Lung Cancer Risk Prediction Research Articles

CN16 Lung cancer risk prediction nomogram in Chinese female non-smokers

About 53% of lung cancers in females are not attributable to smoking worldwide. The aim was to develop and validate a simple and non-invasive model which could assess and stratify lung cancer risk in female non-smokers in China. A large-sample size, population-based study was conducted under the framework of a population-based Cancer Screening Program in Urban China (CanSPUC). Data on the lung cancer screening in Henan province, China, from October 2013 to October 2019 were used and randomly divided into the training and validation sets. Related risk factors were identified through multivariable Cox regression analysis, followed by establishment of risk prediction nomogram. Discrimination [area under the curve (AUC)] and calibration were further performed to assess the validation of risk prediction nomogram in the training set, and then validated by the validation set. A total of 151,834 eligible subjects were included, with a mean age of 55.34 years. Subjects were randomly divided into the training (75,917) and validation (75,917) sets. Elder age, history of chronic respiratory disease, first-degree family history of lung cancer, menopause, and history of benign breast disease were the independent risk factors for lung cancer. Using these five variables, we plotted 1-year, 3-year, and 5-year lung cancer risk prediction nomogram. The AUC was 0.762, 0.718, and 0.703 for the 1-, 3- and 5-year lung cancer risk in the training set, respectively. In the validation set, the model showed a good predictive discrimination, with the AUC was 0.646, 0.658, and 0.650 for the 1-, 3- and 5-year lung cancer risk. We developed and validated a simple and non-invasive lung cancer risk model in female non-smokers. This model can be applied to identify and triage patients at high risk for developing lung cancers in female non-smokers.

OA13.05 Lung Cancer Risk Prediction Nomogram in Chinese Female Non-smokers

About 53% of lung cancers in females are not attributable to smoking worldwide. The aim was to develop and validate a simple and non-invasive model which could assess and stratify lung cancer risk in female non-smokers in China.

Screening Criteria Evaluation for Expansion in Pulmonary Neoplasias (SCREEN)

The SCREEN study investigated screening eligibility and survival outcomes between heavy smokers and light-or-never-smokers with lung cancer to determine whether expanded risk factor analysis is needed to refine screening criteria. SCREEN is a retrospective study of 917 lung cancer patients diagnosed between 2005 and 2018 in Nova Scotia, Canada. Screening eligibility was determined using the National Lung Screening Trial (NSLT) criteria. Mortality risk between heavy smokers and light-or-never-smokers was compared using proportional-hazards models. The median follow-up was 2.9 years. The cohort was comprised of 179 (46.1%) female heavy smokers and 306 (57.8%) female light-or-never-smokers. Light-or-never-smokers were more likely to have a diagnosis of adenocarcinoma [n=378 (71.6%)] compared to heavy smokers [n=234 (60.5%); P< 0.001]. Heavy smokers were more frequently diagnosed with squamous cell carcinoma [n=111 (28.7%)] compared to light-or-never-smokers, [n=100 (18.9%); P< 0.001]. Overall, 36.9% (338) of patients met NLST screening criteria. There was no difference in 5-year survival between light-or-never-smokers and heavy smokers [55.2% (338) vs 58.5% (529); P = 0.408; HR 1.06, 95% CI 0.80-1.40; P = 0.704]. Multivariate analysis showed that males had an increased mortality risk [HR 2.00 (95% CI 1.57-2.54); P< 0.001]. Half of lung cancer patients were missed with the conventional screening criteria. There were more curable, stage 1 tumors among light-or-never-smokers. Smoking status and age alone may be insufficient predictors of lung cancer risk and prognosis. Expanded risk factor analysis is needed to refine lung cancer screening criteria.

Higher order genes interaction in DNA repair and cytokine genes polymorphism and risk to lung cancer in North Indians.

