence of lung cancer and mortality among civil construction industry workers: A protocol for a systematic review and meta-analysis.

The construction sector is one of the most stable growth industries in the world. However, many studies have suggested an association between occupational exposure in civil construction and lung cancer risk. Thus, this study aims to assess lung cancer risk in civil construction workers occupationally exposed to physical and chemical agents through a systematic review and meta-analysis. Studies will be identified by searching PUBMED, Embase, SCOPUS, WEB OF SCIENCE and the reference list of included articles. Eligible study designs will be cohort, cross-sectional, and case-control studies that report occupational exposure to physical or chemical agents and lung cancer risk through mortality or incidence outcomes. A meta-analysis will be used to combine odds ratios (ORs) from case-control studies and relative risks (RR) from cohort studies. Two reviewers will independently screen articles, extract data, and assess scientific quality using standardized forms and ROBINS-E tool if available. Otherwise, the New-Castle Ottawa rating scale will be used. Any of those will also be used in combination with the GRADE approach for quality of evidence. Overall risk estimates and their corresponding 95% confidence intervals (CIs) will be obtained using the random-effects model meta-analysis. This systematic review and meta-analysis will be conducted following the Meta-analysis of Observational Studies in Epidemiology (MOOSE) guidelines. Results will be reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. This review will identify and synthesize studies investigating the association between occupational exposure in the construction industry and lung cancer. The findings will help governmental entities and researchers with evidence-based decision-making because they will integrate and validate the evidence on construction workers' health effects due to occupational exposure. PROSPERO CRD42020164209.

Analytical validation of the Percepta genomic sequencing classifier; an RNA next generation sequencing assay for the assessment of Lung Cancer risk of suspicious pulmonary nodules

BackgroundBronchoscopy is a common procedure used for evaluation of suspicious lung nodules, but the low diagnostic sensitivity of bronchoscopy often results in inconclusive results and delays in treatment. Percepta Genomic Sequencing Classifier (GSC) was developed to assist with patient management in cases where bronchoscopy is inconclusive. Studies have shown that exposure to tobacco smoke alters gene expression in airway epithelial cells in a way that indicates an increased risk of developing lung cancer. Percepta GSC leverages this idea of a molecular “field of injury” from smoking and was developed using RNA sequencing data generated from lung bronchial brushings of the upper airway. A Percepta GSC score is calculated from an ensemble of machine learning algorithms utilizing clinical and genomic features and is used to refine a patient’s risk stratification.MethodsThe objective of the analysis described and reported here is to validate the analytical performance of Percepta GSC. Analytical performance studies characterized the sensitivity of Percepta GSC test results to input RNA quantity, the potentially interfering agents of blood and genomic DNA, and the reproducibility of test results within and between processing runs and between laboratories.ResultsVarying the amount of input RNA into the assay across a nominal range had no significant impact on Percepta GSC classifier results. Bronchial brushing RNA contaminated with up to 10% genomic DNA by nucleic acid mass also showed no significant difference on classifier results. The addition of blood RNA, a potential contaminant in the bronchial brushing sample, caused no change to classifier results at up to 11% contamination by RNA proportion. Percepta GSC scores were reproducible between runs, within runs, and between laboratories, varying within less than 4% of the total score range (standard deviation of 0.169 for scores on 4.57 scale).ConclusionsThe analytical sensitivity, analytical specificity, and reproducibility of Percepta GSC laboratory results were successfully demonstrated under conditions of expected day to day variation in testing. Percepta GSC test results are analytically robust and suitable for routine clinical use.

Application of logistic regression and convolutional neural network in prediction and diagnosis of high-risk populations of lung cancer.

