Lung Cancer Risk Prediction Research Articles

Prediction Model for Lung Cancer in High-Risk Nodules Being Considered for Resection: Development and Validation in a Chinese Population.

BackgroundDetermining benign and malignant nodules before surgery is very difficult when managing patients with pulmonary nodules, which further makes it difficult to choose an appropriate treatment. This study aimed to develop a lung cancer risk prediction model for predicting the nature of the nodule in patients’ lungs and deciding whether to perform a surgical intervention.MethodsThis retrospective study included patients with pulmonary nodules who underwent lobectomy or sublobectomy at Tianjin Medical University General Hospital between 2017 and 2020. All subjects were further divided into training and validation sets. Multivariable logistic regression models with backward selection based on the Akaike information criterion were used to identify independent predictors and develop prediction models.ResultsTo build and validate the model, 503 and 260 malignant and benign nodules were used. Covariates predicting lung cancer in the current model included female sex, age, smoking history, nodule type (pure ground-glass and part-solid), nodule diameter, lobulation, margin (smooth, or spiculated), calcification, intranodular vascularity, pleural indentation, and carcinoembryonic antigen. The final model of this study showed excellent discrimination and calibration with a concordance index (C-index) of 0.914 (0.890–0.939). In an independent sample used for validation, the C-index for the current model was 0.876 (0.825–0.927) compared with 0.644 (0.559–0.728) and 0.681 (0.605–0.757) for the Mayo and Brock models. The decision curve analysis showed that the current model had higher discriminatory power for malignancy than the Mayo and the Brock models.ConclusionsThe current model can be used in estimating the probability of lung cancer in nodules requiring surgical intervention. It may reduce unnecessary procedures for benign nodules and prompt diagnosis and treatment of malignant nodules.

Screening for Lung Cancer in Individuals Who Never Smoked: An International Association for the Study of Lung Cancer Early Detection and Screening Committee Report

Screening with low-dose computed tomography of high-risk individuals with a smoking history reduces lung cancer mortality. Current screening guidelines and eligibility criteria can miss more than 50% of lung cancers, and in some geographic areas, such as East Asia, a large proportion of the missed lung cancers are in never-smokers. Although randomized trials revealed the benefits of screening for people who smoke, these trials generally excluded never-smokers. Thus, the feasibility and effectiveness of lung cancer screening of individuals who never smoked are uncertain. Several known and suspected risk factors for lung cancers in never-smokers such as exposure to secondhand smoke, occupational carcinogens, radon, air pollution, and pulmonary diseases, such as chronic obstructive pulmonary disease and interstitial lung diseases, and intrinsic factors, such as age, are well noted. In this regard, knowledge of risk factors may make possible quantification and prediction of lung cancer risk in never smokers. It is worth considering if and how never smokers could be included in population-based screening programs. As the implementation of these programs is challenging in many countries owing to multiple factors and the epidemiologic differences by global regions, these issues will need to be evaluated in each country taking into account various factors, including accuracy of risk assessment and cost-effectiveness of screening in never smokers. This report aims to outline current knowledge on risk factors for lung cancer in never smokers to propose research strategies for this topic and initiate a broader discussion on lung cancer screening of never smokers. Similar considerations can be made in current and ex-smokers, which do not fulfill the current screening inclusion criteria, but otherwise are at increased risk. Although screening of never smokers may in the future be effectively conducted, current evidence to support widespread implementation of this practice is lacking.

Artificial Intelligence-Based Prediction of Lung Cancer Risk Using Nonimaging Electronic Medical Records: Deep Learning Approach.

