Browsing by Autor "Daniel Illanes"

Now showing 1 - 10 of 10

Artificial Intelligence algorithm for real-time detection and counting of Trypanosoma cruzi parasites using smartphone microscopy
(2025) Lin Lin; A. Solano; Fabiola Gonzales; Mary Cruz Torrico; Daniel Illanes; Nuria Díez; David Bermejo-Peláez; Elena Dacal; Ramón Vallés-López; Luis Pastor
Abstract Chagas disease affects 6–7 million people worldwide and causes approximately 12,000 deaths annually. Diagnostic methods vary by disease stage, with serological tests commonly used in the chronic phase, while microscopy and molecular techniques like PCR and LAMP are employed in the acute phase. While microscopy remains the most accessible tool in resource constrained settings, its effectiveness depends on skilled personnel, creating diagnostic bottlenecks. To overcome these limitations, we developed a portable, smartphone-integrated AI system for real-time Trypanosoma cruzi detection in microscopy images. The platform combines a 3D-printed microscope adapter which aligns the smartphone camera with microscope ocular to digitize images, telemedicine-enabled annotation workflows, and lightweight AI models (SSD-MobileNetV2, YOLOv8) deployed on smartphone for real-time analysis. Trained on a diverse dataset of human samples (478 images from 20 samples), including thick/thin blood smears and cerebrospinal fluid) and murine thin smears (570 images from 33 samples), the SSD-MobileNetV2 model achieved 86% precision, 87% recall, and 86.5% F1-score on human samples, demonstrating robust performance across variable imaging conditions. This system enables rapid, accurate parasite detection in field settings without advanced infrastructure, addressing critical gaps in early diagnosis and monitoring. Its modular design allows adaptation to other pathogens and cellular structures, offering a scalable solution for neglected tropical disease diagnostics. By bridging AI innovation with microscopy, this approach holds promise for advancing equitable healthcare delivery in endemic regions and aligning with global health priorities. Author Summary Chagas disease is a life-threatening illness affecting millions, primarily in Latin America, where access to advanced laboratory equipment and trained specialists is limited. One method of diagnosis is microscopic examination of blood or cerebrospinal fluid samples, it provides immediate results without requiring complex facilities, but its effectiveness depends on the expertise of trained microscopists. We developed a simple, low-cost tool that combines a smartphone, a light microscope, and artificial intelligence (AI) to assist the diagnosis. By attaching a smartphone to a microscope with a 3D-printed adapter, users analyze microscopy images with real-time AI assistance, detecting the parasites causing Chagas disease. Our results show that this approach is accurate and could be useful for regions with limited healthcare infrastructure. It reduces reliance on specialized training and expensive equipment, helping communities diagnose Chagas faster. Beyond Chagas, this approach can be adapted to detect other diseases, offering a versatile tool for fighting neglected tropical illnesses. By bridging gaps in healthcare access, we hope to empower frontline workers and contribute to global efforts to reduce the burden of these diseases on vulnerable populations.
Assessment of a Leishmaniasis Reporting System in Tropical Bolivia Using the Capture-Recapture Method
(American Society of Tropical Medicine and Hygiene, 2017) Daniel Eid Rodríguez; Miguel Guzmán-Rivero; Ernesto Rojas; Isabel Goicolea; Anna‐Karin Hurtig; Daniel Illanes; Miguel San Sebastiån
This study evaluates the level of underreporting of the National Program of Leishmaniasis Control (NPLC) in two communities of Cochabamba, Bolivia during the period 2013-2014. Montenegro skin test-confirmed cases of cutaneous leishmaniasis (CL) were identified through active surveillance during medical campaigns. These cases were compared with those registered in the NPLC by passive surveillance. After matching and cleaning data from the two sources, the total number of cases and the level of underreporting of the National Program were calculated using the capture-recapture analysis. This estimated that 86 cases of CL (95% confidence interval [CI]: 62.1-110.8) occurred in the study period in both communities. The level of underreporting of the NPLC in these communities was very high: 73.4% (95% CI: 63.1-81.5%). These results can be explained by the inaccessibility of health services and centralization of the NPLC activities. This information is important to establish priorities among policy-makers and funding organizations as well as implementing adequate intervention plans.
