A Validated Clinical Risk Prediction Model for Lung Cancer in Smokers of All Ages and Exposure Types: A HUNT Study

Evaluation of risk prediction models to select lung cancer screening participants in Europe: a prospective cohort consortium analysis

BACKGROUND

Lung cancer risk prediction models might efficiently identify individuals who should be offered lung cancer screening. However, their performance has not been comprehensively evaluated in Europe. We aimed to externally validate and evaluate the performance of several risk prediction models that predict lung cancer incidence or mortality in prospective European cohorts.

METHODS

We analysed 240 137 participants aged 45-80 years with a current or former smoking history from nine European countries in four prospective cohorts from the pooled database of the Lung Cancer Cohort Consortium: the Alpha-Tocopherol, Beta-Carotene Cancer Prevention Study (Finland), the Nord-Trøndelag Health Study (Norway), CONSTANCES (France), and the European Prospective Investigation into Cancer and Nutrition (Denmark, Germany, Italy, Spain, Sweden, the Netherlands, and Norway). We evaluated ten lung cancer risk models, which comprised the Bach, the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial 2012 model (PLCOm2012), the Lung Cancer Risk Assessment Tool (LCRAT), the Lung Cancer Death Risk Assessment Tool (LCDRAT), the Nord-Trøndelag Health Study (HUNT), the Optimized Early Warning Model for Lung Cancer Risk (OWL), the University College London-Death (UCLD), the University College London-Incidence (UCLI), the Liverpool Lung Project version 2 (LLP version 2), and the Liverpool Lung Project version 3 (LLP version 3) models. We quantified model calibration as the ratio of expected to observed cases or deaths and discrimination using the area under the receiver operating characteristic curve (AUC). For each model, we also identified risk thresholds that would screen the same number of individuals as each of the US Preventive Services Task Force 2021 (USPSTF-2021), the US Preventive Services Task Force 2013 (USPSTF-2013), and the Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON) criteria.

FINDINGS

Among the participants, 1734 lung cancer cases and 1072 lung cancer deaths occurred within five years of enrolment. Most models had reasonable calibration in most countries, although the LLP version 2 overpredicted risk by more than 50% in eight countries (expected to observed ≥1·50). The PLCOm2012, LCDRAT, LCRAT, Bach, HUNT, OWL, UCLD, and UCLI models showed similar discrimination in most countries, with AUCs ranging from 0·68 (95% CI 0·59-0·77) to 0·83 (0·78-0·89), whereas the LLP version 2 and LLP version 3 showed lower discrimination, with AUCs ranging from 0·64 (95% CI 0·57-0·72) to 0·78 (0·74-0·83). When pooling data from all countries (but excluding the HUNT cohort), 33·9% (73 313 of 216 387) of individuals were eligible by USPSTF-2021 criteria, which included 74·8% (1185) of lung cancers and 76·3% (730) of lung cancer deaths occurring over 5 years. Fewer individuals were selected by USPSTF-2013 and NELSON criteria. After applying thresholds to select a population of equal size to USPSTF-2021, the PLCOm2012, LCDRAT, LCRAT, Bach, HUNT, OWL, UCLD, and UCLI, models identified 77·6%-79·1% of future cases, although they selected slightly older individuals compared with USPSTF-2021 criteria. Results were similar for USPSTF-2013 and NELSON.

INTERPRETATION

Several lung cancer risk prediction models showed good performance in European countries and might improve the efficiency of lung cancer screening if used in place of categorical eligibility criteria.

FUNDING

US National Cancer Institute, l'Institut National du Cancer, Cancer Research UK.

The HUNT lung-SNP model: genetic variants plus clinical variables improve lung cancer risk assessment over clinical models

PURPOSE

The HUNT Lung Cancer Model (HUNT LCM) predicts individualized 6-year lung cancer (LC) risk among individuals who ever smoked cigarettes with high precision based on eight clinical variables. Can the performance be improved by adding genetic information?

METHODS

A polygenic model was developed in the prospective Norwegian HUNT2 study with clinical and genotype data of individuals who ever smoked cigarettes (n = 30749, median follow up 15.26 years) where 160 LC were diagnosed within six years. It included the variables of the original HUNT LCM plus 22 single nucleotide polymorphisms (SNPs) highly associated with LC. External validation was performed in the prospective Norwegian Tromsø Study (n = 2663).

RESULTS

The novel HUNT Lung-SNP model significantly improved risk ranking of individuals over the HUNT LCM in both HUNT2 (p < 0.001) and Tromsø (p < 0.05) cohorts. Furthermore, detection rate (number of participants selected to detect one LC case) was significantly better for the HUNT Lung-SNP vs. HUNT LCM in both cohorts (42 vs. 48, p = 0.003 and 11 vs. 14, p = 0.025, respectively) as well as versus the NLST, NELSON and 2021 USPSTF criteria. The area under the receiver operating characteristic curve (AUC) was higher for the HUNT Lung-SNP in both cohorts, but significant only in HUNT2 (AUC 0.875 vs. 0.844, p < 0.001). However, the integrated discrimination improvement index (IDI) indicates a significant improvement of LC risk stratification by the HUNT Lung-SNP in both cohorts (IDI 0.019, p < 0.001 (HUNT2) and 0.013, p < 0.001 (Tromsø)).

CONCLUSION

The HUNT Lung-SNP model could have a clinical impact on LC screening and has the potential to replace the HUNT LCM as well as the NLST, NELSON and 2021 USPSTF criteria in a screening setting. However, the model should be further validated in other populations and evaluated in a prospective trial setting.

Promising microRNAs in pre-diagnostic serum associated with lung cancer up to eight years before diagnosis: a HUNT study

INTRODUCTION

Blood biomarkers for early detection of lung cancer (LC) are in demand. There are few studies of the full microRNome in serum of asymptomatic subjects that later develop LC. Here we searched for novel microRNA biomarkers in blood from non-cancer, ever-smokers populations up to eight years before diagnosis.

METHODS

Serum samples from 98,737 subjects from two prospective population studies, HUNT2 and HUNT3, were considered initially. Inclusion criteria for cases were: ever-smokers; no known cancer at study entrance; 0-8 years from blood sampling to LC diagnosis. Each future LC case had one control matched to sex, age at study entrance, pack-years, smoking cessation time, and similar HUNT Lung Cancer Model risk score. A total of 240 and 72 serum samples were included in the discovery (HUNT2) and validation (HUNT3) datasets, respectively, and analysed by next-generation sequencing. The validated serum microRNAs were also tested in two pre-diagnostic plasma datasets from the prospective population studies NOWAC (n = 266) and NSHDS (n = 258). A new model adding clinical variables was also developed and validated.

