Improve Lung Cancer Research Articles

Improving lung cancer diagnoses: a machine learning approach for detection and prediction in CT-Scan image analysis

Improving lung cancer diagnoses: a machine learning approach for detection and prediction in CT-Scan image analysis

Emerging Nanomedicine Approaches in Targeted Lung Cancer Treatment.

Lung cancer, the leading cause of cancer-related deaths worldwide, is characterized by its aggressive nature and poor prognosis. As traditional chemotherapy has the disadvantage of non-specificity, nanomedicine offers innovative approaches for targeted therapy, particularly through the development of nanoparticles that can deliver therapeutic agents directly to cancer cells, minimizing systemic toxicity and enhancing treatment efficacy. VEGF and VEGFR are shown to be responsible for activating different signaling cascades, which will ultimately enhance tumor development, angiogenesis, and metastasis. By inhibiting VEGF and VEGFR signaling pathways, these nanotherapeutics can effectively disrupt tumor angiogenesis and proliferation. This review highlights recent advancements in nanoparticle design, including lipid-based, polymeric, and inorganic nanoparticles, and their clinical implications in improving lung cancer outcomes, exploring the role of nanomedicine in lung cancer diagnoses and treatment.

MicroRNA-130a-3p regulates osimertinib resistance by targeting runt-related transcription factor 3 in lung adenocarcinoma

Overcoming resistance to epidermal growth factor receptor tyrosine kinase inhibitors, including osimertinib, is urgent to improve lung cancer treatment outcomes. Extracellular vesicle (EV)-derived microRNAs (EV-miRNAs) play important roles in drug resistance and serve as promising biomarkers. In this study, we aimed to identify EV-miRNAs associated with osimertinib resistance and investigate their clinical relevance. The release of excess EVs was confirmed in the osimertinib-resistant lung adenocarcinoma cell line PC9OR. The exposure of PC9OR-derived EVs and EV-miRNAs to PC9 cells increased cell viability after osimertinib treatment. Microarray analysis revealed that miR-130a-3p was upregulated in EVs derived from PC9OR cells and another osimertinib-resistant cell line (H1975OR). Transfection with miR-130a-3p attenuated osimertinib-induced cytotoxicity and apoptosis in both PC9 and H1975 cells, whereas osimertinib resistance in PC9OR cells was reversed after miR-130a-3p inhibition. Bioinformatics analysis revealed that runt-related transcription factor 3 is a target gene of miR-130a-3p, and it induced osimertinib resistance in PC9 cells. Patients with lower baseline serum miR-130a-3p concentrations had longer progression-free survival. miR-130a-3p is a potential therapeutic target and a predictive biomarker of osimertinib resistance in adenocarcinomas.

Analysis of the association between immune-related adverse events and the effectiveness in patients with advanced non-small-cell-lung cancer.

Immune checkpoint inhibitors (ICIs) have improved lung cancer treatment but are associated with immune-related adverse events (irAEs). This study analyzes the relationship between irAEs and treatment effectiveness in advanced non-small cell lung cancer (NSCLC) patients. We conducted a retrospective study of NSCLC patients treated with ICIs from March 2019 to October 2022 at Zhongshan Hospital (Xiamen). Patients were divided into irAE and non-irAE groups, and treatment outcomes were compared. A total of 154 patients were included, with 36.4% in the irAE group and 63.6% in the non-irAE group. Most irAEs were Grade 1-2 (86.4%), with 13.6% being Grade 3 or higher. The irAE group had higher disease control rates (DCR: 94.6% vs. 76.5%, P = 0.004) and objective response rates (ORR: 42.9% vs. 26.5%, P = 0.037). Median progression-free survival (PFS) was longer in the irAE group (18 vs. 9months, HR: 0.53, P = 0.001), as was overall survival (OS: 39.5 vs. 16months, HR: 0.46, P = 0.001). Landmark analysis at 6 and 12weeks confirmed that irAEs were associated with improved outcomes. Moreover, patients who experienced two or more adverse events during treatment had significantly longer OS compared to those who had only one or no adverse events (41.6months vs. 34.0 vs. 23.6, P = 0.003). Patients with irAEs demonstrated better outcomes, including ORR, DCR, PFS, and OS. Further studies on biomarkers and irAE incidence are warranted to improve lung cancer management.

