In the context of global climate changes, zoonotic and vector-borne diseases may intensify their threat to human health [1]. Lyme disease (LD) is a good example of a complex disease that is affected by global changes, including climate disruption and changing landscapes [2–5]. Transmitted to humans by a tick bite, LD is caused by the bacteria Borrelia burgdorferi sensu lato whose reservoirs include wild animals such as small rodents and various bird species [6]. Its main geographic distribution is Eurasia and North America. It is currently the most frequent vector-borne disease in temperate countries on Northern hemisphere with incidence rising in many of them. In Europe, about 85,000 cases are reported annually [7] and a recent adjusted estimation evaluates that the number of cases per year could reach 300,000 in the United States [8]. LD vectors have been increasingly found in new northern locations, such as in South-Eastern Canada, where Ixodes scapularis ticks have recently become established and where LD is emerging [9, 10].

LD preventive strategies can be divided into actions targeting human populations, such as the promotion of individual preventive behaviors through enhanced public health communications or the development of a vaccine against LD, and actions that aim to reduce the exposure of individuals by reducing tick density in the environment [11–15]. For this second category of actions, several interventions have been tested in experimental settings or in the field, and include actions that directly target tick populations via the use of acaricides or landscaping, and indirect actions that target wild animals which are hosts of the vector and/or reservoirs of the agent, such as the reduction of deer density, the treatment of deer against ticks, the treatment of small rodents against ticks and the vaccination of rodents against Borrelia sp (environmental preventive measures against LD are reviewed in Piesman and Eisen [11]). While most public health efforts have been focused on promoting individual preventive measures in the populations at risk in affected countries, no clear consensus has been reached among experts and public health professionals as to what constitute the best practices for LD prevention. One reason for this is that the majority of proposed strategies may have potential impacts which can be conflicting with their positive effects on human health, such as high public costs, unknown public acceptability, complex implementation and uncertain efficacy to reduce LD incidence [16].

Prevention and control of zoonoses and vector-borne diseases such as LD is a complex challenge that needs to be addressed with a systemic and transdisciplinary approach. Multi-criteria decision aid (MCDA) tools comes from the field of decision sciences and have been used to prioritize and rank public health interventions, including preventive interventions for zoonoses and vector-borne diseases [17, 16, 18]. Several multi-criteria analysis methodologies exist to study different types of problems [19], including for ranking multiple options based on a list of decision criteria, for which the PROMETHEE method (Preference Ranking Organization Method for Enrichment Evaluations) has been widely used [20, 21]. PROMETHEE method is in the family of outranking methods in MCDA and can be understood as a 10-step systematic process which can be broadly divided into two phases [16]. First, the ‘problem structuring’ phase leads to the building of a MCDA matrix that allows the evaluation of a list of possible options according to a list of decision criteria. The criteria should be exhaustive, coherent and non-reductant and should represent all important issues as identified by concerned stakeholders in relation to the problem. The measurement scale of the criteria can be either quantitative or qualitative, a flexibility that permits the incorporation of expert assessment whenever literature or field-supported data are missing on an aspect of the problem. The criteria can be weighted by different stakeholders according to the criteria’s relative importance in the decision process. Second, the ‘decision analysis’ phase proceeds to pair-wise comparisons to produce several outputs with the objective of facilitating decision-making, including stakeholder and overall group rankings of options. Option profiles and decision maps (GAIA plans [22]) are outputs that are useful for visualizing points of convergence and divergence points among stakeholders across the range of issues captured by the identified criteria.

Aenishaenslin and colleagues [16] used MCDA to prioritize actions for LD surveillance, prevention and control in the province of Quebec, Canada, in an epidemiological context of LD emergence with low global incidence. One of the main conclusions made by the authors was that a part of the models parameters, and particularly the list of criteria, could be seen as a generic structure for other vector-borne and zoonotic disease management contexts.

