Deceptive Measures of "Success" in Early Cancer Detection

Abstract

Early detection of cancer is considered a cornerstone of preventive medicine and is widely perceived as the gateway to reducing cancer deaths. Based on this assumption, large trials are currently underway to evaluate the accuracy of early detection tests. It is imperative, therefore, to set meaningful "success criteria" in early detection that reflect true improvements in health outcomes. This article discusses the pitfalls of measuring the success of early detection tests for cancer, particularly in the context of screening programs, and provides illustrative examples that demonstrate how commonly used metrics can be deceptive. Early detection can result in downstaging (favourable stage shift) when more early-stage cancers are diagnosed, even without reducing late-stage disease, potentially leading to overdiagnosis and overtreatment. Survival statistics, primarily cancer-specific survival, can be misleading due to lead time, where early detection simply extends the known duration of the disease without prolonging actual lifespan or improving overall survival. Additionally, the misuse of relative measures, such as proportions, ratios, and percentages, often make it impossible to ascertain the true benefit of a procedure and can distort the impact of screening as they are influenced by diagnostic practices, misleadingly improving perceived mortality reductions. Understanding these biases is crucial for accurately assessing the effectiveness of cancer detection methods and ensuring appropriate patient care.

Keywords: cancer; early diagnosis; overdiagnosis; stage distribution; survival.

Figure 1

Melanoma incidence and mortality trends in Australia. (A) The graphic depicts the relative rates (incidence, blue line; mortality, red line) over time between 1982 and 2017, age-adjusted to the Australian population according to the original Cancer Australia registry [22]. The rates in 1982 serve as the reference group. The arrow depicts the introduction of checkpoint inhibitors in the treatment of melanoma. (B) The graphic schematically depicts the most common occurrences that could explain a gap between incidence and mortality rates over time, namely, the true increase in incidence, with or without improved treatment, and overdiagnosis. The tinier blue lines represent the incidence trends that we would expect to have compared to mortality (red line) if the gap was only explained by increased background incidence (incidence and mortality grow in parallel) and improved treatment (the disparity between incidence and mortality increases).