RESULTS

Fifteen unique microRNAs were discovered and validated in the pre-diagnostic serum datasets when all cases were contrasted against all controls, all with AUC > 0.60. In combination as a 15-microRNAs signature, the AUC reached 0.708 (discovery) and 0.703 (validation). A non-small cell lung cancer signature of six microRNAs showed AUC 0.777 (discovery) and 0.806 (validation). Combined with clinical variables of the HUNT Lung Cancer Model (age, gender, pack-years, daily cough parts of the year, hours of indoor smoke exposure, quit time in years, number of cigarettes daily, body mass index (BMI)) the AUC reached 0.790 (discovery) and 0.833 (validation). These results could not be validated in the plasma samples.

CONCLUSION

There were a few significantly differential expressed microRNAs in serum up to eight years before diagnosis. These promising microRNAs alone, in concert, or combined with clinical variables have the potential to serve as early diagnostic LC biomarkers. Plasma is not suitable for this analysis. Further validation in larger prospective serum datasets is needed.

Improving Lung Cancer Screening Selection: The HUNT Lung Cancer Risk Model for Ever-Smokers Versus the NELSON and 2021 United States Preventive Services Task Force Criteria in the Cohort of Norway: A Population-Based Prospective Study

Background

Improving the method for selecting participants for lung cancer (LC) screening is an urgent need. Here, we compared the performance of the Helseundersøkelsen i Nord-Trøndelag (HUNT) Lung Cancer Model (HUNT LCM) versus the Dutch-Belgian lung cancer screening trial (Nederlands-Leuvens Longkanker Screenings Onderzoek (NELSON)) and 2021 United States Preventive Services Task Force (USPSTF) criteria regarding LC risk prediction and efficiency.

Methods

We used linked data from 10 Norwegian prospective population-based cohorts, Cohort of Norway. The study included 44,831 ever-smokers, of which 686 (1.5%) patients developed LC; the median follow-up time was 11.6 years (0.01-20.8 years).

Results

Within 6 years, 222 (0.5%) individuals developed LC. The NELSON and 2021 USPSTF criteria predicted 37.4% and 59.5% of the LC cases, respectively. By considering the same number of individuals as the NELSON and 2021 USPSTF criteria selected, the HUNT LCM increased the LC prediction rate by 41.0% and 12.1%, respectively. The HUNT LCM significantly increased sensitivity (p < 0.001 and p = 0.028), and reduced the number needed to predict one LC case (29 versus 40, p < 0.001 and 36 versus 40, p = 0.02), respectively. Applying the HUNT LCM 6-year 0.98% risk score as a cutoff (14.0% of ever-smokers) predicted 70.7% of all LC, increasing LC prediction rate with 89.2% and 18.9% versus the NELSON and 2021 USPSTF, respectively (both p < 0.001).

Conclusions

The HUNT LCM was significantly more efficient than the NELSON and 2021 USPSTF criteria, improving the prediction of LC diagnosis, and may be used as a validated clinical tool for screening selection.

A prediction model for classifying maternal pregnancy smoking using California state birth certificate information

BACKGROUND

Systematically recorded smoking data are not always available in vital statistics records, and even when available it can underestimate true smoking rates.

OBJECTIVE

To develop a prediction model for maternal tobacco smoking in late pregnancy based on birth certificate information using a combination of self- or provider-reported smoking and biomarkers (smoking metabolites) in neonatal blood spots as the alloyed gold standard.

METHODS

We designed a case-control study where childhood cancer cases were identified from the California Cancer Registry and controls were from the California birth rolls between 1983 and 2011 who were cancer-free by the age of six. In this analysis, we included 894 control participants and performed high-resolution metabolomics analyses in their neonatal dried blood spots, where we extracted cotinine [mass-to-charge ratio (m/z) = 177.1023] and hydroxycotinine (m/z = 193.0973). Potential predictors of smoking were selected from California birth certificates. Logistic regression with stepwise backward selection was used to build a prediction model. Model performance was evaluated in a training sample, a bootstrapped sample, and an external validation sample.

RESULTS

Out of seven predictor variables entered into the logistic model, five were selected by the stepwise procedure: maternal race/ethnicity, maternal education, child's birth year, parity, and child's birth weight. We calculated an overall discrimination accuracy of 0.72 and an area under the receiver operating characteristic curve (AUC) of 0.81 (95% confidence interval [CI] 0.77, 0.84) in the training set. Similar accuracies were achieved in the internal (AUC 0.81, 95% CI 0.77, 0.84) and external (AUC 0.69, 95% CI 0.64, 0.74) validation sets.

CONCLUSIONS

This easy-to-apply model may benefit future birth registry-based studies when there is missing maternal smoking information; however, some smoking status misclassification remains a concern when only variables from the birth certificate are used to predict maternal smoking.

Open science practices need substantial improvement in prognostic model studies in oncology using machine learning

OBJECTIVE

To describe the frequency of open science practices in a contemporary sample of studies developing prognostic models using machine learning methods in the field of oncology.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching the MEDLINE database between December 1, 2022, and December 31, 2022, for studies developing a multivariable prognostic model using machine learning methods (as defined by the authors) in oncology. Two authors independently screened records and extracted open science practices.

RESULTS

We identified 46 publications describing the development of a multivariable prognostic model. The adoption of open science principles was poor. Only one study reported availability of a study protocol, and only one study was registered. Funding statements and conflicts of interest statements were common. Thirty-five studies (76%) provided data sharing statements, with 21 (46%) indicating data were available on request to the authors and seven declaring data sharing was not applicable. Two studies (4%) shared data. Only 12 studies (26%) provided code sharing statements, including 2 (4%) that indicated the code was available on request to the authors. Only 11 studies (24%) provided sufficient information to allow their model to be used in practice. The use of reporting guidelines was rare: eight studies (18%) mentioning using a reporting guideline, with 4 (10%) using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis statement, 1 (2%) using Minimum Information About Clinical Artificial Intelligence Modeling and Consolidated Standards Of Reporting Trials-Artificial Intelligence, 1 (2%) using Strengthening The Reporting Of Observational Studies In Epidemiology, 1 (2%) using Standards for Reporting Diagnostic Accuracy Studies, and 1 (2%) using Transparent Reporting of Evaluations with Nonrandomized Designs.

CONCLUSION

The adoption of open science principles in oncology studies developing prognostic models using machine learning methods is poor. Guidance and an increased awareness of benefits and best practices of open science are needed for prediction research in oncology.

Identification of non-small cell lung cancer with chronic obstructive pulmonary disease using clinical symptoms and routine examination: a retrospective study

Background

Patients with non-small cell lung cancer (NSCLC) and patients with NSCLC combined with chronic obstructive pulmonary disease (COPD) have similar physiological conditions in early stages, and the latter have shorter survival times and higher mortality rates. The purpose of this study was to develop and compare machine learning models to identify future diagnoses of COPD combined with NSCLC patients based on the patient's disease and routine clinical data.