Based on this hypothesis, the aim of the current study was to evaluate the applicability of the MCDA model for LD preventive interventions previously developed in Quebec in a different epidemiological context. More precisely, we had the objective to identify parameters that were directly transferable and those that needed to be modified to capture issues specific to the new context. For this purpose, Switzerland was chosen as a result of its contrasting LD epidemiological situation. In this country, LD has been endemic for over thirty years with a high incidence of 83 cases per 100,000 inhabitants estimated in 2010 [23]. LD ecology differs between Europe and North America with a greater diversity of species that can be reservoirs of the bacteria, hosts species of the vector and the primary tick vector, Ixodes ricinus, generally found in European regions [24]. Despite this, the majority of the recommended preventive strategies are believed to be applicable in both contexts. A secondary objective of the study was to contrast the main results produced with the Swiss MCDA model with those of the Quebec MCDA model [16].

The 12 original criteria from the Quebec model were considered as important and were retained in the model without modification. In addition, the Swiss stakeholders suggested four new criteria, for a total of 16 criteria. The efficacy of the intervention to reduce the incidence of disseminated LD cases was added to the ‘public health’ category of criteria (disseminated LD cases represents the subset of cases for which the infection has become systemic, resulting generally in a more severe illness). The ability of the intervention to raise the level of public awareness was added to the ‘social impacts’ category. The sustainability of the intervention’s effect and the level of coherence within the European strategy to prevent LD were added to the ‘economic, operational and strategic’ category (Table 2). The description of measurement scales for each criterion can be found in S1 Table.

The list of potential interventions was modified following discussion with stakeholders. Six interventions were removed, two were modified and two new interventions were added, resulting in a final list of 13 interventions labeled INT0 to INT12 (see Table 3: modification details and justifications). The resulting performance matrix can be found in S2 Table. During the second focus group meeting held in November 2014, all stakeholders agreed that the modified model (criteria, interventions and performance matrix) was representative of important issues relative to LD prevention in Switzerland.

Weights per category and specific criteria varied according to stakeholders (Table 4). For 7 out of 9 stakeholders, the highest weight was given to the public health category, but other category weights varied greatly between stakeholders. Fig 1 shows the distribution of criteria weights for Swiss and Quebec stakeholders from the Quebec model for scenario B (showing only criteria included in the Quebec model). Fig 1 highlights the variation in weight distribution between Swiss and Quebec stakeholders, and shows how for seven criteria out of twelve, the weight range was larger among Swiss stakeholders. The largest variation can be observed for criteria ‘Adverse public health effect’ (PH3), where Swiss stakeholders weights ranged from 3 to 40, compared to a weight range of only 6 to 12 by Quebec stakeholders [16].

The overall group ranking performed under scenario A (all criteria) shows that one intervention clearly outperforms all the others: ‘Large communication campaign’ (INT3), as the preferred intervention, with a score of 81, followed by ‘Status quo’ (INT0) (score = 65) and ‘Reduction of human visits to high-risk public areas via the use of fences or prohibitive signs’ (INT1) (score = 58.5) (Table 5). All interventions targeting human populations (INT0 to INT6) were positioned in a higher rank than interventions from other categories (INT7 to INT12, targeting ticks through direct or indirect actions) (Table 5). The first top two ranked interventions, INT3 and INT0, were the same under both scenarios A and B (Table 5, Fig 2). When ranks were compared under scenarios A and B, we observed that the most important differences in rank orderings were found for interventions ‘Special clinics for diagnosis of complex cases’ (INT4) and ‘Special clinics for complex cases management’ (INT5), which moved from position 4 in scenario A to position 7 in scenario B (Table 5, Fig 2A and 2B). ‘Human vaccination’ (INT2) gained two positions and moved from position 5 in scenario A to position 3 in scenario B. All other interventions changed by no more than one position in the order of ranking.