BackgroundArtificial intelligence approaches can integrate complex features and can be used to predict a patient’s risk of developing lung cancer, thereby decreasing the need for unnecessary and expensive diagnostic interventions.ObjectiveThe aim of this study was to use electronic medical records to prescreen patients who are at risk of developing lung cancer.MethodsWe randomly selected 2 million participants from the Taiwan National Health Insurance Research Database who received care between 1999 and 2013. We built a predictive lung cancer screening model with neural networks that were trained and validated using pre-2012 data, and we tested the model prospectively on post-2012 data. An age- and gender-matched subgroup that was 10 times larger than the original lung cancer group was used to assess the predictive power of the electronic medical record. Discrimination (area under the receiver operating characteristic curve [AUC]) and calibration analyses were performed.ResultsThe analysis included 11,617 patients with lung cancer and 1,423,154 control patients. The model achieved AUCs of 0.90 for the overall population and 0.87 in patients ≥55 years of age. The AUC in the matched subgroup was 0.82. The positive predictive value was highest (14.3%) among people aged ≥55 years with a pre-existing history of lung disease.ConclusionsOur model achieved excellent performance in predicting lung cancer within 1 year and has potential to be deployed for digital patient screening. Convolution neural networks facilitate the effective use of EMRs to identify individuals at high risk for developing lung cancer.

Individual 5-Year Lung Cancer Risk Prediction Model in Korea Using a Nationwide Representative Database

Simple SummaryFrom the representative data in Korea, we developed individual lung cancer risk prediction model of Korean adults. Our model would serve as a tool to screen high-risk individuals who would benefit from participating in lung cancer screening in a clinical setting applicable to health examinees or the general adult population. We believe that interactive approaches between healthcare providers and examinees using an easily accessible and visualized risk score can be used for the development of health policies for lung cancer prevention.Early detection of lung cancer by screening has contributed to reduce lung cancer mortality. Identifying high risk subjects for lung cancer is necessary to maximize the benefits and minimize the harms followed by lung cancer screening. In the present study, individual lung cancer risk in Korea was presented using a risk prediction model. Participants who completed health examinations in 2009 based on the Korean National Health Insurance (KNHI) database (DB) were eligible for the present study. Risk scores were assigned based on the adjusted hazard ratio (HR), and the standardized points for each risk factor were calculated to be proportional to the b coefficients. Model discrimination was assessed using the concordance statistic (c-statistic), and calibration ability assessed by plotting the mean predicted probability against the mean observed probability of lung cancer. Among candidate predictors, age, sex, smoking intensity, body mass index (BMI), presence of chronic obstructive pulmonary disease (COPD), pulmonary tuberculosis (TB), and type 2 diabetes mellitus (DM) were finally included. Our risk prediction model showed good discrimination (c-statistic, 0.810; 95% CI: 0.801–0.819). The relationship between model-predicted and actual lung cancer development correlated well in the calibration plot. When using easily accessible and modifiable risk factors, this model can help individuals make decisions regarding lung cancer screening or lifestyle modification, including smoking cessation.

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.

Predicting Lung Cancer Risk in Diverse Populations

Predicting Lung Cancer Risk in Diverse Populations

Screen-detected solid nodules: from detection of nodule to structured reporting.

Lung cancer screening (LCS) is gaining some interest worldwide after positive results from International trials. Unlike other screening practices, LCS is performed by an extremely sensitive test, namely low-dose computed tomography (LDCT) that can detect the smallest nodules in lung parenchyma. Up-to-date detection approaches, such as computer aided detection systems, have been increasingly employed for lung nodule automatic identification and are largely used in most LCS programs as a complementary tool to visual reading. Solid nodules of any size are represented in the vast majority of subjects undergoing LDCT. However, less than 1% of solid nodules will be diagnosed lung cancer. This fact calls for specific characterization of nodules to avoid false positives, overinvestigation, and reduce the risks associated with nodule work up. Recent research has been exploring the potential of artificial intelligence, including deep learning techniques, to enhance the accuracy of both detection and characterisation of lung nodule. Computer aided detection and diagnosis algorithms based on artificial intelligence approaches have demonstrated the ability to accurately detect and characterize parenchymal nodules, reducing the number of false positives, and to outperform some of the currently used risk models for prediction of lung cancer risk, potentially reducing the proportion of surveillance CT scans. These forthcoming approaches will eventually integrate a new reasoning for development of future guidelines, which are expected to evolve into precision and personalized stratification of lung cancer risk stratification by continuous fashion, as opposed to the current format with a limited number of risk classes within fixed thresholds of nodule size. This review aims to detail the standard of reference for optimal management of solid nodules by low-dose computed and its projection into the fine selection of candidates for work up.

