DMDiego Montenegro

Diego Montenegro

*This is an algorithmically generated author record based on publicly available information.

Diego Montenegro has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Col-Ovo: Smartphone-based artificial intelligence for rapid counting of Aedes mosquito eggs under field conditions

    by Juan Almanza, Diego Montenegro

    Background: The global expansion of Aedes aegypti mosquitoes has intensified the transmission of dengue, Zika, and chikungunya viruses, increasing the need for scalable surveillance tools. OviCol, a low-cost ovitrap-based strategy integrating mosquito monitoring and control, has shown promise for community-based vector management. However, large-scale deployment generates thousands of oviposition substrates that require labor-intensive manual egg counting, creating a major operational bottleneck. This study aimed to develop and evaluate Col-Ovo, an artificial intelligence-based system for automated counting of Ae. aegypti eggs from smartphone images collected under routine field conditions. Methods: Col-Ovo was developed using a YOLOv11m object-detection model trained on 275 oviposition substrates (20.5 cm strips) collected through operational surveillance activities. Images were captured in situ using smartphones without preprocessing and included samples stained with bioattractants (blackstrap molasses and Saccharomyces cerevisiae ) as well as sand and particulate debris. The system was designed to tolerate image compression generated by messaging platforms, such as WhatsApp. Performance was assessed by comparing automated egg counts with expert manual counts and virtual-human counts conducted through the OviLab platform using >200% image magnification. Agreement between methods was evaluated using correlation and concordance analyses. Results: Col-Ovo successfully detected and quantified Ae. aegypti eggs under challenging field conditions, including heavily stained and debris-contaminated substrates. Col-Ovo showed strong agreement with human evaluators (Spearman ρ = 0.91; Lin’s ρc = 0.89; MAE = 22.1 eggs) and with OviLab counts, with no significant difference in paired comparisons ( P = 0.252). The system reduced processing time from approximately 15 min per substrate to less than 3 s, representing a substantial increase in operational efficiency. Performance remained robust when analyzing compressed smartphone images shared through common messaging applications. Conclusions: Col-Ovo provides a rapid, accurate, and scalable approach for quantifying Ae. aegypti eggs from smartphone images. By eliminating the need for specialized equipment or image preprocessing, the system addresses a critical barrier to large-scale ovitrap surveillance. Integrated with the OviLab platform, Col-Ovo offers a flexible digital infrastructure that can strengthen vector surveillance, support timely public health responses, and facilitate the expansion of community-based mosquito control programs.

  • Open Access

    Col-Ovo: Smartphone-based artificial intelligence for rapid counting of Aedes mosquito eggs under field conditions

    by Juan Almanza, Diego Montenegro

    Background: OviCol has recently been proposed as a disruptive strategy for the surveillance and control of synanthropic Aedes mosquitoes, vectors of dengue, Zika, and chikungunya viruses. The approach integrates monitoring and control through ultra–low-cost ovitraps (~0.2 USD), bioattractants, and egg inactivation using hot water. However, large-scale ovitrap surveillance generates thousands of egg substrates that require time-consuming manual counting, creating a major operational bottleneck. To address this limitation, we developed Col-Ovo, an artificial intelligence–based tool for automated counting of Aedes aegypti eggs from real field samples, together with OviLab, a digital platform for annotation, curation, and management of entomological image datasets. Methodology/Principal Findings: The detection model was trained using YOLOv11m on a dataset of 275 oviposition substrates (20.5 cm strips) collected under routine operational conditions. Images were captured in situ without preprocessing and included substrates heavily stained by bioattractants such as blackstrap molasses and dry yeast (Saccharomyces cerevisiae), as well as sand and particulate debris, reflecting realistic field conditions. The system was designed to operate with standard smartphone images and tolerate compression artifacts produced by messaging platforms such as WhatsApp. Performance was evaluated by comparing automated egg counts with expert manual counts and with virtual-human counts conducted in OviLab using >200% image magnification. Col-Ovo achieved >95% agreement with expert counts and 88% agreement with OviLab while reducing processing time from approximately 15 minutes to <3 seconds per sample. Conclusions/Significance: Col-Ovo enables rapid, scalable quantification of Ae. aegypti eggs from smartphone images, addressing a critical operational barrier in ovitrap-based surveillance. The system requires no image preprocessing or specialized hardware and is accessible through a lightweight web interface supported by an AI architecture that allows retraining for new ecological contexts or additional Aedes species. Integrated with OviLab, this platform provides a flexible digital infrastructure that can strengthen routine vector surveillance and community-level control programs across regions where Aedes mosquitoes continue to expand.

