Risk prediction models for selection of lung cancer screening candidates: A retrospective validation study

Summary

Background Selection of candidates for lung cancer screening based on individual risk has been proposed as an alternative to criteria based on age and cumulative smoking exposure (pack-years). Nine previously established risk models were assessed for their ability to identify those most likely to develop or die from lung cancer. All models considered age and various aspects of smoking exposure (smoking status, smoking duration, cigarettes per day, pack-years smoked, time since smoking cessation) as risk predictors. In addition, some models considered factors such as gender, race, ethnicity, education, body mass index, chronic obstructive pulmonary disease, emphysema, personal history of cancer, personal history of pneumonia, and family history of lung cancer. Methods and findings Retrospective analyses were performed on 53,452 National Lung Screening Trial (NLST) participants (1,925 lung cancer cases and 884 lung cancer deaths) and 80,672 Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial (PLCO) ever-smoking participants (1,463 lung cancer cases and 915 lung cancer deaths). Six-year lung cancer incidence and mortality risk predictions were assessed for (1) calibration (graphically) by comparing the agreement between the predicted and the observed risks, (2) discrimination (area under the receiver operating characteristic curve [AUC]) between individuals with and without lung cancer (death), and (3) clinical usefulness (net benefit in decision curve analysis) by identifying risk thresholds at which applying risk-based eligibility would improve lung cancer screening efficacy. To further assess performance, risk model sensitivities and specificities in the PLCO were compared to those based on the NLST eligibility criteria. Calibration was satisfactory, but discrimination ranged widely (AUCs from 0.61 to 0.81). The models outperformed the NLST eligibility criteria over a substantial range of risk thresholds in decision curve analysis, with a higher sensitivity for all models and a slightly higher specificity for some models. The PLCOm2012, Bach, and Two-Stage Clonal Expansion incidence models had the best overall performance, with AUCs >0.68 in the NLST and >0.77 in the PLCO. These three models had the highest sensitivity and specificity for predicting 6-y lung cancer incidence in the PLCO chest radiography arm, with sensitivities >79.8% and specificities >62.3%. In contrast, the NLST eligibility criteria yielded a sensitivity of 71.4% and a specificity of 62.2%. Limitations of this study include the lack of identification of optimal risk thresholds, as this requires additional information on the long-term benefits (e.g., life-years gained and mortality reduction) and harms (e.g., overdiagnosis) of risk-based screening strategies using these models. In addition, information on some predictor variables included in the risk prediction models was not available. Conclusions Selection of individuals for lung cancer screening using individual risk is superior to selection criteria based on age and pack-years alone. The benefits, harms, and feasibility of implementing lung cancer screening policies based on risk prediction models should be assessed and compared with those of current recommendations.

Key Points

• 1Nine risk prediction models were assessed for their effectiveness in identifying lung cancer candidates
• 2The study utilized data from two major lung cancer screening trials
• 3Results indicated that risk-based selection outperformed traditional age and pack-year criteria
• 4The PLCOm 2012, Bach, and Two-Stage Clonal Expansion models showed the best performance
• 5Further evaluation of the benefits and harms of risk-based screening policies is necessary.

Related articles

• Evaluating large language models for clinical note processing: local fine-tuning and internal-external validation using electronic health records from South Asia

  This research paper evaluates the effectiveness of large language models for processing clinical notes from electronic health records in South Asia, focusing on local fine-tuning and validation. It discusses the potential application of LLMs in clinical settings, particularly in resource-limited environments.

• Cardiac Cycle & Physiology: Understanding Cardiac Function

  This document provides a detailed overview of cardiac physiology, including the cardiac cycle, blood flow processes, and the cardiac conduction system. It aims to inform readers about the mechanics of the heart and its role in circulation.

• Cardiac Cycle & Physiology

  This document provides a comprehensive overview of cardiac cycle phases, blood flow through the heart, and the electrophysiology of cardiac conduction. It details the processes of deoxygenation and oxygenation of blood and the physiological aspects of cardiac output and common cardiovascular assessment findings.

• The Dual Pillars of Clinical and Community Care

  This document provides an in-depth examination of nutritional assessment and surveillance in clinical and community settings, offering guidelines on measuring malnutrition indicators and the importance of dietary interventions.

• Cather Simpson Lecture Research Brief Inaugural David Breen

  Cather Simpson Lecture Research Brief Inaugural David Breen Lecture | 14 October 2026 | 12 pm to 1 pm | AM103 The "Nespresso" of Diagnostics: Centrifugal Microfluidics for Point-of-Care Diagnostics; “Can we