The early detection, early diagnosis, and early treatment of lung cancer are the best strategies to improve the 5-year survival rate. Logistic regression analysis can be a helpful tool in the early detection of high-risk groups of lung cancer. Convolutional neural network (CNN) could distinguish benign from malignant pulmonary nodules, which is critical for early precise diagnosis and treatment. Here, we developed a risk assessment model of lung cancer and a high-precision classification diagnostic model using these technologies so as to provide a basis for early screening of lung cancer and for intelligent differential diagnosis. A total of 355 lung cancer patients, 444 patients with benign lung disease and 472 healthy people from The First Affiliated Hospital of Zhengzhou University were included in this study. Moreover, the dataset of 607 lung computed tomography images was collected from the above patients. The logistic regression method was employed to screen the high-risk groups of lung cancer, and the CNN model was designed to classify pulmonary nodules into benign or malignant nodules. The area under the curve of the lung cancer risk assessment model in the training set and the testing set were 0.823 and 0.710, respectively. After finely optimizing the settings of the CNN, the area under the curve could reach 0.984. This performance demonstrated that the lung cancer risk assessment model could be used to screen for high-risk individuals with lung cancer and the CNN framework was suitable for the differential diagnosis of pulmonary nodules.

Towards radiologist-level cancer risk assessment in CT lung screening using deep learning.

Lung cancer is the leading cause of cancer mortality in the US, responsible for more deaths than breast, prostate, colon and pancreas cancer combined and large population studies have indicated that low-dose computed tomography (CT) screening of the chest can significantly reduce this death rate. Recently, the usefulness of Deep Learning (DL) models for lung cancer risk assessment has been demonstrated. However, in many cases model performances are evaluated on small/medium size test sets, thus not providing strong model generalization and stability guarantees which are necessary for clinical adoption. In this work, our goal is to contribute towards clinical adoption by investigating a deep learning framework on larger and heterogeneous datasets while also comparing to state-of-the-art models. Three low-dose CT lung cancer screening datasets were used: National Lung Screening Trial (NLST, n = 3410), Lahey Hospital and Medical Center (LHMC, n = 3154) data, Kaggle competition data (from both stages, n = 1397 + 505) and the University of Chicago data (UCM, a subset of NLST, annotated by radiologists, n = 132). At the first stage, our framework employs a nodule detector; while in the second stage, we use both the image context around the nodules and nodule features as inputs to a neural network that estimates the malignancy risk for the entire CT scan. We trained our algorithm on a part of the NLST dataset, and validated it on the other datasets. Special care was taken to ensure there was no patient overlap between the train and validation sets. The proposed deep learning model is shown to: (a) generalize well across all three data sets, achieving AUC between 86% to 94%, with our external test-set (LHMC) being at least twice as large compared to other works; (b) have better performance than the widely accepted PanCan Risk Model, achieving 6 and 9% better AUC score in our two test sets; (c) have improved performance compared to the state-of-the-art represented by the winners of the Kaggle Data Science Bowl 2017 competition on lung cancer screening; (d) have comparable performance to radiologists in estimating cancer risk at a patient level.

P43.01 Utility of Sputum for Non-Invasive Assessment of Lung Cancer Risk with the LuCED® Test: Specimen Satisfactory Rate

P43.01 Utility of Sputum for Non-Invasive Assessment of Lung Cancer Risk with the LuCED® Test: Specimen Satisfactory Rate

Validation of multivariable lung cancer risk prediction models for the personalized assignment of optimal screening frequency: a retrospective analysis of data from the German Lung Cancer Screening Intervention Trial (LUSI).