Integrative Biomarker Panel for Improved Lung Cancer Diagnosis Using Plasma microRNAs and Sputum Bacterial DNA.

This study aimed to evaluate if integrating diverse molecular biomarkers in plasma and sputum could improve the diagnosis of lung cancer. The study analyzed miRNAs in plasma and bacterial DNA in sputum from 58 lung cancer patients and 62 cancer-free smokers using droplet digital PCR. The individual plasma miRNA and sputum bacterial biomarkers had sensitivities of 62-71% and specificities of 61-79% for diagnosing lung cancer. A panel of plasma miRNA or sputum bacterial biomarkers produced sensitivities of 79-85% and specificities of 74-82%. An integromic signature consisting of two miRNAs in plasma and three bacterial biomarkers in sputum had a higher sensitivity (87%) and specificity (89%) compared to individual biomarkers. The signature's diagnostic value was confirmed in a validation cohort of 56 lung cancer patients and 59 controls, independent of tumor stage, histological type, and demographic factors. Integrating diverse molecular biomarkers in plasma and sputum could improve the diagnosis of lung cancer.

P2.17B.03 Improving Lung Cancer Screening Utilization and Efficiency Through a Patient-Centered Pathway with Virtual Visits

P2.17B.03 Improving Lung Cancer Screening Utilization and Efficiency Through a Patient-Centered Pathway with Virtual Visits

Leveraging a geographic information system (GIS) to identify lung cancer care disparities and opportunities in rural Appalachia.

78 Background: The Rural Appalachian Lung Cancer Screening Initiative is led by the Association of Cancer Care Centers (ACCC) and patient advocacy partners. Recognized by the White House Cancer Moonshot, this initiative seeks to improve lung cancer screening rates by partnering with health systems in rural Appalachia to develop and implement interventions. An 11-county region bordering West Virginia, Virginia, and Kentucky has significantly higher mortality and lung cancer incidence rates than the national rates of 35.0 and 54.0 per 100,000 people, respectively (Table 1). This region was identified as the focus area for the initiative with participation from health systems in Pike County, KY, and Buchanan County, VA. Methods: To understand availability of local resources, ACCC developed an interactive GIS tool that identifies screening and referral locations as well as essential services in the region. Lung cancer screening sites, oncology services, mammography locations, critical access hospitals, NCI-designated cancer centers, federally qualified health centers (FQHCs) and look-alikes, rural health clinics, and primary care/general health services were identified from publicly available data and data requested from state departments of health. Facilities were contacted to verify services when unclear. STATA 18 was used to combine and clean data for upload to Google MyMaps, creating an interactive map. Results: Of the 11 counties, all contain at least 1 FQHC or primary care site. However, 5 of the counties do not have lung cancer screening sites and 7 of the counties do not have oncology service sites (Table). The closest NCI-designated cancer centers to the participating sites are over 140 miles away. Conclusions: While there is a notable presence of primary care, access to lung cancer screening and oncology care is limited. Sites can utilize this map to inform development of interventions by considering potential geographical challenges, identifying referral sites, outreach opportunities, and partners to facilitate lung cancer screening and education. Further, these methods are replicable, and can be used to inform current access to care and improve equitable delivery of lung cancer screening in regions across the U.S. Distribution of lung cancer mortality, incidence, and infrastructure within initiative focus region. Region Mortality*(per 100,000) Incidence*(per 100,000) # Lung Cancer Screening Sites # Oncology Services Sites KY (1 county) 70 109.3 2 2 VA (6 counties) 45.0 – 61.4 42.9 – 68.6 4 3 WV (4 counties) 57.6 – 74.8 100.4 – 111.5 1 0 *Lung & Bronchus, 2016-2020 age-adjusted death rates (KY, VA, WV) and incidence rates (KY, WV). Lung & Bronchus, 2015-2019 age-adjusted incidence rate (VA). Source: statecancerprofiles.cancer.gov.

P4.04D.06 Improving Lung Cancer Risk Prediction in Asbestos Exposed Individuals: An Ensemble Approach

P4.04D.06 Improving Lung Cancer Risk Prediction in Asbestos Exposed Individuals: An Ensemble Approach

Structured multidisciplinary decision making and survival in the prospective observational Detecting Early Lung Cancer (DELUGE) in the Mississippi Delta cohort.