Lung cancer pathological process involves cumulative effects exerted by gene polymorphism(s), epigenetic modifications, and alterations in DNA repair machinery. Further, DNA damage due to oxidative stress, chronic inflammation, and the interplay between genetic and environmental factors is also an etiologic milieu of this malignant disease. The present study aims to assess the prognostic value of DNA repair, cytokines, and GST gene polymorphism in lung cancer patients who had not received any neoadjuvant therapy. In this case-control study, 127 cases and 120 controls were enrolled. DNA from the blood samples of both patients and controls was used to genotype XRCC1Arg399Gln, XPDLys751Gln, and interleukin-1 (IL-1β) genes by polymerase chain reaction (PCR)-restriction fragment length polymorphism method, whereas multiplex PCR was performed to genotype GSTT1 and GSTM1. Binary logistic regression analysis showed that XRCC1Arg399Gln-mutant genotype (Gln/Gln, odds ratio [OR] = 4.6, 95% confidence interval [CI]: 2.2-9.6) and GSTT1 null (OR = 2.7, 95% CI: 1.6-4.5) were linked to cancer susceptibility. Generalized multidimensional reduction analysis of higher order gene-gene interaction using cross-validation testing (CVT) accuracy showed that GSTT1 (CVT 0.62, P = 0.001), XPD751 and IL-1β (CVT 0.6, P = 0.001), and XRCC1399, XPD751, and interleukin-1 receptor antagonists (IL-1RN) (CVT 0.98, P = 0.001) were single-, two-, and three-factor best model predicted, respectively, for lung cancer risk. Classification and regression tree analysis results showed that terminal nodes which contain XRCC1399-mutant genotype (AA) had increased the risk to lung cancer. The present study demonstrated that XRCC1399 (Gln/Gln), GSTT1, and IL-1RN allele I, I/II served as the risk genotypes. These genes could serve as the biomarkers to predict lung cancer risk.

Lung cancer risk prediction nomogram in Chinese female non-smokers.

10530 Background: About 53% of lung cancers in females are not attributable to smoking worldwide. The aim was to develop and validate a simple and non-invasive model which could assess and stratify lung cancer risk in female non-smokers in China. Methods: A large-sample size, population-based study was conducted under the framework of a population-based Cancer Screening Program in Urban China (CanSPUC). Data on the lung cancer screening in Henan province, China, from October 2013 to October 2019 were used and randomly divided into the training and validation sets. Related risk factors were identified through multivariable Cox regression analysis, followed by establishment of risk prediction nomogram. Discrimination [area under the curve (AUC)] and calibration were further performed to assess the validation of risk prediction nomogram in the training set, and then validated by the validation set. Results: A total of 151,834 eligible subjects were included, with a mean age of 55.34 years. Subjects were randomly divided into the training (75,917) and validation (75,917) sets. Elder age, history of chronic respiratory disease, first-degree family history of lung cancer, menopause, and history of benign breast disease were the independent risk factors for lung cancer. Using these five variables, we plotted 1-year, 3-year, and 5-year lung cancer risk prediction nomogram. The AUC was 0.762, 0.718, and 0.703 for the 1-, 3- and 5-year lung cancer risk in the training set, respectively. In the validation set, the model showed a good predictive discrimination, with the AUC was 0.646, 0.658, and 0.650 for the 1-, 3- and 5-year lung cancer risk. Conclusions: We developed and validated a simple and non-invasive lung cancer risk model in female non-smokers. This model can be applied to identify and triage patients at high risk for developing lung cancers in female non-smokers.

Clinical validation of a deep-learning–based model to predict lung cancer risk from chest X-rays.