  • Open Access

    Programmatic implementation of Ovicol ovitraps for Aedes control in Colombia: operational adherence, effectiveness, and comparisons with AGO and BG-Sentinel traps

    by Gómez Laureano, Osorio Juan, Herrera Orley, Diego Montenegro

    Introduction. The global expansion of Aedes aegypti and Aedes albopictus has intensified arboviral epidemics, generating annual socio-economic losses exceeding USD 2 billion, mainly in the Americas. The desiccation-resistant egg stage plays a key role in mosquito persistence and spread, yet remains insufficiently targeted by current control strategies. Objective. To evaluate the operational feasibility and effectiveness of a low-cost, handcrafted ovitrap (Ovicol) implemented by two territorial health entities (ETSs) in Colombia, and to compare its performance with industrial AGO and BG-Sentinel (BGS) traps. Methods. Ovicol traps were baited with birdseed or molasses + yeast attractants. In Santa Marta, traps were installed in public areas (markets, cemeteries, sports complexes) using diflubenzuron; in San José del Guaviare, they were deployed in institutions (hotels, schools, health centers) using diflubenzuron and Bacillus thuringiensis israelensis (BTi). Data were analyzed through descriptive statistics, ANOVA/χ², nonparametric tests, and spatial cluster detection. Results. In Santa Marta, 41,677 eggs (100% A. aegypti ) were eliminated in five weeks. The Oviposition Positivity Index (OPI) ranged from 40.6–74.5%, with up to 88% trap loss at one site due to vandalism. In Guaviare, Ovicol detected oviposition within 24 h and outperformed AGO in Aedes detection (OPI = 65.2% vs. 30.8%; r = 0.87; p < 0.001). The fermented birdseed attractant achieved higher positivity (Kruskal–Wallis H = 9.42; p = 0.009). Compared with BGS, Ovicol showed superior field stability—BGS suffered ≥ 70% disconnections during weekends—and low concordance (Kappa = − 0.17). Conclusions. Ovicol is a cost-effective, operationally feasible, and eco-sustainable tool for Aedes surveillance and control. By surpassing AGO and complementing BGS, it enhances spatiotemporal resolution for early microfocus detection and targeted response. Acting as a lethal trap, one diflubenzuron tablet (normally for 200 L) can treat ≈ 800 Ovicol (0.25 L each), extending coverage to ~ 800 households and achieving an ~ 800-fold increase in larvicide efficiency. These findings support Ovicol’s incorporation into national programs to promote sustainable, community-driven Integrated Vector Management (IVM).

  • Open Access

    Ovitrampas artesanales y agua caliente: estrategia auxiliar para el control del mosquito Aedes aegypti en Colombia

    by Katherine Arrieta-Ángel, Keylin Polo-Silva, Natalia Ospino-Sierra, Dayan Corpa-Choperena, Elkin Monterrosa, Isaacs Alemán, Diego Montenegro

    RESUMEN Objetivo. Evaluar las ovitrampas artesanales como una estrategia auxiliar sostenible para controlar el mosquito Aedes aegypti, alineada con la Agenda 2030 para el desarrollo sostenible. Método. Se diseñaron ovitrampas blancas y negras con recipientes plásticos de 0,95 L, servilletas y papel film. Se probaron tres tratamientos: agua, agua con alpiste, y agua con alpiste más diflubenzurón, en Montería y Ayapel (Colombia) durante 15 semanas. Los datos se analizaron con Python® vía ChatGPT; se comparó el conteo manual de huevos con un sistema de inteligencia artificial (IA) y se evaluaron métodos ovicidas en laboratorio. Resultados. Las ovitrampas con alpiste, y un costo menor de 20 centavos de dólar estadounidense, lograron índices de positividad (IPO) superiores al 78,0%, y permitieron capturar un promedio de 385 huevos por trampa por semana. Durante todo el estudio, aproximadamente 100 ovitrampas eliminaron 67 868 huevos, y previnieron la evolución a 48 458 adultos (47,2% hembras). Las trampas negras (IPO: 54,47%) superaron a las blancas (IPO: 41,24%), aunque sin diferencias significativas. El tratamiento con alpiste y diflubenzurón fue el más efectivo. El conteo manual de huevos fue más preciso que el conteo con IA. Además, el uso de agua caliente (80-100 °C) logró una eficacia ovicida del 100%, y superó al diflubenzurón. La comunidad mostró alta aceptación y comunicó beneficios significativos en la reducción de mosquitos. Conclusión. Las ovitrampas artesanales y la inmersión semanal de papeles en agua caliente son una estrategia rentable, accesible y ecológica que puede integrarse fácilmente en programas de control vectorial en zonas urbanas y rurales endémicas de arbovirosis, y minimiza el uso de insecticidas y el impacto ambiental.


