Lung cancer risk prediction: a tool for early detection

Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions

Foundation model, trained on a diverse range of data and adaptable to a myriad of tasks, is advancing healthcare. It fosters the development of healthcare artificial intelligence (AI) models tailored to the intricacies of the medical field, bridging the gap between limited AI models and the varied nature of healthcare practices. The advancement of a healthcare foundation model (HFM) brings forth tremendous potential to augment intelligent healthcare services across a broad spectrum of scenarios. However, despite the imminent widespread deployment of HFMs, there is currently a lack of clear understanding regarding their operation in the healthcare field, their existing challenges, and their future trajectory. To answer these critical inquiries, we present a comprehensive and in-depth examination that delves into the landscape of HFMs. It begins with a comprehensive overview of HFMs, encompassing their methods, data, and applications, to provide a quick understanding of the current progress. Subsequently, it delves into a thorough exploration of the challenges associated with data, algorithms, and computing infrastructures in constructing and widely applying foundation models in healthcare. Furthermore, this survey identifies promising directions for future development in this field. We believe that this survey will enhance the community's understanding of the current progress of HFMs and serve as a valuable source of guidance for future advancements in this domain.

Emerging trends and hotspots in lung cancer-prediction models research

Objective

In recent years, lung cancer-prediction models have become popular. However, few bibliometric analyses have been performed in this field.

Methods

This study aimed to reveal the scientific output and trends in lung cancer-prediction models from a global perspective. In this study, publications were retrieved and extracted from the Web of Science Core Collection (WoSCC) database. CiteSpace 6.1.R3 and VOSviewer 1.6.18 were used to analyze hotspots and theme trends.

Results

A marked increase in the number of publications related to lung cancer-prediction models was observed. A total of 2711 institutions from in 64 countries/regions published 2139 documents in 566 academic journals. China and the United States were the leading country in the field of lung cancer-prediction models. The institutions represented by Fudan University had significant academic influence in the field. Analysis of keywords revealed that lncRNA, tumor microenvironment, immune, cancer statistics, The Cancer Genome Atlas, nomogram, and machine learning were the current focus of research in lung cancer-prediction models.

Conclusions

Over the last two decades, research on risk-prediction models for lung cancer has attracted increasing attention. Prognosis, machine learning, and multi-omics technologies are both current hotspots and future trends in this field. In the future, in-depth explorations using different omics should increase the sensitivity and accuracy of lung cancer-prediction models and reduce the global burden of lung cancer.

Developing a risk prediction tool for lung cancer in Kent and Medway, England: cohort study using linked data

BACKGROUND

Lung cancer has the poorest survival due to late diagnosis and there is no universal screening. Hence, early detection is crucial. Our objective was to develop a lung cancer risk prediction tool at a population level.

METHODS

We used a large place-based linked data set from a local health system in southeast England which contained extensive information covering demographic, socioeconomic, lifestyle, health, and care service utilisation. We exploited the power of Machine Learning to derive risk scores using linear regression modelling. Tens of thousands of model runs were undertaken to identify attributes which predicted the risk of lung cancer.

RESULTS

Initially, 16 attributes were identified. A final combination of seven attributes was chosen based on the number of cancers detected which formed the Kent & Medway lung cancer risk prediction tool. This was then compared with the criteria used in the wider Targeted Lung Health Checks programme. The prediction tool outperformed by detecting 822 cases compared to 581 by the lung check programme currently in operation.

CONCLUSION

We have demonstrated the useful application of Machine Learning in developing a risk score for lung cancer and discuss its clinical applicability.

Systematic Review of Lung Cancer Screening: Advancements and Strategies for Implementation

Lung cancer is the leading cause of cancer-related deaths in Europe, with low survival rates primarily due to late-stage diagnosis. Early detection can significantly improve survival rates, but lung cancer screening is not currently implemented in Italy. Many countries have implemented lung cancer screening programs for high-risk populations, with studies showing a reduction in mortality. This review aimed to identify key areas for establishing a lung cancer screening program in Italy. A literature search was conducted in October 2022, using the PubMed and Scopus databases. Items of interest included updated evidence, approaches used in other countries, enrollment and eligibility criteria, models, cost-effectiveness studies, and smoking cessation programs. A literature search yielded 61 scientific papers, highlighting the effectiveness of low-dose computed tomography (LDCT) screening in reducing mortality among high-risk populations. The National Lung Screening Trial (NLST) in the United States demonstrated a 20% reduction in lung cancer mortality with LDCT, and other trials confirmed its potential to reduce mortality by up to 39% and detect early-stage cancers. However, false-positive results and associated harm were concerns. Economic evaluations generally supported the cost-effectiveness of LDCT screening, especially when combined with smoking cessation interventions for individuals aged 55 to 75 with a significant smoking history. Implementing a screening program in Italy requires the careful consideration of optimal strategies, population selection, result management, and the integration of smoking cessation. Resource limitations and tailored interventions for subpopulations with low-risk perception and non-adherence rates should be addressed with multidisciplinary expertise.

Association between biological aging and lung cancer risk: Cohort study and Mendelian randomization analysis

Chronological age only represents the passage of time, whereas biological age reflects the physiology states and the susceptibility to morbidity and mortality. The association between biological age and lung cancer risk remains controversial. Hence, we conducted a prospective analysis in the UK Biobank study and two-sample Mendelian randomization analysis to investigate this association. Biological aging was evaluated by PhenoAgeAccel, derived from routine clinical biomarkers. Independent of chronological age, PhenoAgeAccel was positively associated with the risk of overall and histological subtypes of lung cancer. There was a joint effect of PhenoAgeAccel and genetics in lung cancer incidence. In Mendelian randomization analysis, the genetically predicted PhenoAgeAccel was associated with the increased risk of overall lung cancer, small cell, and squamous cell carcinoma. Our findings suggest PhenoAgeAccel is an independent risk factor for lung cancer, which could be incorporated with polygenic risk score to identify high-risk individuals for lung cancer.

Developing and Validating a Lung Cancer Risk Prediction Model: A Nationwide Population-Based Study

Lung cancer can be challenging to diagnose in the early stages, where treatment options are optimal. We aimed to develop 1-year prediction models for the individual risk of incident lung cancer for all individuals aged 40 or above living in Denmark on 1 January 2017. The study was conducted using population-based registers on health and sociodemographics from 2007-2016. We applied backward selection on all variables by logistic regression to develop a risk model for lung cancer and applied the models to the validation cohort, calculated receiver-operating characteristic curves, and estimated the corresponding areas under the curve (AUC). In the populations without and with previously confirmed cancer, 4274/2,826,249 (0.15%) and 482/172,513 (0.3%) individuals received a lung cancer diagnosis in 2017, respectively. For both populations, older age was a relevant predictor, and the most complex models, containing variables related to diagnoses, medication, general practitioner, and specialist contacts, as well as baseline sociodemographic characteristics, had the highest AUC. These models achieved a positive predictive value (PPV) of 0.0127 (0.006) and a negative predictive value (NPV) of 0.989 (0.997) with a 1% cut-off in the population without (with) previous cancer. This corresponds to 1.2% of the screened population experiencing a positive prediction, of which 1.3% would be incident with lung cancer. We have developed and tested a prediction model with a reasonable potential to support clinicians and healthcare planners in identifying patients at risk of lung cancer.

