Onchocerciasis (river blindness) is caused by chronic infection with Onchocerca volvulus, a filarial nematode that is transmitted by Simulium spp. (Diptera: Simuliidae). The disease constitutes a serious public health concern and an enormous source of socio-economic loss in many developing countries, most severely in sub-Saharan Africa and, to a lesser extent, Latin America [1-5]. The current strategy for the elimination of onchocerciasis relies on mass treatment of endemic communities with ivermectin. A variety of treatment regimens, including quarterly, semi-annual and annual treatment have proven effective in focally interrupting transmission and eliminating the parasite in Latin America and in isolated foci in Africa over different time frames [6-12]. High coverage (≥ 85% of eligible persons) community-wide treatment of residents for a minimum of 15 years is believed to be sufficient to reduce the load of microfilariae in human hosts below the threshold that can sustain transmission by black fly vectors, thus locally eliminating the infection [7].

The elimination guidelines set forth by the Onchocerciasis Elimination Program for the Americas (OEPA) and the World Health Organization (WHO) use the prevalence of the infective stage of O. volvulus larvae in the black fly vectors as a major metric for determining whether or not transmission has been successfully interrupted in an endemic community [13,14]. The threshold used for declaring elimination is less than one O. volvulus per 2,000 female black flies per endemic community. At least 6,000 flies must be tested by Polymerase Chain Reaction (PCR-pool screening) in each endemic community to satisfy this standard [13-15]. To date, the collection of such large numbers of black flies has been problematic, as the primary method for collecting host-seeking black flies is the use of human landing collections [16-18]. This method involves stationing adult humans in areas of high Simulium densities and collecting black flies that attempt to land and blood-feed. Apart from the fact that this method has been a subject of criticism due to the potential risk of human collector’s exposure to infection during the early stages of a control program [19], it may be difficult for fly collectors to capture the large number flies needed to document that transmission has been interrupted where biting rates are low or highly seasonal. Thus, the development of trap(s) to replace human landing collections is becoming increasingly important as the focus in onchocerciasis shifts from control to elimination, and in some cases post-treatment surveillance [20].

Various attempts have been made to design black fly traps using both visual and chemical attraction techniques [21-25]. Most of these studies were conducted in West Africa where members of the Simulium damnosum species complex serve as the primary vectors for the causative agent of onchocerciasis, Onchocerca volvulus. In Latin America, Simulium ochraceum sensu lato is the most important vector of this parasite; until recently it was associated with ≥ 70% of transmission in the six countries where the disease occurred. The ecology and behavior of S. ochraceum s.l. is distinctly different from S. damnosum s.l., the primary vector in Africa [26-29], potentially complicating the prospects for development of a single trap that efficiently captures both species. As part of longitudinal studies in designing an improved black fly trap for monitoring and surveillance transmission of O. volvulus, field studies were carried out at endemic sites in Chiapas, Mexico, to evaluate different trap designs. Here we report the results of field trials and optimization of a promising design (Esperanza window trap) for the collection of host-seeking S. ochraceum s.l.

The data presented here demonstrate the feasibility of using traps to replace human bait (vector collectors) in onchocerciasis monitoring and elimination programs. In initial field trials it was obvious that the several trap designs evaluated were not equally effective for collecting S. ochraceum s.l. females, but that some traps would be amenable to further development and experimentation (e.g. Figure 3). The Esperanza window trap showed the most initial promise, and also proved to be effective in subsequent tests (Figures 4-6). Since repeatability of results has been lacking in most black fly trapping studies [36], the consistent productivity of the Esperanza window trap was very encouraging.

After the first round trap comparisons field tests focused solely upon optimizing the Esperanza window trap for collecting S. ochraceum s.l. females. Modifications to the Esperanza window traps included replacing glass with acrylic panes and replacing the awkward wooden frame with aluminum, resulting in a lighter, and more manageable design that collected more black flies than the initial prototype. Additional experiments testing the effectiveness of available chemical lures (including CO₂) indicated that olfactory attractants were key in trapping success.

It is interesting that Esperanza window traps with blue fabric collected more S. ochraceum s.l. females than did traps with other colors of fabric. Blue is reported to be attractive to tsetse flies (Glossina spp.) [37], and it is used as a dominant fabric color in tsetse trap fabrication [38]. Yeast-generated CO₂ was as effective as commercial CO₂. This is particularly important since onchocerciasis-endemic areas are often quite remote, and obtaining CO₂ cylinders in these areas can pose a serious operational difficulty. Yeast-generated CO₂ will likely conserve monetary resources, since the ingredients (yeast, sugar, water) and materials (plastic bottles, plastic tubing/hose) are easy to locate or improvise. Furthermore fermentation of sugar by yeast produces not only CO₂, but also a variety of volatile organic compounds (alcohols, esters, aldehydes and fatty acids) that are known to attract the arthropods that are attracted to vertebrates [33].