35 Background: Lung cancer screening (LCS) and incidental lung nodule programs (LNP) are associated with improved lung cancer survival (OS); multidisciplinary care (MDC) enhances guideline concordance. We evaluated the outcomes of patients with LCS- or LNP-detected lung cancer who received care with, versus without, structured program-based multidisciplinary decision-making within a large, tri-state regional community healthcare system. Methods: Prospective observational study of patients enrolled into LCS and LNP in the DELUGE cohort. Data on patients diagnosed with lung cancer was linked to a prospective institutional MDC database to classify care delivery as MDC or non-MDC. We compared patient demographic and clinical characteristics, including stage distribution with chi-square tests, OS with the log-rank test, and used proportional hazards models for death with hazard ratios adjusted for age, sex, race, smoking history, insurance status and histologic type. Results: From 2015 to 2023, 504 patients were diagnosed through LCS, 195 (39%) had MDC; 1714 through LNP, 712 (42%) had MDC; 2,218 in total through both early detection programs, 907 (41%) had MDC (Table). 89% of MDC recipients resided in metropolitan areas, compared to 60% of non-MDC patients (p<0.0001). There was a median of 1 (Interquartile range: 1-2) comorbidity across all subsets. Adenocarcinoma was more common among the MDC subsets: 46% v 35% LCS, 56% v 43% LNP; small cell lung cancer was more common among the non-MDC subsets: 11% v 18% LCS, 9% v 14% LNP (p=0.0005). Clinical Stage I was more frequent among MDC v non-MDC subsets for LCS, LNP, and both (all p<0.001, Table). OS was significantly higher in MDC v non-MDC (p<0.0001), aggregate 3-year OS was 75% v 55% (LCS), 60% v 42% (LNP), 63% v 45% (both); and 5-year OS was 65% v 51% (LCS), 49% v 34% (LNP), 52% v 37% (both), respectively. Sensitivity analysis restricting the cohorts to metropolitan patients only or to patients who received care within the institutions where the MDC was active yielded similar results. Conclusions: Structured multidisciplinary decision-making was strongly associated with significant stage re-distribution and better OS among patients diagnosed with lung cancer through screening or lung nodule programs. The MDC structure needs to be embedded within early lung cancer detection programs for optimal results. Variable LCS: MDC? LNP: MDC? Both Programs: MDC? Yes; n=195 No; n=309 Yes; n=712 No; n=1002 Yes; n=907 No; n=1311 Median age, years 68 68 69 71 69 70 Female, % 49 48 51 50 50 49 Black race, % 13 20 30 22 26 22 Medicaid/uninsured, % 2 5 7 7 6 7 Actively smoking, % 70 74 46 52 51 57 Stage I v IV, % 66 v 11 47 v 21 52 v 19 33 v 34 55 v 17 36 v 31 Surgical resection, % 52 32 45 20 46 23 Adjusted HR for death Ref 1.9 (1.3, 2.7) Ref 1.6 (1.4, 1.9) Ref 1.7 (1.4, 1.9)

Lung nodule classification using radiomics model trained on degraded SDCT images

Background and ObjectiveLow-dose computed tomography (LDCT) screening has shown promise in reducing lung cancer mortality; however, it suffers from high false positive rates and a scarcity of available annotated datasets. To overcome these challenges, we propose a novel approach using synthetic LDCT images generated from standard-dose CT (SDCT) scans from the LIDC-IDRI dataset. Our objective is to develop and validate an interpretable radiomics-based model for distinguishing likely benign from likely malignant pulmonary nodules. MethodsFrom a total of 1010 CT images (695 SDCTs and 315 LDCTs), we degraded SDCTs in the sinogram domain and obtained 1950 nodules as the training set. The 675 nodules from the LDCTs were stratified into 50%-50% partitions for validation and testing. Radiomic features were extracted from nodules, and three feature sets were assessed using: a) only shape and size (SS) features, b) all features but SS features, and c) all features. A systematic pipeline was developed to optimize the feature set and evaluate multiple machine learning models. Models were trained using degraded SDCT, validated and tested on the LDCT nodules. ResultsTraining a logistic regression model using three SS features yielded the most promising results, achieving on the test set mean balanced accuracy, sensitivity, specificity, and AUC-ROC scores of 0.81, 0.76, 0.85, and 0.87, respectively. ConclusionsOur study demonstrates the feasibility and effectiveness of using synthetic LDCT images for developing a relatively accurate radiomics-based model in lung nodule classification. This approach addresses challenges associated with LDCT screening, offering potential implications for improving lung cancer detection and reducing false positives.