10507 Background: Screening with chest CT prevents lung cancer death, but only 5% of eligible Americans are screened. The updated 2022 Centers for Medicare and Medicaid Services (CMS) criteria expand eligibility to 50-77 year-olds, current or former (&lt;15 years) smokers, with a ≥20 pack-year history. However, smoking quit date and pack-years are often not available in the electronic medical record (EMR), stymying identification of high-risk smokers for lung cancer screening (LCS). We previously developed a free, open-source deep-learning model (CXR-LC) that identifies smokers at high risk of lung cancer better than the 2015 CMS criteria, based on a chest X-ray (CXR) image automatically extracted from the EMR. CXR-LC was developed in the PLCO trial, an asymptomatic LCS population. The present study externally validates CXR-LC using existing CXRs obtained through usual care and compares CXR-LC to the expanded 2022 CMS lung screening eligibility criteria. Methods: Current or former smokers who had a routine clinical CXR in 2013-2014 were included. Patients with known lung cancer or who were undergoing LCS were excluded. Smoking status and 2022 CMS LCS eligibility were determined by manual review of the EMR. The primary outcome was 6-year incident lung cancer, identified using International Classification of Disease (ICD) codes and confirmed through discharge summaries and pathology reports. The CXR-LC model and the 2022 CMS eligibility criteria were compared for prediction of 6-year incident lung cancer. Results: Among 10,784 patients (mean age 63.1± 6.8 years; 61.0% male), CMS eligibility could be determined in 45% (4,886/10,784), with 55% missing pack-year or quit date data. In this population, 3.9% (191/4,886) developed lung cancer. The 2022 CMS criteria missed 57% (109/191) of lung cancers, while CXR-LC missed 8.9% (17/191, p &lt; 0.001). After adjusting for sex, race, and prevalent COPD, the hazard ratio for CXR-LC eligibility (3.6, 95% CI [2.2,6.0]) was greater than for CMS eligibility (2.7, 95% CI [2.0,3.7]). In the 5,897 patients for whom CMS eligibility could not be determined, CXR-LC eligible patients had a 3-fold higher rate of lung cancer than CXR-LC ineligible patients (3.8% vs. 1.3%, p &lt; 0.001). All CXR-LC eligible groups had 6-year lung cancer incidence &gt;3.5%, above accepted screening risk thresholds of &gt;1.5% and &gt;2%. Conclusions: Using routine CXRs from the EMR, CXR-LC identified high-risk smokers who may benefit from LCS with CT, complementary to the 2022 CMS eligibility criteria. [Table: see text]

Assessment of background levels of autoantibodies as a prognostic marker for severe SARS-CoV-2 infection.

Background: Patients with more severe forms of SARS-CoV-2 exhibit activation of immunological cascades. Participants (current or ex-smokers with at least 20 years pack history) in a trial (Early Diagnosis of Lung Cancer, Scotland [ECLS]) of autoantibody detection to predict lung cancer risk had seven autoantibodies measured 5 years before the pandemic. This study compared the response to Covid infection in study participants who tested positive and negative to antibodies to tumour-associated antigens: p53, NY-ESO-1, CAGE, GBU4-5, HuD, MAGE A4 and SOX2. Methods: Autoantibody data from the ECLS study was deterministically linked to the EAVE II database, a national, real-time prospective cohort using Scotland’s health data infrastructure, to describe the epidemiology of SARS-CoV-2 infection, patterns of healthcare use and outcomes. The strength of associations was explored using a network algorithm for exact contingency table significance testing by permutation. Results: There were no significant differences discerned between SARS-CoV-2 test results and EarlyCDT-Lung test results (p = 0.734). An additional analysis of intensive care unit (ICU) admissions detected no significant differences between those who tested positive and negative. Subgroup analyses showed no difference in COVID-19 positivity or death rates amongst those diagnosed with chronic obstructive pulmonary disease (COPD) with positive and negative EarlyCDT results. Conclusions: This hypothesis-generating study demonstrated no clinically valuable or statistically significant associations between EarlyCDT positivity in 2013-15 and the likelihood of SARS-CoV-2 positivity in 2020, ICU admission or death in all participants (current or ex-smokers with at least 20 years pack history) or in those with COPD or lung cancer.