XML-GBM lung: An explainable machine learning-based application for the diagnosis of lung cancer

Lung cancer has been the leading cause of cancer-related deaths worldwide. Early detection and diagnosis of lung cancer can greatly improve the chances of survival for patients. Machine learning has been increasingly used in the medical sector for the detection of lung cancer, but the lack of interpretability of these models remains a significant challenge. Explainable machine learning (XML) is a new approach that aims to provide transparency and interpretability for machine learning models. The entire experiment has been performed in the lung cancer dataset obtained from Kaggle. The outcome of the predictive model with ROS (Random Oversampling) class balancing technique is used to comprehend the most relevant clinical features that contributed to the prediction of lung cancer using a machine learning explainable technique termed SHAP (SHapley Additive exPlanation). The results show the robustness of GBM's capacity to detect lung cancer, with 98.76% accuracy, 98.79% precision, 98.76% recall, 98.76% F-Measure, and 0.16% error rate, respectively. Finally, a mobile app is developed incorporating the best model to show the efficacy of our approach.

A Systems Biology and LASSO-Based Approach to Decipher the Transcriptome-Interactome Signature for Predicting Non-Small Cell Lung Cancer

The lack of precise molecular signatures limits the early diagnosis of non-small cell lung cancer (NSCLC). The present study used gene expression data and interaction networks to develop a highly accurate model with the least absolute shrinkage and selection operator (LASSO) for predicting NSCLC. The differentially expressed genes (DEGs) were identified in NSCLC compared with normal tissues using TCGA and GTEx data. A biological network was constructed using DEGs, and the top 20 upregulated and 20 downregulated hub genes were identified. These hub genes were used to identify signature genes with penalized logistic regression using the LASSO to predict NSCLC. Our model’s development involved the following steps: (i) the dataset was divided into 80% for training (TR) and 20% for testing (TD1); (ii) a LASSO logistic regression analysis was performed on the TR with 10-fold cross-validation and identified a combination of 17 genes as NSCLC predictors, which were used further for development of the LASSO model. The model’s performance was assessed on the TD1 dataset and achieved an accuracy and an area under the curve of the receiver operating characteristics (AUC-ROC) of 0.986 and 0.998, respectively. Furthermore, the performance of the LASSO model was evaluated using three independent NSCLC test datasets (GSE18842, GSE27262, GSE19804) and achieved high accuracy, with an AUC-ROC of >0.99, >0.99, and 0.95, respectively. Based on this study, a web application called NSCLCpred was developed to predict NSCLC.

Machine learning to reveal an astute risk predictive framework for Gynecologic Cancer and its impact on women psychology: Bangladeshi perspective

BACKGROUND

In this research, an astute system has been developed by using machine learning and data mining approach to predict the risk level of cervical and ovarian cancer in association to stress.

RESULTS

For functioning factors and subfactors, several machine learning models like Logistics Regression, Random Forest, AdaBoost, Naïve Bayes, Neural Network, kNN, CN2 rule Inducer, Decision Tree, Quadratic Classifier were compared with standard metrics e.g., F1, AUC, CA. For certainty info gain, gain ratio, gini index were revealed for both cervical and ovarian cancer. Attributes were ranked using different feature selection evaluators. Then the most significant analysis was made with the significant factors. Factors like children, age of first intercourse, age of husband, Pap test, age are the most significant factors of cervical cancer. On the other hand, genital area infection, pregnancy problems, use of drugs, abortion, and the number of children are important factors of ovarian cancer.

CONCLUSION

Resulting factors were merged, categorized, weighted according to their significance level. The categorized factors were indexed using ranker algorithm which provides them a weightage value. An algorithm has been formulated afterward which can be used to predict the risk level of cervical and ovarian cancer in relation to women's mental health. The research will have a great impact on the low incoming country like Bangladesh as most women in low incoming nations were unaware of it. As these two can be described as the most sensitive cancers to women, the development of the application from algorithm will also help to reduce women's mental stress. More data and parameters will be added in future for research in this perspective.

Lung cancer screening strategy for non-high-risk individuals: a narrative review

Lung cancer is the deadliest malignancy worldwide, accounting for almost 20% of all cancer deaths. Clinical trials, such as NLST and NELSON, have proved the survival benefit of lung cancer screening using low-dose computed tomography (LDCT), and most of the lung cancer screening guidelines recommended annual lung cancer screening by LDCT for high-risk individuals. However, a relatively high proportion of lung cancer patients do not have risk factors, and it is questionable whether non-high-risk individuals should receive LDCT screening. In this review, we reviewed risk factors of lung cancer and summarized the benefits and potential harms of LDCT screening. After clarifying the differences between China and western countries in lung cancer screening, we recommended that non-high-risk individuals should receive LDCT screening with an interval of five to ten years. To better balance benefits and harms from LDCT screening, we also proposed a flexible screening strategy using LDCT based on lung cancer risk. Hopefully, it may help reduce unnecessary radiation exposure from CT scans while decreasing mortality of lung cancer.

A new tool to predict lung cancer based on risk factors

BACKGROUND

Lung cancer is one of the deadliest cancer in the world. Hundreds of researches are presented annually in the field of lung cancer treatment, diagnosis and early prediction. The current research focuses on the early prediction of lung cancer via analysis of the most dangerous risk factors.

METHODS

A novel tool for the early prediction of lung cancer is designed following three stages: the analysis of an international cancer database, the classification study of the results of local medical questionnaires and the international medical opinion obtained from recently published medical reports.

RESULTS

The tool is tested using local medical cases and the local medical opinion(s) is (are) used to determine the accuracy of the scores obtained. The Machine Learning approaches are also used to analyze 1000 patient records from an international dataset to compare our results with the international ones.

CONCLUSIONS

The designed tool facilitates computing the risk factors for people who are unable to perform costly hospital tests. It does not require entering all risk inputs and produces the risk factor of lung cancer as a percentage in less than a second. The comparative study with medical opinion and the performance evaluation have confirmed the accuracy of the results.

Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients

Background

An accurate and simple risk prediction model that would facilitate earlier detection of pancreatic adenocarcinoma (PDAC) is not available at present. In this study, we compare different algorithms of risk prediction in order to select the best one for constructing a biomarker-based risk score, PancRISK.