Empowering minoritized Alabamians screened for lung cancer-The Alabama Lung Cancer Awareness Screening and Education (ALCASE) project.

In Alabama only 4% of those eligible have been screened for lung cancer. The ALCASE project focused on navigating eligible individuals to lung cancer screening. Trained local staff enrolled screen eligible individuals from seven rural counties and one urban county. Demographics and knowledge of and barriers to lung cancer screening were collected using questionnaires. Education was provided and individuals were navigated to undergo screening. Descriptive statistics for enrolled and screened participants were computed using SAS 9.4. Debriefing interviews were conducted with the ALCASE staff regarding facilitators/barriers to implementing this project and lessons learned. Using NVivo, themes were identified through a combined deductive and inductive process. In total, 447 people were contacted of which 257 were enrolled. Participants were predominantly African American (86.8%), female (56.8%), and 86.4% had health insurance. Study participants acknowledged the need for more education of lung cancer/screening procedures; help navigating clinics for screening services and having healthcare facilities close to home. The top five barriers to getting screened were transportation, financial issues, emotional concerns, healthcare insurance, and COVID-19. Of the 257, 106 participants (41%) completed a primary care referral and were screened for lung cancer. Debriefing interviews revealed: (i) Overall impressions of implementing ALCASE were positive. (ii) Barriers in implementing ALCASE were identified predominantly at the physician and institutional level. (iii) Facilitators in implementing ALCASE were identified at multiple levels. (iv) Suggestions on improving lung cancer screening leaned toward mitigating barriers at the institutional and structural level. Ability to get screened is severely challenged by both personal and structural barriers.

Differential Radiomics-Based Signature Predicts Lung Cancer Risk Accounting for Imaging Parameters in NLSTCohort.

Lung cancer remains the leading cause of cancer-related mortality worldwide, with most cases diagnosed at advanced stages. Hence, there is a need to develop effective predictive models for early detection. This study aims to investigate the impact of imaging parameters and delta radiomic features from temporal scans on lung cancer risk prediction. Using the National Lung Screening Trial (NLST) within a nested case-control study involving 462 positive screenings, radiomic features were extracted from temporal computed tomography (CT) scans and harmonized with ComBat method to adjust variations in slice thickness category (TC) and reconstruction kernel type (KT). Both harmonized and non-harmonized features from baseline (T0), delta features between T0 and a year later (T1), and combined T0 and delta features were utilized for the analysis. Feature reduction was done using LASSO, followed by five feature selection (FS) methods and nine machine learning (ML) models, evaluated with 5-fold cross-validation repeated 10 times. Synthetic Minority Oversampling Technique (SMOTE) was applied to address class imbalances for lung cancer risk prediction. Models using delta features outperformed baseline features, with SMOTE consistently boosting performance when using combination of baseline and delta features. TC-based harmonized features improved performance with SMOTE, but overall, harmonization did not significantly enhance the model performance. The highest test score of 0.76 was achieved in three scenarios: delta features with a Gradient Boosting (GB) model (TC-based harmonization and MultiSurf FS); and T0 + delta features, with both a Support Vector Classifier (SVC) model (KT-based harmonization and F-test FS), and an XGBoost (XGB) model (TC-based harmonization and Mutual Information (MI) FS), all using SMOTE. This study underscores the significance of delta radiomic features and balanced datasets to improve lung cancer prediction. While our findings are based on a subsample of NLST data, they provide a valuable foundation for further exploration. Further research is needed to assess the impact of harmonization on imaging-derived models. Future investigations should explore advanced harmonization techniques and additional imaging parameters to develop robust radiomics-based biomarkers of lung cancer risk.

The American Cancer Society National Lung Cancer Roundtable strategic plan: Promoting guideline-concordant lung cancer staging.

