Lay abstract for Statistics in Medicine article: Cost-effectiveness analysis under multiple effectiveness outcomes: A probabilistic approach

Each week, we will be publishing lay 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 Statistics in Medicine, with the full article now available to read  here.

Arsham, ABebu, IMathew, TCost-effectiveness analysis under multiple effectiveness outcomes: A probabilistic approachStatistics in Medicine20231– 20. doi: 10.1002/sim.9841

The economic evaluation of a new treatment is decisive in determining resource allocation between that treatment and a competing intervention. The criteria and analysis used to facilitate such evaluations are of emerging importance when there are priorities and multiple outcomes in the decision-making process.

In this work, probability-based criteria are developed to assess the cost-effectiveness of a new treatment compared to a standard treatment in the presence of a cost outcome and multiple measures of effectiveness. The proposed probability metrics quantify cost-effectiveness and incorporate policy maker priorities. Additionally, the criteria can be tailored to include relevant thresholds that may be required for cost-effectiveness evaluation. For example, a new treatment may need to provide a minimum gain in effectiveness compared to a standard treatment. Confidence limits are developed for the new probability criteria to determine if a new treatment is cost-effective.

The methodologies are illustrated on a study pertaining to the treatment of type two diabetes. Numerical and graphical results demonstrate the impact of thresholds on the probability of cost-effectiveness. The probability metrics are versatile as they may be modified for inclusion of different outcomes, priorities, and thresholds. These metrics and methods complement other evaluations, such as multi-criteria decision analysis.

More Details