Methods

Data were obtained from 237 patients with COPD combined with NSCLC as well as NSCLC admitted to Ningxia Hui Autonomous Region People's Hospital from October 2013 to July 2022. Six machine learning algorithms (K-nearest neighbor, logistic regression, eXtreme gradient boosting, support vector machine, naïve Bayes, and artificial neural network) were used to develop prediction models for NSCLC combined with COPD. Sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, Mathews correlation coefficient (MCC), Kappa, area under the receiver operating characteristic curve (AUROC)and area under the precision-recall curve (AUPRC) were used as performance indicators to evaluate the performance of the models.

Results

135 patients with NSCLC combined with COPD, 102 patients with NSCLC were included in the study. The results showed that pulmonary function and emphysema were important risk factors and that the support vector machine-based identification model showed optimal performance with accuracy:0.946, recall:0.940, specificity:0.955, precision:0.972, npv:0.920, F1 score:0.954, MCC:0.893, Kappa:0.888, AUROC:0.975, AUPRC:0.987.

Conclusion

The use of machine learning tools combining clinical symptoms and routine examination data features is suitable for identifying the risk of concurrent NSCLC in COPD patients.

Secondary prevention and treatment innovation of early stage non-small cell lung cancer: Impact on diagnostic-therapeutic pathway from a multidisciplinary perspective

Lung cancer (LC) is the leading cause of cancer-related death worldwide, mostly because the lack of a screening program so far. Although smoking cessation has a central role in LC primary prevention, several trials on LC screening through low-dose computed tomography (LDCT) in a high risk population showed a significant reduction of LC related mortality. Most trials showed heterogeneity in terms of selection criteria, comparator arm, detection nodule method, timing and intervals of screening and duration of the follow-up. LC screening programs currently active in Europe as well as around the world will lead to a higher number of early-stage Non Small Cell Lung Cancer (NSCLC) at the diagnosis. Innovative drugs have been recently transposed from the metastatic to the perioperative setting, leading to improvements in terms of resection rates and pathological responses after induction chemoimmunotherapy, and disease free survival with targeted agents and immune checkpoint inhibitors. The present review summarizes available evidence about LC screening, highlighting potential pitfalls and benefits and underlining the impact on the diagnostic therapeutic pathway of NSCLC from a multidisciplinary perspective. Future perspectives in terms of circulating biomarkers under evaluation for patients' risk stratification as well as a focus on recent clinical trials results and ongoing studies in the perioperative setting will be also presented.

Lung Cancer Risk Prediction Nomogram in Nonsmoking Chinese Women: Retrospective Cross-sectional Cohort Study

BACKGROUND

It is believed that smoking is not the cause of approximately 53% of lung cancers diagnosed in women globally.

OBJECTIVE

The study aimed to develop and validate a simple and noninvasive model that could assess and stratify lung cancer risk in nonsmoking Chinese women.

METHODS

Based on the population-based Cancer Screening Program in Urban China, this retrospective, cross-sectional cohort study was carried out with a vast population base and an immense number of participants. The training set and the validation set were both constructed using a random distribution of the data. Following the identification of associated risk factors by multivariable Cox regression analysis, a predictive nomogram was developed. Discrimination (area under the curve) and calibration were further performed to assess the validation of risk prediction nomogram in the training set, which was then validated in the validation set.

RESULTS

In sum, 151,834 individuals signed up to take part in the survey. Both the training set (n=75,917) and the validation set (n=75,917) were comprised of randomly selected participants. Potential predictors for lung cancer included age, history of chronic respiratory disease, first-degree family history of lung cancer, menopause, and history of benign breast disease. We displayed 1-year, 3-year, and 5-year lung cancer risk-predicting nomograms using these 5 factors. In the training set, the 1-year, 3-year, and 5-year lung cancer risk areas under the curve were 0.762, 0.718, and 0.703, respectively. In the validation set, the model showed a moderate predictive discrimination.

CONCLUSIONS

We designed and validated a simple and noninvasive lung cancer risk model for nonsmoking women. This model can be applied to identify and triage people at high risk for developing lung cancers among nonsmoking women.

Possible Bias in Supervised Deep Learning Algorithms for CT Lung Nodule Detection and Classification

Simple Summary

Artificial Intelligence (AI) algorithms can assist clinicians in their daily tasks by automatically detecting and/or classifying nodules in chest CT scans. Bias of such algorithms is one of the reasons why implementation of them in clinical practice is still not widely adopted. There is no published review on the bias that these algorithms may contain. This review aims to present different types of bias in such algorithms and present possible ways to mitigate them. Only then it would be possible to ensure that these algorithms work as intended under many different clinical settings.

Abstract

Artificial Intelligence (AI) algorithms for automatic lung nodule detection and classification can assist radiologists in their daily routine of chest CT evaluation. Even though many AI algorithms for these tasks have already been developed, their implementation in the clinical workflow is still largely lacking. Apart from the significant number of false-positive findings, one of the reasons for that is the bias that these algorithms may contain. In this review, different types of biases that may exist in chest CT AI nodule detection and classification algorithms are listed and discussed. Examples from the literature in which each type of bias occurs are presented, along with ways to mitigate these biases. Different types of biases can occur in chest CT AI algorithms for lung nodule detection and classification. Mitigation of them can be very difficult, if not impossible to achieve completely.

Risk of bias of prognostic models developed using machine learning: a systematic review in oncology

BACKGROUND

Prognostic models are used widely in the oncology domain to guide medical decision-making. Little is known about the risk of bias of prognostic models developed using machine learning and the barriers to their clinical uptake in the oncology domain.

METHODS

We conducted a systematic review and searched MEDLINE and EMBASE databases for oncology-related studies developing a prognostic model using machine learning methods published between 01/01/2019 and 05/09/2019. The primary outcome was risk of bias, judged using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). We described risk of bias overall and for each domain, by development and validation analyses separately.

RESULTS

We included 62 publications (48 development-only; 14 development with validation). 152 models were developed across all publications and 37 models were validated. 84% (95% CI: 77 to 89) of developed models and 51% (95% CI: 35 to 67) of validated models were at overall high risk of bias. Bias introduced in the analysis was the largest contributor to the overall risk of bias judgement for model development and validation. 123 (81%, 95% CI: 73.8 to 86.4) developed models and 19 (51%, 95% CI: 35.1 to 67.3) validated models were at high risk of bias due to their analysis, mostly due to shortcomings in the analysis including insufficient sample size and split-sample internal validation.

CONCLUSIONS

The quality of machine learning based prognostic models in the oncology domain is poor and most models have a high risk of bias, contraindicating their use in clinical practice. Adherence to better standards is urgently needed, with a focus on sample size estimation and analysis methods, to improve the quality of these models.