BackgroundCurrent guidelines for lung cancer screening via low-dose computed tomography recommend annual screening for all candidates meeting basic eligibility criteria. However, lung cancer risk of eligible screening participants can vary widely, and further risk stratification could be used to individually optimize screening intervals in view of expected benefits, possible harms and financial costs. To this effect, models have been developed in the US National Lung Screening Trial based on self-reported lung cancer risk factors and imaging data. We evaluated these models using data from an independent screening trial in Germany.MethodsWe examined the Polynomial model by Schreuder et al., the Lung Cancer Risk Assessment Tool extended by CT characteristics (LCRAT + CT) by Robbins et al., and a criterion of presence vs. absence of pulmonary nodules ≥4 mm (Patz et al.), applied to sub-sets of screening participants according to eligibility criteria. Discrimination was evaluated via the receiver operating characteristic curve. Delayed diagnoses and false positive results were calculated at various thresholds of predicted risk. Model calibration was assessed by comparing mean predicted risk versus observed incidence.ResultsOne thousand five hundred and six participants were eligible for the validation of the LCRAT + CT model, and 1,889 for the validation of the Polynomial model and Patz criterion, yielding areas under the receiver operating characteristic curve of 0.73 (95% CI: 0.63, 0.82), 0.75 (0.67, 0.83), and 0.56 (0.53, 0.72) respectively. Skipping 50% annual screenings (participants within the 5 lowest risk deciles by LCRAT + CT in any round or by the Polynomial model; baseline screening round), would have avoided 75% (21.9%, 98.7%) and 40% (21.8%, 61.1%) false positive screen tests and delayed 10% (1.8%, 33.1%) or no (0%, 32.1%) diagnoses, respectively. Using the Patz criterion, referring 63.2% (61.0% to 65.4%) of participants to biennial screening would have avoided 4% (0.2% to 22.3%) of false positive screen tests but delayed 55% (24.6% to 81.9%) diagnoses.ConclusionsIn this German trial, the LCRAT + CT and Polynomial models showed useful discrimination of screening participants for one-year lung cancer risk following CT examination. Our results illustrate the remaining heterogeneity in risk within screening-eligible subjects and the trade-off between a low-frequency screening approach and delayed detection.

A model based on the quantification of complement C4c, CYFRA 21-1 and CRP exhibits high specificity for the early diagnosis of lung cancer

Lung cancer screening detects early-stage cancers, but also a large number of benign nodules. Molecular markers can help in the lung cancer screening process by refining inclusion criteria or guiding the management of indeterminate pulmonary nodules. In this study, we developed a diagnostic model based on the quantification in plasma of complement-derived fragment C4c, cytokeratin fragment 21–1 (CYFRA 21–1) and C-reactive protein (CRP). The model was first validated in two independent cohorts, and showed a good diagnostic performance across a range of lung tumor types, emphasizing its high specificity and positive predictive value. We next tested its utility in two clinically relevant contexts: assessment of lung cancer risk and nodule malignancy. The scores derived from the model were associated with a significantly higher risk of having lung cancer in asymptomatic individuals enrolled in a computed tomography (CT)-screening program (OR = 1.89; 95% CI = 1.20 –2.97). Our model also served to discriminate between benign and malignant pulmonary nodules (AUC: 0.86; 95% CI = 0.80 –0.92) with very good specificity (92%). Moreover, the model performed better in combination with clinical factors, and may be used to reclassify patients with intermediate-risk indeterminate pulmonary nodules into patients who require a more aggressive work-up. In conclusion, we propose a new diagnostic biomarker panel that may dictate which incidental or screening-detected pulmonary nodules require a more active work-up.

Deep Multi-path Network Integrating Incomplete Biomarker and Chest CT Data for Evaluating Lung Cancer Risk.

Clinical data elements (CDEs) (e.g., age, smoking history), blood markers and chest computed tomography (CT) structural features have been regarded as effective means for assessing lung cancer risk. These independent variables can provide complementary information and we hypothesize that combining them will improve the prediction accuracy. In practice, not all patients have all these variables available. In this paper, we propose a new network design, termed as multi-path multi-modal missing network (M3Net), to integrate the multi-modal data (i.e., CDEs, biomarker and CT image) considering missing modality with multiple paths neural network. Each path learns discriminative features of one modality, and different modalities are fused in a second stage for an integrated prediction. The network can be trained end-to-end with both medical image features and CDEs/biomarkers, or make a prediction with single modality. We evaluate M3Net with datasets including three sites from the Consortium for Molecular and Cellular Characterization of Screen-Detected Lesions (MCL) project. Our method is cross validated within a cohort of 1291 subjects (383 subjects with complete CDEs/biomarkers and CT images), and externally validated with a cohort of 99 subjects (99 with complete CDEs/biomarkers and CT images). Both cross-validation and external-validation results show that combining multiple modality significantly improves the predicting performance of single modality. The results suggest that integrating subjects with missing either CDEs/biomarker or CT imaging features can contribute to the discriminatory power of our model (p < 0.05, bootstrap two-tailed test). In summary, the proposed M3Net framework provides an effective way to integrate image and non-image data in the context of missing information.

