CT Screening For Lung Cancer Research Articles

Accuracy and Impact of AI Software for Nodule and Cancer Detection at Lung Cancer Screening CT.

Accuracy and Impact of AI Software for Nodule and Cancer Detection at Lung Cancer Screening CT.

AI-enabled cardiac chambers volumetry in non-contrast coronary artery calcium CT scans vs. contrast-enhanced coronary CT angiography scans in the same patients

Abstract Introduction We have developed an AI-enabled automated volumetry of cardiac chambers (AutoChamber) that works both on non-contrast ECG-gated cardiac CT scans used for coronary artery calcium (CAC) score, and non-contrast non-gated lung cancer screening CT scans. We have recently reported the agreement between AutoChamber measurements vs cardiac MRI measurements. Here we report AutoChamber results on non-contrast CAC scans and contrast enhanced coronary CT angiography (CTA). Methods We have obtained CT images from a previously published study in which 131 cases underwent non-contrast CAC and contrast enhanced CCTA at research institute. The cases consisted of 52.4% women with ages 55.0 ± 10.1 years. The cardiac chambers volume in 131 cases of contrast enhanced CCTA were measured using automated chamber volumetry by Philips Brilliance Volume v 4.5; Philips Healthcare. Results The correlations between Philips’ automated chamber volumetry in contrast enhanced CCTA scans versus AutoChamber automated volumetry in non-contrast CAC scans for left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), and left ventricular wall (LVW) volume were 0.73, 0.65, 0.85, 0.93, 0.90, respectively (P for all <0.01). Conclusion AI-enabled AutoChamber volumetry based on non-contrast cardiac scans is feasible, and correlates reasonably well with contrast-enhanced cardiac CT scans. Further studies are warranted to reproduce these results and explore the add-on value of AutoChamber to CAC scans.

Software using artificial intelligence for nodule and cancer detection in CT lung cancer screening: systematic review of test accuracy studies

ObjectivesTo examine the accuracy and impact of artificial intelligence (AI) software assistance in lung cancer screening using CT.MethodsA systematic review of CE-marked, AI-based software for automated detection and analysis of...

EP.04B.04 Defining A Positive CT Screening for Lung Cancer Using Different Nodule Sizes: Implications from a Prospective Cohort Study in China

EP.04B.04 Defining A Positive CT Screening for Lung Cancer Using Different Nodule Sizes: Implications from a Prospective Cohort Study in China

Lung Nodule Management in Low-Dose CT Screening for Lung Cancer: Lessons from the NELSON Trial.

Screening with low-dose CT (LDCT) in a high-risk population, as defined by age and smoking behavior, reduces lung cancer-related mortality. However, LDCT screening presents a major challenge. Numerous, mostly benign, nodules are seen in the lungs during screening. The question is how to distinguish the malignant from the benign nodules. Various studies use different protocols for nodule management. The Dutch-Belgian NELSON (Nederlands-Leuvens Longkanker Screenings Onderzoek) trial, the largest European lung cancer screening trial, used distinctions based on nodule volumetric assessment and growth rate. This review discusses key findings from the NELSON study regarding the characteristics of screening-detected nodules, including nodule size and its volumetric assessment, growth rate, subtype, and their associated malignancy risk. These results are compared with findings from other screening studies and current recommendations for lung nodule management. By examining differences in nodule management strategies and providing a comprehensive overview of outcomes specific to lung cancer screening, this review aims to contribute to the broader discussion on optimizing lung nodule management in screening programs.