Selection of individuals for lung cancer screening based on risk prediction model performance and economic factors – The Ontario experience

IntroductionRandomized controlled trials have shown that screening with computed tomography reduces lung cancer mortality but is most effective when applied to high-risk individuals. Accurate lung cancer risk prediction models effectively select individuals for screening. Few pilots or programs have implemented risk models for enrolling individuals for screening in real-world, population-based settings. This report describes implementation of the PLCOm2012 risk prediction model in the Ontario Health (Cancer Care Ontario) lung cancer screening Pilot. MethodsIn the Pilot’s Health Technology Assessment, 576 categorical age/pack-years/quit-years scenarios were evaluated using MISCAN microsimulation modeling and cost-effectiveness analyses. A preferred model was selected which provided the most life-years gained per cost. The PLCOm2012 was compared to the preferred MISCAN scenario at a threshold that yielded the same number eligible (risk ≥2.0 %/6-years). ResultsThe PLCOm2012 had significantly higher sensitivity and predictive value (68.1 % vs 59.6 %, p < 0.0001; 4.90 % vs 4.29 %, p = 0.044), and an Expert Panel selected it for use in the Pilot. The Pilot cancer detection rate was significantly higher than in the NLST (p = 0.009) or NELSON (p = 0.003) and there was a significant shift to early stage compared to historical Ontario Cancer Registry statistics (p < 0.0001). Pre- and post-Pilot evaluations found that conducting quality risk assessments were not excessively time consuming or difficult, and participants’ satisfaction was high. ConclusionsThe PLCOm2012 was efficiently implemented in the Pilot in a real-world setting and is being used to transition into a provincial program. Compared to categorical age/pack-years/quit-years criteria, risk assessment using the PLCOm2012 can lead to effective and efficient screening.

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.

ES12.01 Patient Perspective on Lung Cancer Screening and Health Disparities

Lung cancer is the leading cause of cancer deaths in much of the world. Over 80% of lung cancer deaths are caused by tobacco. Systematic reviews show smoking rates are higher in low socio-economic status individuals.(1) This is true even in low and middle income countries(2). In the United States Native Americans and Alaska Natives have the highest tobacco use; 32.3% of Native Americans/Alaska Natives use any tobacco product as compared to 21.9% of Whites. In Canada, the Intuit have the highest smoking rates; 74% of Intuits in Canada smoke as compared to 23% of non-Aboriginal individuals in Ontario.(3) Smoking rates in Australian Indigenous populations are about double those of Non-indigenous populations.(4) Indigenous/Native populations and Blacks are at higher risk of lung cancer than non-indigenous populations and Whites. They are diagnosed at a younger age and have higher lung cancer incidence and mortality rates. In the US, Black men have 15% higher lung cancer incidence rates and 19% higher mortality rates than whites. Overall US indigenous/native populations have 8.8% higher lung cancer incidence rates than non-Hispanic whites with local incidence rates up to 80% higher in Alaska Native, Southern and Northern Plain populations.(5) Similarly, in Australia indigenous populations have higher lung cancer incidence and mortality rates and a younger age at diagnosis. (4) In the Ontario province in Canada lung cancer incidence rates are 19% higher for indigenous men and 48% higher for indigenous women as compared to non-Indigenous men and women respectively. Mortality in indigenous men is 13% higher and 43% higher in women than non-indigenous men and women respectively.(6) Age and smoking history don’t capture everyone at equivalent risk. Blacks are less likely to meet current CT lung screening criteria in the US than whites. Aldrich et al. assessed eligibility for CT lung screening using 2013 USPSTF screening guidelines in the Southern Community Cohort.(7) In their sample of 48,364 individuals, 17% of Blacks were eligible for screening as compared to 31% of whites. In the subset diagnosed with lung cancer (n= 1269): 32% of Blacks would have been eligible for screening as compared to 56% of whites. The American Lung Association 2020 State of Lung Cancer Report shows US CT lung screening rates are still low. The national average is 5.7% with large state to state variation. Massachusetts has the highest screening rate at 18.5% and Utah the lowest at 1%. Significant challenges remain for patients, especially those in disadvantage populations. These include lack of access to care, lack of awareness of the option for screening, difficult to understand eligibility criteria, distrust of the medical community, stigma and implicit bias due to the close association with smoking, nihilism and low perceived risk of getting lung cancer. Disadvantaged populations experience double stigma; the stigma of their lung cancer and the stigma of their disadvantage. It’s imperative to address eligibility, awareness, and access to CT lung screening for Blacks, indigenous/native populations and other disadvantaged populations to avoid increasing the current mortality and morbidity disparity for these populations. Encouragingly, in the US, the USPSTF updated draft CT lung screening recommendations lower the age of eligibility from 55 to 50 and the smoking history from 30 to 20 pack years. This will help address the disparity in screening eligibility between Blacks and whites of equivalent risk. A better approach to screen those at highest equivalent risk is to use a lung cancer risk prediction model as part of eligibility criteria. Recommended interventions include: Implementation of outreach programs to raise awareness and to provide CT lung screening in underserved communities. A good example of this is the Crosbie et al. UK mobile van lung health check study (8) Develop relationships with national and local minority organizations and partner with native/indigenous community leaders Form multidisciplinary state/provincial/local CT lung screening coalitions and learning collaboratives. Share lessons learned. Include lung cancer risk prediction model risk score in eligibility criteria. Example approaches include the Cancer Care Ontario program in Canada and the International Lung Screening Trial. Education to address stigma and clinician implicit bias and nihilism. Position lung cancer screening as health choice, similar to mammography and colonoscopy, co-develop culturally tailored education materials, public health campaigns raising awareness about stigma and implicit bias including information on glamorization of smoking in the early days when many eligible for CT lung screening started smoking.