Communication of personalised disease risk by general practitioners to motivate smoking cessation in England: a cost-effectiveness and research prioritisation study

BACKGROUND AND AIMS

Communication of personalised disease risk can motivate smoking cessation. We assessed whether routine implementation of this intervention by general practitioners (GPs) in England is cost-effective or whether we need further research to better establish its effectiveness.

DESIGN

Cost-effectiveness analysis (CEA) with value of information (VoI) analysis from the UK National Health Service perspective, using GP communication of personalised disease risk on smoking cessation versus usual care.

SETTING

GP practices in England.

STUDY POPULATION

Healthy smokers aged 35-60 years attending the GP practice.

MEASUREMENTS

Effectiveness of GP communication of personalised disease risk on smoking cessation was estimated through systematic review and meta-analysis. A Bayesian CEA was then performed using a lifetime Markov model on smokers aged 35-60 years that measured lifetime costs and quality-adjusted life-years (QALYs) assigned to the four diseases contributing the most to smoking-related morbidity, mortality and costs: chronic obstructive pulmonary disease, lung cancer, myocardial infarction and stroke. Costs and QALYs for each disease state were obtained from the literature. VoI analysis identified sources of uncertainty in the CEA and assessed how much would be worth investing in further research to reduce this uncertainty.

FINDINGS

The meta-analysis odds ratio for the effectiveness estimate of GP communication of personalised disease risk was 1.48 (95% credibility interval, 0.91-2.26), an absolute increase in smoking cessation rates of 3.84%. The probability of cost-effectiveness ranged 89-94% depending on sex and age. VoI analysis indicated that: (i) uncertainty in the effectiveness of the intervention was the driver of the overall uncertainty in the CEA; and (ii) a research investment to reduce this uncertainty is justified if lower than £27.6 million (£7 per smoker).

CONCLUSIONS

Evidence to date shows that, in England, incorporating disease risk communication into general practitioners' practices to motivate smoking cessation is likely to be cost-effective compared with usual care.

Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review

BACKGROUND

Describe and evaluate the methodological conduct of prognostic prediction models developed using machine learning methods in oncology.

METHODS

We conducted a systematic review in MEDLINE and Embase between 01/01/2019 and 05/09/2019, for studies developing a prognostic prediction model using machine learning methods in oncology. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement, Prediction model Risk Of Bias ASsessment Tool (PROBAST) and CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies (CHARMS) to assess the methodological conduct of included publications. Results were summarised by modelling type: regression-, non-regression-based and ensemble machine learning models.

RESULTS

Sixty-two publications met inclusion criteria developing 152 models across all publications. Forty-two models were regression-based, 71 were non-regression-based and 39 were ensemble models. A median of 647 individuals (IQR: 203 to 4059) and 195 events (IQR: 38 to 1269) were used for model development, and 553 individuals (IQR: 69 to 3069) and 50 events (IQR: 17.5 to 326.5) for model validation. A higher number of events per predictor was used for developing regression-based models (median: 8, IQR: 7.1 to 23.5), compared to alternative machine learning (median: 3.4, IQR: 1.1 to 19.1) and ensemble models (median: 1.7, IQR: 1.1 to 6). Sample size was rarely justified (n = 5/62; 8%). Some or all continuous predictors were categorised before modelling in 24 studies (39%). 46% (n = 24/62) of models reporting predictor selection before modelling used univariable analyses, and common method across all modelling types. Ten out of 24 models for time-to-event outcomes accounted for censoring (42%). A split sample approach was the most popular method for internal validation (n = 25/62, 40%). Calibration was reported in 11 studies. Less than half of models were reported or made available.

CONCLUSIONS

The methodological conduct of machine learning based clinical prediction models is poor. Guidance is urgently needed, with increased awareness and education of minimum prediction modelling standards. Particular focus is needed on sample size estimation, development and validation analysis methods, and ensuring the model is available for independent validation, to improve quality of machine learning based clinical prediction models.

Liquid Biopsy in Type 2 Diabetes Mellitus Management: Building Specific Biosignatures via Machine Learning

BACKGROUND

The need for minimally invasive biomarkers for the early diagnosis of type 2 diabetes (T2DM) prior to the clinical onset and monitoring of β-pancreatic cell loss is emerging. Here, we focused on studying circulating cell-free DNA (ccfDNA) as a liquid biopsy biomaterial for accurate diagnosis/monitoring of T2DM.

METHODS

ccfDNA levels were directly quantified in sera from 96 T2DM patients and 71 healthy individuals via fluorometry, and then fragment DNA size profiling was performed by capillary electrophoresis. Following this, ccfDNA methylation levels of five β-cell-related genes were measured via qPCR. Data were analyzed by automated machine learning to build classifying predictive models.

RESULTS

ccfDNA levels were found to be similar between groups but indicative of apoptosis in T2DM. INS (Insulin), IAPP (Islet Amyloid Polypeptide-Amylin), GCK (Glucokinase), and KCNJ11 (Potassium Inwardly Rectifying Channel Subfamily J member 11) levels differed significantly between groups. AutoML analysis delivered biosignatures including GCK, IAPP and KCNJ11 methylation, with the highest ever reported discriminating performance of T2DM from healthy individuals (AUC 0.927).

CONCLUSIONS

Our data unravel the value of ccfDNA as a minimally invasive biomaterial carrying important clinical information for T2DM. Upon prospective clinical evaluation, the built biosignature can be disruptive for T2DM clinical management.

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

Background

About 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.

Methods

A 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.

Results

A 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.

Conclusions

We 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.

A risk prediction model for selecting high-risk population for computed tomography lung cancer screening in China

OBJECTIVE

Two large randomized controlled trials (RCTs) have demonstrated that low dose computed tomography (LDCT) screening reduces lung cancer mortality. Risk-prediction models have been proved to select individuals for lung cancer screening effectively. With the focus on established risk factors for lung cancer routinely available in general cancer screening settings, we aimed to develop and internally validated a risk prediction model for lung cancer.

MATERIALS AND METHODS

Using data from the Cancer Screening Program in Urban China (CanSPUC) in Henan province, China between 2013 and 2019, we conducted a prospective cohort study consisting of 282,254 participants including 126,445 males and 155,809 females. Detailed questionnaire, physical assessment and follow-up were completed for all participants. Using Cox proportional risk regression analysis, we developed the Henan Lung Cancer Risk Models based on simplified questionnaire. Model discrimination was evaluated by concordance statistics (C-statistics), and model calibration was evaluated by the bootstrap sampling, respectively.

RESULTS

By 2020, a total of 589 lung cancer cases occurred in the follow-up yielding an incident density of 64.91/100,000 person-years (pyrs). Age, gender, smoking, history of tuberculosis and history of emphysema were included into the model. The C-index of the model for 1-year lung cancer risk was 0.766 and 0.741 in the training set and validation set, respectively. In stratified analysis, the model showed better predictive power in males, younger participants, and former or current smoking participants. The model calibrated well across the deciles of predicted risk in both the overall population and all subgroups.