Potential of Inflammatory Protein Signatures for Enhanced Selection of People for Lung Cancer Screening.

Simple SummarySelection of appropriate high-risk smokers is one of the major challenges for implementing low-dose computed tomography screening for lung cancer. Many lung cancer risk prediction models have been proposed to supplement lung cancer screening. This study evaluated the potential of inflammatory protein markers to enhance lung cancer risk stratification beyond lung cancer risk models. The addition of inflammatory protein markers to existing lung cancer risk models improved risk prediction. The inflammatory protein markers may enhance current risk stratification and may be useful to identify high-risk populations for lung cancer screening.Randomized trials have demonstrated a substantial reduction in lung cancer (LC) mortality by screening heavy smokers with low-dose computed tomography (LDCT). The aim of this study was to assess if and to what extent blood-based inflammatory protein biomarkers might enhance selection of those at highest risk for LC screening. Ever smoking participants were chosen from 9940 participants, aged 50–75 years, who were followed up with respect to LC incidence for 17 years in a prospective population-based cohort study conducted in Saarland, Germany. Using proximity extension assay, 92 inflammation protein biomarkers were measured in baseline plasma samples of ever smoking participants, including 172 incident LC cases and 285 randomly selected participants free of LC. Smoothly clipped absolute deviation (SCAD) penalized regression with 0.632+ bootstrap for correction of overoptimism was applied to derive an inflammation protein biomarker score (INS) and a combined INS-pack-years score in a training set, and algorithms were further evaluated in an independent validation set. Furthermore, the performances of nine LC risk prediction models individually and in combination with inflammatory plasma protein biomarkers for predicting LC incidence were comparatively evaluated. The combined INS-pack-years score predicted LC incidence with area under the curves (AUCs) of 0.811 and 0.782 in the training and the validation sets, respectively. The addition of inflammatory plasma protein biomarkers to established nine LC risk models increased the AUCs up to 0.121 and 0.070 among ever smoking participants from training and validation sets, respectively. Our results suggest that inflammatory protein biomarkers may have potential to improve the selection of people for LC screening and thereby enhance screening efficiency.

THE EFFECTIVENESS ANALYSIS OF RANDOM FOREST ALGORITHMS WITH SMOTE TECHNIQUE IN PREDICTING LUNG CANCER RISK

When compared with other types of cancer, most of the population with cancer die from lung cancer.A person needs to do a screening test through X-rays, CT scans, and MRI to detect the disease. However, before carrying out the process, the doctor will ordinarily investigate a medical history and physical examination first to study the symptoms and possible risk factors for lung cancer. The lung cancer data set has a class imbalance that affects the performance of the random forest algorithm in predicting the risk of lung cancer. This study aims to employ the SMOTE technique to the random forest algorithm to increase accuracy in predicting lung cancer risk. In this research, data processing and analysis use the Python programming language. The test results show an accuracy value of 88% with an AUC value of 0.93. When employing the random forest method to forecast lung cancer risk, the SMOTE technique is useful in dealing with class imbalances in the data set.

Developing an understanding of artificial intelligence lung nodule risk prediction using insights from the Brock model