Combining pulmonary and cardiac computed tomography biomarkers for disease-specific risk modelling in lung cancer screening.

Combined assessment of cardiovascular disease (CVD), COPD and lung cancer may improve the effectiveness of lung cancer screening in smokers. The aims were to derive and assess risk models for predicting lung cancer incidence, CVD mortality and COPD mortality by combining quantitative computed tomography (CT) measures from each disease, and to quantify the added predictive benefit of self-reported patient characteristics given the availability of a CT scan. A survey model (patient characteristics only), CT model (CT information only) and final model (all variables) were derived for each outcome using parsimonious Cox regression on a sample from the National Lung Screening Trial (n=15 000). Validation was performed using Multicentric Italian Lung Detection data (n=2287). Time-dependent measures of model discrimination and calibration are reported. Age, mean lung density, emphysema score, bronchial wall thickness and aorta calcium volume are variables that contributed to all final models. Nodule features were crucial for lung cancer incidence predictions but did not contribute to CVD and COPD mortality prediction. In the derivation cohort, the lung cancer incidence CT model had a 5-year area under the receiver operating characteristic curve of 82.5% (95% CI 80.9-84.0%), significantly inferior to that of the final model (84.0%, 82.6-85.5%). However, the addition of patient characteristics did not improve the lung cancer incidence model performance in the validation cohort (CT model 80.1%, 74.2-86.0%; final model 79.9%, 73.9-85.8%). Similarly, the final CVD mortality model outperformed the other two models in the derivation cohort (survey model 74.9%, 72.7-77.1%; CT model 76.3%, 74.1-78.5%; final model 79.1%, 77.0-81.2%), but not the validation cohort (survey model 74.8%, 62.2-87.5%; CT model 72.1%, 61.1-83.2%; final model 72.2%, 60.4-84.0%). Combining patient characteristics and CT measures provided the largest increase in accuracy for the COPD mortality final model (92.3%, 90.1-94.5%) compared to either other model individually (survey model 87.5%, 84.3-90.6%; CT model 87.9%, 84.8-91.0%), but no external validation was performed due to a very low event frequency. CT measures of CVD and COPD provides small but reproducible improvements to nodule-based lung cancer risk prediction accuracy from 3 years onwards. Self-reported patient characteristics may not be of added predictive value when CT information is available.

Predictors of Lung Cancer Risk: An Ecological Study Using Mortality and Environmental Data by Municipalities in Italy.