One second observation is that the range between maximum and minimum scores of interventions decreases from scenario A (maximum score = 81 and minimum score = 31) to scenario B (maximum score = 71 and minimum score = 37). The score of an intervention calculated with the PROMETHEE method can be considered as a numerical representation of ‘how well’ an intervention outranks another, considering its intrinsic performance on each criterion and all stakeholders weighting schemes. Globally, higher an intervention scores when compared to other intervention’s scores, more performant it is relative to the others. On the contrary, if all intervention scores are closed to each other, it is harder to clearly identify interventions that truly outrank others. Thus, the score range difference suggests that preference for the best-ranked interventions was stronger under the first scenario, when all criteria were taken into account (Table 5).

The GAIA decision map produced under scenario A showed a good level of agreement among stakeholders, with all stakeholders (S1 to S9) positioned in the same general direction as the overall group decision vector shown in red (S1A Fig). Interventions targeting ticks through direct actions on the environment (INT7 and INT8, in green in the map) or through actions on hosts (INT9 to INT12, in red in the map) shown on the left side of the decision map suggest that these interventions were not preferred by the group. This was also the case in the analysis performed with the Quebec model (S1B Fig).

Criteria and their general category from the Quebec model were directly transposable to the Swiss context. The addition of four new criteria and follow-up discussion with Swiss stakeholders suggests that the new model succeeded in capturing specific issues of the LD epidemiological situation and geopolitical context of Switzerland. The inclusion of ‘Reduction in incidence of disseminated LD cases’ (PHC4) is revealing. By including this criterion that focuses on the reduction of a subset of LD cases in addition to ‘Reduction of LD incidence’ (PHC1), Swiss stakeholders underlined their specific concerns relating to severe cases. Notably, two stakeholders (S3 and S5) put more weights on this criterion than on PHC1. Given that early LD cases can be treated most often successfully, it is understandable that a high-incidence region may want to prioritize actions to reduce severe LD cases which are of particular concern for the population and which may have the higher societal costs, in contrast to a lower incidence region such as the province of Quebec. The addition of ‘Level of public awareness’ (SIC3) and ‘Sustainability of effect’ (SEC6) can also be understood in light of the country’s LD history: the Swiss population has coped with this ongoing public health issue for a long time and may have observed or perceived that short-term actions may not be appropriate in their context. Finally, the inclusion of ‘Level of coherence with European strategies’ (SEC7) is understandable given the geographical and political situation of Switzerland, even if only low weights were attributed to this criterion by all stakeholders (weights range from 0 to 7).

The proposed interventions listed in the Quebec model needed modifications to suit the Swiss situation and this may be explained by the geographical and the social context of Switzerland. For example, as stated by stakeholders during the focus groups, the Swiss population has placed great value on sustainability and on the protection of its environment. Consequently, all large scale environmental actions, short-term interventions and those with little literature support on efficacy were removed.

The larger weight ranges among Swiss stakeholders compared to the Quebec study may be explained by examining the composition of the stakeholder groups. In Switzerland, an advisor group on tick-borne diseases already exists within the National Reference Centre for Tick-Borne Diseases [25]. This group includes a representative of the LD patients advocacy group in Switzerland, as well as a representative of the Swiss Accident Insurance Fund, which is responsible for insurance coverage of LD patients in Switzerland, and hence was more heterogeneous in terms of perspectives and concerns than the group that had participated in the Quebec study, which was mostly composed of public health and environmental specialists working in public organisations or academic institutions. Keeping this observation in mind, it is indeed interesting to see that a good level of agreement (comparable with the Quebec study) was still achieved. The addition of the four criteria in the Swiss context had the effect of making the model more ‘discriminating’ between interventions, by increasing the distance between scores of the highest and lowest ranked interventions (Fig 2). This highlights the added value of the validation process with local stakeholders.

Finally, the fact that the top ranked interventions are those targeting human populations (top six ranked interventions in Switzerland) was also observed in the Quebec study (four on the five top ranked interventions) [16]. In this previous study, the implementation of large communication campaigns was not included as an intervention, so we cannot directly compare the best-ranked interventions. One important point to keep in mind when using MCDA is that one strength of the approach is not to identify one unique or best solution, but rather to identify complementary interventions. This can be done using the interventions profiles, which are not presented in this paper, but which are described in [16].

