“During the COVID-19 crisis, experts worldwide developed numerous software tools to enhance outbreak modeling and analytics. Yet, many of these solutions remain isolated, leading to duplicated effort, lack of interoperability, and poor documentation, support, and maintenance” said Dr. Danil Mikhailov, executive director of data.org. “The opportunity for global collaboration and resource-sharing remains largely unrealized. Through generous support from The Rockefeller Foundation, our partnership with the WHO Pandemic Hub reinforces our commitment to leveraging data for social good and brings us closer to our long-standing vision of a safer, healthier global community.”

“Climate change’s rising temperatures and extreme weather are fueling outbreaks of malaria, cholera, and other deadly diseases. Health leaders can outsmart infectious threats like these by combining climate and health information to predict where pathogens will spread – and digital tools can put that data at their fingertips,” said Dr. Naveen Rao, senior vice president of health, The Rockefeller Foundation. “We’re proud to support the sharing of world-class pandemic preparedness technology so people can stay healthy in a warmer world.”

The WHO Pandemic Hub fosters a collaborative environment for innovators, scientists, and experts from across a wide spectrum of disciplines, leveraging and sharing cutting-edge technology and anchoring our work in the needs of stakeholders around the world. Building on expertise across disciplines, sectors, and regions, the Hub leverages WHO’s convening power to foster global solutions built on an architecture of global collaboration and trust. By leveraging Epiverse’s existing collaborative network—including academic partners—data.org will support the WHO Pandemic Hub in crafting the “Pandemic and Epidemic Intelligence (PEI) Collaboratory.” Tailored for pandemic intelligence professionals, the PEI Collaboratory will make digital public goods more accessible for WHO country members and partners engaging on the platform. There, they will find a space that fosters collaboration, the sharing of ideas and best practices, and joint problem-solving for better public health results. 

Across both the PEI Collaboratory and Epiverse networks, data.org also aims to increase the uptake of Epiverse digital public goods in low- to middle-income nations to streamline the global public health tech arena, granting open access to best-in-class epidemic intelligence resources for health institutions globally. This builds on data.org’s ongoing work with The London School of Hygiene & Tropical Medicine, The Medical Research Council Unit The Gambia, Universidad de los Andes, and Pontificia Universidad Javeriana, where locally-developed tools and human-centered design are leading to more effective, more equitable public health solutions. As part of this process, community-based champions will be identified and mobilized to build trust locally and lead change management efforts in a way that increases in-country adoption. Outreach to other existing communities of practice will likewise help identify a diverse group of stakeholders and bring them into the fold to use Epiverse tools and engage with the growing community.

“Collaborative efforts in the realm of global health data are not just strategic, but essential,” said Dr. Julia Fitzner, unit head of insights and analytics at the World Health Organization. “As we’ve witnessed, isolated solutions can only go so far. By uniting our expertise and resources with data.org through the PEI Collaboratory, we’re not just aiming to respond to global health threats but to anticipate them. Our shared vision is to empower nations, especially those most vulnerable, with the tools and insights they need for a healthier tomorrow.”

About data.org

data.org is accelerating the power of data to solve some of our greatest global challenges. Launched in 2020 by the Mastercard Center for Inclusive Growth and The Rockefeller Foundation, data.org serves as a platform for partnerships to build the field of data for social impact by widening access to the tools, resources, and talent needed to make sustainable and equitable change.    

A global organization, data.org convenes and coordinates across sectors and is committed to supporting and amplifying visionary — but also practical — solutions to drive greater impact, through data.

About WHO Hub for Pandemic and Epidemic Intelligence

The WHO Hub for Pandemic and Epidemic Intelligence is working towards a world where collaborative surveillance empowers countries and communities to minimise the impact of pandemic and epidemic threats. Collaborative surveillance, a key concept within WHO’s framework to strengthen the global architecture for health emergency prevention, preparedness, response and resilience (HEPR), facilitates the systematic strengthening of capacity and collaboration among diverse stakeholders globally, both within and beyond the health sector, to enhance public health intelligence and improve evidence for decision-making.

With the support of the Government of the Federal Republic of Germany, the WHO Pandemic Hub was established in September 2021 in Berlin, as part of the WHO’s Health Emergencies Programme. More info here.

About The Rockefeller Foundation

The Rockefeller Foundation is a pioneering philanthropy built on collaborative partnerships at the frontiers of science, technology, and innovation that enable individuals, families, and communities to flourish. We make big bets to promote the well-being of humanity and make opportunity universal and sustainable by advancing the global climate transition and ensuring everyone can participate in it. Our focus is on mobilizing collective action that transforms four systems that are essential to the well-being of people and planet: energy, agriculture, health, and finance systems. For more information, sign up for our newsletter at rockefellerfoundation.org and follow us on X @RockefellerFdn.

