The impact of overdiagnosis on the selection of efficient lung cancer screening strategies

Abstract

The U.S. Preventive Services Task Force (USPSTF) recently updated their national lung screening guidelines and recommended low-dose computed tomography (LDCT) for lung cancer (LC) screening through age 80. However, the risk of overdiagnosis among older populations is a concern. Using four comparative models from the Cancer Intervention and Surveillance Modeling Network, we evaluate the overdiagnosis of the screening program recommended by USPSTF in the U.S. 1950 birth cohort. We estimate the number of LC deaths averted by screening (D) per overdiagnosed case (O), yielding the ratio D/O, to quantify the trade-off between the harms and benefits of LDCT. We analyze 576 hypothetical screening strategies that vary by age, smoking, and screening frequency and evaluate efficient screening strategies that maximize the D/O ratio and other metrics including D and life-years gained (LYG) per overdiagnosed case. The estimated D/O ratio for the USPSTF screening program is 2.85 (model range: 1.5-4.5) in the 1950 birth cohort, implying LDCT can prevent ∼3 LC deaths per overdiagnosed case. This D/O ratio increases by 22% when the program stops screening at an earlier age 75 instead of 80. Efficiency frontier analysis shows that while the most efficient screening strategies that maximize the mortality reduction (D) irrespective of overdiagnosis screen through age 80, screening strategies that stop at age 75 versus 80 produce greater efficiency in increasing life-years gained per overdiagnosed case. Given the risk of overdiagnosis with LC screening, the stopping age of screening merits further consideration when balancing benefits and harms.

Keywords: USPSTF; computed tomography; health policy; lung cancer; lung cancer screening; microsimulation; overdiagnosis; simulation model.

Figure 1

Overdiagnosis risk (%) of 576 scenarios by stopping age of screening programs for each model and gender. Overdiagnosis risk is calculated as the number of overdiagnosed cases divided by the number of screen-detected cases. The number for each box represents a median of overdiagnosis risk of screening programs with given stopping age. “KW” denotes Kruskal-Wallis (K-W) test.

Figure 2

Comparisons of overdiagnosis risks and D/O ratios (the number of LC deaths prevented per overdiagnosed case) of the USPSTF and the NLST-like scenarios, by gender and both genders combined. Note: Overdiagnosis risk is calculated as the number of overdiagnosed cases divided by the number of screen-detected cases.

Figure 3

Consensus screening scenarios chosen for males by maximizing: (i) D, the number of LC deaths prevented (A); (ii) D/O, the number of LC deaths prevented per overdiagnosed case (B); (iii) life-years gained (LYG) (C); (iv) life-year gained per overdiagnosed case (LYG/O)(D); (v) D-O, net LC deaths prevented subtracting overdiagnosed cases (E); (vi) and D/(O/S), the number of LC deaths prevented per overdiagnosis risk (F), where S is the number of screen-detected cases. In each figure, we show the outcomes under several screening strategies that vary by age and smoking eligibility criteria. Each dot represents a specific screening strategy, with selected scenarios highlighted in color. Here, the x-axis is the number of CT screens that need to be performed under each strategy. Panel A shows the number of LC deaths avoided versus no-screening (D, y-axis) under the given strategy. Panels B–F show alternative outcome metrics: LC deaths avoided per overdiagnosed case (D/O, panel B), life-years gained (LYG, panel C), life-years gained per overdiagnosed case (LYG/O, panel D), the net prevented LC deaths subtracted by the number of overdiagnosed cases (D-O, panel E), and the number of LC deaths prevented per overdiagnosis risk (D/(O/S), panel F). Within each metric, a consensus scenario was identified by choosing a scenario that is defined as an “efficient scenario” (i.e. top 25% closest scenarios to the efficient frontier) by at least three out of the four models under each metric. The consensus scenarios are listed in the legend box and highlighted for a representative model. For each panel, the NLST-like and the USPSTF scenarios are plotted for reference purposes, regardless on whether or not they are included in the consensus list. The results for females are shown in Supplemental Figure 5–6. Note: Each legend box shows the scenarios selected by consensus across the four models and annotated as Frequency–Start Age (y)–Stop Age (y)–Pack- Years–Years Since Quitting.