How to Deal with Cost Differences at Baseline

Abstract

Although the routine starting point of an analysis should always be an unadjusted analysis of the cost effectiveness, a baseline difference between treatment groups should be adjusted for. This should be done by reported patient characteristics or, when these are not sufficiently present, by baseline costs as a substitute. This adjustment should be carried out most preferably with a regression-based method.

An economic evaluation of a multicomponent self‐management intervention for adults with epilepsy (ZMILE study)

“…Hence, it is important to investigate this influence. 33 The lack of effectiveness of the MCI on the ESES and EQ-5D-5L may be explained by several factors. Of course, it could be that the intervention is not effective.…”

“…33,34 One-way sensitivity analyses were performed by the following: (1) using disease-specific QALYs based on the QOLIE-31-P; (2) applying a healthcare perspective, instead of a societal perspective, as some European countries tend to adopt this; (3) excluding the costs of the MEMS for the CAU group, as patients in the CAU group did not receive any feedback from the MEMS and simply used the device for research purposes; and (4) by using the UK tariff to value the EQ-5D-5L health states.…”

Cost-Effectiveness of Structured Education in Children With Type-1 Diabetes Mellitus

“…However, with small refinements, the Sheffield Type 1 Diabetes Policy Model could be used to analyse the effects of additional interventions. For example, the Model will be used to analyse trials for adolescents (aged [16][17][18][19][20][21] called Working with Insulin, Carbs, Ketones and Exercise to manage Diabetes (WICKED) [23].…”

“…When the cost data were analysed for individuals with complete utility data only, the cost of each arm reduced, suggesting that the cost per individual for those individuals with a missing utility data was higher on average than the overall mean. Once the missing utility data had been imputed, the mean cost value for each arm approached back to the level of A regression-based adjustment, which controls for the baseline value and the treatment arm, applied on the cost values [17]. This approach resulted in costs differences that were similar to the simple adjusted differences when complete case data were used, whereas they were significantly different when imputed data was used ( Table 2).…”

Health technology assessment of hyperphosphatemia management among hemodialysis patients in Lebanon

“…Feasible statistical means are needed to allow simultaneous multiple adjustments and the generation of patient-level data (for bootstrapping and for the construction of cost-effectiveness acceptability curves). Furthermore, as these baseline differences suggest higher baseline use of resources and costs in the DD group, it would have been wise to collect costs data at baseline, and complement our analysis with a regression-based adjustment of patient-level cost data [76]. Although it is not common to report baseline costs in trial-based economic evaluations, van Asselt et al [76] argued that costs at baseline would influence costs during the trial and presented the case for reporting these costs and investigating their influence, in order to be able to attribute the difference that is found afterwards to the intervention.…”