This study focused on the evaluation of an existing MCDA model developed in Quebec for the Swiss context and we see a few key limitations to the approach used. A list of criteria and interventions from the Quebec model were presented and adjusted by Swiss stakeholders, but these criteria might have been different if Swiss stakeholders had created their own model, without reference to the Quebec model. This method was used in accordance to our study objective, but has likely influenced Swiss stakeholders in the inclusion of or in the choice of a measurement unit for certain issues relative to the decision-making process.

An important consideration in designing MCDA models is that criteria should be independent, in order to avoid double counting when calculating global scores if two criteria measure the same impacts. Some criteria identified in the Swiss model are interrelated. For example, the reduction of the entomological risk, the reduction of Lyme disease cases and the reduction of disseminated LD cases are not fully independent. They represent three main objectives of LD prevention and are indicators of the effectiveness of the intervention. To include the three of them may have led to inflate the importance of this effectiveness consideration in the global rankings and is a limitation of the current study. Nevertheless, weighting the criteria by taking into account the general category can prevent this bias by assuring that the weight of each category of issues truly represents its perceived importance. Full independence of criteria is hard to achieve when dealing with complex problematics such as LD prevention. Moreover, eliminating criteria that are perceived by stakeholders as important in the decision-making process because they are not completely independent can decrease the representability of real issues and limit the use of the model by decision-makers. Also, the list of criteria in this study was developed in order to achieve a balance between sufficient independence and comprehensiveness to capture LD prevention issues in Switzerland.

Another limit to consider in the interpretation of the results is the use of a normalization process to calculate weights of the stakeholders when removing the added criteria. These weights were used to allow comparisons between Quebec and Swiss stakeholders in Fig 1, and to perform group ranking under scenario B. This methodological choice may have introduced some bias in the weighting schemes, as stakeholders might have preferred to change the distribution of the remaining weights if the list of criteria was reduced. The impact of this bias is probably minimal.

Also, performance evaluations of interventions used qualitative categorical indicators for every criterion. If ordinal scales are well suited for the evaluation of certain types of criteria, such as the level of complexity, numerical scales would be more appropriate for other criteria, such as the level of reduction in human case incidence and the costs for the public and the private sectors. This was also the case in the Quebec model and reflects the availability of data at the time of the study. In the other hand, the fact that MCDA models can include qualitative evaluations such as expert assessments can also be considered as a strength of this approach, because it allows to take into account issues for which data are not available or not representative of the context, instead of completely ignoring them or their limits. Moreover, it can help to identify the main knowledge gaps and orient future researches.

Finally, both the Quebec and the Swiss models used the PROMETHEE method and D-Sight Software to perform multi-criteria analysis, which is desirable in order to compare the results. However, other methods and software for MCDA exist [21, 37]. Guidelines have been proposed to help select an appropriate MCDA method [38], but the impact of the use of different MCDA methods and /or software on one particular prioritization problematic in the field of public health has not been well described in the published literature.

The current study suggests that beyond the specificity of the MCDA models developed for Quebec and adapted for Switzerland, their general structure captures the fundamental and common issues that characterize the complexity of vector-borne disease prevention, as all criteria and most of the interventions were directly transferable from one context to the other. Nonetheless, the model adaptation process, performed in this study using a participatory approach with local stakeholders, appears important to enhance the specificity of the model to local considerations.

Moreover, the generic parameters of the MCDA models developed in Quebec and in Switzerland, and particularly the general categories of criteria, are well aligned with the ‘One health’ approach, which encourages international, interdisciplinary and cross-sectoral actions for diseases at the human-animal-environment interface [39]. We believe that the generic structure of MCDA models developed in Quebec and adapted in Switzerland could provide a practical tool for the management of vector-borne and zoonotic diseases in coherence with the ‘One health’ perspective.

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. In light of these findings, we believe that further studies would be of great value to enhance our understanding on the notion of a core set of criteria that would be widely applicable to framing the relative efficacy of possible public health interventions for vector-borne and other zoonotic diseases.