Accurate staging improves lung cancer survival by increasing the chances of delivering stage-appropriate therapy. However, there is underutilization of, and variability in, the use of guideline-recommended diagnostic tests used to stage lung cancer. Consequently, the American Cancer Society National Lung Cancer Roundtable (ACS NLCRT) convened the Triage for Appropriate Treatment Task Group-a multidisciplinary expert and stakeholder panel-to identify knowledge and/or resource gaps contributing to guideline-discordant staging and make recommendations to overcome these gaps. The task group determined the following: Gap 1: facilitators of and barriers to guideline-concordant staging are incompletely understood; Recommendation 1: identify facilitators of and barriers to guideline-concordant lung cancer staging; Gap 2: the level of evidence supporting staging algorithms is low-to-moderate; Recommendation 2: prioritize comparative-effectiveness studies evaluating lung cancer staging; Gap 3: guideline recommendations vary across professional societies; Recommendation 3: harmonize guideline recommendations across professional societies; Gap 4: existing databases do not contain sufficient information to measure guideline-concordant staging; Recommendation 4: augment existing databases with the information required to measure guideline-concordant staging; Gap 5: health systems do not have a performance feedback mechanism for lung cancer staging; Recommendation 5: develop and implement a performance feedback mechanism for lung cancer staging; Gap 6: patients rarely self-advocate for guideline-concordant staging; Recommendation 6: increase opportunities for patient self-advocacy for guideline-concordant staging; and Gap 7: current health policies do not motivate guideline-concordant lung cancer staging; Recommendation 7: organize a representative working group under the ACS NLCRT that promotes policies that motivate guideline-concordant lung cancer staging. PLAIN LANGUAGE SUMMARY: Staging-determining the degree of cancer spread-is important because it helps clinicians choose the best cancer treatment. Receiving the best cancer treatment leads to the best possible patient outcomes. Practice guidelines are intended to help clinicians stage patients with lung cancer. However, lung cancer staging in the United States often varies from practice guideline recommendations. This report identifies seven opportunities to improve lung cancer staging.

Deep Learning and MRI Biomarkers for Precise Lung Cancer Cell Detection and Diagnosis

Aim This research work aimed to combine different AI methods to create a modular diagnosis system for lung cancer, including Convolutional Neural Network (CNN), K-Nearest Neighbors (KNN), VGG16, and Recurrent Neural Network (RNN) on MRI biomarkers. Models have then been evaluated and compared in their effectiveness in detecting cancer, using a meticulously selected dataset containing 2045 MRI images, with emphasis being put on documenting the benefits of the multimodal approach for attacking the complexities of the disease. Background Lung cancer remains the most common cause of cancer death in the world, partly because of the challenges in diagnosis and the late stage of presentation. Although Magnetic Resonance Imaging (MRI) has become a critical modality in the identification and staging of lung cancer, too often, its effectiveness is curtailed by the interpretative variance among radiologists. Recent advances in machine learning hold great promise for augmenting the analysis of MRI and perhaps even increasing diagnostic accuracy with the start of timely treatment. In this work, the integration of advanced machine learning models with MRI biomarkers to solve these problems has been investigated. Objective The purpose of the present paper was to assess the effectiveness of integrating various machine-learning models with MRI biomarkers for lung cancer diagnostics, such as CNN, KNN, VGG16, and RNN. The dataset involved 2,045 MRI images, and the performances of the models were investigated by comparing their performance metrics to determine the best configuration of interconnection while underpinning the necessity of this multimodal approach for accurate diagnoses and, consequently, better patient outcomes. Methods For this study, we used 2045 MRI images, with 70% for training and 30% for validation. We used four machine-learning models to work on the photos: CNN, KNN, VGG16, and RNN. Systematic performance measures were included in the study: accuracy, recall, precision, and F1 score. The confusion matrices of this study compared the diagnostic power of every model to comprehend the pragmatic use of the models in a real-world predictive capability. Results The scores for the model were found to be better with the convolutional neural network in terms of recall, accuracy in measures tested, precision, and F1. The rest of the models, KNN, VGG16, and RNN, performed decently but were slightly lower in performance than CNN. The in-depth analysis through confusion matrices thus established the predictive reliability of the models in revealing immense insight into the capability of identifying true positives and minimizing false negatives in enhancing the diagnostic accuracy of lung cancer detection. Conclusion The findings obtained have shown further support and great potential for integrating advanced machine learning models with MRI biomarkers to improve lung cancer diagnosis. The high performance of CNN, high sensitivity and specificity of the KNN model, and robustness of results obtained from VGG16 and RNN models have pointed to the potential feasibility of AI in the accurate detection of cancer. Our work has shown strong support for this multimodal diagnostic approach, which might impact future practice in oncology through the integration of AI to improve treatment strategies and patient outcomes in medical imaging.