CONCLUSIONS

We developed and internally validated a simple risk prediction model for lung cancer, which may be useful to identify high-risk individuals for more intensive screening for cancer prevention.

A CpG Methylation Signature as a Potential Marker for Early Diagnosis of Hepatocellular Carcinoma From HBV-Related Liver Disease Using Multiplex Bisulfite Sequencing

Background

Aberrant methylation of CpG sites served as an epigenetic marker for building diagnostic, prognostic, and recurrence models for hepatocellular carcinoma (HCC).

Methods

Using Illumina 450K and EPIC Beadchip, we identified 34 CpG sites in peripheral blood mononuclear cell (PBMC) DNA that were differentially methylated in early HCC versus HBV-related liver diseases (HBVLD). We employed multiplex bisulfite sequencing (MBS) based on next-generation sequencing (NGS) to measure methylation of 34 CpG sites in PBMC DNA from 654 patients that were divided into a training set (n = 442) and a test set (n = 212). Using the training set, we selected and built a six-CpG-scorer (namely, cg14171514, cg07721852, cg05166871, cg18087306, cg05213896, and cg18772205), applying least absolute shrinkage and selection operator (LASSO) regression. We performed multivariable analyses of four candidate risk predictors (namely, six-CpG-scorer, age, sex, and AFP level), using 20 times imputation of missing data, non-linearly transformed, and backwards feature selection with logistic regression. The final model’s regression coefficients were calculated according to “Rubin’s Rules”. The diagnostic accuracy of the model was internally validated with a 10,000 bootstrap validation dataset and then applied to the test set for validation.

Results

The area under the receiver operating characteristic curve (AUROC) of the model was 0.81 (95% CI, 0.77–0.85) and it showed good calibration and decision curve analysis. Using enhanced bootstrap validation, adjusted C-statistics and adjusted Brier score were 0.809 and 0.199, respectively. The model also showed an AUROC value of 0.84 (95% CI 0.79–0.88) of diagnosis for early HCC in the test set.

Conclusions

Our model based on the six-CpG-scorer was a reliable diagnosis tool for early HCC from HBVLD. The usage of the MBS method can realize large-scale detection of CpG sites in clinical diagnosis of early HCC and benefit the majority of patients.

Lung cancer in the older population:Interactive effects of angiotensin converting enzyme gene polymorphism (rs 4340 ID) and tobacco addiction in risk assessment

BACKGROUND

rs4340ID polymorphism of angiotensin-converting enzyme (ACE) correlates with serum ACE levels in many known cancers. This study analyzed ACE rs4340 ID polymorphism in lung cancer (LC) in older patients of North India and correlated it with addiction status.

METHODS

The study enrolled all subjects aged 60 years and above with 154 LC and 205 healthy controls. Genotyping was done by polymerase chain reaction (PCR) and validated by sequencing of 10% of the sample. Statistical analysis was done by SPSS Statistics 21.

RESULTS

Genotype II was observed to have a significant 2.21-fold increased risk of LC as compared to the DD genotype and 3.43-folds enhanced risk with interaction of I allele with tobacco consumption habits as compared to D allele in LC was seen.

CONCLUSION

The risk of LC was higher with II genotype as compared to DD genotype. Interactive effect showed that I allele with tobacco habits may increase the risk of LC.

Methylation Status of Corticotropin-Releasing Factor (CRF) Receptor Genes in Colorectal Cancer

The corticotropin-releasing factor (CRF) system has been strongly associated with gastrointestinal pathophysiology, including colorectal cancer (CRC). We previously showed that altered expression of CRF receptors (CRFRs) in the colon critically affects CRC progression and aggressiveness through regulation of colonic inflammation. Here, we aimed to assess the potential of CRFR methylation levels as putative biomarkers in CRC. In silico methylation analysis of CRF receptor 1 (CRFR1) and CRF receptor 2 (CRFR2) was performed using methylome data derived by CRC and Crohn's disease (CD) tissues and CRC-derived circulating cell-free DNAs (ccfDNAs). In total, 32 and 33 differentially methylated sites of CpGs (DMCs) emerged in CRFR1 and CRFR2, respectively, between healthy and diseased tissues. The methylation patterns were verified in patient-derived ccfDNA samples by qMSP and associated with clinicopathological characteristics. An automated machine learning (AutoML) technology was applied to ccfDNA samples for classification analysis. In silico analysis revealed increased methylation of both CRFRs in CRC tissue and ccfDNA-derived datasets. CRFR1 hypermethylation was also noticed in gene body DMCs of CD patients. CRFR1 hypermethylation was further validated in CRC adjuvant-derived ccfDNA samples, whereas CRFR1 hypomethylation, observed in metastasis-derived ccfDNAs, was correlated to disease aggressiveness and adverse prognostic characteristics. AutoML analysis based on CRFRs methylation status revealed a three-feature high-performing biosignature for CRC diagnosis with an estimated AUC of 0.929. Monitoring of CRFRs methylation-based signature in CRC tissues and ccfDNAs may be of high diagnostic and prognostic significance in CRC.

A Comparison of Web-Based Cancer Risk Calculators That Inform Shared Decision-making for Lung Cancer Screening

INTRODUCTION

To align patient preferences and understanding with harm-benefit perception, the Centers for Medicare & Medicaid Services (CMS) mandates that providers engage patients in a collaborative shared decision-making (SDM) visit before LDCT. Nonetheless, patients and providers often turn instead to the web for help making decisions. Several web-based lung cancer risk calculators (LCRCs) provide risk predictions and screening recommendations; however, the accuracy, consistency, and subsequent user interpretation of these predictions between LCRCs is ambiguous. We conducted a systematic review to assess this variability.

DESIGN

Through a systematic Internet search, we identified 10 publicly available LCRCs and categorized their input variables: demographic factors, cancer history, smoking status, and personal/environmental factors. To assess variance in LCRC risk prediction outputs, we developed 16 hypothetical patients along a risk continuum, illustrated by randomly assigned input variables, and individually compared them to each LCRC against the empirically validated "gold-standard" PLCO risk model in order to evaluate the accuracy of the LCRCs within identical time-windows.

RESULTS

From the inclusion criteria, 11 calculators were initially identified. The analyzed calculators also vary in output characteristics and risk depiction for hypothetical patients. There were 13 total instances across ten hypothetical patients in which the sample standard error exceeded the mean risk percentage across all general samples and set standard calculations. The largest measured difference is 16.49% for patient 8, and the smallest difference is 0.01% for patient 2. The largest measured difference is 16.49% for patient 8, and the smallest difference is 0.01% for patient 2.