Methods

Three hundred and seventy-nine patients with available measurements of three urine biomarkers, (LYVE1, REG1B and TFF1) using retrospectively collected samples, as well as creatinine and age, were randomly split into training and validation sets, following stratification into cases (PDAC) and controls (healthy patients). Several machine learning algorithms were used, and their performance characteristics were compared. The latter included AUC (area under ROC curve) and sensitivity at clinically relevant specificity.

Results

None of the algorithms significantly outperformed all others. A logistic regression model, the easiest to interpret, was incorporated into a PancRISK score and subsequently evaluated on the whole data set. The PancRISK performance could be even further improved when CA19-9, commonly used PDAC biomarker, is added to the model.

Conclusion

PancRISK score enables easy interpretation of the biomarker panel data and is currently being tested to confirm that it can be used for stratification of patients at risk of developing pancreatic cancer completely non-invasively, using urine samples.

Impact of a Lung Cancer Screening Information Film on Informed Decision-making: A Randomized Trial

Rationale: Lung cancer screening has the potential to save lives, but it also carries a risk of potential harms. Explaining the benefits and harms of screening in a way that is balanced and comprehensible to individuals with various levels of education is essential. Although a shared decision-making approach is mandated by the Centers for Medicare & Medicaid Services, there have been no randomized studies to evaluate the impact of different forms of lung screening information. Objectives: To evaluate the impact of a novel information film on informed decision-making in individuals considering participating in lung cancer screening. Methods: A subset of participants from LSUT (Lung Screen Uptake Trial) were randomly allocated either to view the information film and receive a written information booklet or to receive the booklet alone. The primary outcome was the objective knowledge score after intervention. Secondary outcomes included subjective knowledge, decisional conflict, final screening participation, and acceptability of the materials. Univariate and multivariate analyses were performed to determine differences in pre- and postintervention knowledge scores in both groups and between groups for the primary and secondary outcomes. Results: In the final analysis of 229 participants, both groups showed significantly improved subjective and objective knowledge scores after intervention. This improvement was greatest in the film + booklet group, where mean objective knowledge improved by 2.16 points (standard deviation [SD] 1.8) compared with 1.84 points (SD 1.9) in the booklet-alone group (β coefficient 0.62; confidence interval, 0.17-1.08; P = 0.007 in the multivariable analysis). Mean subjective knowledge increased by 0.92 points (SD 1.0) in the film + booklet group and 0.55 points (SD 1.1) in the booklet-alone group (β coefficient 0.32; CI, 0.05-0.58; P = 0.02 in the multivariable analysis). Decisional certainty was higher in the film + booklet (mean 8.5/9 points [SD 1.3], group than in the booklet-alone group (mean 8.2/9 points [SD 1.5]). Both information materials were well accepted, and there were no differences in final screening participation rates between groups. Conclusions: The information film improved knowledge and reduced decisional conflict without affecting lung-screening uptake. Clinical trial registered with clinicaltrials.gov (NCT02558101).

Estimating the risk of PTSD in recent trauma survivors: results of the International Consortium to Predict PTSD (ICPP)

A timely determination of the risk of post-traumatic stress disorder (PTSD) is a prerequisite for efficient service delivery and prevention. We provide a risk estimate tool allowing a calculation of individuals' PTSD likelihood from early predictors. Members of the International Consortium to Predict PTSD (ICPP) shared individual participants' item-level data from ten longitudinal studies of civilian trauma survivors admitted to acute care centers in six countries. Eligible participants (N=2,473) completed an initial clinical assessment within 60 days of trauma exposure, and at least one follow-up assessment 4-15 months later. The Clinician-Administered PTSD Scale for DSM-IV (CAPS) evaluated PTSD symptom severity and diagnostic status at each assessment. Participants' education, prior lifetime trauma exposure, marital status and socio-economic status were assessed and harmonized across studies. The study's main outcome was the likelihood of a follow-up PTSD given early predictors. The prevalence of follow-up PTSD was 11.8% (9.2% for male participants and 16.4% for females). A logistic model using early PTSD symptom severity (initial CAPS total score) as a predictor produced remarkably accurate estimates of follow-up PTSD (predicted vs. raw probabilities: r=0.976). Adding respondents' female gender, lower education, and exposure to prior interpersonal trauma to the model yielded higher PTSD likelihood estimates, with similar model accuracy (predicted vs. raw probabilities: r=0.941). The current model could be adjusted for other traumatic circumstances and accommodate risk factors not captured by the ICPP (e.g., biological, social). In line with their use in general medicine, risk estimate models can inform clinical choices in psychiatry. It is hoped that quantifying individuals' PTSD risk will be a first step towards systematic prevention of the disorder.

Global Epidemiology of Lung Cancer

While lung cancer has been the leading cause of cancer-related deaths for many years in the United States, incidence and mortality statistics - among other measures - vary widely worldwide. The aim of this study was to review the evidence on lung cancer epidemiology, including data of international scope with comparisons of economically, socially, and biologically different patient groups. In industrialized nations, evolving social and cultural smoking patterns have led to rising or plateauing rates of lung cancer in women, lagging the long-declining smoking and cancer incidence rates in men. In contrast, emerging economies vary widely in smoking practices and cancer incidence but commonly also harbor risks from environmental exposures, particularly widespread air pollution. Recent research has also revealed clinical, radiologic, and pathologic correlates, leading to greater knowledge in molecular profiling and targeted therapeutics, as well as an emphasis on the rising incidence of adenocarcinoma histology. Furthermore, emergent evidence about the benefits of lung cancer screening has led to efforts to identify high-risk smokers and development of prediction tools. This review also includes a discussion on the epidemiologic characteristics of special groups including women and nonsmokers. Varying trends in smoking largely dictate international patterns in lung cancer incidence and mortality. With declining smoking rates in developed countries and knowledge gains made through molecular profiling of tumors, the emergence of new risk factors and disease features will lead to changes in the landscape of lung cancer epidemiology.

Development and Validation of Lifestyle-Based Models to Predict Incidence of the Most Common Potentially Preventable Cancers

BACKGROUND

Most risk models for cancer are either specific to individual cancers or include complex or predominantly non-modifiable risk factors.

METHODS

We developed lifestyle-based models for the five cancers for which the most cases are potentially preventable through lifestyle change in the UK (lung, colorectal, bladder, kidney, and esophageal for men and breast, lung, colorectal, endometrial, and kidney for women). We selected lifestyle risk factors from the European Code against Cancer and obtained estimates of relative risks from meta-analyses of observational studies. We used mean values for risk factors from nationally representative samples and mean 10-year estimated absolute risks from routinely available sources. We then assessed the performance of the models in 23,768 participants in the EPIC-Norfolk cohort who had no history of the five selected cancers at baseline.

