Adaptation and Evaluation of a Multi-Criteria Decision Analysis Model for Lyme Disease Prevention

Abstract

Designing preventive programs relevant to vector-borne diseases such as Lyme disease (LD) can be complex given the need to include multiple issues and perspectives into prioritizing public health actions. A multi-criteria decision aid (MCDA) model was previously used to rank interventions for LD prevention in Quebec, Canada, where the disease is emerging. The aim of the current study was to adapt and evaluate the decision model constructed in Quebec under a different epidemiological context, in Switzerland, where LD has been endemic for the last thirty years. The model adaptation was undertaken with a group of Swiss stakeholders using a participatory approach. The PROMETHEE method was used for multi-criteria analysis. Key elements and results of the MCDA model are described and contrasted with the Quebec model. All criteria and most interventions of the MCDA model developed for LD prevention in Quebec were directly transferable to the Swiss context. Four new decision criteria were added, and the list of proposed interventions was modified. Based on the overall group ranking, interventions targeting human populations were prioritized in the Swiss model, with the top ranked action being the implementation of a large communication campaign. The addition of criteria did not significantly alter the intervention rankings, but increased the capacity of the model to discriminate between highest and lowest ranked interventions. The current study suggests that beyond the specificity of the MCDA models developed for Quebec and Switzerland, their general structure captures the fundamental and common issues that characterize the complexity of vector-borne disease prevention. These results should encourage public health organizations to adapt, use and share MCDA models as an effective and functional approach to enable the integration of multiple perspectives and considerations in the prevention and control of complex public health issues such as Lyme disease or other vector-borne and zoonotic diseases.

Fig 1. Distribution of weights for Swiss (dark lines. n = 9) and Quebec (dotted lines. n = 8) stakeholders for the 12 original criteria.

Legend: PHC1 Reduction in incidence of human cases; PHC2 Reduction in entomological risk; PHC3 Impacts of adverse health effects; AEC1 Impact on habitat; AEC2 Impact on wildlife; SIC1 Level of public acceptance; SIC2 Proportion of population benefitting from intervention; SEC1 Cost to the public sector; SEC2 Cost to the private sector; SEC3 Delay before results; SEC4 Complexity; SEC5 Impact on organisation’s credibility.

Fig 2. Effect of Swiss criteria removal on intervention scores (Y axis).

Legend: In scenario (A), the overall group ranking considered all criteria from the Swiss model and in scenario (B). The overall group ranking considered only the original criteria from the Quebec model. The model becomes less discriminating between the “best” and “worst” interventions when Swiss criteria are removed (INT0 Status quo; INT1 Reduction of human visits to high-risk public areas via the use of fences or prohibitive signs; INT2 Human vaccination; INT3 Large communication campaign; INT4 Making available special clinics for diagnosis of complex cases; INT5 Making available special clinics for complex LD cases management; INT6 Learning sessions for physicians; INT7 Small scale acaricide application; INT8 Small scale landscaping; INT9‘4-poster' device; INT10 Deer hunting; INT11 Exclusion of deer by fencing; INT12 ‘Damminix’ device).