Abstract B046: Factors influencing patient decision-making to complete Low Dose CT screening for lung cancer

Abstract As part of a randomized, controlled trial (RCT) to increase lung cancer screening (LCS) with low-dose CT scan (LDCT) within the Choctaw Nation of Oklahoma’s tribal health system, we conducted a qualitative study to explore the barriers behind patient decisions to forego screening. Thirty eligible participants who had been in the RCT for at least one year were identified as LCS completers (n=7) or non-completers (n=23). A single interviewer completed all interviews using a semi-structured interview guide, designed to explore experiences, barriers/facilitators to LCS, factors influencing screening decisions, and suggested strategies for expanding the LCS program into the community. Interviews were recorded and transcribed verbatim. Data were analyzed using conventional content analysis. Most non-completers reported having no conversations about the availability of LCS with their primary care provider (PCP) or receiving any information about the LCS program. In contrast, the completers all reported PCP-initiated discussions about the LCS program, their risk factors, and an overview of the testing process. Key themes that emerged included fears, e.g., being unsure about what the test involves, afraid of being diagnosed with lung cancer and what might follow, and afraid of dying. Some voiced concerns, e.g., feeling guilty as active smokers and being stigmatized should they be diagnosed with lung cancer. Many participants posited that there was no reason for screening without symptoms. Lack of understanding, especially about cancer care, was identified as a contributing factor. Suggested strategies to increase the reach into the community included using existing infrastructure within Choctaw Nation, such as disseminating information through the tribal newsletter, inserts in prescription refills, and notifications via the patient portal. Community education programs at local community centers, particularly around senior citizen meals, were offered as strategies to change the perception that lung cancer is a death sentence. Hosting an informational booth at the annual tribal Labor Day festival was commonly suggested. In conclusion, multiple reasons were cited for forgoing LDCT screening. In this tribal setting, findings are similar to ones documented in other settings. This suggests that interventions to overcome these challenges may build off known evidence-based interventions, such as the recommendations for cancer prevention documented by the Community Preventive Services Task Force. Addressing fears through multiple educational approaches and adapting strategies from the American Lung Association to address stigma could lead to enhanced interventions. Finally, capitalizing on tribal resources (newsletter) and tribal events to increase LCS awareness may be promising strategies to improve screening in the local tribal setting. Citation Format: Kathleen Dwyer, Zsolt Nagykaldi, Mark Doescher, Dorothy A. Rhoades. Factors influencing patient decision-making to complete Low Dose CT screening for lung cancer [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr B046.

Abstract A132: Missed Opportunities? Regional availability of Low Dose CT lung cancer screening facility locations in the year prior to diagnoses: A descriptive comparison of American Indian and Non-Hispanic White lung cancer patients in North Carolina

Abstract INTRODUCTION American Indians (AI) have much higher incidence rates of lung cancer (LC) compared with non-Hispanic Whites (NHW) in the US. While low-dose computed tomography (LDCT) screening facilitates early detection of lung cancer, it is unknown how available LDCT screenings are to racially and geographically diverse populations in North Carolina (NC). To address this gap in knowledge, we conducted a descriptive study to characterize incident LC cases among AIs and NHWs, the distance from their location at diagnosis to the nearest LDCT screening facility and explored whether distance was associated with late-stage LC diagnoses. Methods Data were obtained from the Cancer Information and Population Health Resource (CIPHR), which comprise data from NC Central Cancer Registry (CCR) as well as public and private health insurance claims for the state. We identified ZIP codes and dates of rendered service for facilities providing LDCT by searching through claims from 2015-20. In addition, we identified incident LC cases among AIs and NHWs aged ≥18 years, from 2015-19. We assembled lists of LDCT facilities that existed in the year prior to each incident LC case. We calculated the minimum centroid to centroid distance to all facilities. Clinical attributes included age at diagnosis, sex, histology, stage at diagnosis, and rurality as measured by Rural Urban Commuting Area. Risk ratios were calculated for late-stage LC diagnoses across a range of thresholds for patient’s distance to nearest LDCT screening facility for AIs and NHWs. Results We identified 388 AI and 26,867 NHW incident LC cases in NC between 2015-20. Compared to NHWs, the median age at diagnosis for AIs was 5 years younger (AI: 65 vs. NHW: 69); more frequently male (AI: 54% vs NHW: 51%); and almost twice as likely to reside in rural areas (AI: 52% vs. NHW: 28%). There were no differences in late-stage LC diagnoses (AI: 54% vs. NHW: 52%). For distance (in miles) to the nearest LDCT screening facility, the median [Interquartile range] was twice as high for AIs (9.9 miles [0.8, 16.30]) compared to NHWs (5.3 miles [0, 12.1]). Among NHWs, there were statistically significant associations between distance and late-stage LC diagnosis at the shortest distance threshold of 5 miles (RR=1.04; 95%CL: 1.02, 1.07) through the threshold of 30 miles (RR=1.10 95%CL: 1.05, 1.15). There was no association across any distance threshold among AI lung cancer patients. Conclusions The large difference in accessibility of LDCT screening was not strongly associated with metastatic lung cancer diagnoses, possibly because so many patients were diagnosed late, reflecting poor early detection across all populations. We found that 80% of AIs with LC lived more than 10 miles away from LDCT screening facilities. This geographic distance may increase difficulty accessing cancer care geographically, and contribute to suboptimal LC screening rates. If efforts are to be made to increase early detection and improve survival, accessibility needs to be addressed on different dimensions. Citation Format: Bradford E. Jackson, Marc Emerson, Daniel Carrizosa, Chris Baggett, Lisa Spees, Joel Begay, Ana Salas, Yadurshirni Raveendran, Tomi Akinyemiju, Rachel Denlinger-Apte, Stephanie Wheeler, Ronny Bell. Missed Opportunities? Regional availability of Low Dose CT lung cancer screening facility locations in the year prior to diagnoses: A descriptive comparison of American Indian and Non-Hispanic White lung cancer patients in North Carolina [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A132.