CONCLUSION

Substantial variability in the depiction of lung cancer risk for hypothetical patients exists across the web-based LCRCs due to their respective inputs and risk prediction models. To foster informed decision-making in the SDM-LDCT context, the input variables, risk prediction models, risk depiction, and screening recommendations must be standardized to best practice.

Personalising lung cancer screening: An overview of risk-stratification opportunities and challenges

Randomised clinical trials have shown the efficacy of computed tomography lung cancer screening, initiating discussions on whether and how to implement population‐based screening programs. Due to smoking behaviour being the primary risk‐factor for lung cancer and part of the criteria for determining screening eligibility, lung cancer screening is inherently risk‐based. In fact, the selection of high‐risk individuals has been shown to be essential in implementing lung cancer screening in a cost‐effective manner. Furthermore, studies have shown that further risk‐stratification may improve screening efficiency, allow personalisation of the screening interval and reduce health disparities. However, implementing risk‐based lung cancer screening programs also requires overcoming a number of challenges. There are indications that risk‐based approaches can negatively influence the trade‐off between individual benefits and harms if not applied thoughtfully. Large‐scale implementation of targeted, risk‐based screening programs has been limited thus far. Consequently, questions remain on how to efficiently identify and invite high‐risk individuals from the general population. Finally, while risk‐based approaches may increase screening program efficiency, efficiency should be balanced with the overall impact of the screening program. In this review, we will address the opportunities and challenges in applying risk‐stratification in different aspects of lung cancer screening programs, as well as the balance between screening program efficiency and impact.

Lung cancer screening: who pays? Who receives? The European perspectives

Lung cancer is the leading cause of cancer-related death worldwide, and its early detection is critical to achieving a curative treatment and to reducing mortality. Low-dose computed tomography (LDCT) is a highly sensitive technique for detecting noninvasive small lung tumors in high-risk populations. We here analyze the current status of lung cancer screening (LCS) from a European point of view. With economic burden of health care in most European countries resting on the state, it is important to reduce costs of screening and improve its effectiveness. Current cost-effectiveness analyses on LCS have indicated a favorable economic profile. The most recently published analysis reported an incremental cost-effectiveness ratio (ICER) of €3,297 per 1 life-year gained adjusted for the quality of life (QALY) and €2,944 per life-year gained, demonstrating a 90% probability of ICER being below €15,000 and a 98.1% probability of being below €25,000. Different risk models have been used to identify the target population; among these, the PLCOM2012 in particular allows for the selection of the population to be screened with high sensitivity. Risk models should also be employed to define screening intervals, which can reduce the general number of LDCT scans after the baseline round. Future perspectives of screening in a European scenario are related to the will of the policy makers to implement policy on a large scale and to improve the effectiveness of a broad screening of smoking-related disease, including cardiovascular prevention, by measuring coronary calcium score on LDCT. The employment of artificial intelligence (AI) in imaging interpretation, the use of liquid biopsies for the characterization of CT-detected undetermined nodules, and less invasive, personalized surgical treatments, will improve the effectiveness of LCS.

Deciphering the Methylation Landscape in Breast Cancer: Diagnostic and Prognostic Biosignatures through Automated Machine Learning

DNA methylation plays an important role in breast cancer (BrCa) pathogenesis and could contribute to driving its personalized management. We performed a complete bioinformatic analysis in BrCa whole methylome datasets, analyzed using the Illumina methylation 450 bead-chip array. Differential methylation analysis vs. clinical end-points resulted in 11,176 to 27,786 differentially methylated genes (DMGs). Innovative automated machine learning (AutoML) was employed to construct signatures with translational value. Three highly performing and low-feature-number signatures were built: (1) A 5-gene signature discriminating BrCa patients from healthy individuals (area under the curve (AUC): 0.994 (0.982-1.000)). (2) A 3-gene signature identifying BrCa metastatic disease (AUC: 0.986 (0.921-1.000)). (3) Six equivalent 5-gene signatures diagnosing early disease (AUC: 0.973 (0.920-1.000)). Validation in independent patient groups verified performance. Bioinformatic tools for functional analysis and protein interaction prediction were also employed. All protein encoding features included in the signatures were associated with BrCa-related pathways. Functional analysis of DMGs highlighted the regulation of transcription as the main biological process, the nucleus as the main cellular component and transcription factor activity and sequence-specific DNA binding as the main molecular functions. Overall, three high-performance diagnostic/prognostic signatures were built and are readily available for improving BrCa precision management upon prospective clinical validation. Revisiting archived methylomes through novel bioinformatic approaches revealed significant clarifying knowledge for the contribution of gene methylation events in breast carcinogenesis.

Potential Disparities by Sex and Race or Ethnicity in Lung Cancer Screening Eligibility Rates

BACKGROUND

Criteria for low-dose CT scan lung cancer screening vary across guidelines. Knowledge of the eligible pool across demographic groups can enable policy and programmatic decision-making, particularly for disproportionately affected populations.

RESEARCH QUESTION

What are the eligibility rates for low-dose CT scan screening according to sex and race or ethnicity and how do these rates relate to corresponding lung cancer incidence rates?

STUDY DESIGN AND METHODS

This was a cross-sectional study using data from the 2015 National Health Interview Survey adult and cancer control supplement files. In addition to eligibility rates, the ratio of the eligibility rate to the lung cancer incidence rate in a given population group (eligibility to incidence [E-I] ratio) also was determined. Guidelines assessed were: Centers for Medicare and Medicaid Services, National Comprehensive Cancer Network, and US Preventive Services Task Force current or with expansion of age and smoking or quit thresholds. We also assessed a risk model (PLCO_M2012 risk model).

RESULTS

Total numbers eligible based on current guidelines ranged from 8.3 to 13.3 million, representing 8.3% to 13.4% of the US population 50 to 80 years of age, and up to 17.5 million with expanded criteria. Overall eligibility rates on average were about 10 percentage points higher for men than women. For both men and women, and both overall and among ever smokers, non-Hispanic Whites had the highest eligibility rates across all guidelines, followed generally by non-Hispanic Blacks, and then Asians and Hispanics. Among both men and women, non-Hispanic Whites had the highest E-I ratios across all guidelines; non-Hispanic Black men had higher lung cancer incidence, but 30% to 50% lower E-I ratios, than non-Hispanic White men.

INTERPRETATION

Screening eligibility rates vary widely across guidelines, with disparities evident in E-I ratios, including among non-Hispanic Black men, despite higher lung cancer burden. Consideration of smoking duration in risk assessment criteria may address current disparities.

