A young patient provides a blood sample to a study nurse in Machala, Ecuador. Un paciente joven provee una muestra de sangre a una enfermera del estudio en Machala, Ecuador. Image credit: Dany Krom

GAINESVILLE, FL – Helping patients with dengue can be challenging – especially in countries with multiple diseases spread by mosquitoes. Dengue, chikungunya, and Zika are viruses spread by the same type of mosquito; all three viruses are present in Ecuador and many other countries in Latin America and the Caribbean. Patients infected with one of these viruses tend to have similar, indistinct symptoms, which can make it difficult for a clinician to determine which disease is affecting the patient and which treatment steps to take. Most critically, the clinician must determine whether the patient should be checked into the hospital for close monitoring, or if the patient can be sent home to rest and recover. Failing to hospitalize a sick patient can be a deadly mistake, but sending too many patients to be hospitalized can overwhelm health systems and increase costs to the public health sector.

New clinical prediction research through a collaboration between the Quantitative Disease Ecology and Conservation (QDEC) Lab Group at the University of Florida and SUNY—Upstate Medical University tests the ability of machine learning to predict whether these patients should be hospitalized or not, using patient information collected by the clinician. The study, Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection was recently published in PLoS Neglected Tropical Diseases and was completed through collaborative efforts between students and researchers at the University of Florida, SUNY – Upstate Medical University, Cornell University, and the Ecuadorian Ministry of Public Health. Patient information and laboratory test results were collected from patients recruited into an ongoing arbovirus surveillance study as well as hundreds of paper medical records that were processed using machine learning.

Machine learning is a method wherein data are used to make predictions by applying a model or series of calculations (called algorithms) to the data. There are hundreds of machine learning algorithms – some might work really well or might fail entirely to make accurate predictions for a given dataset. “Our approach is unique in that we don’t assume that one algorithm is superior – we test and compare multiple algorithms to find the one that works best for our data” says Dr. Rachel Sippy, a postdoctoral researcher with QDEC and SUNY–Upstate Medical University and lead author of the paper. “Now that we have found an algorithm that works well with these types of patient information, we can test it on new groups of patients and confirm that it works under many circumstances.”

The published research lays the groundwork for the creation of a tool that clinicians could use at the bedside. The authors envision a mobile app where the clinician enters the patient data and receives a recommendation to hospitalize the patient or send them home. “While the experience of clinicians could never be replaced with an app, these kinds of decision-support tools can provide valuable additional information that can be taken into account by the clinician who is faced with making a potentially lifesaving decision,” explains Dr. Anna Stewart Ibarra, co-author of the publication.

Read Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection, in PLoS Neglected Tropical Diseases.

Predicciones de Aprendizaje Automático de Pacientes con Dengue Arrojan Resultados Prometedores

GAINESVILLE, FL – Ayudar a los pacientes con dengue puede ser un desafío – especialmente en países con múltiples enfermedades transmitidas por mosquitos. Dengue, chikungunya y zika son virus transmitidos por el mismo tipo de mosquito, los tres virus están presentes en el Ecuador y en muchos otros países de América Latina y el Caribe. Pacientes infectados con uno de estos virus tienden a tener síntomas similares, indistintos lo cual puede dificultar al médico a determinar cuál enfermedad está afectando al paciente y qué pasos de tratamiento debe tomar. Lo más crítico es que el médico debe determinar si el paciente debería ser ingresado en el hospital para un monitoreo más cercano o si el paciente puede ser enviado a casa para descansar y recuperarse. No hospitalizar a un paciente enfermo puede ser un error mortal, pero enviar muchos pacientes a ser hospitalizados puede abrumar los sistemas de salud e incrementar los costos al sector de salud pública.

Una nueva investigación de predicción clínica a través de una colaboración entre el Quantitative Disease Ecology and Conservation (QDEC) Lab Group de la Universidad de Florida y la Universidad Médica de SUNY Upstate, prueba la capacidad del aprendizaje automático para predecir si estos pacientes deberían ser hospitalizados o no, utilizando la información del paciente recogido por el médico. El estudio, Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection, se publicó recientemente en PLoS Neglected Tropical Diseases y se completó mediante esfuerzos de colaboración entre estudiantes e investigadores de la Universidad de Florida, SUNY – Upstate, Universidad de Cornell y el Ministerio de Salud Pública de Ecuador. La información del paciente y los resultados de las pruebas de laboratorio se obtuvieron de los pacientes reclutados en un estudio de vigilancia de arbovirus en curso, así como también de cientos de registros médicos en papel que se procesaron mediante el aprendizaje automático.