Current status of lung cancer care in Germany in the context of treatment centralization and lack of personnel

Lung cancer is the malignancy with the highest mortality rate worldwide. In January 2025, the German public healthcare system will introduce a new regulation according to which a centre can offer surgery for lung cancer only if it carries out a minimum number of lung resections. The purpose of this directive is to reduce the number of centres offering surgical treatment for primary lung cancer, thus centralising and improving lung cancer care. It is expected that the introduction of this regulation will lead to a significant shift in the staffing of thoracic units. The purpose of this survey was to examine the current occupational structures behind the units of thoracic surgery and respiratory medicine. We performed an online survey through the German Society for Thoracic Surgery and the Association of Respiratory Physicians. The responding centres were divided in two groups, centres that were certified by the German Cancer Society or the Society for Thoracic Surgery and centres which were not certified. The response rate was 29.3% (respiratory physicians) and 31.9% (thoracic surgeons); 67% of the participating colleagues answered that their unit was an independent department. The majority of the participants reported having to share the on-call duty of the trainees with other departments in order to be able to cover the required shifts. 35% of the respiratory physicians and 57% of the thoracic surgeons reported having vacant job posts in their units. The introduction of the minimum quantity regulation will have significant consequences for the treatment of lung cancer in Germany. The current staff shortage in healthcare will lead to both medical and nursing staff needing to be redistributed in order to meet the needs that will arise in 2025. Operating lists, theatre days, and operative equipment will need to be redistributed as well, not only within hospitals but probably on a nationwide level. A negative impact of the new regulation is to be expected on research and academic activities since most university hospitals are not expected to reach the minimum number of lung resections that is required in order keep performing lung cancer surgery.

Lung Cancer Detection Using Convolutional Neural Networks

Lung cancer is among the most prevalent and deadly cancers worldwide. Accurate diagnosis and early detection are critical for improving lung cancer patient outcomes and survival rates. Thanks to developments in medical imaging technology, computer-aided diagnosis (CAD) systems have shown a great deal of promise in helping radiologists identify and diagnose lung cancer from medical images. Here, we present the use of convolutional neural networks (CNNs) to create an early detection system (CAD) for lung cancer. The suggested approach uses lung computed tomography (CT) scans as input and use a CNN architecture to extract high-level features from the pictures. We use transfer learning to enhance a CNN model trained on a large dataset of CT images. The CNN model has been taught to determine if a specific CT image contains lung cancer or not. We evaluate the performance of the proposed CAD system on a dataset of CT scans of the lungs from different institutions. The trial's results show that our CNN-based CAD system can reliably and precisely identify lung cancer from CT scans. We also show the comparative performance of our proposed system against the state-of-the-art machine learning methods for lung cancer prediction. In conclusion, the suggested CNN-based deep learning-based CAD system has produced encouraging results for lung cancer detection from CT scans. The approach might help radiologists identify and classify lung cancer early on, leading to better patient outcomes and survival rates. The viability and usefulness of the suggested approach in clinical practice require more study

Developing a systems-focused tool for modeling lung cancer screening resource needs

BackgroundEarly detection through screening dramatically improves lung cancer survival rates, including among war Veterans, who are at heightened risk. The effectiveness of low dose computed tomography scans in lung cancer screening (LCS) prompted the Veteran’s Affairs Lung Precision Oncology Program (VA LPOP) to increase screening rates. We aimed to develop an adaptive population health tool to determine adequate resource allocation for the program, with a specific focus on primary care providers, nurse navigators, and radiologists.MethodsWe developed a tool using C + + that uses inputs that represents the process of the VA LCS program in Ann Arbor, Michigan to calculate FTEs of human resource needs to screen a given population. Further, we performed a sensitivity analysis to understand how resource needs are impacted by changes in population, screening eligibility, and time allocated for the nurse navigators’ tasks.ResultsUsing estimates from the VA LCS Program as demonstrative inputs, we determined that the greatest number of full-time equivalents required were for radiologists, followed by nurse navigators and then primary care providers, for a target population of 75,000. An increase in the population resulted in a linear increase of resource needs, with radiologists experiencing the greatest rate of increase, followed by nurse navigators and primary care providers. These resource requirements changed with primary care providers, nurse navigators and radiologists demonstrating the greatest increase when 1–20, 20–40 and > 40% of Veterans accepted to be screened respectively. Finally, when increasing the time allocated to check eligibility by the nurse navigator from zero to three minutes, there was a linear increase in the full-time equivalents required for the nurse navigator.ConclusionVariation of resource utilization demonstrated by our user facing tool emphasizes the importance of tailored strategies to accommodate specific population demographics and downstream work. We will continue to refine this tool by incorporating additional variability in system parameters, resource requirements following an abnormal test result, and resource distribution over time to reach steady state. While our tool is designed for a specific program in one center, it has wider applicability to other cancer screening programs.