Lung cancer (LC) mortality remains a consistent part of the total deaths occurring worldwide. Its etiology is complex as it involves multifactorial components. This work aims in providing an epidemiological assessment on occupational and environmental factors associated to LC risk by means of an ecological study involving the 8092 Italian municipalities for the period 2006–2015. We consider mortality data from mesothelioma as proxy of asbestos exposure, as well as PM2.5 and radon levels as a proxy of environmental origin. The compensated cases for occupational respiratory diseases, urbanization and deprivation were included as predictors. We used a negative binomial distribution for the response, with analysis stratified by gender. We estimated that asbestos is responsible for about 1.1% (95% CI: 0.8, 1.4) and 0.5% (95% CI: 0.2, 0.8) of LC mortality in males and females, respectively. The corresponding figures are 14.0% (95% CI: 12.5, 15.7) and 16.3% (95% CI: 16.2, 16.3) for PM2.5 exposure, and 3.9% (95% CI: 3.5, 4.2) and 1.6% (95% CI: 1.4, 1.7) for radon exposure. The assessment of determinants contribution to observed LC deaths is crucial for improving awareness of its origin, leading to increase the equity of the welfare system.

Performance of various risk prediction models in a large lung cancer screening cohort in Gdańsk, Poland-a comparative study.

BackgroundOptimal selection criteria for the lung cancer screening programme remain a matter of an open debate. We performed a validation study of the three most promising lung cancer risk prediction models in a large lung cancer screening cohort of 6,631 individuals from a single European centre.MethodsA total of 6,631 healthy volunteers (aged 50–79, smoking history ≥30 pack-years) were enrolled in the MOLTEST BIS programme between 2016 and 2018. Each participant underwent a low-dose computed chest tomography scan, and selected participants underwent a further diagnostic work-up. Various lung cancer prediction models were applied to the recruited screenees, i.e., (I) Tammemagi’s Prostate, Colorectal, and Ovarian Cancer Screening Trial 2012 (PLCOm2012), (II) Liverpool Lung Project (LLP) model, and (III) Bach’s lung cancer risk model. Patients (I) with 6-year lung cancer probability ≥1.3% were considered as high risk in PLCOm2012 model, (II) in LLP model with 5-year lung cancer probability ≥5.0%, and (III) in Bach’s model with 5-year lung cancer probability ≥2.0%. The particular model cut-off values were employed to the cohort to evaluate each model’s performance in the screened population.ResultsLung cancer was diagnosed in 154 (2.3%) participants. Based on the risk estimates by PLCOm2012, LLP and Bach’s models there were 82.4%, 50.3% and 19.8% of the MOLTEST BIS participants, respectively, who fulfilled the above-mentioned threshold criteria of a lung cancer development probability. Of those detected with lung cancer, 97.4%, 74.0% and 44.8% were eligible for screening by PLCOm2012, LLP and Bach’s model criteria, respectively. In Tammemagi’s risk prediction model only four cases (2.6%) would have been missed from the group of 154 lung cancer patients primarily detected in the MOLTEST BIS.ConclusionsLung cancer screening enrollment based on the risk prediction models is superior to NCCN Group 1 selection criteria and offers a clinically significant reduction of screenees with a comparable proportion of detected lung cancer cases. Tammemagi’s risk prediction model reduces the proportion of patients eligible for inclusion to a screening programme with a minimal loss of detected lung cancer cases.

Multi-Criteria Decision Support System for Lung Cancer Prediction

Lung cancer is one of the most common deadly malignant tumours, with the most rapid morbidity and death worldwide. Cancer risk prediction is a challenging and complex task in the field of healthcare. Many studies have been carried out by researchers to analyse and establish lung cancer symptoms and factors. However, further improvements are vital and required to be conducted in order to overcome the persistent challenges. In this study, a multi-criteria decision support system for lung cancer risk prediction based on a web-based survey data has been presented and realised. The proposed framework aims to incorporate the powerful of analytical hierarchy process (AHP) with artificial neural network for constituting lung cancer prediction model. The multiple criteria decision-making strategy (AHP) assigns a weight to each individual cancer symptom feature from survey data. The weighted features are then used to train multi-layer perceptron artificial neural network (ANN) to build a disease prediction model. Experimental analysis and evaluation performed on 276 subjects revealed promising prediction performance of developed lung cancer prediction framework in terms of various classification metrics.