ObjectivesTo determine if predictions of the Lung Cancer Prediction convolutional neural network (LCP-CNN) artificial intelligence (AI) model are analogous to the Brock model.MethodsIn total, 10,485 lung nodules in 4660 participants from the National Lung Screening Trial (NLST) were analysed. Both manual and automated nodule measurements were inputted into the Brock model, and this was compared to LCP-CNN. The performance of an experimental AI model was tested after ablating imaging features in a manner analogous to removing predictors from the Brock model. First, the nodule was ablated leaving lung parenchyma only. Second, a sphere of the same size as the nodule was implanted in the parenchyma. Third, internal texture of both nodule and parenchyma was ablated.ResultsAutomated axial diameter (AUC 0.883) and automated equivalent spherical diameter (AUC 0.896) significantly improved the accuracy of Brock when compared to manual measurement (AUC 0.873), although not to the level of the LCP-CNN (AUC 0.936). Ablating nodule and parenchyma texture (AUC 0.915) led to a small drop in AI predictive accuracy, as did implanting a sphere of the same size as the nodule (AUC 0.889). Ablating the nodule leaving parenchyma only led to a large drop in AI performance (AUC 0.717).ConclusionsFeature ablation is a feasible technique for understanding AI model predictions. Nodule size and morphology play the largest role in AI prediction, with nodule internal texture and background parenchyma playing a limited role. This is broadly analogous to the relative importance of morphological factors over clinical factors within the Brock model.Key Points• Brock lung cancer risk prediction accuracy was significantly improved using automated axial or equivalent spherical measurements of lung nodule diameter, when compared to manual measurements.• Predictive accuracy was further improved by using the Lung Cancer Prediction convolutional neural network, an artificial intelligence-based model which obviates the requirement for nodule measurement.• Nodule size and morphology are important factors in artificial intelligence lung cancer risk prediction, with nodule texture and background parenchyma contributing a small, but measurable, role.

Lung cancer risk prediction models based on pulmonary nodules: A systematic review.

BackgroundScreening with low‐dose computed tomography (LDCT) is an efficient way to detect lung cancer at an earlier stage, but has a high false‐positive rate. Several pulmonary nodules risk prediction models were developed to solve the problem. This systematic review aimed to compare the quality and accuracy of these models.MethodsThe keywords “lung cancer,” “lung neoplasms,” “lung tumor,” “risk,” “lung carcinoma” “risk,” “predict,” “assessment,” and “nodule” were used to identify relevant articles published before February 2021. All studies with multivariate risk models developed and validated on human LDCT data were included. Informal publications or studies with incomplete procedures were excluded. Information was extracted from each publication and assessed.ResultsA total of 41 articles and 43 models were included. External validation was performed for 23.2% (10/43) models. Deep learning algorithms were applied in 62.8% (27/43) models; 60.0% (15/25) deep learning based researches compared their algorithms with traditional methods, and received better discrimination. Models based on Asian and Chinese populations were usually built on single‐center or small sample retrospective studies, and the majority of the Asian models (12/15, 80.0%) were not validated using external datasets.ConclusionThe existing models showed good discrimination for identifying high‐risk pulmonary nodules, but lacked external validation. Deep learning algorithms are increasingly being used with good performance. More researches are required to improve the quality of deep learning models, particularly for the Asian population.

Prediction of lung cancer risk based on age and smoking history

Background and ObjectiveThe CISNET models provide predictions for dying of lung cancer in any year of life as a function of age and smoking history, but their predictions are quite variable and the models themselves can be complex to implement. Our goal was to develop a simple empirical model of the risk of dying of lung cancer that is mathematically constrained to produce biologically appropriate probability predictions as a function of current age, smoking start age, quit age, and smoking intensity. MethodsThe six adjustable parameters of the model were evaluated by fitting its predictions of cancer death risk versus age to the mean of published predictions made by the CISNET models for the never smoker and for six different scenarios of lifetime smoking burden. ResultsThe mean RMS fitting error of the model was 6.16 × 10 -2 (% risk of dying of cancer per year of life) between 55 and 80 years of age. The model predictions increased monotonically with current age, quit age and smoking intensity, and decreased with increasing start age. ConclusionsOur simple model of the risk of dying of lung cancer in any given year of life as a function of smoking history is easily implemented and thus may serve as a useful tool in situations where the mortality risks of smoking need to be estimated.