The Azygos Esophageal Recess Is Not to Be Missed in Screening Lung Cancer With LDCT.

Lesion overlooking and late diagnostic workup can compromise the efficacy of low-dose CT (LDCT) screening of lung cancer (LC), implying more advanced and less curable disease stages. We hypothesized that the azygos esophageal recess (AER) of the right lower lobe (RLL) might be an area prone to lesion overlooking in LC screening. Two radiologists reviewed the LDCT examinations of all the screen-detected incident LCs observed in the active arm of 2 randomized clinical trials: ITALUNG and national lung screening trial. Those in the AER were compared with those in the remainder of the RLL for possible differences in diagnostic lag according to the Lung-RADS 1.1 recommendations, size, stage, and mortality. Six (11.7%) of 51 screen-detected incident LCs of the RLL were located in the AER. The diagnostic lag time was significantly longer (P=0.046) in the AER LC (mean 14±9mo) than in the LC in the remaining RLL (mean 7.3±1mo). Size and stage at diagnosis were not significantly different. All 6 subjects with LC in the AER and 16 (35.5%) of 45 subjects with LC in the remaining RLL (P=0.004) died of LC after a median follow-up of 12 years. Our retrospective study indicates that AER might represent a lung region of the RLL prone to have early LC overlooked due to detection or interpretation errors with possible detrimental consequences for the subject undergoing LC screening.

Assessing Thoracic Vertebral Bone Mineral Density (T8-T10) for Osteoporosis Diagnosis During CT Lung Cancer Screening in Older Adults.

Osteoporosis diagnosis often utilizes quantitative computed tomography (QCT). This study explored the validity of applying lumbar bone mineral density (LBMD) standards to thoracic vertebrae (T8-T10) for osteoporosis detection during CT lung cancer screenings. This study investigated the utility of thoracic BMD (BMD-T8-T10) for detecting osteoporosis in older persons during CT lung cancer screening. We studied 701 participants who underwent QCT scans for both LBMD and BMD-T8-T10. Osteoporosis was diagnosed using ACR criteria based on LBMD. We determined BMD-T8-T10 thresholds via a receiver operating characteristic (ROC) curve and translated BMD-T8+T9+T10 to LBMD (TTBMD) using linear regression. Kappa test was used to evaluate the accuracy of BMD-T8-T10 thresholds and TTBMD in diagnosing osteoporosis. Raw BMD-T8-T10 poorly identified osteoporosis (kappa = 0.51). ROC curve analysis identified BMD-T8-T10 thresholds for osteopenia (138 mg/cm3) and osteoporosis (97 mg/cm3) with areas under the curve of 0.97 and 0.99, respectively. We normalized BMD-T8-T10 to TTBMD based on the formula: TTBMD = 0.9 × BMD-T8-T10 - 2.56. These thresholds (kappa = 0.74) and TTBMD performed well in detecting osteoporosis/osteopenia (kappa = 0.74). Both calculating BMD-T8-T10 threshold (138.0 mg/cm3 for osteopenia and 97 mg/cm3 for osteoporosis) and normalizing BMD-T8-T10 to LBMD demonstrated good performance in identifying osteoporosis in older adults during CT lung cancer screening.