A 10-year follow-up study of yearly indoor radon measurements in homes, review of other studies and implications on lung cancer risk estimates

Uncertainty on long-term average radon concentration has a large impact on lung cancer risk assessment in epidemiological studies. The uncertainty can be estimated by year-to-year radon concentration variability, however few data are available. In Italy a study has been planned and conducted to evaluate year-to-year radon variability over several years in normally inhabited dwellings, mainly located in Rome. This is the longest study of this kind in Europe; repeat radon measurements are carried out for 10 years using LR-115 radon detectors in the same home in consecutive years. The study includes 84 dwellings with long-term average radon concentration ranging from 28 to 636 Bq/m3. The result shows that year-to-year variability of repeated measurements made in the same home in different years is low, with an overall coefficient of variation of 17%. This is smaller than most of those observed in studies from other European countries and USA, ranging from 15% to 62%. Influencing factors that may explain the differences between this study and other studies have been discussed. Due to the low yearly variability estimated in the present 10-year study, a negligible impact on lung cancer risk estimate for the Italian epidemiological study is expected.

Abstract IA16: Lung Cancer Risk Assessment in Diverse Populations: One Size Cannot Fit All

Abstract Lung cancer is the leading cause of cancer related deaths in the United States with an estimate of over 200,000 new cases and 135,720 deaths in 2020. Despite the development of precision therapies, immunotherapy and improved surgical techniques, the overall 5-year survival has remained below that of many other malignancies and significant disparities continue to persist. Black American males tend to present with later-stage disease, are less likely to undergo appropriate staging and thus, have a higher lung cancer mortality. The National Lung Screening Trial I (NLST) determined that low-dose CT (LDCT) screening could reduce lung cancer specific mortality by nearly 20% and overall mortality by 6.7%. However, studies suggest that clinically useful models for improved lung cancer risk stratification will be essential to the identification of those most likely to benefit from screening while minimizing unnecessary screening and associated risks. In NLST, only 4% of enrolled participants were Black Americans. Recent investigation demonstrates that current screening eligibility criteria are insufficient in identifying Black Americans at risk for lung cancer a large percentage of whom are diagnosed at a younger age than White Americans and with less tobacco consumption. As a result, current draft recommendations include reducing both age and smoking screening eligibility to 50 years of age and 20 pack years respectively with a goal of narrowing gaps in disparities in early lung cancer diagnosis and outcome. Here, we will review current models for lung cancer risk stratification that incorporate sociodemographic factors, comorbid illnesses and non-invasive biomarkers and discuss their clinical application to diverse populations. Citation Format: Patrick Nana-Sinkam. Lung Cancer Risk Assessment in Diverse Populations: One Size Cannot Fit All [abstract]. In: Proceedings of the AACR Virtual Conference: Thirteenth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2020 Oct 2-4. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(12 Suppl):Abstract nr IA16.