Correction to: risk factors for cutaneous leishmaniasis in the rainforest of Bolivia: a cross-sectional study
(BioMed Central, 2018) Daniel Eid Rodríguez; Miguel Guzmán-Rivero; Ernesto Rojas; Isabel Goicolea; Anna‐Karin Hurtig; Daniel Illanes; Miguel San Sebastiån
Dietary Patterns Among 13-17-Years Old School Adolescents: A National Comparison of the Three Geographical Regions in Bolivia
(2021) Noelia Villalta; Nattalia Arauco; Marisol Mamani; Daniel Illanes; Pramil N. Singh; Lenildo de Moura; Joan Sabaté
Abstract Introduction Bolivia is considered one to the most biodiverse countries in the world. It has three ecological floors or geographical regions (highlands, plains and valleys) with very different climatic and cultural characteristics. Traditionally dietary patterns varied in each region. Because two-thirds of premature deaths are associated with behaviors that begin in adolescence, understanding dietary patterns among adolescents is important to improving health. The aim of this study was to identify dietary patterns of adolescents in the different geographical regions of Bolivia. Methodology Data were obtained from the World Health Organization’s Global School-based Student Health Survey 2018 that assesses risky behaviors and protective factors in students aged 13 to 17 years old. It uses an observational cross-sectional method and included 7945 adolescents in schools that were representative of all students in this age group in each of the three geographical regions in Bolivia. Results 3.9% of students in Bolivia are food insecure, with the highest percentage in the highlands (4.6%) and the lowest in the plains (3.1%). Adolescents in the highlands consume vegetables and fruits more frequently than adolescents in the plains and valleys. Water consumption in the valleys was 19.6% students who drink 1-3 glasses/d. Dairy consumption ≥2 in 7 days is higher in the highlands and lower in the valleys. Consumption of soft drinks at ≥1 glass per day is 34.3% in the plains and 30.1% in the valleys. Junk food consumption ≥1 in 7 days was 62.0% with a greater presence on the plains at 65.7%. Conclusion The highlands revealed a greater presence of protective factors than the other regions. The valley, despite having greater access to fruits and vegetables, has a greater presence of risky behaviors. Teenagers in the plains have greater exposure to advertising and access to junk food at school.
Factores que influyen en el retraso del diagnóstico del VIH
(2016) Rocio Quiroga Troche; Ariel Leguizamón Castro; Daniel Illanes; Mildreth Castro
Objetivo: determinar los factores que influyen en el retraso del diagnostico del VIH desde la percepcion de los pacientes y del personal medico, en el municipio del Cercado.Metodos: estudio transversal descriptivo y cuantitativo, a traves de entrevistas a pacientes VIH (+), encuestas a personal medico y revision de historias clinicas.Resultados: se reviso 121 historias clinicas de pacientes VIH(+), en distintos establecimientos de salud, observandose un Diagnostico Tardio (DT) en el 65%, considerando la presencia de enfermedades oportunistas al momento inicial del diagnostico y 60% considerando el recuento de linfocitos CD4 < 200. En la entrevista con los pacientes, 59% no tenia pareja estable; 80% no se consideraba vulnerable a la enfermedad y 44% tenia informacion incompleta o nula sobre el VIH/SIDA. En el analisis estadistico, se encontro relacion: (variable edad y sexo respecto a entre quienes hay mas posibilidad de transmision) con un valor de p= 0,000000049 en la primera asociacion y un valor de p= 0,000012 en la segunda; entre las variables (edad respecto a saber sobre VIH) con un valor de p= 0,000013; entre las variables (tener pareja estable respecto a considerarse a riesgo) con un valor de p= 0,00098; entre (Nivel de instruccion respecto al motivo de realizacion de la prueba rapida para VIH) con un valor de p= 0,00083. En la entrevista con los medicos el 39% de ellos tienen un conocimiento insuficiente sobre VIH/SIDA y la norma.Conclusiones: en el retraso del diagnostico del VIH influyen factores como: la percepcion de riesgo, la oferta de la prueba y el conocimiento erroneo del VIH; ademas el nivel de instruccion y la edad influyen en el acceso a la informacion. Para mejorar el diagnostico se debe mejorar la informacion, hacerla mas completa, adecuada y accesible; buscando un cambio de actitud en la poblacion.Palabras claves: retraso del diagnostico, informacion incompleta, cambio de actitud, educacion en salud, prevencion
Prevalence and determinants of cardiovascular disease risk factors using the WHO STEPS approach in Cochabamba, Bolivia
(BioMed Central, 2019) Yercin Mamani Ortiz; Miguel San Sebastiån; Ada Ximena Armaza; Jenny M. Luizaga; Daniel Illanes; Marcia Ferrel; Paola A. Mosquera
Real Time PCR for the Evaluation of Treatment Response in Clinical Trials of Adult Chronic Chagas Disease: Usefulness of Serial Blood Sampling and qPCR Replicates
(2018) Rudy Parrado; Ramírez Jc; Anabelle de la Barra; Cristina Alonso‐Vega; Natalia Juiz; Lourdes Ortiz; Daniel Illanes; Faustino Torrico; Joaquím Gascón; Fabiana Alves
Abstract This work evaluated a serial blood sampling procedure to enhance the sensitivity of duplex real time PCR (qPCR) for baseline detection and quantification of parasitic loads and post-treatment identification of failure in the context of clinical trials for treatment of chronic Chagas disease, namely DNDi-CH-E1224-001 ( NCT01489228 ) and MSF-DNDi PCR sampling optimization study ( NCT01678599 ). Patients from Cochabamba (N= 294), Tarija (N = 257), and Aiquile (N= 220) were enrolled. Three serial blood samples were collected at each time-point, and qPCR triplicates were tested per sample. The first two samples were collected during the same day and the third one seven days later. A patient was considered PCR positive if at least one qPCR replicate was detectable. Cumulative results of multiple samples and qPCR replicates enhanced the proportion of pre-treatment sample positivity from 54.8 to 76.2%, 59.5 to 77.8%, and 73.5 to 90.2% in Cochabamba, Tarija, and Aiquile cohorts, respectively and increased cumulative detection of treatment failure from 72.9 to 91.7%, 77.8 to 88.9%, and 42.9 to 69.1% for E1224 low, short, and high dosage regimes, respectively; and from 4.6 to 15.9% and 9.5 to 32.1% for the benznidazole (BZN) arm in the DNDi-CH-E1224-001 and MSF-DNDi studies, respectively. The monitoring of patients treated with placebo in the DNDi-CH-E1224-001 trial revealed fluctuations in parasitic loads and occasional non-detectable results. This serial sampling strategy enhanced PCR sensitivity to detecting treatment failure during follow-up and has the potential for improving recruitment capacity in Chagas disease trials which require an initial positive qPCR result for patient admission.