RESULTS

In men, the combined risk model showed good discrimination [AUC, 0.71; 95% confidence interval (CI), 0.69-0.73] and calibration. Discrimination was lower in women (AUC, 0.59; 95% CI, 0.57-0.61), but calibration was good. In both sexes, the individual models for lung cancer had the highest AUCs (0.83; 95% CI, 0.80-0.85 for men and 0.82; 95% CI, 0.76-0.87 for women). The lowest AUCs were for breast cancer in women and kidney cancer in men.

CONCLUSIONS

The discrimination and calibration of the models are both reasonable, with the discrimination for individual cancers comparable or better than many other published risk models.

IMPACT

These models could be used to demonstrate the potential impact of lifestyle change on risk of cancer to promote behavior change.

Risk prediction models for lung cancer: Perspectives and dissemination

Objective

The objective was to systematically assess lung cancer risk prediction models by critical evaluation of methodology, transparency and validation in order to provide a direction for future model development.

Methods

Electronic searches (including PubMed, EMbase, the Cochrane Library, Web of Science, the China National Knowledge Infrastructure, Wanfang, the Chinese BioMedical Literature Database, and other official cancer websites) were completed with English and Chinese databases until April 30th, 2018. Main reported sources were input data, assumptions and sensitivity analysis. Model validation was based on statements in the publications regarding internal validation, external validation and/or cross-validation.

Results

Twenty-two studies (containing 11 multiple-use and 11 single-use models) were included. Original models were developed between 2003 and 2016. Most of these were from the United States. Multivariate logistic regression was widely used to identify a model. The minimum area under the curve for each model was 0.57 and the largest was 0.87. The smallest C statistic was 0.59 and the largest 0.85. Six studies were validated by external validation and three were cross-validated. In total, 2 models had a high risk of bias, 6 models reported the most used variables were age and smoking duration, and 5 models included family history of lung cancer.

Conclusions

The prediction accuracy of the models was high overall, indicating that it is feasible to use models for high-risk population prediction. However, the process of model development and reporting is not optimal with a high risk of bias. This risk affects prediction accuracy, influencing the promotion and further development of the model. In view of this, model developers need to be more attentive to bias risk control and validity verification in the development of models.

A web-based prediction score for head and neck cancer referrals

OBJECTIVE

Following the announcement of the NHS Cancer Plan in 2000, anyone suspected of having cancer has to be seen by a specialist within 2 weeks of referral. Since this introduction, studies have shown that only 6.3%-14.6% of 2-week referrals were diagnosed with a head and neck cancer and that majority of the cancer diagnoses were via other referral routes. These studies suggest that the referral scheme is not currently cost-effective. Our aim is to develop a scoring system that determines the risk of head and neck cancer in a patient, which can then be used to aid GP referrals.

DESIGN

Retrospective data were collected from 1075 patients with 2-week head and neck cancer referrals from general practitioners. The retrospective data collected included patients' demographics, risk factors and relevant investigations. The data were used as input into a logistic regression to arrive at our model. Our approach included data analysis, machine learning techniques, statistical inference and model validation metrics to arrive at the best performing model. The model was then tested with more data from 235 prospective patients.

RESULTS

Using our results from the logistic regression, we created a web-based tool that GPs can use to calculate their patient's probability of cancer and use this result to assist in their decision regarding referral. Our prototype can be seen in Figure 2.

CONCLUSION

We have created a prototype scoring system that can be hosted online to assist GPs with their referrals with a sensitivity of 31% and specificity of 92%. While we acknowledge that there are several limitations to our model, we believe we have created a novel preliminary scoring system that has the potential to be improved dramatically with further data and be very helpful for GPs in a long run.

Lung cancer risk to personalise annual and biennial follow-up computed tomography screening

BACKGROUND

All lung cancer CT screening trials used fixed follow-up intervals, which may not be optimal. We developed new lung cancer risk models for personalising screening intervals to 1 year or 2 years, and compared these with existing models.

METHODS

We included participants in the CT arm of the National Lung Screening Trial (2002-2010) who underwent a baseline scan and a first annual follow-up scan and were not diagnosed with lung cancer in the first year. True and false positives and the area under the curve of each model were calculated. Internal validation was performed using bootstrapping.

RESULTS

Data from 24 542 participants were included in the analysis. The accuracy was 0.785, 0.693, 0.697, 0.666 and 0.727 for the polynomial, patient characteristics, diameter, Patz and PanCan models, respectively. Of the 24 542 participants included, 174 (0.71%) were diagnosed with lung cancer between the first and the second annual follow-ups. Using the polynomial model, 2558 (10.4%, 95% CI 10.0% to 10.8%), 7544 (30.7%, 30.2% to 31.3%), 10 947 (44.6%, 44.0% to 45.2%), 16 710 (68.1%, 67.5% to 68.7%) and 20 023 (81.6%, 81.1% to 92.1%) of the 24 368 participants who did not develop lung cancer in the year following the first follow-up screening round could have safely skipped it, at the expense of delayed diagnosis of 0 (0.0%, 0.0% to 2.7%), 8 (4.6%, 2.2% to 9.2%), 17 (9.8%, 6.0% to 15.4%), 44 (25.3%, 19.2% to 32.5%) and 70 (40.2%, 33.0% to 47.9%) of the 174 lung cancers, respectively.

CONCLUSIONS

The polynomial model, using both patient characteristics and baseline scan morphology, was significantly superior in assigning participants to 1-year or 2-year screening intervals. Implementing personalised follow-up intervals would enable hundreds of participants to skip a screening round per lung cancer diagnosis delayed.

Combining ctnnb1 genetic variability with epidemiologic factors to predict lung cancer susceptibility

OBJECTIVE

Early detection and diagnosis of lung cancer remain challenging but would improve patient prognosis. The goal of this study is to develop a model to estimate the risk of lung cancer for a given individual.

METHODS

We conducted a case-control study to develop a predictive model to identify individuals at high risk for lung cancer. Clinical data from 500 lung cancer patients and 500 population-based age- and gender-matched controls were used to develop and evaluate the model. Associations between environmental variants together with single nucleotide polymorphisms (SNPs) of beta-catenin (ctnnb1) and lung cancer risk were analyzed using a logistic regression model. The predictive accuracy of the model was determined by calculating the area under the receiver operating characteristic (ROC) curve.

RESULTS

Prior diagnosis of chronic obstructive pulmonary disease (COPD), pulmonary tuberculosis, family history of cancer, and smoking are lung cancer risk factors. The area under the curve (AUC) was 0.740, and the sensitivity, specificity, and Youden index were 0.718, 0.660, and 0.378, respectively.

CONCLUSION

Our risk prediction model for lung cancer is useful for distinguishing high-risk individuals.

Effect of interventions incorporating personalised cancer risk information on intentions and behaviour: a systematic review and meta-analysis of randomised controlled trials

OBJECTIVE

To provide a comprehensive review of the impact on intention to change health-related behaviours and health-related behaviours themselves, including screening uptake, of interventions incorporating information about cancer risk targeted at the general adult population.

