Why standard survival models can provide misleading results in complex medical outcomes
In short: Researchers who study mortality often use specific mathematical models to predict risk. However, a review of epidemiological methods found that these standard models can produce biased results when multiple different causes of death or illness are possible at the same time.
In cases of competing risks, the mathematical relationship between the rate of an event and its actual risk is lost. This means that treating a competing event as if the person simply dropped out of the study leads to overestimating the likelihood of the primary outcome. The study used a stem cell transplantation example to illustrate how different factors can influence the rate of an event differently than the actual cumulative incidence.
The review highlights that researchers must choose their models carefully based on whether they want to understand the underlying hazard or the actual probability of an event occurring.
Why it matters: Understanding the distinction between hazard rates and actual risks is crucial for accurately interpreting medical data.
Opens the Intellect+ feed with this card first. Swipe up for the next one.
Sources
- Summary by Intellect · source: Research: Andersen et al. (2012). Competing risks in epidemiology: possibilities and pitfalls. International Journal of Epidemiology.
To cite this card, link to https://intellectplus.co.uk/app/science-research-why-standard-survival-models-can-provide-misleading-results.
How we source, check and correct cards: Editorial standards.
General information, not professional advice. Spotted an error? Flag the card or see corrections and complaints.
Intellect Plus is a visual educational discovery platform for exploring fascinating facts and ideas. Brain Food, Not Brain Rot. What is Intellect Plus?
Related
More in Science · Latest · A–Z · All topics