Research ethics training of trainers: developing capacity of bolivian health science and civil society leaders
(University of Chile, 2016) Annette Aalborg; Sarah Sullivan; Jacqueline Cortes; Armando Basagoitia; Daniel Illanes; Matthew Green
Research and research ethics (RE) capacity is a key element for addressing health priorities of low -and middleincome countries (LMICs). With support from a NIH/FIC Research Ethics Education and Curriculum Development grant, a RE Training of Trainers (
Risk factors for cutaneous leishmaniasis in the rainforest of Bolivia: a cross-sectional study
(BioMed Central, 2018) Daniel Eid Rodríguez; Miguel Guzmán-Rivero; Ernesto Rojas; Isabel Goicolea; Anna‐Karin Hurtig; Daniel Illanes; Miguel San Sebastiån
It is advisable to focus on education and prevention policies at an early age for activities related to either leisure or work. Further research is needed to assess the influence of gender-associated behavior for the risk of cutaneous leishmaniasis.
Usefulness of Serial Blood Sampling and PCR Replicates for Treatment Monitoring of Patients with Chronic Chagas Disease
(American Society for Microbiology, 2018) Rudy Parrado; Juan Carlos Ramı́rez; Anabelle de la Barra; Cristina Alonso‐Vega; Natalia Juiz; Lourdes Ortiz; Daniel Illanes; Faustino Torrico; Joaquím Gascón; Fabiana Alves
This work evaluated a serial blood sampling procedure to enhance the sensitivity of duplex real-time quantitative PCR (qPCR) for baseline detection and quantification of parasitic loads and posttreatment identification of failure in the context of clinical trials for treatment of chronic Chagas disease, namely, DNDi-CH-E1224-001 (ClinicalTrials.gov registration no. NCT01489228) and the MSF-DNDi PCR Sampling Optimization Study (NCT01678599). Patients from Cochabamba (n = 294), Tarija (n = 257), and Aiquile (n = 220) were enrolled. Three serial blood samples were collected at each time point, and qPCR triplicates were tested for each sample. The first two samples were collected during the same day and the third one 7 days later. A patient was considered PCR positive if at least one qPCR replicate was detectable. Cumulative results of multiple samples and qPCR replicates enhanced the proportion of pretreatment sample positivity from 54.8% to 76.2%, 59.5% to 77.8%, and 73.5% to 90.2% in Cochabamba, Tarija, and Aiquile cohorts, respectively. This strategy increased the detection of treatment failure from 72.9% to 91.7%, 77.8% to 88.9%, and 42.9% to 69.1% for E1224 low-, short-, and high-dosage regimens, respectively, and from 4.6% to 15.9% and 9.5% to 32.1% for the benznidazole arm in the DNDi-CH-E1224-001 and MSF-DNDi studies, respectively. The addition of the third blood sample and third qPCR replicate in patients with nondetectable PCR results in the first two samples gave a small, non-statistically significant improvement in qPCR positivity. No change in clinical sensitivity was seen with a blood volume increase from 5 to 10 ml. The monitoring of patients treated with placebo in the DNDi-CH-E1224-001 trial revealed fluctuations in parasitic loads and occasionally nondetectable results. In conclusion, a serial sampling strategy enhanced PCR sensitivity to detecting treatment failure during follow-up and has the potential for improving recruitment capacity in Chagas disease trials, which require an initial positive qPCR result for patient admission.