El aprendizaje automático es un método donde los datos son usados para hacer predicciones aplicando un modelo o series de cálculos (llamados algoritmos) a los datos. Existen cientos de algoritmos de aprendizaje automático – algunos pueden funcionar realmente o pueden fallar por completo para hacer predicciones precisas para un conjunto de datos dados. “Nuestro enfoque es único en el sentido de que nosotros no asumimos que un algoritmo es superior – probamos y comparamos múltiples algoritmos para encontrar el que mejor funcione para nuestros datos” dice Dra. Rachel Sippy, una investigadora posdoctoral con QDEC y SUNY-Upstate y autora principal de la publicación. “Ahora que hemos encontrado un algoritmo que funciona bien con este tipo de información del paciente, podemos probarlo en nuevos grupos de pacientes y confirmar que funciona bajo muchas circunstancias.”

La investigación publicada sienta las bases para la creación de una herramienta que los médicos podrían usar como cabecera. Los autores visualizan una aplicación en teléfono donde los médicos ingresen los datos de los pacientes y reciban una recomendación para hospitalizar al paciente o enviarlos a casa. “Mientras la experiencia de los médicos podría nunca ser reemplazada con la aplicación, este tipo de herramientas de apoyo a la toma de decisiones puede proporcionar información adicional valiosa que puede tener en cuenta el médico quien se enfrenta a tomar una decisión potencialmente vital”, explica la Dra. Anna Stewart Ibarra, coautora de la publicación.

Lee Severity Index for Suspected Arbovirus (SISA): Machine learning for accurate prediction of hospitalization in subjects suspected of arboviral infection, en PLoS Neglected Tropical Diseases.

Media contact: Mike Ryan Simonovich

GAINESVILLE, FL – Fighting mosquito-borne disease can be costly – in both health and financial resources. While mosquito control is an effective way to combat the spread of diseases like dengue fever, the cost of spraying every house in a city quickly adds up. These costs limit public health vector control programs, which often operate on limited annual budgets.

The team of UF researchers used methods from transportation geography to model the most efficient driving routes from Ministry of Health mosquito control centers (black squares) to neighborhoods throughout the city of Machala, Ecuador.
El equipo de investigadores de la Universidad de Florida usó métodos de transportación geográfica para hacer una maqueta de las rutas más eficientes del Ministerio de Salud Pública de los centros del control del zancudo (cuadrados negros) hacia vecindarios en la ciudad de Machala, Ecuador.

New geospatial science research from the Quantitative Disease Ecology and Conservation (QDEC) Lab Group at the University of Florida aims to improve the efficiency of mosquito control programs by borrowing methods from transportation geography to solve medical geography problems – optimizing routes using road network analysis. The study, “A network analysis framework to improve the delivery of mosquito abatement services in Machala, Ecuador”, recently published in the International Journal of Health Geographics, was conducted in the city of Machala, Ecuador in collaboration with the Ecuadorian Ministry of Health. Locations with potentially higher risk of mosquito-borne disease activity were identified, and the researchers created models of the best delivery routes from ministry-operated mosquito control facilities and every neighborhood in Machala.

In addition to identifying the most efficient driving routes, the team also determined which control facility locations were ideal under different management priorities. Public health workers typically spray for mosquitoes in response to incoming disease cases reported to the health department. Instead, some neighborhoods could be targeted ahead of outbreaks based on environmental risk factors. Moving control facilities closer to at-risk neighborhoods translates into monetary savings. “Health ministry priorities and strategies may change over time,” says Cat Lippi, a PhD student in QDEC and lead author on the paper. “This work provides a new way for health officials to compare the delivery cost of different management strategies when developing their control programs.”