  • Open Access

    Genetic diversity and population structure of Rhipicephalus sanguineus sensu lato across different regions of Colombia

    by Luisa Páez-Triana, Marina Muñoz, Giovanny Herrera, Darwin A. Moreno-Pérez, Gabriel A. Tafur-Gómez, Diego Montenegro, Manuel A. Patarroyo, Alberto Paniz-Mondolfi, Juan David Ramírez

    Background: There has been a long-standing debate over the taxonomic status of Rhipicephalus sanguineus sensu lato. Different studies worldwide have reported the occurrence of different well-defined lineages, in addition to Rhipicephalus sanguineus sensu stricto. To date, there are very few studies examining the diverse aspects of this tick in Colombia. We assessed the population structure and genetic diversity of R. sanguineus s.l. in eight departmental regions across Colombia. Methods: A total of 170 ticks were collected from dogs in different departments of Colombia. All specimens were morphologically compatible with R. sanguineus s.l. and subjected to genetic analysis. DNA sequences were obtained for the 12S rDNA, cytochrome oxidase I (COI) and internal transcribed spacer 2 (ITS2) markers. A concatenated set of all mitochondrial markers was also constructed. Next, maximum likelihood phylogenetic trees were constructed using the sequences generated herein and sequences available in GenBank. Finally, we assessed different summary statistics and analysed population structure and divergence with Fst and Dxy and demographic changes with Tajima's D and Fu and Li’s statistical tests. Results: Analysis of the 12S rDNA and COI revealed that all R. sanguineus s.l. specimens collected across different regions of Colombia clustered within the tropical lineage. Micro-geographical analyses showed that the tick population from Amazonas formed a distinct cluster separated from the other sequences, with moderate Fst and Dxy values. However, no signs of a robust population structure were found within the country. The results of Fu’s FS tests, together with the haplotype networks and diversity values, signal a possible population expansion of this tick species in Colombia. Conclusions: Evidence provided herein supports the tropical lineage as the main circulating lineage in Colombia, exhibiting a general lack of genetic structure except for the Amazonas region. Graphical


  • Open Access

    Uso de tecnologías en el lugar de atención para el manejo de la pandemia por COVID-19 en Colombia

    by Diego Montenegro-López

    Objective. To propose a health care model that integrates point-of-care technologies and artificial intelligence for the management of the COVID-19 pandemic. Methods. A theoretical model was used in which one million people accessed the mobile application CoronApp-Colombia, which collects personal data, signs, symptoms and epidemiological links compatible with COVID-19. With the information from the app artificial intelligence techniques (data science) were applied in a virtual situation room. Results. Users compatible with COVID-19 were prioritized and subjected to a rapid diagnostic test for antiSARS-CoV-2 antibodies. Screening with the rapid diagnostic test would allow detection of sero-reactive individuals, for whom diagnostic confirmation would be carried out using molecular biology (PCR). Information from positive cases confirmed by PCR would be re-screened using artificial intelligence and spatial statistical techniques to identify geographical foci of infection. These foci could be actively searched for contacts with positive index cases and the diagnostic route would be followed again using the rapid diagnostic test and PCR. Conclusion. This model may be useful for countries in the region with weak or absent technological platforms for PCR diagnosis to maximize existing resources, estimate the epidemiological burden of COVID-19 (infection, morbidity, mortality and lethality) and implement containment, mitigation and control plans according to their needs.


  • Usefulness of autocidal gravid ovitraps for the surveillance and control of Aedes ( Stegomyia ) aegypti (Diptera: Culicidae) in eastern Colombia

    by D. Montenegro, L. Martinez, K. Tay, T. Hernandez, D. Noriega, L. Barbosa, J. Muñoz, H. Mateus, J. Daza, A. Teherán, et al.