DESIGN

A systematic review and random-effects meta-analysis.

DATA SOURCES

An electronic search of MEDLINE, EMBASE, CINAHL and PsycINFO from 1 January 2000 to 1 July 2017.

INCLUSION CRITERIA

Randomised controlled trials of interventions including provision of a personal estimate of future cancer risk based on two or more non-genetic variables to adults recruited from the general population that include at least one behavioural outcome.

RESULTS

We included 19 studies reporting 12 outcomes. There was significant heterogeneity in interventions and outcomes between studies. There is evidence that interventions incorporating personalised cancer risk information do not affect intention to attend or attendance at screening (relative risk 1.00 (0.97-1.03)). There is limited evidence that they increase smoking abstinence, sun protection, adult skin self-examination and breast examination, and decrease intention to tan. However, they do not increase smoking cessation, parental child skin examination or intention to protect skin. No studies assessed changes in diet, alcohol consumption or physical activity.

CONCLUSIONS

Interventions incorporating personalised cancer risk information do not affect uptake of screening, but there is limited evidence of effect on some health-related behaviours. Further research, ideally including objective measures of behaviour, is needed before cancer risk information is incorporated into routine practice for health promotion in the general population.

Responses to provision of personalised cancer risk information: a qualitative interview study with members of the public

BACKGROUND

It is estimated that nearly 600,000 cancer cases in the UK could have been avoided in the past five years if people had healthier lifestyles. A number of theories of behaviour change suggest that before people will change health behaviours, they must accept that a risk applies to them. This study aimed to explore the views of the public on receiving personalised cancer risk information and the potential for that information to motivate behaviour change.

METHODS

We conducted 27 interviews with members of the public (mean age 49 ± 23 years). Each participant completed a questionnaire to allow calculation of their risk of developing the most common cancers (10 for women, 8 for men). During the interviews we presented their risk using a web-based tool developed for the study and discussions covered their views on receiving that information. Each interview was audio-recorded and then analysed using thematic analysis.

RESULTS

Participants generally viewed the concept of personalised cancer risk positively. The first reaction of almost all when presented with their 10-year risk of an individual cancer without any further context was that it was low and not concerning. Views on what constituted a high risk ranged widely, from 0.5 to 60%. All felt seeing the impact of changes in lifestyle was helpful. For some this led to intentions to change behaviour, but reductions in risk were not always motivating as the risks were considered low and differences small.

CONCLUSIONS

Provision of personalised cancer risk was well received and may be a useful addition to other cancer prevention initiatives. Further work is needed in particular to develop ways to present cancer risk that reflect the general perception of what constitutes a risk high enough to motivate behaviour change and help patients contextualise a less well known health risk by providing a frame of reference.

On meta- and mega-analyses for gene-environment interactions

Gene-by-environment (G × E) interactions are important in explaining the missing heritability and understanding the causation of complex diseases, but a single, moderately sized study often has limited statistical power to detect such interactions. With the increasing need for integrating data and reporting results from multiple collaborative studies or sites, debate over choice between mega- versus meta-analysis continues. In principle, data from different sites can be integrated at the individual level into a "mega" data set, which can be fit by a joint "mega-analysis." Alternatively, analyses can be done at each site, and results across sites can be combined through a "meta-analysis" procedure without integrating individual level data across sites. Although mega-analysis has been advocated in several recent initiatives, meta-analysis has the advantages of simplicity and feasibility, and has recently led to several important findings in identifying main genetic effects. In this paper, we conducted empirical and simulation studies, using data from a G × E study of lung cancer, to compare the mega- and meta-analyses in four commonly used G × E analyses under the scenario that the number of studies is small and sample sizes of individual studies are relatively large. We compared the two data integration approaches in the context of fixed effect models and random effects models separately. Our investigations provide valuable insights in understanding the differences between mega- and meta-analyses in practice of combining small number of studies in identifying G × E interactions.

DNA methylation age of blood predicts future onset of lung cancer in the women's health initiative

Lung cancer is considered an age-associated disease, whose progression is in part due to accumulation of genomic instability as well as age-related decline in system integrity and function. Thus even among individuals exposed to high levels of genotoxic carcinogens, such as those found in cigarette smoke, lung cancer susceptibility may vary as a function of individual differences in the rate of biological aging. We recently developed a highly accurate candidate biomarker of aging based on DNA methylation (DNAm) levels, which may prove useful in assessing risk of aging-related diseases, such as lung cancer. Using data on 2,029 females from the Women's Health Initiative, we examined whether baseline measures of “intrinsic epigenetic age acceleration” (IEAA) predicted subsequent lung cancer incidence. We observed 43 lung cancer cases over the nearly twenty years of follow-up. Results showed that standardized measures of IEAA were significantly associated with lung cancer incidence (HR: 1.50, P = 3.4×10⁻³). Furthermore, stratified Cox proportional hazard models suggested that the association may be even stronger among older individuals (70 years or above) or those who are current smokers. Overall, our results suggest that IEAA may be a useful biomarker for evaluating lung cancer susceptibility from a biological aging perspective.

Combining Telomerase Reverse Transcriptase Genetic Variant rs2736100 with Epidemiologic Factors in the Prediction of Lung Cancer Susceptibility

Genetic variants from a considerable number of susceptibility loci have been identified in association with cancer risk, but their interaction with epidemiologic factors in lung cancer remains to be defined. We sought to establish a forecasting model for identifying individuals with high-risk of lung cancer by combing gene single-nucleotide polymorphisms with epidemiologic factors. Genotyping and clinical data from 500 lung cancer cases and 500 controls were used for developing the logistic regression model. We found that lung cancer was associated with telomerase reverse transcriptase (TERT) rs2736100 single-nucleotide polymorphism. The TERT rs2736100 model was still significantly associated with lung cancer risk when combined with environmental and lifestyle factors, including lower education, lower BMI, COPD history, heavy cigarettes smoking, heavy cooking emission, and dietary factors (over-consumption of meat and deficiency in fish/shrimp, vegetables, dairy products, and soybean products). These data suggest that combining TERT SNP and epidemiologic factors may be a useful approach to discriminate high and low-risk individuals for lung cancer.