Media Contact 

data.org: Emma Marty | emma@data.org

The post data.org Partners with the World Health Organization on Global Health Response appeared first on data.org.

Ha pasado un año desde que la colaboración global Epiverse-TRACE se expandió a América Latina y el Caribe (LAC).

Con el apoyo del International Development Research Centre (IDRC) de Canadá, en TRACE-LAC, nuestro objetivo ha sido construir un conjunto de herramientas de datos de alta calidad, de código abierto e interoperable para el análisis de datos epidemiológicos. Además, buscamos crear una comunidad de usuarios que ayude a informar a los tomadores de decisiones en la respuesta a epidemias en la región.

El proyecto inició con la asociación entre la Universidad Javeriana y la Universidad de los Andes para ingresar a la iniciativa TRACE liderada por el LSHTM y el MRC The Gambia. En ese proceso Zulma M. Cucunubá, Catalina González-Uribe y Juan Manuel Cordovez establecieron  un modelo de trabajo colaborativo a través de la integración de  un equipo multidisciplinario conformado por personas expertas en ciencia de datos, modelamiento matemático, ciencias sociales y toma de decisiones en salud pública.

A partir de esto, se trazaron tres líneas de acción para fortalecer el ecosistema en ciencia de datos y salud en LAC.

Caracterización del contexto sociotécnico para el análisis de datos en Colombia

Esta línea de acción, dirigida por Natalia Niño, cuenta con un grupo de expertos en ciencias sociales que exploran el ecosistema de actores en ciencias de datos y salud mediante la creación de un mapa de actores en Colombia, incluyendo la identificación de actores en áreas STEAM y barreras de acceso a herramientas de análisis y entrenamiento. El grupo ha identificado al menos 250 actores de organizaciones relevantes para la respuesta a epidemias, así como actores clave en el entrenamiento formal en ciencia de datos y organizaciones que promueven acciones con enfoque de género y ciencia de datos, uno de los temas transversales de TRACE-LAC.

Para identificar algunas de las barreras, el grupo adoptó un enfoque cualitativo con el cual se han realizado entrevistas a personas que trabajan en ciencia de datos en salud para comprender las razones por las que eligen trabajar en esta área, a pesar de los persistentes desafíos para captar y retener talento humano en el sector de ciencia datos para el impacto social.  

En este proceso, se han identificado varias similitudes entre los entrevistados. Algunas de estas incluyen incentivos percibidos no financieros como trabajar con colegas profesionales, los constantes desafíos intelectuales, pertenecer a una comunidad y el empoderamiento para las mujeres. Además, el grupo de ciencias sociales está construyendo un inventario de bases de datos de código abierto en Colombia para poner este recurso a disposición de los diferentes paquetes de R que el grupo de desarrollo de software de TRACE-LAC está creando.

Fortalecimiento de la capacidad regional para el análisis de datos en América Latina

Esta línea, liderada por Zulma Cucunubá, está compuesta por un grupo de expertos en educación que tiene como objetivo fortalecer las capacidades regionales para análisis de datos mediante el diseño de estrategias de entrenamiento presencial y de e-learning. Lo anterior con el fin de captar, atraer y retener a trabajadores de salud pública, estudiantes e investigadores de áreas STEAM. Estas estrategias están adaptadas para satisfacer las necesidades de los tomadores de decisiones e investigadores y se enfocan en la inclusión, la diversidad, la equidad y la accesibilidad.

El componente de e-learning incluye el desarrollo de un kit de entrenamiento en epidemiología, análisis y respuesta a brotes en América Latina y el Caribe, que estará disponible en una plataforma virtual. Durante el primer año, el equipo exploró conocimientos, necesidades y desafíos de la potencial comunidad de usuarios y su entorno de aprendizaje en Colombia. Además, probó algunos de los materiales de capacitación con usuarios en áreas que son relativamente fáciles de acceder geográficamente.

Para esto, se organizaron varios talleres y conferencias donde los participantes aprendieron sobre programación básica en R, el uso de sivirep (paquete de R desarrollado por el equipo de desarrollo de software en la Javeriana), modelamiento de enfermedades infecciosas, análisis de brotes y vigilancia de salud pública.

Los talleres fueron bien recibidos por 274 participantes que incluyeron epidemiólogos de campo, profesionales de entidades gubernamentales en salud y grupos académicos. Además, tuvieron una respuesta inesperada de futuras generaciones de científicos de datos para quienes la usabilidad y la practicidad de las herramientas fueron un factor clave en el aprendizaje sobre el análisis y el control de enfermedades infecciosas. Las personas demostraron su interés en ampliar el conocimiento en herramientas que les permitan responder adecuadamente a la próxima pandemia.

En el segundo año, el equipo de entrenamiento llegará a comunidades más remotas para probar los materiales y comprender los desafíos de la formación tanto online como offline en el desarrollo de la plataforma de e-learning.