    In the past decade, new strategies have been developed to control the Aedes aegypti (Diptera: Culicidae) mosquito vector, as well as a broad range of arboviral agents. Vector control surveillance programmes in Puerto Rico and Australia have implemented the Centers for Disease Control and Prevention autocidal gravid ovitrap (AGO), which has had an impact on vector density and, consequently, the epidemiology of arboviral infections. Colombia intends to establish the AGO as a new tool for the surveillance and control of the A. aegypti vector. AGOs were evaluated in a hyperendemic area for dengue virus during an 8‐week period in Villavicencio city, eastern Colombia. The results indicated that the AGOs detect a high density of A. aegypti , with positive results for these traps of over 80% and an average catch of six individuals per trap per week. Acceptance of AGOs in the community exceeded 95%, and adherence was around 89%. This study's results demonstrate, for the first time in Colombia, that traps are a useful tool for the surveillance of A. aegypti . Future studies must consider the implementation of AGOs in the region.


  • Open Access

    One World, One Health Challenge: The Holistic Understanding of Rickettsiosis Integrating Multi-Criteria Analysis Techniques and Spatial Statistics

    by Diego Montenegro, Ana Paula da Cunha, Ingrid Machado, Liliane Duraes, Stefan Vilges de Oliveira, Marcel Pedroso, Gilberto S. Gazêta, Reginaldo P. Brazil

    Among the human diseases caused by etiological agents transmitted by ticks in Brazil, the most prevalent and public health interest is that one caused by species of Rickettsia—Spotted Fever (SF). We applied the concept “One World, One Health” to achieve a proper understanding of SF and determine risk scenarios for human infection by pathogenic Rickettsia in the state of Rio de Janeiro (RJ). Multi-criteria decision analysis and spatial statistics were performed on data encompassing epidemiology, health care, biotic determents, and socioeconomic and demographic variables. The construction of multi-criteria descriptors used 33 indicators ordered in 12 sub criteria of 5 major categories: public health, environmental health, acarology, veterinary health, and microbiology. SF happened nonrandomly in RJ and the risk was heterogeneous in the weight of indicators contribution mainly associated with the criteria acarology (35.11%), microbiology (33.25%), and veterinary medicine (23.96%). Spatially, and according to the PROMETHEE algorithm, ticks from Amblyomma sculptum class and dogs are determinants for the occurrence of human cases of SF in RJ. To define indicators of SF and plan health actions, the “One World, One Health” concept proved to be applicable at three levels: (i) the local or possible areas of infection, (ii) the population or municipality, and (iii) the ecosystem or state. The model of study is flexible according to the reality of the endemic areas and also demonstrates its applicability from a national to a local (home) scale.


  • Open Access

    Evaluating the Surveillance System for Spotted Fever in Brazil Using Machine-Learning Techniques

    by Diego Montenegro Lopez, Flávio Luis de Mello, Cristina Maria Giordano Dias, Paula Almeida, Milton Araújo, Monica Avelar Magalhães, Gilberto Salles Gazeta, Reginaldo Peçanha Brasil

    This work analyses the performance of the Brazilian spotted fever (SF) surveillance system in diagnosing and confirming suspected cases in the state of Rio de Janeiro (RJ), from 2007 to 2016 (July) using machine-learning techniques. Of the 890 cases reported to the Disease Notification Information System (SINAN), 11.7% were confirmed as SF, 2.9% as dengue, 1.6% as leptospirosis, and 0.7% as tick bite allergy, with the remainder being diagnosed as other categories (10.5%) or unspecified (72.7%). This study confirms the existence of obstacles in the diagnostic classification of suspected cases of SF by clinical signs and symptoms. Unlike man–capybara contact (1.7% of cases), man–tick contact (71.2%) represents an important risk indicator for SF. The analysis of decision trees highlights some clinical symptoms related to SF patient death or cure, such as: respiratory distress, convulsion, shock, petechiae, coma, icterus, and diarrhea. Moreover, cartographic techniques document patient transit between RJ and bordering states and within RJ itself. This work recommends some changes to SINAN that would provide a greater understanding of the dynamics of SF and serve as a model for other endemic areas in Brazil.


  • Open Access

    Multi-criteria decision analysis and spatial statistic: an approach to determining human vulnerability to vector transmission of Trypanosoma cruzi

    by Diego Montenegro, Ana Paula Da Cunha, Simone Ladeia-Andrade, Mauricio Vera, Marcel Pedroso, Angela Junqueira

    Key words: vulnerability; Chagas disease; multi-criteria decision analysis; spatial statistic; PROMETHEE method; GAIA method