These models can be used to improve public vector control services and reduce operating costs. “The results of this study have implications beyond Ecuador – and beyond dengue,” says senior author Dr. Sadie Ryan, the principal investigator for QDEC. “The framework we present can be used by any agency that plans for intervention through mosquito control operators.”

Read A network analysis framework to improve the delivery of mosquito abatement services in Machala, Ecuador, at the International Journal of Health Geographics.

Nuevo Enfoque a través de la Red para la Distribución del Control del Zancudo rinde ideas en una Ciudad del Sur del Ecuador

GAINESVILLE, FL – Pelear contra enfermedades causadas por el zancudo puede ser costoso. Aún cuando el control del zancudo es una manera efectiva de combatir la propagación de enfermedades como la fiebre del dengue, el precio de fumigar cada casa en una ciudad aumenta las cifras de costo rápidamente. Estos costos limitan programas del control del vector para la salud pública, el mismo que opera con presupuestos muy limitados.

Investigaciones nuevas de ciencias geoespaciales de el Quantitative Disease Ecology and Conservation (QDEC) Lab Group de la Universidad de Florida tienen como objetivo mejorar la eficiencia de programas para el control del zancudo al métodos de la transportación geográfica para resolver problemas médicos basados en la geografía, optimizando rutas de análisis de la red. El estudio “A network analysis framework to improve the delivery of mosquito abatement services in Machala, Ecuador”, recientemente publicado en la Revista Internacional de la Geografía de la Salud, se llevó a cabo en la ciudad de Machala, Ecuador en colaboración con el Ministerio de Salud Pública del Ecuador. Se identificaron lugares con más potenciales de actividad de riesgo para la transmición de enfermedades causadas por zancudos, y los investigadores crearon modelos de las rutas de más eficacia, manejados por el ministerio, en el entrego de los servicios para el control del zancudo y todos los vecindarios de Machala

A más de identificar las rutas de entrega más eficientes, el equipo también determinó cuáles ubicaciones de servicio de control fueron las más ideales bajo diferentes prioridades de adminis

tración. Los trabajadores de salud pública típicamente fumigan para zancudos respondiendo a casos de enfermedades reportados al departamento de salud. En vez, algunos vecindarios podrían ser asistidos antes de un brote basado en riesgos del ambiente. El mover servicios de control más cerca a los vecindarios en riesgo se traduce como ahorros monetarios. “Las prioridades y estrategias del ministerio de salud pueden cambiar al pasar del tiempo,” dice Cat Lippi, estudiante de PhD en QDEC y autora que encabeza este estudio. “Este trabajo de investigación provee una nueva pauta para dirigentes de la salud para comparar el costo de entrega de diferentes estrategias de administración cuando desarrollan sus programas de control.”

Estos modelos pueden ser usados para mejorar servicios de control del vector y reducir costos de operación. “Los resultados de este estudio tienen implicaciones más allá del Ecuador – y más allá del dengue,” dice la autora mayor Dra. Sadie Ryan, la investigadora principal de QDEC. “El armazón que presentamos puede ser utilizado por cualquier agencia que planea la intervención a través de operadores de control del zancudo.”

Lee A network analysis framework to improve the delivery of mosquito abatement services in Machala, Ecuador, en International Journal of Health Geographics.

Media contact: Mike Ryan Simonovich

Dr. Cynthia Simmons presented as an invited featured speaker at the International Colloquium on Socio-Environmental Politics at Rhodes House, Oxford University, on 31 Jan 2020 in a talk titled Dynamic Amazonia: Lessons for a Changing World.

Amazonia is critical to the global environment given its store of biodiversity and its repository of carbon. Since the mid-20th century, the Amazonian countries – particularly Brazil, Ecuador, Peru, and Bolivia – have implemented a variety of infrastructure projects meant to tap the region’s resources and open it to human settlement. Consequently, a large fraction of the forest has been converted to agricultural use. At the same time, human populations have grown precipitously to more than 20,000,000 people – many of whom live in an expanding network of urban areas that span the basin. There is little doubt that development has transformed the region’s environment and put the heritage of its indigenous peoples at risk. Despite global concerns for maintaining Amazonia’s ecological and cultural integrity, a new infrastructure program joined by all the South American nations has initiated a complex transformation of the region that will turn it into a transportation hub, a continental source of hydropower, and a preferred location for industrial development. Resulting environmental changes will be intensified by global warming. Amazonia is a dynamic region on the verge of dramatic anthropogenic change. What will happen to its remaining ecosystems and indigenous peoples? What will happen to those who came as colonists and worked hard to establish frontier livelihoods? In this presentation I address the three main questions to be debated at the colloquium. First, how to make sense of Amazonia today, given the rising violence and threats to the environment? Second, what Lessons have we learned, or better yet, should we have learned? Third, what recommendations can be made that will move us toward a socially and environmentally just future?