Risk assessment and prediction for lung cancer among Hong Kong Chinese men

Objective: The discriminatory power of previous risk prediction models for all lung cancers generally ranged from 0.57 to 0.72. We constructed individual risk prediction models for all lung cancers and its specific histological subtypes among Hong Kong general male population. Methods: Epidemiological data of 1069 male lung cancer cases confirmed by histology and 1208 community controls were included in this analysis. Community controls were randomly selected from the general male population frequency-matched by age and sex. Annual concentration of ambient PM2.5 and PM10 air pollution were retrospectively reconstructed based on individual household location and the nearest monitoring station data. LASSO-model was used to select optimal risk factors for each specific prediction model. Receiver-operator characteristic curves (ROC) and the area under the curve (AUC) was used to demonstrate the model performance and the ability to differentiate cases from non-cases. Results: AUC for all lung cancers was 0.782 (95%CI: 0.762-0.801) and the discriminatory power increased to 0.824 (95%CI: 0.807-0.841) after PM10 was included into the prediction model, and this improvement was consistently shown in prediction models stratified by smoking status. When the prediction models included ambient PM10 and were further specified by histological subtypes, a notably higher AUC was demonstrated for squamous cell lung cancer (0.878, 95%CI: 0.857-0.898) than that of the adenocarcinoma (0.778, 95%CI: 0.751-0.804). Conclusion: Lung cancer risk assessment tool in Hong Kong Chinese men based on LASSO selection is promising, which shows a relatively higher discriminative accuracy than those developed in many other populations. Risk model is improved after including PM10 air pollution, indicating the importance of addressing ambient PM air pollution in risk prediction. However, external validation of this model in an independent population is recommended to be the next necessary step. [Funding source: Research Grant Council, HKSAR, Project no. CUHK4460/03M]

Artificial neural networks improve LDCT lung cancer screening: a comparative validation study

BackgroundThis study proposes a prediction model for the automatic assessment of lung cancer risk based on an artificial neural network (ANN) with a data-driven approach to the low-dose computed tomography (LDCT) standardized structure report.MethodsThis comparative validation study analysed a prospective cohort from Chiayi Chang Gung Memorial Hospital, Taiwan. In total, 836 asymptomatic patients who had undergone LDCT scans between February 2017 and August 2018 were included, comprising 27 lung cancer cases and 809 controls. A derivation cohort of 602 participants (19 lung cancer cases and 583 controls) was collected to construct the ANN prediction model. A comparative validation of the ANN and Lung-RADS was conducted with a prospective cohort of 234 participants (8 lung cancer cases and 226 controls). The areas under the curves (AUCs) of the receiver operating characteristic (ROC) curves were used to compare the prediction models.ResultsAt the cut-off of category 3, the Lung-RADS had a sensitivity of 12.5%, specificity of 96.0%, positive predictive value of 10.0%, and negative predictive value of 96.9%. At its optimal cut-off value, the ANN had a sensitivity of 75.0%, specificity of 85.0%, positive predictive value of 15.0%, and negative predictive value of 99.0%. The area under the ROC curve was 0.764 for the Lung-RADS and 0.873 for the ANN (P = 0.01). The two most important predictors used by the ANN for predicting lung cancer were the documented sizes of partially solid nodules and ground-glass nodules.ConclusionsCompared to the Lung-RADS, the ANN provided better sensitivity for the detection of lung cancer in an Asian population. In addition, the ANN provided a more refined discriminative ability than the Lung-RADS for lung cancer risk stratification with population-specific demographic characteristics. When lung nodules are detected and documented in a standardized structured report, ANNs may better provide important insights for lung cancer prediction than conventional rule-based criteria.

Artificial Intelligence and Data Mining to Assess Lung Cancer Risk: Challenges and Opportunities.

Artificial Intelligence and Data Mining to Assess Lung Cancer Risk: Challenges and Opportunities.

Abstract 1137: Deep targeted and whole exome sequencing identifies driver mutations in the airway epithelium of individuals at high risk for lung cancer

