search

giabaio / BCEA

Bayesian Cost Effectiveness Analysis. Given the results of a Bayesian model (possibly based on MCMC) in the form of simulations from the posterior distributions of suitable variables of costs and clinical benefits for two or more interventions, produces a health economic evaluation. Compares one of the interventions (the "reference") to the others ("comparators"). Produces many summary and plots to analyse the results
https://gianluca.statistica.it/software/bcea/
GNU General Public License v3.0
40 stars 16 forks source link

Cost effectiveness for non-standard models #13

Closed seabbs closed 4 years ago

seabbs commented 4 years ago

In my group we have a lot of people working on dynamic infectious disease models and then running cost effectiveness. This means they are typically working with simulation output for model states that they then apply health utilities and costs to.

Would you be interested in either some additional tooling or a simple vignette walking through how to take a model like this and use {BCEA} with it.

Linked to #6

giabaio commented 4 years ago

Together with a former PhD student, we too have done some work on infectious diseases and cost-effectiveness analysis. See some links here (including relevant literature) and a talk I gave at Imperial earlier this year, here.

I think that to some extent, infectious disease analyses may be integrated within the standard paradigm for cost-effectiveness --- essentially, the point in our work was that you have a trade-off between the resolution in the dynamic model and the fitness for the purposes of the wider economic analysis. And stuff like the "expanded" framework of (Bayesian) Markov models, which approximate to a good degree (at least in the examples we've considered) the full continuous-time transmission models could be very well suited for cost-effectiveness analysis.

Having said that, there may be lots more to discuss and potentially more complex models to be constructed. We have used extensively BCEA in our work on infectious disease (and in our set up, it was just another analysis with more of the same). If you have specific cases where that would not be the case, then shout and we can discuss.

seabbs commented 4 years ago

Yes, I very much agree that the current package works well for this. You are correct that resolution can add an additional step but ultimately this seems fairly easy to resolve.

Essentially my point is that some more documentation - in the form of a vignette - would really help to make this clear. Having a clear case study taking the output of an ID model and walking through the CE steps would be very useful to my group and I imagine others. This might help with the perception that BCEA is not model agnostic.

Again happy to work on a pull request for this.

giabaio commented 4 years ago

OK. I'll close this now, then --- but with the understanding we're both on it! :-)