Lung Screening Benefits and Challenges: A Review of The Data and Outline for Implementation

Lung cancer is the leading cause of cancer-related deaths worldwide, accounting for almost a fifth of all cancer-related deaths. Annual computed tomographic lung cancer screening (CTLS) detects lung cancer at earlier stages and reduces lung cancer-related mortality among high-risk individuals. Many medical organizations, including the U.S. Preventive Services Task Force, recommend annual CTLS in high-risk populations. However, fewer than 5% of individuals worldwide at high risk for lung cancer have undergone screening. In large part, this is owing to delayed implementation of CTLS in many countries throughout the world. Factors contributing to low uptake in countries with longstanding CTLS endorsement, such as the United States, include lack of patient and clinician awareness of current recommendations in favor of CTLS and clinician concerns about CTLS-related radiation exposure, false-positive results, overdiagnosis, and cost. This review of the literature serves to address these concerns by evaluating the potential risks and benefits of CTLS. Review of key components of a lung screening program, along with an updated shared decision aid, provides guidance for program development and optimization. Review of studies evaluating the population considered "high-risk" is included as this may affect future guidelines within the United States and other countries considering lung screening implementation.

Democratic and ethical problem of lung cancer screening: exclusion of true high-risk populations. Can it be fixed? Yes

Screening a population for a potentially deadly disease, the ultimate goal must be to prevent morbidity and mortality from this disease for the whole population. Unlike breast cancer or cervical cancer screening, where all women are screened after a certain age, CT screening for lung cancer has been based on selection of putative high-risk individuals based on age and smoking cut-off values. The type of selection used leaves too many high-risk individuals behind. The solution is to use only validated risk prediction models for selection.

Chronic non-communicable disease risk calculators - An overview, part I

This review identifies the different risk assessment tools that stratify the individual's risk of four of the eight leading causes of death in women: breast cancer, lung cancer, colorectal cancer and osteoporosis. It will be followed by the publication of a second paper that summarizes the risk assessment tools for the other four leading causes of death (myocardial infarction, stroke, diabetes mellitus type 2 and dementia). The different tools were compared by their use of different variables and validation criteria. To corroborate the validation process, validation study papers were considered for each risk assessment tool. Four tables, one for each illness, were designed. The tables provide an outline for each risk assessment tool, which includes its inventor/company, required variables, advantages, disadvantages and validity. These tables simplify the comparison of the different tools and enable the identification of the most suitable one for each patient.

Recommendations for Implementing Lung Cancer Screening with Low-Dose Computed Tomography in Europe

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was demonstrated in the National Lung Screening Trial (NLST) to reduce mortality from the disease. European mortality data has recently become available from the Nelson randomised controlled trial, which confirmed lung cancer mortality reductions by 26% in men and 39-61% in women. Recent studies in Europe and the USA also showed positive results in screening workers exposed to asbestos. All European experts attending the "Initiative for European Lung Screening (IELS)"-a large international group of physicians and other experts concerned with lung cancer-agreed that LDCT-LCS should be implemented in Europe. However, the economic impact of LDCT-LCS and guidelines for its effective and safe implementation still need to be formulated. To this purpose, the IELS was asked to prepare recommendations to implement LCS and examine outstanding issues. A subgroup carried out a comprehensive literature review on LDCT-LCS and presented findings at a meeting held in Milan in November 2018. The present recommendations reflect that consensus was reached.

Recommendations for Implementing Lung Cancer Screening with Low-Dose Computed Tomography in Europe

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was demonstrated in the National Lung Screening Trial (NLST) to reduce mortality from the disease. European mortality data has recently become available from the Nelson randomised controlled trial, which confirmed lung cancer mortality reductions by 26% in men and 39-61% in women. Recent studies in Europe and the USA also showed positive results in screening workers exposed to asbestos. All European experts attending the "Initiative for European Lung Screening (IELS)"-a large international group of physicians and other experts concerned with lung cancer-agreed that LDCT-LCS should be implemented in Europe. However, the economic impact of LDCT-LCS and guidelines for its effective and safe implementation still need to be formulated. To this purpose, the IELS was asked to prepare recommendations to implement LCS and examine outstanding issues. A subgroup carried out a comprehensive literature review on LDCT-LCS and presented findings at a meeting held in Milan in November 2018. The present recommendations reflect that consensus was reached.

Risk prediction model for lung cancer incorporating metabolic markers: Development and internal validation in a Chinese population

BACKGROUND

Low-dose computed tomography screening has been proved to reduce lung cancer mortality, however, the issues of high false-positive rate and overdiagnosis remain unsolved. Risk prediction models for lung cancer that could accurately identify high-risk populations may help to increase efficiency. We thus sought to develop a risk prediction model for lung cancer incorporating epidemiological and metabolic markers in a Chinese population.

METHODS

During 2006 and 2015, a total of 122 497 people were observed prospectively for lung cancer incidence with the total person-years of 976 663. Stepwise multivariable-adjusted logistic regressions with P_entry  = .15 and P_stay  = .20 were conducted to select the candidate variables including demographics and metabolic markers such as high-sensitivity C-reactive protein (hsCRP) and low-density lipoprotein cholesterol (LDL-C) into the prediction model. We used the C-statistic to evaluate discrimination, and Hosmer-Lemeshow tests for calibration. Tenfold cross-validation was conducted for internal validation to assess the model's stability.

RESULTS

A total of 984 lung cancer cases were identified during the follow-up. The epidemiological model including age, gender, smoking status, alcohol intake status, coal dust exposure status, and body mass index generated a C-statistic of 0.731. The full model additionally included hsCRP and LDL-C showed significantly better discrimination (C-statistic = 0.735, P = .033). In stratified analysis, the full model showed better predictive power in terms of C-statistic in younger participants (<50 years, 0.709), females (0.726), and former or current smokers (0.742). The model calibrated well across the deciles of predicted risk in both the overall population (P_HL  = .689) and all subgroups.

CONCLUSIONS

We developed and internally validated an easy-to-use risk prediction model for lung cancer among the Chinese population that could provide guidance for screening and surveillance.

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.

'Reduced' HUNT model outperforms NLST and NELSON study criteria in predicting lung cancer in the Danish screening trial

Hypothesis

We hypothesise that the validated HUNT Lung Cancer Risk Model would perform better than the NLST (USA) and the NELSON (Dutch‐Belgian) criteria in the Danish Lung Cancer Screening Trial (DLCST).

Methods

The DLCST measured only five out of the seven variables included in validated HUNT Lung Cancer Model. Therefore a ‘Reduced’ model was retrained in the Norwegian HUNT2-cohort using the same statistical methodology as in the original HUNT model but based only on age, pack years, smoking intensity, quit time and body mass index (BMI), adjusted for sex. The model was applied on the DLCST-cohort and contrasted against the NLST and NELSON criteria.