An Immediate outcome of the workshop is the Oxford Letter for the Amazon, signed by Signed by indigenous and peasant representatives, politicians, civil societymembers, students,artists, activists,researchersand academics. Read the whole letter at AgroCultures.

Thursday, February 27, 2020

2:50-3:50 PM (Period 8)

Turlington Hall Room 3018

University of Florida

All are welcome to attend.

Our Masters Students will present their research in a poster session for this Colloquium.

Dr. Robert Walker‘s work was recently featured in Catastrophic Amazon tipping point less than 30 years away: study, an article in Mongabay.

The present study, led by Robert Walker at the University of Florida, Gainesville, combined projections of future agricultural expansion published by Brazil’s Ministry of Agriculture, Livestock and Food Supply (MAPA) and the Food and Agricultural Organization of the United Nations (FAO), along with plans for the region’s industrial and infrastructure development, in order to estimate the total area of the Amazon basin that could be deforested by 2050.

They found that agricultural expansion and infrastructure development over the next thirty years could put the Amazon rainforest well beyond the tipping point for shifting to a savanna biome.

MedGeo researchers from the Quantitative Disease Ecology & Conservation Lab (QDEC Lab) and  Spatial Epidemiology & Ecology Research Laboratory (SEER Lab) made a strong showing at Emerging Pathogens Institute‘s EPI Research Day 2020!

QDEC Lab’s Stephanie Mundis presents Characterization of spatial and temporal factors related to Eastern Equine Encephalitis virus spillover in Orange County Florida
QDEC Lab’s Cat Lippi presents Social-ecological influences on dengue fever and a comparison of surveillance indicators in Machala, Ecuador
SEER Lab’s Dr. Michael Norris presents Estimating the local infectious zone and risk factors for anthrax transmission in West Texas
SEER Lab’s Dr. Michael Norris presents Alteration of exosporium surface oligosaccharides: Evidence of convergent patho-evolution in Bacillus anthracis
SEER Lab’s Dr. Michael Norris presents Seroprevalence of melioidosis among swine in two Vietnamese provinces
SEER Lab’s Maria Uribasterra presents White-tailed Deer Contact Rates on a High-fenced Property in Northern Florida
QDEC’s Dr. Rachel Sippy presents Prediction of Microsurveillance Using Machine Learning
QDEC’s Shreejana Bhattarai presents Evaluating vector control interventions to eliminate malaria from Nepal
QDEC’s Dr. Alexis White presents Applications and modeling of TickBot: a tick-killing robot

Speaker: Maíra Irigaray Castro

PhD Student, Department of Geography, University of Florida

Thursday, February 13, 2020

2:50-3:50 PM (Period 8)

Turlington Hall Room 3018

University of Florida

All are welcome to attend.

The Munduruku Movement Ipereğ Ayũ (MMIA), which in Munduruku translates to “We are strong; We know how to protect ourselves and all We believe in,” is a new autonomous social movement at the forefront to resist the government’s destructive plans for Amazonia and ensure legal guarantees to self-determination and homelands. Also, of interest is the Wakoborûn Indigenous Women’s Association and Movement (WIWM), an organization within MMIA that was formed in 2017 to unite the Munduruku women in the struggle. MMIA and WIWM have been recognized for their efforts to educate and empower a broad segment of the Munduruku people, facilitate organizational cohesion among the tribal communities, and establish alliances with regional, transnational, and global organizations and movements. Despite growing international attention, very little has been written about them beyond the grey literature. The goal of my research is to fill this gap in the scholarship, providing a fuller account of MMIA and WIWM by employing a decolonizing framework that integrates Feminist and Indigenous Political Ecology with Geographies of Resistance to illuminate MMIA and WIWM’s genesis stories, and explore how their experiences through cycles of contention triggered by Amazonia development pressures define their grievances and shape their organizational structure and strategies for collective action.