Baseline computed tomography screening and blood microRNA predict lung cancer risk and define adequate intervals in the BioMILD trial

Large randomized trials have demonstrated that lung cancer (LC) screening with low-dose computed tomography (LDCT) reduces LC mortality in heavy smokers. We previously showed in the MILD screening trial that the combination of a prespecified circulating microRNA (miRNA) signature classifier (MSC) and LDCT improves the accuracy of LDCT alone. The primary aim of the prospective BioMILD study was to assess the additional value of the blood MSC assay at the time of baseline LDCT with the goal of personalizing LC screening intervals. The study enrolled 4119 volunteers from January 2013 to March 2016, with a median follow-up of 5.3 years. Baseline LDCT and miRNAs stratified participants into four groups: CT-/MSC- (n= 2664; 64.7%); CT-/MSC+ (n= 800; 19.4%); CT+/MSC- (n= 446; 10.8%); and CT+/MSC+ (n= 209; 5.1%). As per the protocol, those in the CT-/MSC- and CT-/MSC+ groups were allocated to LDCT repeat at 3-year and 1-year intervals; CT+ participants were allocated for 1-year or earlier intervals on the basis of LDCT features independent of MSC results. CT+ participants had a 15.8-fold higher 4-year LC incidence than CT- participants (95% confidence interval 10.34-24.05), and MSC+ participants had a 2.0-fold higher 4-year LC incidence than MSC- participants (95% confidence interval 1.40-2.90); there was no evidence that the MSC effect differed between CT+ and CT- participants. LC incidence at 4 years was 0.8% in CT-/MSC-, 1.1% in CT-/MSC+, 10.8% in CT+/MSC-, and 20.1% in CT+/MSC+ participants. LC mortality rates at 5 years in the four risk groups were 0.5 in CT-/MSC-, 1.5 in CT-/MSC+, 4.2 in CT+/MSC-, and 10.1 in CT+/MSC+. The combined use of LDCT and blood miRNAs at baseline predicts individual LC incidence and mortality, with a major effect of MSC for LDCT-positive individuals. These findings may have important implications in personalizing screening intervals.

Blood-Based Biomarker Panel for Personalized Lung Cancer Risk Assessment.

To investigate whether a panel of circulating protein biomarkers would improve risk assessment for lung cancer screening in combination with a risk model on the basis of participant characteristics. A blinded validation study was performed using prostate lung colorectal ovarian (PLCO) Cancer Screening Trial data and biospecimens to evaluate the performance of a four-marker protein panel (4MP) consisting of the precursor form of surfactant protein B, cancer antigen 125, carcinoembryonic antigen, and cytokeratin-19 fragment in combination with a lung cancer risk prediction model (PLCOm2012) compared with current US Preventive Services Task Force (USPSTF) screening criteria. The 4MP was assayed in 1,299 sera collected preceding lung cancer diagnosis and 8,709 noncase sera. The 4MP alone yielded an area under the receiver operating characteristic curve of 0.79 (95% CI, 0.77 to 0.82) for case sera collected within 1-year preceding diagnosis and 0.74 (95% CI, 0.72 to 0.76) among the entire specimen set. The combined 4MP + PLCOm2012 model yielded an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.82 to 0.88) for case sera collected within 1 year preceding diagnosis. The benefit of the 4MP in the combined model resulted from improvement in sensitivity at high specificity. Compared with the USPSTF2021 criteria, the combined 4MP + PLCOm2012 model exhibited statistically significant improvements in sensitivity and specificity. Among PLCO participants with ≥ 10 smoking pack-years, the 4MP + PLCOm2012 model would have identified for annual screening 9.2% more lung cancer cases and would have reduced referral by 13.7% among noncases compared with USPSTF2021 criteria. A blood-based biomarker panel in combination with PLCOm2012 significantly improves lung cancer risk assessment for lung cancer screening.

Construction and Validation of a Lung Cancer Risk Prediction Model for Non-Smokers in China.