Abstract Insights into tumor mutational burden of the airway epithelium may play important role in stratifying individuals at different levels of risk for lung cancer. Comparison of the genetic profiles of normal airway epithelial cells to tumor mutations can yield valuable information regarding shared mutations as well as presence of neoantigens. We hypothesized that cytologically normal bronchial epithelium of patients with lung cancer and those at high risk for lung cancer harbor driver mutations that can be identified by deep targeted sequencing of selected genes implicated in cancer and whole exome sequencing. We performed next generation sequence-based CAPP-Seq (CAncer Personalized Profiling by deep Sequencing) and whole exome sequencing (WES) of DNA from the bronchial epithelial cells from the bronchial brushings of individuals at-risk (low and high) for lung cancer and patients with lung cancer. Bronchial brushings were collected from consented individuals at the time of bronchoscopy at Vanderbilt University Medical Center and the Nashville Veterans Affairs Medical Center. We used Tammemagi risk model to calculate the risk of developing lung cancer. Lung tumor tissues from matched individuals were also sequenced. Using CAPPSeq, a total of 129 mutations were identified in bronchial brushings. Among individuals without cancer, driver mutations included TP53, PIK3CA, NOTCH1, KRAS, MET, CUL3, NF1, KEAP1 and EGFR mutations in 5 out of 13 high risk and 2 out of 7 low risk individuals. Among individuals with cancer, 13 out of 22 brushings harbored driver mutations in TP53, PIK3CA, ARID1A, PTEN, NOTCH1, KRAS, MET, NFE2L2, CUL3, NF1, and KEAP1 of which mutations in TP53 and PTEN were identified in both tumor and bronchial brushings. At least one mutation was called in 18 brushings of individuals with lung cancer. Mutations detected in both individuals with and without cancer were TP53, PIK3CA, NOTCH1, KRAS, MET, CUL3, and NF1. Using WES on the DNA from the same bronchial brushings (low risk-9; high risk-8 and lung cancer-17), we identified 90 mutations that were also identified by CAPPSeq. Most of the mutations identified by CAPPSeq with &amp;gt;5% variant allelic frequencies (VAF) were also identified by WES. However, WES was not sensitive enough to identify mutations with less than 0.5% VAF. Out of 9 mutations in TP53 identified in the brushings by CAPPSeq, 4 were identified by WES. Mutation in KMTD2, a histone methylation enzyme and believed to be a tumor suppressor, was identified by WES in the brushings and the tumor tissues of patients with lung cancer as well as in one high risk brushings. We identified mutations in cancer driver genes in the bronchial brushings of individuals with and without lung cancer. This field of cancerization effect may provide a tool for risk assessment for lung cancer. This research was funded by U01CA196405 to PPM. Citation Format: SM Jamshedur Rahman, Shih-kai Chu, Shilin Zhao, Yong Zou, Angela Hui, Thomas Stricker, Maximilian Diehn, Pierre P. Massion. Deep targeted and whole exome sequencing identifies driver mutations in the airway epithelium of individuals at high risk for lung cancer [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 1137.

Cancer Screening Program in Urban Kunming of Yunnan: Evaluation of Lung Cancer Risk Assessment and Screening

背景与目的肺癌是最常见的恶性肿瘤，预后较差，5年生存率较低，早期筛查是肺癌防治的重要措施。目前，不同国家和地区发布了相应的肺癌筛查指南，但我国仍缺乏基于中国人群研究的指南。因此，国家癌症中心在全国启动了多中心的城市癌症早诊早治项目研究。本研究分析了城市癌症早诊早治项目中云南省单中心的肺癌高危人群评估模型及临床筛查应用效果，为探索适合我国国情的肺癌高危人群评估模型及制定和更新中国人群肺癌筛查指南提供一定的参考依据。方法采取整群抽样的方法，于2015年1月-2019年12月对云南省昆明市4个主城区36个街道办事处165, 337人进行问卷调查及肺癌风险评估，评估为高风险者进行胸部低剂量计算机断层扫描（low-dose computed tomography, LDCT）筛查。同时对所有参与者进行主动随访和被动随访，获得详细的临床结局，进行统计分析。结果整体人群5年间经病理确诊肺癌患者264例，总体肺癌发生率为0.16%（264/165, 337），高风险组（0.31%, 116/37, 914）高于非高风险组（0.12%, 148/127, 423），差异有统计学意义（P < 0.001）。不同性别和不同年龄的亚组分析显示高风险组肺癌发生率均高于非高风险组，均有统计学差异（P < 0.001），但在未进行LDCT筛查组无统计学差异（P=0.73）。肺癌高危人群评估模型的敏感性为43.94%（116/264），特异性为77.10%（127, 275/165, 073）。筛查组早诊率为72.97%（54/74），明显高于非筛查组的28.48%（43/151）。结论国家重大公共卫生服务项目城市癌症筛查项目肺癌高危人群评估模型能有效检出高风险人群，提高肺癌早诊率。