Glycemic control in diabetic patients improved overall lung cancer survival across diverse populations.

The consequence of diabetes on lung cancer overall survival (OS) is debated. This retrospective study used 2 large lung cancer databases to assess comprehensively diabetes effects on lung cancer OS in diverse demographic populations, including health disparity. The University of Texas MD Anderson Cancer Center database (32 643 lung cancer patients with 11 973 patients with diabetes) was extracted from electronic health records (EHRs) using natural language processing (NLP). Associations were between diabetes and lung cancer prognostic features (age, sex, race, body mass index [BMI], insurance status, smoking, stage, and histopathology). Hemoglobin A1C (HgbA1c) and glucose levels assessed glycemic control. Validation was with a Louisiana cohort (17 768 lung cancer patients with 5402 patients with diabetes) enriched for health disparity cases. Kaplan-Meier analysis, log-rank test, multivariable Cox proportional hazard models, and survival tree analyses were employed. Lung cancer patients with diabetes exhibited marginally elevated OS or no statistically significant difference versus nondiabetic patients. When examining OS for 2 glycemic levels (HgbA1c > 7.0 or glucose > 154 mg/dL vs HgbA1c > 9.0 or glucose > 215 mg/dL), a statistically significant improvement in OS occurred in lung cancer patients with controlled versus uncontrolled glycemia (P < .0001). This improvement spanned sex, age, smoking status, insurance status, stage, race, BMI, histopathology, and therapy. Survival tree analysis revealed that obese and morbidly obese patients with controlled glycemia had higher lung cancer OS than comparison groups. These findings indicate a need for optimal glycemic control to improve lung cancer OS in diverse populations with diabetes.

Immunotherapy Improves the Survival of Stage 4 Non-Small Cell Lung Cancer Patients at the US Population Level: The Real-World Evidence.

Immunotherapy has revolutionized the management of lung cancer and improved lung cancer survival in trials, but its real-world impact at the population level remains unclear. Using data obtained from eight Surveillance, Epidemiology, and End Results (SEER) registries from 2004 through 2019, we addressed the long-term trends in the incidence, incidence-based mortality (IBM), and survival of lung cancer patients in the United States. The incidence and IBM of both non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) all significantly decreased steadily from 2004 to 2019. The 1-year survival (1-YS) of both NSCLC and SCLC improved over time, with the best improvement observed for Stage 4 NSCLC. Two significant turning points of Stage 4 NSCLC 1-YS were observed over the years: 0.63% (95% confidence interval [CI]: 0.33%-0.93%) from 2004 to 2010, 0.81% (95% CI: 0.41%-1.21%) from 2010 to 2014 and a striking 2.09% (95% CI: 1.70%-2.47%) from 2014 to 2019. The same two turning points in 1-YS were pronounced for Stage 4 NSCLC in women, which were coincident with the introduction of epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs) and immunotherapy. However, for Stage 4 NSCLC in men, only one significant turning point in the 1-YS starting in 2014 was found, which might only correspond to immunotherapy. Significant period effects in reduced IBM were also observed for both Stage 4 AD and Stage 4 SQCC during the period. This SEER analysis found that immunotherapy improved the survival of Stage 4 NSCLC patients at the population level in the United States. This real-world evidence confirms that immunotherapy has truly revolutionized the management of lung cancer.

1565P Improving lung cancer screening selection: Hunt Lung Cancer Model (HUNT LCM) versus PLCOm2012, early results after two rounds of screening in a prospective screening pilot study in Norway (TIDL)

1565P Improving lung cancer screening selection: Hunt Lung Cancer Model (HUNT LCM) versus PLCOm2012, early results after two rounds of screening in a prospective screening pilot study in Norway (TIDL)