BackgroundAbout 15% of lung cancers in men and 53% in women are not attributable to smoking worldwide. The aim was to develop and validate a simple and non-invasive model which could assess and stratify lung cancer risk in non-smokers in China.MethodsA large-sample size, population-based study was conducted under the framework of the Cancer Screening Program in Urban China (CanSPUC). Data on the lung cancer screening in Henan province, China, from October 2013 to October 2019 were used and randomly divided into the training and validation sets. Related risk factors were identified through multivariable Cox regression analysis, followed by establishment of risk prediction nomogram. Discrimination [area under the curve (AUC)] and calibration were further performed to assess the validation of risk prediction nomogram in the training set, and then validated by the validation set.ResultsA total of 214,764 eligible subjects were included, with a mean age of 55.19 years. Subjects were randomly divided into the training (107,382) and validation (107,382) sets. Elder age, being male, a low education level, family history of lung cancer, history of tuberculosis, and without a history of hyperlipidemia were the independent risk factors for lung cancer. Using these six variables, we plotted 1-year, 3-year, and 5-year lung cancer risk prediction nomogram. The AUC was 0.753, 0.752, and 0.755 for the 1-, 3- and 5-year lung cancer risk in the training set, respectively. In the validation set, the model showed a moderate predictive discrimination, with the AUC was 0.668, 0.678, and 0.685 for the 1-, 3- and 5-year lung cancer risk.ConclusionsWe developed and validated a simple and non-invasive lung cancer risk model in non-smokers. This model can be applied to identify and triage patients at high risk for developing lung cancers in non-smokers.

The Value of Blood-Based Measures of Liver Function and Urate in Lung Cancer Risk Prediction: A Cohort Study and Health Economic Analysis

The Value of Blood-Based Measures of Liver Function and Urate in Lung Cancer Risk Prediction: A Cohort Study and Health Economic Analysis

CRPMKB: a knowledge base of cancer risk prediction models for systematic comparison and personalized applications.

In the era of big data and precision medicine, accurate risk assessment is a prerequisite for the implementation of risk screening and preventive treatment. A large number of studies have focused on the risk of cancer, and related risk prediction models have been constructed, but there is a lack of effective resource integration for systematic comparison and personalized applications. Therefore, the establishment and analysis of the cancer risk prediction model knowledge base (CRPMKB) is of great significance. The current knowledge base contains 802 model data. The model comparison indicates that the accuracy of cancer risk prediction was greatly affected by regional differences, cancer types and model types. We divided the model variables into four categories: environment, behavioral lifestyle, biological genetics and clinical examination, and found that there are differences in the distribution of various variables among different cancer types. Taking 50 genes involved in the lung cancer risk prediction models as an example to perform pathway enrichment analyses and the results showed that these genes were significantly enriched in p53 Signaling and Aryl Hydrocarbon Receptor Signaling pathways which are associated with cancer and specific diseases. In addition, we verified the biological significance of overlapping lung cancer genes via STRING database. CRPMKB was established to provide researchers an online tool for the future personalized model application and developing. This study of CRPMKB suggests that developing more targeted models based on specific demographic characteristics and cancer types will further improve the accuracy of cancer risk model predictions. CRPMKB is freely available at http://www.sysbio.org.cn/CRPMKB/. The data underlying this article are available in the article and in its online supplementary material. Supplementary data are available at Bioinformatics online.

Characterization of adductomic totality of NNK, (R)-NNAL and (S)-NNAL in A/J mice, and their correlations with distinct lung carcinogenicity.