Results

Among the 4051 smokers in the DLCST with 10 years follow-up, median age was 57.6, BMI 24.75, pack years 33.8, cigarettes per day 20 and most were current smokers. For the same number of individuals selected for screening, the performance of the ‘Reduced’ HUNT was increased in all metrics compared with both the NLST and the NELSON criteria. In addition, to achieve the same sensitivity, one would need to screen fewer people by the ‘Reduced’ HUNT model versus using either the NLST or the NELSON criteria (709 vs 918, p=1.02e-11 and 1317 vs 1668, p=2.2e-16, respectively).

Conclusions

The ‘Reduced’ HUNT model is superior in predicting lung cancer to both the NLST and NELSON criteria in a cost-effective way. This study supports the use of the HUNT Lung Cancer Model for selection based on risk ranking rather than age, pack year and quit time cut-off values. When we know how to rank personal risk, it will be up to the medical community and lawmakers to decide which risk threshold will be set for screening.

Prediction of the 1-Year Risk of Incident Lung Cancer: Prospective Study Using Electronic Health Records from the State of Maine

BACKGROUND

Lung cancer is the leading cause of cancer death worldwide. Early detection of individuals at risk of lung cancer is critical to reduce the mortality rate.

OBJECTIVE

The aim of this study was to develop and validate a prospective risk prediction model to identify patients at risk of new incident lung cancer within the next 1 year in the general population.

METHODS

Data from individual patient electronic health records (EHRs) were extracted from the Maine Health Information Exchange network. The study population consisted of patients with at least one EHR between April 1, 2016, and March 31, 2018, who had no history of lung cancer. A retrospective cohort (N=873,598) and a prospective cohort (N=836,659) were formed for model construction and validation. An Extreme Gradient Boosting (XGBoost) algorithm was adopted to build the model. It assigned a score to each individual to quantify the probability of a new incident lung cancer diagnosis from October 1, 2016, to September 31, 2017. The model was trained with the clinical profile in the retrospective cohort from the preceding 6 months and validated with the prospective cohort to predict the risk of incident lung cancer from April 1, 2017, to March 31, 2018.

RESULTS

The model had an area under the curve (AUC) of 0.881 (95% CI 0.873-0.889) in the prospective cohort. Two thresholds of 0.0045 and 0.01 were applied to the predictive scores to stratify the population into low-, medium-, and high-risk categories. The incidence of lung cancer in the high-risk category (579/53,922, 1.07%) was 7.7 times higher than that in the overall cohort (1167/836,659, 0.14%). Age, a history of pulmonary diseases and other chronic diseases, medications for mental disorders, and social disparities were found to be associated with new incident lung cancer.

CONCLUSIONS

We retrospectively developed and prospectively validated an accurate risk prediction model of new incident lung cancer occurring in the next 1 year. Through statistical learning from the statewide EHR data in the preceding 6 months, our model was able to identify statewide high-risk patients, which will benefit the population health through establishment of preventive interventions or more intensive surveillance.

Circulating cell-free DNA in breast cancer: size profiling, levels, and methylation patterns lead to prognostic and predictive classifiers

Blood circulating cell-free DNA (ccfDNA) is a suggested biosource of valuable clinical information for cancer, meeting the need for a minimally-invasive advancement in the route of precision medicine. In this paper, we evaluated the prognostic and predictive potential of ccfDNA parameters in early and advanced breast cancer. Groups consisted of 150 and 16 breast cancer patients under adjuvant and neoadjuvant therapy respectively, 34 patients with metastatic disease and 35 healthy volunteers. Direct quantification of ccfDNA in plasma revealed elevated concentrations correlated to the incidence of death, shorter PFS, and non-response to pharmacotherapy in the metastatic but not in the other groups. The methylation status of a panel of cancer-related genes chosen based on previous expression and epigenetic data (KLK10, SOX17, WNT5A, MSH2, GATA3) was assessed by quantitative methylation-specific PCR. All but the GATA3 gene was more frequently methylated in all the patient groups than in healthy individuals (all p < 0.05). The methylation of WNT5A was statistically significantly correlated to greater tumor size and poor prognosis characteristics and in advanced stage disease with shorter OS. In the metastatic group, also SOX17 methylation was significantly correlated to the incidence of death, shorter PFS, and OS. KLK10 methylation was significantly correlated to unfavorable clinicopathological characteristics and relapse, whereas in the adjuvant group to shorter DFI. Methylation of at least 3 or 4 genes was significantly correlated to shorter OS and no pharmacotherapy response, respectively. Classification analysis by a fully automated, machine learning software produced a single-parametric linear model using ccfDNA plasma concentration values, with great discriminating power to predict response to chemotherapy (AUC 0.803, 95% CI [0.606, 1.000]) in the metastatic group. Two more multi-parametric signatures were produced for the metastatic group, predicting survival and disease outcome. Finally, a multiple logistic regression model was constructed, discriminating between patient groups and healthy individuals. Overall, ccfDNA emerged as a highly potent predictive classifier in metastatic breast cancer. Upon prospective clinical evaluation, all the signatures produced could aid accurate prognosis.

Selecting lung cancer screenees using risk prediction models-where do we go from here

The National Lung Screening Trial (NLST) demonstrated that low dose computed tomography (LDCT) screening could reduce lung cancer mortality by 20% in high-risk individuals. The United States Preventive Services Task Force (USPSTF) and Centers for Medicare and Medicaid Services (CMS) approved lung cancer screening. The NLST, USPSTF and CMS define high risk as smoking ≥30 pack-years, smoking within the past 15 years, and being ages 55-74, 55-80 or 55-77. Retrospective studies demonstrated selection using model-estimated risk is superior to NLST-like criteria: higher sensitivity and positive predictive value (PPV), more deaths averted and higher cost-effectiveness. Projects are underway that may additionally support use of risk to determine eligibility. Firstly, the International Lung Screen Trial (ILST) is prospectively enrolling 4,000 individuals for screening if individuals have PLCOm2012 model risk ≥1.5% or are USPSTF+ve. Six-year follow-up will allow comparisons. Interim results support the risk approach. Secondly, Cancer Care Ontario started the Lung Cancer Screening Pilot for People at High Risk in order to find optimal design for province-wide programmatic screening. They are enrolling 3,000 individuals to screening based on PLCOm2012 risk ≥2%. Some hesitation to recommend screening selection based on model risk comes from the observation that selected individuals are older, have more comorbidities, are expected to have fewer life years and quality-adjusted life years (QALY) and are more likely to die from competing causes. We show that 25.6% of NLST eligible smokers are at low risk (6-year lung cancer incidence proportion =0.008). This group will not benefit from screening but has lower age, fewer comorbidities and fewer competing causes of death. When they are excluded from the NLST+ve group, age, comorbidity count and competing causes of death are similar to those in the PLCOm2012+ve group. In some jurisdictions, model-based lung cancer screening selection needs to take into consideration the elevated risk in blacks and indigenous peoples.