Yesterday, SEER Lab and QDEC Lab held an impromptu meeting in the GIS Teaching Lab (Turlington Hall 3006) to listen to David Quammen discuss the 2019-nCoV coronavirus emerging out of China on Fresh Air on NPR. David Quammen is a long-time science writer and the author of the 2012 non-fiction “Spillover”, which journals the pursuit of novel pathogens that spill from animal populations into humans.

Throughout our human history, zoonoses have crossed from animals to humans. Diseases such as anthrax (studied by SEER Lab), malaria (studied by QDEC), Ebola, and HIV are all examples of zoonoses. Malaria and HIV represent two examples of pathogens that have made the leap and now maintain human-to-human transmission. The available evidence suggests that 2019-nCoV is a bat virus that spilled into the human population through a wet market – a live animal/slaughter market in China. It is not yet known if or what intermediate host may have amplified the infection in humans, but new evidence suggests 2019-nCoV is successfully transmitting human-to-human.

Dr. Jose Miguel Ponciano, Associate Professor of Biology and SEER/QDEC collaborator, joined and shared his expertise in evaluating the genetic patterns of the available nCoV genome sequences being shared with the scientific community. Emerging diseases represent a perfect intersection of physical, human, and biogeography.

Interested in learning more? Check out the #MedGeo program in the department and come join us for our next MedGeo Brief.

University of Florida Department of Geography
The Navi-Gator
February 2020, ISSUE 4 (Download PDF)

Evening of excellence
Continued…
Congratulations to our winners! We loved having you all for a night of celebration, reward and remembrance!
Anderson Award for International Travel- Leandra Merz

Top Published Research Articles- Mehedy Hassan for Geospatial Analysis and Techniques & Global, Environmental, and Social Change
Cat Lippi & Stephanie Mundis for Medical Geography in Global Health
Evan Coe Award in Medical Geography- Stephanie Mundis

Spread the Word!
University of Florida in South Africa
Application Deadline: February 15, 2020!
Students will be on safari in Kruger National Park
Eligibility:
Open to ALL majors GPA 2.5 or higher, in good standing Interest in Africa & Conservation previously taken GEA3600: Geography of Africa (recommended)
Email Dr. Jane Southworth for more information jsouthwo@ufl.edu

Where Are they now?
Our recent grads have found themselves in some interesting places!
Dr. Roberta Mendonca de Carvalho, class of 2019, now teaches and researches at the University of Pittsburgh!

 

Image courtesy Dr. Darla Munroe

Land Systems and Climate Justice

Speaker: Dr. Darla Munroe

Professor & Department Chair, Department of Geography, The Ohio State University

Friday, 21 February 2020

3:00 – 4:30 PM

Reitz Union G330

University of Florida

There is greater recognition among IPCC and other scientific networks of the complex role land systems play in adaptation to and mitigation of climate change. Encouraging key shifts in land systems to more sustainable uses is necessary to food security, societal well-being, and the health of terrestrial ecosystems. However, policy interventions that do not address how and why current challenges reflect the profitability of environmental degradation, and that fail to prioritize social justice are unlikely to address root causes of unsustainable land systems.

Ohio State University, Department of Geography Professor & Department Chair, Dr. Darla Munroe will present her research in the second of two talks for the University of Florida 2020 Anderson Research Lecture series, in a talk titled Land Systems and Climate Justice.

Dr. Darla Munroe is an economic, and human-environment geographer specializing in landscape-level, long-run environment-economy relationships, with a particular focus on how political and economic restructuring manifest in local land-use change. She is a member of the Scientific Steering Committee for the Global Land Programme and Co-Editor-in-Chief of the Journal of Land Use Science. Her research is comparative, addressing land systems, particularly forests at the urban-rural interface in Eastern Europe, Central America, and Southeast Asia. Her current research focuses on boom-bust natural resource economies and forested community change in Appalachian Ohio.