Simultaneous testing of multiple trap types, as performed in our initial trap screening presents several operational and analytical challenges. Some of the traps tested present large visual cues (Bellec plaques and Esperanza window traps), while others presented primarily olfactory cues (e.g. BG-Sentinel). The Esperanza window trap presented a large visual target as well as olfactory lures. Testing this broad array of trap types, some with olfactory cues and others without makes it quite difficult to tease apart the subtle interplay of long and short-distance stimuli that ultimately result in a fly being captured by a particular trap. For example, a long distance olfactory cue emanating from one of the trap types might draw flies into the field plot. Once in the vicinity of the traps, a shorter distance signal (visual or olfactory) from a different trap type may cause a change in a fly’s trajectory so that the fly is actually captured by a trap that is different from the one that originally lured the fly to the experimental plot. In this scenario, the trap that ends up capturing the fly may perform better in the presence of a long-distance olfactory cue originating from a neighboring trap than if evaluated without other traps. However, given the temporal (day-to-day), spatial and environmental variation in fly activity, testing traps independently (on different days) and then trying to compare trap captures between traps across different days or locations would present its own set of analytical challenges. That said, our results indicate that the traps that utilized chemical lures caught the overwhelming majority of black flies (Figure 3). The four traps that utilized lures (Esperanza window trap, human silhouette, BG-Sentinel with human scent lure and BG-Sentinel with octenol) collected 95.4% of the captured flies, while the three unbaited traps (Bellec plaques horizontal and vertical and Clear window trap) captured only 4.6% of the total. This would suggest that flies are drawn into the trapping arena by olfactory cues emitted by baited traps, but traps with multimodal profiles, such as the Esperanza trap, outperformed unbaited traps in actually capturing flies.

Exactly what features of the Esperanza trap are responsible for its relative “success” in the field are not easy to ascertain. The optimized version of the trap utilized multiple visual and olfactory cues that likely worked in concert to maximize its attractiveness to S. ochraceum s.l. females. Trap color appeared to have a strong effect on black fly capture, when other variables were held constant. Experimental evidence suggests that spectral reflectance and polarization of reflected light are key determinants of how insects respond to visual stimuli [39]. For example, the black-and-white striped patterns of zebra coats result in alternating directions of reflected light polarization. Stripe width has a profound impact on attractiveness of zebras to tabanids, with attraction decreasing along with decreasing stripe width, due to disruptive patterns of reflected light polarization [40]. Spectral reflectance of visual stimuli (especially host silhouettes) is thought to be inversely related to attraction of host-seeking diurnal flies, including black flies [41] and tabanids [42]. The number of simuliids orienting and landing on silhouette traps of various reflectances was found to be greater when reflectance was lowest [41]. Tabanid traps treated with a product that reduced ultraviolet reflectance from cloth fabrics increased the catch of tabanids in canopy traps by 24% [42]. The optimized Esperanza window trap with clear acrylic panels (nearly eliminating UV reflectance [43]) collected significantly more females than the trap with glass panels, supporting the notion that spectral reflectance is inversely related to attractiveness of a visual stimulus to black flies. Though only a few hues (of the virtually limitless variety of colors) were evaluated in the current study, the results obtained here generally corroborate the findings of others – that blues and blacks are attractive to host-seeking simuliids [41].

Esperanza window traps, baited with olfactory attractants and CO₂, were nearly as productive as a vector collector team (2 adults working together) in some trials. Considerable variation in trap effectiveness might be expected, based on site-specific conditions. Esperanza traps should therefore be evaluated at other locations with O. volvulus vectors to determine their effectiveness relative to human landing collections. However, it is probably not necessary that an effective trap be as productive as a vector collection team, since a single person can easily maintain five traps (data not shown). By deploying multiple traps, a person working alone can increase daily fly captures by at least threefold over those obtainable using standard collection methods.

While the data presented above suggest that the Esperanza window trap shows promise as a substitute for human landing collections, additional work will be necessary before they can be employed for monitoring and surveillance of onchocerciasis elimination. First, the bait used in the traps must be standardized and optimized. The BG-lure, which is a commercial product, successfully attracted S. ochraceum in fairly large numbers. However, the BG-lure, which employs ammonia, lactic acid, and caproic acid as active ingredients [44], was designed and optimized to attract Aedes spp. mosquitoes [45]. It is likely that this mixture of compounds was not an optimal attractant for black flies and that inclusion or substitution of other compounds found in human breath and sweat will result in an improved bait formulation.

Second, the models used to identify transmission thresholds for O. volvulus have all relied upon entomological indicators derived from human landing collections. Thus, it will be necessary develop algorithms to relate the trap collections to human biting rates and infective rates. In this regard, the fact that the traps appear to collect fly populations that exhibit parity rates which are not significantly different from those obtained by human landing collections carried out in parallel will simplify this process. Previous studies that have examined variability of infection rates associated with human landing collections in S. ochraceum s.l. [46] may prove to be a useful foundation in developing methods to relate trap collections to infective biting rates.

In conclusion, the Esperanza window trap, when baited with CO₂ and olfactory lures collected substantial numbers of S. ochraceum s.l., one of the principal vectors of O. volvulus in Latin America. This trap has the potential for replacing humans as bait in the monitoring and surveillance of onchocerciasis vectors. Eventually, such a trap may prove to be an effective replacement for vector collectors in areas of Latin America and Africa where onchocerciasis remains endemic. These traps have the potential to be extremely useful tools in aiding in the certification of elimination of O. volvulus transmission and in the post-treatment surveillance era.