Liverpool Lung Project lung cancer risk stratification model: calibration and prospective validation

BackgroundEarly detection of lung cancer saves lives, as demonstrated by the two largest published low-dose CT screening trials. Optimal implementation depends on our ability to identify those most at risk.MethodsVersion...

Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine.

Medical imaging is the standard-of-care for early detection, diagnosis, treatment planning, monitoring, and image-guided interventions of lung cancer patients. Most medical images are stored digitally in a standardized Digital Imaging and Communications in Medicine format that can be readily accessed and used for qualitative and quantitative analysis. Over the several last decades, medical images have been shown to contain complementary and interchangeable data orthogonal to other sources such as pathology, hematology, genomics, and/or proteomics. As such, "radiomics" has emerged as a field of research that involves the process of converting standard-of-care images into quantitative image-based data that can be merged with other data sources and subsequently analyzed using conventional biostatistics or artificial intelligence (AI) methods. As radiomic features capture biological and pathophysiological information, these quantitative radiomic features have shown to provide rapid and accurate noninvasive biomarkers for lung cancer risk prediction, diagnostics, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics and emerging AI methods in lung cancer research are highlighted and discussed including advantages, challenges, and pitfalls.

Quantitative Emphysema on Low-Dose CT Imaging of the Chest and Risk of Lung Cancer and Airflow Obstruction: An Analysis of the National Lung Screening Trial

Lung cancer risk prediction models do not routinely incorporate imaging metrics available on low-dose CT (LDCT) imaging of the chest ordered for lung cancer screening. What is the association between quantitative emphysema measured on LDCT imaging and lung cancer incidence and mortality, all-cause mortality, and airflow obstruction in individuals who currently or formerly smoked and are undergoing lung cancer screening? In 7,262 participants in the CT arm of the National Lung Screening Trial, percent low attenuation area (%LAA) was defined as the percentage of lung volume with voxels less than -950 Hounsfield units on the baseline examination. Multivariable Cox proportional hazards models, adjusting for competing risks where appropriate, were built to test for association between %LAA and lung cancer incidence, lung cancer mortality, and all-cause mortality with censoring at 6 years. In addition, multivariable logistic regression models were built to test the cross-sectional association between %LAA and airflow obstruction on spirometry, which was available in 2,700 participants. The median %LAA was 0.8%(interquartile range, 0.2%-2.7%). Every 1%increase in %LAA was independently associated with higher hazards of lung cancer incidence (hazard ratio [HR], 1.02; 95%CI, 1.01-1.03; P= .004), lung cancer mortality (HR, 1.02; 95%CI, 1.00-1.05; P= .045), and all-cause mortality (HR, 1.01; 95%CI, 1.00-1.03; P= .042). Among participants with spirometry, 892 had airflow obstruction. The likelihood of airflow obstruction increased with every 1%increase in %LAA (odds ratio, 1.07; 95%CI, 1.06-1.09; P< .001). A %LAA cutoff of 1%had the best discriminative accuracy for airflow obstruction in participants aged > 65 years. Quantitative emphysema measured on LDCT imaging of the chest can be leveraged to improve lung cancer risk prediction and help diagnose COPD in individuals who currently or formerly smoked and are undergoing lung cancer screening.

Lung cancer screening by low-dose computed tomography: a cost-effectiveness analysis of alternative programmes in the UK using a newly developed natural history-based economic model