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

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

PP01.61 The Use of Low-Dose Lung CT for Lung Cancer Screening in Firefighters

PP01.61 The Use of Low-Dose Lung CT for Lung Cancer Screening in Firefighters

Yorkshire Lung Screening Trial (YLST) pathway navigation study: a protocol for a nested randomised controlled trial to evaluate the effect of a pathway navigation intervention on lung cancer screening uptake

IntroductionLung cancer is the most common cause of cancer death globally. In 2022 the UK National Screening Committee recommended the implementation of a national targeted lung cancer screening programme, aiming...

Coronary Artery Calcification on Low-Dose Lung Cancer Screening CT in South Korea: Visual and Artificial Intelligence-Based Assessment and Association With Cardiovascular Events.

BACKGROUND. Coronary artery calcification (CAC) on lung cancer screening low-dose chest CT (LDCT) is a cardiovascular risk marker. South Korea was the first Asian country to initiate a national LDCT lung cancer screening program, although CAC-related outcomes are poorly explored. OBJECTIVE. The purpose of this article is to evaluate CAC prevalence and severity using visual analysis and artificial intelligence (AI) methods and to characterize CAC's association with major adverse cardiovascular events (MACEs) in patients undergoing LDCT in Korea's national lung cancer screening program. METHODS. This retrospective study included 1002 patients (mean age, 62.4 ± 5.4 [SD] years; 994 men, eight women) who underwent LDCT at two Korean medical centers between April 2017 and May 2023 as part of Korea's national lung cancer screening program. Two radiologists independently assessed CAC presence and severity using visual analysis, consulting a third radiologist to resolve differences. Two AI software applications were also used to assess CAC presence and severity. MACE occurrences were identified by EMR review. RESULTS. Interreader agreement for CAC presence and severity, expressed as kappa, was 0.793 and 0.671, respectively. CAC prevalence was 53.4% by consensus visual assessment, 60.1% by AI software I, and 56.6% by AI software II. CAC severity was mild, moderate, and severe by consensus visual analysis in 28.0%, 10.3%, and 15.1%; by AI software I in 39.9%, 14.0%, and 6.2%; and by AI software II in 34.9%, 14.3%, and 7.3%. MACEs occurred in 36 of 625 (5.6%) patients with follow-up after LDCT (median, 1108 days). MACE incidence in patients with no, mild, moderate, and severe CAC for consensus visual analysis was 1.1%, 5.0%, 2.9%, and 8.6%, respectively (p < .001); for AI software I, it was 1.3%, 3.0%, 7.9%, and 11.3% (p < .001); and for AI software II, it was 1.2%, 3.4%, 7.7%, and 9.6% (p < .001). CONCLUSION. For Korea's national lung cancer screening program, MACE occurrence increased significantly with increasing CAC severity, whether assessed by visual analysis or AI software. The study is limited by the large sex imbalance for Korea's national lung cancer screening program. CLINICAL IMPACT. The findings provide reference data for health care practitioners engaged in developing and overseeing national lung cancer screening programs, highlighting the importance of routine CAC evaluation.