Risk Prediction Models for Lung Cancer: A Systematic Review

Many lung cancer risk prediction models have been published but there has been no systematic review or comprehensive assessment of these models to assess how they could be used in screening. We performed a systematic review of lung cancer prediction models and identified 31 articles that related to 25 distinct models, of which 11 considered epidemiological factors only and did not require a clinical input. Another 11 articles focused on models that required a clinical assessment such as a blood test or scan, and 8 articles considered the 2-stage clonal expansion model. More of the epidemiological models had been externally validated than the more recent clinical assessment models. There was varying discrimination, the ability of a model to distinguish between cases and controls, with an area under the curve between 0.57 and 0.879 and calibration, the model's ability to assign an accurate probability to an individual. In our review we found that further validation studies need to be considered; especially for the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial 2012 Model Version (PLCOM2012) and Hoggart models, which recorded the best overall performance. Future studies will need to focus on prediction rules, such as optimal risk thresholds, for models for selective screening trials. Only 3 validation studies considered prediction rules when validating the models and overall the models were validated using varied tests in distinct populations, which made direct comparisons difficult. To improve this, multiple models need to be tested on the same data set with considerations for sensitivity, specificity, model accuracy, and positive predictive values at the optimal risk thresholds.

Predicting lung cancer prior to surgical resection in patients with lung nodules

BACKGROUND

Existing predictive models for lung cancer focus on improving screening or referral for biopsy in general medical populations. A predictive model calibrated for use during preoperative evaluation of suspicious lung lesions is needed to reduce unnecessary operations for a benign disease. A clinical prediction model (Thoracic Research Evaluation And Treatment [TREAT]) is proposed for this purpose.

METHODS

We developed and internally validated a clinical prediction model for lung cancer in a prospective cohort evaluated at our institution. Best statistical practices were used to construct, evaluate, and validate the logistic regression model in the presence of missing covariate data using bootstrap and optimism corrected techniques. The TREAT model was externally validated in a retrospectively collected Veteran Affairs population. The discrimination and calibration of the model was estimated and compared with the Mayo Clinic model in both the populations.

RESULTS

The TREAT model was developed in 492 patients from Vanderbilt whose lung cancer prevalence was 72% and validated among 226 Veteran Affairs patients with a lung cancer prevalence of 93%. In the development cohort, the area under the receiver operating curve (AUC) and Brier score were 0.87 (95% confidence interval [CI], 0.83-0.92) and 0.12, respectively compared with the AUC 0.89 (95% CI, 0.79-0.98) and Brier score 0.13 in the validation dataset. The TREAT model had significantly higher accuracy (p < 0.001) and better calibration than the Mayo Clinic model (AUC = 0.80; 95% CI, 75-85; Brier score = 0.17).

CONCLUSION

The validated TREAT model had better diagnostic accuracy than the Mayo Clinic model in preoperative assessment of suspicious lung lesions in a population being evaluated for lung resection.

Selecting High-Risk Individuals for Lung Cancer Screening: A Prospective Evaluation of Existing Risk Models and Eligibility Criteria in the German EPIC Cohort

Lung cancer risk prediction models are considered more accurate than the eligibility criteria based on age and smoking in identification of high-risk individuals for screening. We externally validated four lung cancer risk prediction models (Bach, Spitz, LLP, and PLCO(M2012)) among 20,700 ever smokers in the EPIC-Germany cohort. High-risk subjects were identified using the eligibility criteria applied in clinical trials (NELSON/LUSI, DLCST, ITALUNG, DANTE, and NLST) and the four risk prediction models. Sensitivity, specificity, and positive predictive value (PPV) were calculated based on the lung cancers diagnosed in the first 5 years of follow-up. Decision curve analysis was performed to compare net benefits. The number of high-risk subjects identified by the eligibility criteria ranged from 3,409 (NELSON/LUSI) to 1,458 (NLST). Among the eligibility criteria, the DLCST produced the highest sensitivity (64.13%), whereas the NLST produced the highest specificity (93.13%) and PPV (2.88%). The PLCO(M2012) model showed the best performance in external validation (C-index: 0.81; 95% CI, 0.76-0.86; E/O: 1.03; 95% CI, 0.87-1.23) and the highest sensitivity, specificity, and PPV, but the superiority over the Bach model and the LLP model was modest. All the models but the Spitz model showed greater net benefit over the full range of risk estimates than the eligibility criteria. We concluded that all of the lung cancer risk prediction models apart from the Spitz model have a similar accuracy to identify high-risk individuals for screening, but in general outperform the eligibility criteria used in the screening trials.

Lung cancer screening: identifying the high risk cohort

Low dose computed tomography (LDCT) is a viable screening tool for early lung cancer detection and mortality reduction. In practice, the success of any lung cancer screening programme will depend on successful identification of individuals at high risk in order to maximise the benefit-harm ratio. Risk prediction models incorporating multiple risk factors have been recognised as a method of identifying individuals at high risk of developing lung cancer. Identification of individuals at high risk will facilitate early diagnosis, reduce overall costs and also improve the current poor survival from lung cancer. This review summarises the current methods utilised in identifying high risk cohorts for lung cancer as proposed by the Liverpool Lung Project (LLP) risk model, Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial risk models and the prediction model for lung cancer death using quintiles. In addition, the cost-effectiveness of CT screening and future perspective for selecting high risk individuals is discussed.

LLPi: Liverpool Lung Project Risk Prediction Model for Lung Cancer Incidence

Identification of high-risk individuals will facilitate early diagnosis, reduce overall costs, and also improve the current poor survival from lung cancer. The Liverpool Lung Project prospective cohort of 8,760 participants ages 45 to 79 years, recruited between 1998 and 2008, was followed annually through the hospital episode statistics until January 31, 2013. Cox proportional hazards models were used to identify risk predictors of lung cancer incidence. C-statistic was used to assess the discriminatory accuracy of the models. Models were internally validated using the bootstrap method. During mean follow-up of 8.7 years, 237 participants developed lung cancer. Age [hazard ratio (HR), 1.04; 95% confidence interval (CI), 1.02-1.06], male gender (HR, 1.48; 95% CI, 1.10-1.98), smoking duration (HR, 1.04; 95% CI, 1.03-1.05), chronic obstructive pulmonary disease (HR, 2.43; 95% CI, 1.79-3.30), prior diagnosis of malignant tumor (HR, 2.84; 95% CI, 2.08-3.89), and early onset of family history of lung cancer (HR, 1.68; 95% CI, 1.04-2.72) were associated with the incidence of lung cancer. The LLPi risk model had a good calibration (goodness-of-fit χ(2) 7.58, P = 0.371). The apparent C-statistic was 0.852 (95% CI, 0.831-0.873) and the optimism-corrected bootstrap resampling C-statistic was 0.849 (95% CI, 0.829-0.873). The LLPi risk model may assist in identifying individuals at high risk of developing lung cancer in population-based screening programs.

Using Clinical Risk Models for Lung Nodule Classification

Evaluation and diagnosis of indeterminate pulmonary nodules is a significant and increasing burden on our health care system. The advent of lung cancer screening with low-dose computed tomography only exacerbates this problem, and more surgeons will be evaluating smaller and screening discovered nodules. Multiple calculators exist that can help the clinician diagnose lung cancer at the bedside. The Prostate, Lung, Colorectal and Ovarian Cancer (PLCO) model helps to determine who needs lung cancer screening, and the McWilliams and Mayo models help to guide the primary care clinician or pulmonologist with diagnosis by estimating the probability of cancer in patients with indeterminate pulmonary nodules. The Thoracic Research Evaluation And Treatment (TREAT) model assists surgeons to determine who needs a surgical biopsy among patients referred for suspicious lesions. Additional work is needed to develop decision support tools that will facilitate the use of these models in clinical practice, to complement the clinician's judgment and enhance shared decision making with the patient at the bedside.