BackgroundA systematic review of economic evaluations for lung cancer identified no economic models of the UK setting based on disease natural history. We first sought to develop a new model of natural history for population screening, then sought to explore the cost-effectiveness of multiple alternative potential programmes.MethodsAn individual patient model (ENaBL) was constructed in MS Excel® and calibrated against data from the US National Lung Screening Trial. Costs were taken from the UK Lung Cancer Screening Trial and took the perspective of the NHS and PSS. Simulants were current or former smokers aged between 55 and 80 years and so at a higher risk of lung cancer relative to the general population. Subgroups were defined by further restricting age and risk of lung cancer as predicted by patient self-questionnaire. Programme designs were single, triple, annual and biennial arrangements of LDCT screens, thereby examining number and interval length. Forty-eight distinct screening strategies were compared to the current practice of no screening. The primary outcome was incremental cost-effectiveness of strategies (additional cost per QALY gained).ResultsLDCT screening is predicted to bring forward the stage distribution at diagnosis and reduce lung cancer mortality, with decreases versus no screening ranging from 4.2 to 7.7% depending on screen frequency. Overall healthcare costs are predicted to increase; treatment cost savings from earlier detection are outweighed by the costs of over-diagnosis. Single-screen programmes for people 55–75 or 60–75 years with ≥ 3% predicted lung cancer risk may be cost-effective at the £30,000 per QALY threshold (respective ICERs of £28,784 and £28,169 per QALY gained). Annual and biennial screening programmes were not predicted to be cost-effective at any cost-effectiveness threshold.LimitationsLDCT performance was unaffected by lung cancer type, stage or location and the impact of a national screening programme of smoking behaviour was not included.ConclusionLung cancer screening may not be cost-effective at the threshold of £20,000 per QALY commonly used in the UK but may be cost-effective at the higher threshold of £30,000 per QALY.

Exploratory research on developing lung cancer risk prediction model in female non-smokers

Objective: To develop a lung cancer risk prediction model for female non-smokers. Methods: Based on the Kailuan prospective dynamic cohort (2006.05-2015.12), a nested case-control study was conducted. Participants diagnosed with primary pathologically confirmed lung cancer during follow-up were identified as the case group, and others were identified as the control group. A total of 24 701 subjects were included in the study, including 86 lung cancer cases and 24 615 control population, respectively. Questionnaires, physical examinations, and laboratory tests were conducted to collect relevant information. Multivariable-adjusted logistic regressions were conducted to develop a lung cancer risk prediction model. Area Under the Curve (AUC) and Hosmer-Lemeshow tests were used to evaluate discrimination and calibration, respectively. Ten-fold cross-validation was used for internal validation. Results: Two sets of models were developed: the simple model (including age and monthly income) and the metabolic index model [including age, monthly income, fasting blood glucose (FBG), total cholesterol (TC) and high-density lipoprotein cholesterol (HDL-C)].The AUC (95%CI) [0.745 (0.719-0.771)] of the metabolic index model was higher than that of the simple prediction model [0.688 (0.660-0.716)] (P=0.004). Both the simple model (PHL=0.287) and the metabolic index model (PHL=0.134) were well-calibrated. The results of ten-fold cross-validation indicated sufficient stability, with an average AUC of 0.699 and a standard error (SD) of 0.010. Conclusion: By incorporating metabolic markers, accurate and reliable lung cancer risk prediction model for female non smokers could be developed.

Contribution of a Blood-Based Protein Biomarker Panel to the Classification of Indeterminate Pulmonary Nodules.

The workup and longitudinal monitoring for subjects presenting with pulmonary nodules is a pressing clinical problem. A blood-based biomarker panel potentially has utility for identifying subjects at higher risk for harboring a malignant nodule for whom additional workup would be indicated or subjects at reduced risk for whom imaging-based follow-up would be indicated. To assess whether a previously described four-protein biomarker panel, reported to improve assessment of lung cancer risk compared with a smoking-based lung cancer risk model, can provide discrimination between benign and malignant indeterminate pulmonary nodules. A previously validated multiplex enzyme-linked immunoassay was performed on matched case and control samples from each cohort. The biomarker panel was tested in two case-control cohorts of patients presenting with indeterminate pulmonary nodules at the University of Pittsburgh Medical Center and the University of Texas Southwestern. In both cohorts, the biomarker panel resulted in improved prediction of lung cancer risk over a model on the basis of nodule size alone. Of particular note, the addition of the marker panel to nodule size greatly improved sensitivity at a high specificity in both cohorts. A four-marker biomarker panel, previously validated to improve lung cancer risk prediction, was found to also have utility in distinguishing benign from malignant indeterminate pulmonary nodules. Its performance in improving sensitivity at a high specificity indicates potential utility of the marker panel in assessing likelihood of malignancy in otherwise indeterminate nodules.