Impact of single round of low dose CT lung cancer screening on cause of mortality in different socio-economic groups: a post-hoc analysis of long-term follow-up of the UKLS trial

Lower socioeconomic status, as measured by the Index of Multiple Deprivation (IMD), is associated with higher rates of smoking-related disease mortality, and with poor uptake of cancer screening. Here we explore whether socioeconomic status impacts the effectiveness of a single round of low-dose-CT screening, or impacts other causes of death, in the UKLS LDCT screening trial. IMD quintiles were defined according to UK-wide data, with the deprived group defined as the lower two quintiles (Q1-2) and the less deprived as Q3-5. Follow-up data was obtained for lung cancer diagnosis (median follow-up 9.1 years) and cause of death (median follow-up 9.9 years). Outcomes were compared based on IMD group and trial arm (CT or control). More deprived quintiles were less likely to respond to the questionnaire, but this population was more likely to be selected for screening by the LLP risk model. Lower IMD quintiles benefitted from low-dose-CT screening in terms of lung cancer survival (HR 1.89, 95% CI 1.16-3.08) to the same extent as upper quintiles (HR 1.87, 95% CI 1.07-3.26). However, there was a bigger impact on deaths due to COPD and emphysema in more deprived quintiles. Whilst LDCT screening benefit for lung cancer was similar, significant impact on the rates of death from other smoking-related diseases, notably COPD and emphysema, was seen primarily in lower socioeconomic groups. Future research is required to confirm how lung cancer screening benefits other disease outcomes. NIHR Health Technology Assessment Programme; NIHR Policy Research programme; Roy Castle Lung Cancer Foundation.

Impact of deep learning image reconstruction on volumetric accuracy and image quality of pulmonary nodules with different morphologies in low-dose CT

BackgroundThis study systematically compares the impact of innovative deep learning image reconstruction (DLIR, TrueFidelity) to conventionally used iterative reconstruction (IR) on nodule volumetry and subjective image quality (IQ) at highly reduced radiation doses. This is essential in the context of low-dose CT lung cancer screening where accurate volumetry and characterization of pulmonary nodules in repeated CT scanning are indispensable.Materials and methodsA standardized CT dataset was established using an anthropomorphic chest phantom (Lungman, Kyoto Kaguku Inc., Kyoto, Japan) containing a set of 3D-printed lung nodules including six diameters (4 to 9 mm) and three morphology classes (lobular, spiculated, smooth), with an established ground truth. Images were acquired at varying radiation doses (6.04, 3.03, 1.54, 0.77, 0.41 and 0.20 mGy) and reconstructed with combinations of reconstruction kernels (soft and hard kernel) and reconstruction algorithms (ASIR-V and DLIR at low, medium and high strength). Semi-automatic volumetry measurements and subjective image quality scores recorded by five radiologists were analyzed with multiple linear regression and mixed-effect ordinal logistic regression models.ResultsVolumetric errors of nodules imaged with DLIR are up to 50% lower compared to ASIR-V, especially at radiation doses below 1 mGy and when reconstructed with a hard kernel. Also, across all nodule diameters and morphologies, volumetric errors are commonly lower with DLIR. Furthermore, DLIR renders higher subjective IQ, especially at the sub-mGy doses. Radiologists were up to nine times more likely to score the highest IQ-score to these images compared to those reconstructed with ASIR-V. Lung nodules with irregular margins and small diameters also had an increased likelihood (up to five times more likely) to be ascribed the best IQ scores when reconstructed with DLIR.ConclusionWe observed that DLIR performs as good as or even outperforms conventionally used reconstruction algorithms in terms of volumetric accuracy and subjective IQ of nodules in an anthropomorphic chest phantom. As such, DLIR potentially allows to lower the radiation dose to participants of lung cancer screening without compromising accurate measurement and characterization of lung nodules.

HUNCHEST projects-advancing low-dose CT lung cancer screening in Hungary.

Lung cancer, the leading cause of malignancy-related deaths worldwide, demands proactive measures to mitigate its impact. Low-dose computer tomography (LDCT) has emerged as a promising tool for secondary prevention through lung cancer screening (LCS). The HUNCHEST study, inspired by the success of international trials, including the National Lung Cancer Screening Trial and the Dutch NELSON study, embarked on the first LDCT-based LCS program in Hungary. The initiative assessed the screening efficiency, incorporating lung function tests and exploring the interplay between lung cancer and chronic obstructive pulmonary disease (COPD). Building upon this foundation, an implementation trial involving 18 Hungarian centers supported by the Ministry of Human Capacities demonstrated the feasibility of LCS within a multicentric framework. These centers, equipped with radiology capabilities, collaborated with multidisciplinary oncology teams, ensuring optimal patient pathways. However, a critical challenge remained the patient recruitment. To address this, the HUNCHEST 3 project, initiated in 2023, seeks to engage general practitioners (GPs) to reach out to eligible patients within a municipality collective of 60 thousand inhabitants. The project's ultimate success is contingent upon the willingness of eligible individuals to undergo LDCT scans. In conclusion, the HUNCHEST program represents a crucial step in advancing lung cancer screening in Hungary. With a focus on efficiency, multidisciplinary collaboration, and innovative patient recruitment strategies, it endeavors to contribute to the reduction of lung cancer mortality and serve as a blueprint for potential nationwide LCS programs.