Lung cancer is the leading cause of cancer-related deaths. While tobacco use is the main cause, only 10-20% of smokers eventually develop clinical lung cancer. Thus, the ability of lung cancer risk prediction among smokers could transform lung cancer management with early preventive interventions. Given that DNA damage by tobacco carcinogens is the potential root cause of lung carcinogenesis, we characterized the adductomic totality of 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanone (a potent lung carcinogen in tobacco, commonly known as NNK) in the target lung tissues, the liver tissues and the peripheral serum samples in a single-dose NNK-induced lung carcinogenesis A/J mouse model. We also characterized these adductomic totalities from the two enantiomers of 4-(methylnitrosamino)-1-(3-pyridyl)-1-butanol (NNAL, the major in vivo metabolite of NNK) given their distinct carcinogenicity in A/J mice. With these adductomic data, we demonstrated that tissue protein adductomics have the highest abundance. We also identified that the adductomic levels at the 8h time point after carcinogen exposure were among the highest. More importantly, the relationships among these adductomics were characterized with overall strong positive linear correlations, demonstrating the potential of using peripheral serum protein adductomics to reflect DNA adductomics in the target lung tissues. Lastly, we explored the relationships of these adductomics with lung tumor status in A/J mice, providing preliminary but promising evidence of the feasibility of lung cancer risk prediction using peripheral adductomic profiling.

Risk-based prediction model for selecting eligible population for lung cancer screening among ever smokers in Korea.

BackgroundThis study developed a new lung cancer risk prediction model for the Korean population and evaluated the performance, compared to the previously reported risk models developed in Western countries.MethodsAmong the 6,811,893 people who received health examinations from the Korean National Health Insurance Service, 969,351 ever-smokers (40–79 years) were included. Performance of Bach, Lung Cancer Risk Models for Screening, PLCOM2012, Pittsburgh, and Liverpool Lung Project models were evaluated. The ever-smokers were divided into the training and validation datasets by random sampling. The lung cancer risk model was developed and validated in the Korean population. The efficiency of model-based selection for lung cancer screening was compared with the eligible criteria of the National Lung Screening Trial (NLST).ResultsThe Korean lung cancer risk model showed the area under the curve and expected/observed (E/O) ratio of 0.816 and 0.983 in the training dataset and 0.816 and 0.988 in the validation dataset. The Korean lung cancer risk model included age-mean of age, square of age-mean of age, sex, square root of pack-years of smoking, years since cessation, physical activity, alcohol consumption, body mass index, and medical history of chronic pulmonary obstructive disease, emphysema, pneumoconiosis, and interstitial pulmonary disease. Compared with the NLST criteria, the Korean lung cancer risk model’s cut-off criteria (>2.1%) had more improved sensitivity (61.4% vs. 44.3%) and positive predictive value (4.1% vs. 2.9%). The Korean lung cancer risk model showed better discrimination and calibration than previously developed models in Western population.ConclusionsThe Korean lung cancer risk model can select eligible population for low-dose computed tomography screening among the Asian population. The efficiency of risk model-based selection for lung cancer screening is superior to that of fixed criteria-based selection.

Establishment of non-small-cell lung cancer risk prediction model based on prognosis-associated ADME genes.

Purpose: ADME genes are those involved in the absorption, distribution, metabolism, and excretion (ADME) of drugs. In the present study, a non-small-cell lung cancer (NSCLC) risk prediction model was established using prognosis-associated ADME genes, and the predictive performance of this model was evaluated and verified. In addition, multifaceted difference analysis was performed on groups with high and low risk scores.Methods: An NSCLC sample transcriptome and clinical data were obtained from public databases. The prognosis-associated ADME genes were obtained by univariate Cox and lasso regression analyses to build a risk model. Tumor samples were divided into high-risk and low-risk score groups according to the risk score. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes enrichment analyses of the differentially expressed genes and the differences in the immune infiltration, mutation, and medication reactions in the two groups were studied in detail.Results: A risk prediction model was established with seven prognosis-associated ADME genes. Its good predictive ability was confirmed by studies of the model's effectiveness. Univariate and multivariate Cox regression analyses showed that the model’s risk score was an independent prognostic factor for patients with NSCLC. The study also showed that the risk score closely correlated with immune infiltration, mutations, and medication reactions.Conclusion: The risk prediction model established with seven ADME genes in the present study can predict the prognosis of patients with NSCLC. In addition, significant differences in immune infiltration, mutations, and therapeutic efficacy exist between the high- and low-risk score groups.