Lung cancer screening

The United States Preventive Services Task Force recommends lung cancer screening with low-dose computed tomography (LDCT) in adults of age 55 to 80 years who have a 30 pack-year smoking history and are currently smoking or have quit within the past 15 years. This recommendation is largely based on the findings of the National Lung Screening Trial. Both policy-level and clinical decision-making about LDCT screening must consider the potential benefits of screening (reduced mortality from lung cancer) and possible harms. Effective screening requires an appreciation that screening should be limited to individuals at high risk of death from lung cancer, and that the risk of harm related to false positive findings, overdiagnosis, and unnecessary invasive testing is real. A comprehensive understanding of these aspects of screening will inform appropriate implementation, with the objective that an evidence-based and systematic approach to screening will help to reduce the enormous mortality burden of lung cancer.

An individual risk prediction model for lung cancer based on a study in a Chinese population

AIMS AND BACKGROUND

Early detection and diagnosis remains an effective yet challenging approach to improve the clinical outcome of patients with cancer. Low-dose computed tomography screening has been suggested to improve the diagnosis of lung cancer in high-risk individuals. To make screening more efficient, it is necessary to identify individuals who are at high risk.

METHODS AND STUDY DESIGN

We conducted a case-control study to develop a predictive model for identification of such high-risk individuals. Clinical data from 705 lung cancer patients and 988 population-based controls were used for the development and evaluation of the model. Associations between environmental variants and lung cancer risk were analyzed with a logistic regression model. The predictive accuracy of the model was determined by calculating the area under the receiver operating characteristic curve and the optimal operating point.

RESULTS

Our results indicate that lung cancer risk factors included older age, male gender, lower education level, family history of cancer, history of chronic obstructive pulmonary disease, lower body mass index, smoking cigarettes, a diet with less seafood, vegetables, fruits, dairy products, soybean products and nuts, a diet rich in meat, and exposure to pesticides and cooking emissions. The area under the curve was 0.8851 and the optimal operating point was obtained. With a cutoff of 0.35, the false positive rate, true positive rate, and Youden index were 0.21, 0.87, and 0.66, respectively.

CONCLUSIONS

The risk prediction model for lung cancer developed in this study could discriminate high-risk from low-risk individuals.

Personalizing colorectal cancer screening: a systematic review of models to predict risk of colorectal neoplasia

BACKGROUND & AIMS

A valid risk prediction model for colorectal neoplasia would allow patients to be screened for colorectal cancer (CRC) on the basis of risk. We performed a systematic review of studies reporting risk prediction models for colorectal neoplasia.

METHODS

We conducted a systematic search of MEDLINE, Scopus, and Cochrane Library databases from January 1990 through March 2013 and of references in identified studies. Case-control, cohort, and cross-sectional studies that developed or attempted to validate a model to predict risk of colorectal neoplasia were included. Two reviewers independently extracted data and assessed model quality. Model quality was considered to be good for studies that included external validation, fair for studies that included internal validation, and poor for studies with neither.

RESULTS

Nine studies developed a new prediction model, and 2 tested existing models. The models varied with regard to population, predictors, risk tiers, outcomes (CRC or advanced neoplasia), and range of predicted risk. Several included age, sex, smoking, a measure of obesity, and/or family history of CRC among the predictors. Quality was good for 6 models, fair for 2 models, and poor for 1 model. The tier with the largest population fraction (low, intermediate, or high risk) depended on the model. For most models that defined risk tiers, the risk difference between the highest and lowest tier ranged from 2-fold to 4-fold. Two models reached the 0.70 threshold for the C statistic, typically considered to indicate good discriminatory power.

CONCLUSIONS

Most current colorectal neoplasia risk prediction models have relatively weak discriminatory power and have not demonstrated generalizability. It remains to be determined how risk prediction models could inform CRC screening strategies.

Biomarkers of susceptibility to chemical carcinogens: the example of non-Hodgkin lymphomas

BACKGROUND

Genetic susceptibly to suspected chemical and environmental carcinogens may modify the response to exposure. The aim of this review was to explore the issues involved in the study of gene-environment interactions, and to consider the use of susceptibility biomarkers in cancer epidemiology, using non-Hodgkin lymphoma (NHL) as an example.

SOURCES OF DATA

PubMed, EMBASE and Web of Science were searched for peer-reviewed articles considering biomarkers of susceptibility to chemical, agricultural and industrial carcinogens in the aetiology of NHL.

AREAS OF AGREEMENT

The results suggest a modifying role for genetic susceptibility to a number of occupational and environmental exposures including organochlorines, chlorinated solvents, chlordanes and benzene in the aetiology of NHL. The potential importance of these gene-environment interactions in NHL may help to explain the lack of definitive carcinogens identified to date for this malignancy.

AREAS OF CONTROVERSY

Although a large number of genetic variants and gene-environment interactions have been explored for NHL, to date replication is lacking and therefore the findings remain to be validated.

GROWING POINTS AND AREAS TIMELY FOR DEVELOPING RESEARCH

These findings highlight the need for novel standardized methodologies in the study of genetic susceptibility to chemical carcinogens.

Development of a genotyping microarray for studying the role of gene-environment interactions in risk for lung cancer

A microarray (LungCaGxE), based on Illumina BeadChip technology, was developed for high-resolution genotyping of genes that are candidates for involvement in environmentally driven aspects of lung cancer oncogenesis and/or tumor growth. The iterative array design process illustrates techniques for managing large panels of candidate genes and optimizing marker selection, aided by a new bioinformatics pipeline component, Tagger Batch Assistant. The LungCaGxE platform targets 298 genes and the proximal genetic regions in which they are located, using ≈ 13,000 DNA single nucleotide polymorphisms (SNPs), which include haplotype linkage markers with a minimum allele frequency of 1% and additional specifically targeted SNPs, for which published reports have indicated functional consequences or associations with lung cancer or other smoking-related diseases. The overall assay conversion rate was 98.9%; 99.0% of markers with a minimum Illumina design score of 0.6 successfully generated allele calls using genomic DNA from a study population of 1873 lung-cancer patients and controls.