3228: Analysing healthcare benefits and resource implications of lung cancer CT screening in Jordan

3228: Analysing healthcare benefits and resource implications of lung cancer CT screening in Jordan

When to reinvite initially ineligible populations for targeted lung cancer screening?

IntroductionTargeted low-dose CT lung cancer screening reduces lung cancer mortality. England’s Targeted Lung Health Check programme uses risk prediction tools to determine eligibility for biennial screening among people with a...

Thyroid abnormalities identified on CT screening for lung cancer

PurposeBecause incidental thyroid nodules (ITNs) are common extrapulmonary findings in low-dose computed tomography (LDCT) scans for lung cancer screening, we aimed to investigate the frequency of ITNs on LDCT scans separately on baseline and annual repeat scans, the frequency of malignancy among the ITNs, and any association with demographic, clinical, CT characteristics. MethodsRetrospective case series of all 2309 participants having baseline and annual repeat screening in an Early Lung and Cardiac Action Program (MS-ELCAP) LDCT lung screening program from January 2010 to December 2016 was performed. Frequency of ITNs in baseline and annual repeat rounds were determined. Multivariable regression analysis was performed to identify significant predictors. ResultsDominant ITNs were seen in 2.5 % of 2309 participants on baseline and in 0.15 % of participants among 4792 annual repeat LDCTs. The low incidence of new ITNs suggests slow growth as it would take approximately an average of 16.8 years for a new ITN to be detected on annual rounds of screening. Newly detected ITNs on annual repeat LDCT were all smaller than 15 mm. Regression analysis showed that the increasing of age, coronary artery calcifications score and breast density grade were significant predictors for females having an ITN. No significant predictors were found for ITNs in males. ConclusionITNs are detected at LDCT however, no malignancy was found. Certain predictors for ITNs in females have been identified including breast density, which may point towards a common causal pathway.

Demographics and socioeconomic determinants of health predict continued participation in a CT lung cancer screening program

PurposeWe developed machine learning (ML) models to assess demographic and socioeconomic status (SES) variables’ value in predicting continued participation in a low-dose CT lung cancer screening (LCS) program. Materials and Methods480 LCS subjects were retrospectively examined for the following outcomes: (#1) no follow-up (single LCS scan) vs. multiple follow-ups (220 and 260 subjects respectively) and (#2) absent or delayed (>1 month past the due date) follow-up vs timely follow-up (356 and 124 subjects respectively). We quantified the contributions of 14 socioeconomic, demographic, and clinical predictors to LCS adherence, and validated and compared prediction performances of multivariate logistic regression (MLR), support vector machine (SVM) and shallow neural network (NN) models. ResultsFor outcome #1, age, sex, race, insurance status, personal cancer history, and median household income were found to be associated with returning for follow-ups. For outcome #2, age, sex, race, and insurance status were significant predictor of absent/delayed LCS follow-up. Across 5-fold cross-validation, the MLR model achieved an average AUC of 0.732 (95% CI, 0.661-0.803) for outcome #1 and 0.633 (95% CI, 0.602-0.664) for outcome #2 and is the model with best predictive performance overall, whereas NN and SVM tended to overfit training data and fell short on testing data performance for either outcome. ConclusionsWe identified significant predictors of LCS adherence, and our ML models can predict which subjects are at higher risk of receiving no or delayed LCS follow-ups. Our results could inform data-driven interventions to engage vulnerable populations and extend the benefits of LCS.