Layman’s abstract for Pharmaceutical Statistics paper on recurrent time‐to‐event models with ordinal outcomes

Each week, we will be publishing layman’s abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.

The article featured today is from Pharmaceutical Statistics, with the full article now available to read here.

Gebski, VByth, KAsher, RMarschner, IRecurrent time‐to‐event models with ordinal outcomesPharmaceutical Statistics202177– 92https://doi.org/10.1002/pst.2057

Problems having time to event endpoints are common in medical science. However, when these events may themselves be ordered with respect to their degree of severity, harm or benefit. Standard time to event methods cannot easily accommodate these situations and special methods are required. Furthermore, over time if these endpoints re-occur, interest focuses om not just risk of the event but also of the severity of the event. This is the case with patients being treated for cancer who may need to take treatment for long periods and will repeatedly experience different severity levels of toxicity over this time.

This paper proposes methods to address such problems and three approaches are examined in detail: (i) the probability of an individual experiencing an event of a particular severity as their first, second, third….  recurrence up to a certain time; (ii having experienced an event, the probability that the next event will be of a particular severity before a certain time and (iii) having experienced and event, the probability that the next event of a particular severity will be occur sooner/longer than patients receiving a different treatment.

Very few studies have adopted this approach, despite its appeal in incorporating several ordered categories of event outcome. More recently, there has been increased interest in utilizing recurrent events to analyse practical endpoints in the study of disease history and to help quantify the changing pattern of disease over time. For example, in studies of heart failure the analysis of a single fatal event no longer provides sufficient clinical information to manage the disease. Similarly, the grade/frequency/severity of adverse events may be more important than simply prolonged survival in studies of toxic therapies in oncology.

These methods extend the time to event with ordinal outcomes to problems where recurrent/multiple events with such outcomes are common. These relate to areas such as epileptic episodes; cardiovascular events; dialysis and infection and toxicity grades in cancer treatments.

 

More Details