CT screening for lung cancer: countdown to implementation

Implementation of lung cancer CT screening is currently the subject of a major policy decision within the USA. Findings of the US National Lung Screening Trial showed a 20% reduction in lung cancer mortality and a 6·7% decrease in all-cause mortality; subsequently, five US professional and clinical organisations and the US Preventive Services Task Force recommended that screening should be implemented. Should national health services in Europe follow suit? The European community awaits mortality and cost-effectiveness data from the NELSON trial in 2015-16 and pooled findings of European trials. In the intervening years, a recommendation is proposed that a demonstration trial is done in the UK. In this Review, we summarise the existing evidence and identify questions that remain to be answered before the implementation of international lung cancer screening programmes.

Circulating inflammation markers and prospective risk for lung cancer

BACKGROUND

Despite growing recognition of an etiologic role for inflammation in lung carcinogenesis, few prospective epidemiologic studies have comprehensively investigated the association of circulating inflammation markers with lung cancer.

METHODS

We conducted a nested case-control study (n = 526 lung cancer patients and n = 592 control subjects) within the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial. Control subjects were matched to lung cancer case patients on age, sex, follow-up time (median = 2.9 years), randomization year, and smoking (pack-years and time since quitting). Serum levels of 77 inflammation markers were measured using a Luminex bead-based assay. Conditional logistic regression and weighted Cox models were used to estimate odds ratios (ORs) and cumulative risks, respectively.

RESULTS

Of 68 evaluable markers, 11 were statistically significantly associated with lung cancer risk (P trend across marker categories < .05), including acute-phase proteins (C-reactive protein [CRP], serum amyloid A [SAA]), proinflammatory cytokines (soluble tumor necrosis factor receptor 2 [sTNFRII]), anti-inflammatory cytokines (interleukin 1 receptor antagonist [IL-1RA]), lymphoid differentiation cytokines (interleukin 7 [IL-7]), growth factors (transforming growth factor alpha [TGF-A]), and chemokines (epithelial neutrophil-activating peptide 78 [ENA 78/CXCL5], monokine induced by gamma interferon [MIG/CXCL9], B cell-attracting chemokine 1 [BCA-1/CXCL13], thymus activation regulated chemokine [TARC/CCL17], macrophage-derived chemokine [MDC/CCL22]). Elevated marker levels were associated with increased lung cancer risk, with odds ratios comparing the highest vs the lowest group ranging from 1.47 (IL-7) to 2.27 (CRP). For IL-1RA, elevated levels were associated with decreased lung cancer risk (OR = 0.71; 95% confidence interval = 0.51 to 1.00). Associations did not differ by smoking, lung cancer histology, or latency. A cross-validated inflammation score using four independent markers (CRP, BCA-1/CXCL13, MDC/CCL22, and IL-1RA) provided good separation in 10-year lung cancer cumulative risks among former smokers (quartile [Q] 1 = 1.1% vs Q4 = 3.1%) and current smokers (Q1 = 2.3% vs Q4 = 7.9%) even after adjustment for smoking.

CONCLUSIONS

Some circulating inflammation marker levels are associated with prospective lung cancer risk.

Nanoporous carbon sensor with cage-in-fiber structure: highly selective aniline adsorbent toward cancer risk management

Carbon nanocage-embedded nanofibrous film works as a highly selective adsorbent of carcinogen aromatic amines. By using quartz crystal microbalance techniques, even ppm levels of aniline can be repetitively detected, while other chemical compounds such as water, ammonia, and benzene give negligible responses. This technique should be applicable for high-throughput cancer risk management.

Soluble Human Epidermal Growth Factor Receptor 2 (sHER2) as a Potential Risk Assessment, Screening, and Diagnostic Biomarker of Lung Adenocarcinoma

Lung cancer is the leading cause of cancer-related death in the United States. Here, we evaluated the potential clinical utility of soluble human epidermal growth factor receptor 2 (sHER2) for the risk assessment, screening, and diagnosis of non-small cell lung cancer (NSCLC) using an unmatched case-control study design. Serum sHER2 concentrations were measured by immunoassay in 244 primary NSCLC cases and 218 healthy controls. Wilcoxon rank-sum tests, logistic regression models, and receiver operating characteristic plots were used to assess whether sHER2 is associated with lung cancer. Median serum sHER2 concentrations are higher in patients with adenocarcinoma than squamous cell carcinoma regardless of gender, and sHER2 is a weak, independent biomarker of adenocarcinoma, but not of squamous cell carcinoma, adjusted for age and gender. The age-adjusted relative risk (odds) of adenocarcinoma is 3.95 (95% CI: 1.22, 12.81) and 7.93 (95% CI: 2.26, 27.82) greater for women and men with high sHER2 concentrations (≥6.60 ng/mL) vs. low sHER2 concentrations (≤1.85 ng/mL), respectively. When adjusted for each other, sHER2, age, and gender discern healthy controls from patients with primary adenocarcinomas of the lung with 85.9% accuracy. We conclude that even though serum sHER2 is not a strong, stand-alone discriminatory biomarker of adenocarcinoma, sHER2 may be a useful, independent covariate in multivariate risk assessment, screening, and diagnostic models of lung cancer.

Predictive accuracy of the Liverpool Lung Project risk model for stratifying patients for computed tomography screening for lung cancer: a case-control and cohort validation study

BACKGROUND

External validation of existing lung cancer risk prediction models is limited. Using such models in clinical practice to guide the referral of patients for computed tomography (CT) screening for lung cancer depends on external validation and evidence of predicted clinical benefit.

OBJECTIVE

To evaluate the discrimination of the Liverpool Lung Project (LLP) risk model and demonstrate its predicted benefit for stratifying patients for CT screening by using data from 3 independent studies from Europe and North America.

DESIGN

Case-control and prospective cohort study.

SETTING

Europe and North America.

PATIENTS

Participants in the European Early Lung Cancer (EUELC) and Harvard case-control studies and the LLP population-based prospective cohort (LLPC) study.

MEASUREMENTS

5-year absolute risks for lung cancer predicted by the LLP model.

RESULTS

The LLP risk model had good discrimination in both the Harvard (area under the receiver-operating characteristic curve [AUC], 0.76 [95% CI, 0.75 to 0.78]) and the LLPC (AUC, 0.82 [CI, 0.80 to 0.85]) studies and modest discrimination in the EUELC (AUC, 0.67 [CI, 0.64 to 0.69]) study. The decision utility analysis, which incorporates the harms and benefit of using a risk model to make clinical decisions, indicates that the LLP risk model performed better than smoking duration or family history alone in stratifying high-risk patients for lung cancer CT screening.

LIMITATIONS

The model cannot assess whether including other risk factors, such as lung function or genetic markers, would improve accuracy. Lack of information on asbestos exposure in the LLPC limited the ability to validate the complete LLP risk model.

CONCLUSION

Validation of the LLP risk model in 3 independent external data sets demonstrated good discrimination and evidence of predicted benefits for stratifying patients for lung cancer CT screening. Further studies are needed to prospectively evaluate model performance and evaluate the optimal population risk thresholds for initiating lung cancer screening.