Desarrollo de software para análisis de datos:

Usando información de los hallazgos iniciales de los equipos de caracterización sociotécnica y de capacitación, coordinados por Geraldine Gómez en Javeriana y Mauricio Santos en Uniandes, los equipos de desarrollo de software están construyendo seis paquetes en R. Estos tienen como objetivo proporcionar herramientas esenciales para mejorar el análisis, la vigilancia y el reporte de brotes en América Latina y el Caribe.

El proceso de desarrollo de software es iterativo y se basa en una estrecha relación de trabajo con entidades locales, como las secretarías de salud, para garantizar que las herramientas estén de acuerdo con sus necesidades.

Una de las herramientas, sivirep, ya tuvo sus primeras pruebas de usuario con trabajadores en el campo de salud pública en Bogotá. Estas pruebas validan la usabilidad y relevancia, y permitirán que los paquetes lleguen a comunidades más grandes. Durante el segundo año, el equipo continuará codesarrollando paquetes en R que llegarán a otras comunidades de la región. Tres de las herramientas (sivirep, serofoi y epiCo) formaron parte de la exhibición en el LSHTM en abril de 2023.

Explorar el potencial del ecosistema de ciencia de datos y su relación con la salud pública a través de tres líneas de acción nos ha enseñado que involucrar a nuestra comunidad de usuarios es vital para el éxito. Este compromiso continuo, y las prácticas de desarrollo iterativo, nos ayudan a comprender la interacción de los usuarios con el sistema y sus necesidades de capacitación, lo que es crítico para la adopción de las herramientas que diseñamos.

Nuestro primer año de TRACE-LAC ha demostrado que desarrollar herramientas de alta calidad, de código abierto y centradas en el usuario al incorporar mejores prácticas mientras nos adherimos a los valores de la comunidad Epiverse-TRACE, es crucial para construir un ecosistema de datos confiable y próspero.

The post Un año de Epiverse TRACE-LAC: explorando el ecosistema de ciencia de datos y salud en América Latina y el Caribe appeared first on data.org.

It has been one year since the global collaboration Epiverse TRACE expanded to Latin America and the Caribbean.

With support from International Development Research Centre (IDRC), our goal was to build a high-quality, open-source, and interoperable data toolkit for epidemics analytics – and grow an engaged user community – to inform decision-makers in the response to epidemics in Latin America and the Caribbean (TRACE-LAC).

To be part of the TRACE initiative integrated by the LSTHM and the MRC Unit in the Gambia, Zulma M. Cucunubá, Catalina González-Uribe and Juan Manual Cordovez from Universidad Javeriana (Javeriana) and Universidad de los Andes (Uniandes) started by building a strong organizational connection and established a multidisciplinary team of experts in mathematical modelling, social sciences, and decision making. They set up three lines of action, providing the team with the opportunity to assess barriers hindering the transformation of the software ecosystem for data science and health in Latin America and the Caribbean. With this assessment, the team would then be able to put forward solutions to enhance epidemic response in the region through capacity building and software development.

Characterizing the socio-technical context for data analytics in Colombia

Led by Natalia Niño, the social science team started by exploring the ecosystem of actors in data science and epidemics through mapping of stakeholders in Colombia and identifying barriers to access to tools and training. They identified at least 250 actors among organizations relevant to epidemic response, key actors in formal data science training as well as organizations promoting action on gender and data science, one of the cross-cutting themes of TRACE-LAC. To identify some of the barriers, the team adopted a qualitative approach seeking to understand why people choose to work on data science with a focus on health, given the persisting challenges of shortage of talent and lack of proper data ecosystems. They have already identified several commonalities among interviewees including working with peers, professional and intellectual challenge, community building, and empowerment (for women). Additionally, the social science team is building an inventory of open-source databases in Colombia and making this resource available for use within the different R libraries the TRACE-LAC software development team is developing.

Strengthening regional capacity for data analysis in Latin America

Led by Zulma, the training team aims to strengthen the regional capacities for data analytics by designing in-person and e-learning strategies to reach, attract, and retain public health workers, students, and researchers from STEAM areas into data analytics for health. These data analytics are adapted to meet the needs of decision-makers and of researchers focusing on inclusivity, diversity, equity, and accessibility. 

The e-learning component includes the development of an epidemic e-training kit, an online platform for inclusive training on outbreak analytics and response in Latin America. During the first year, the team explored the current knowledge, needs, and challenges of the potential community of users and learning environment in Colombia, and also tested some of the training materials with end-users in areas that are relatively easy to access geographically. They organized various workshops, conferences, and practicals where participants learned about basic programming in R, using sivirep (R library developed by the software development team at Javeriana), infectious disease modeling, outbreak analytics, and public health surveillance.

The workshops were well received among 274 participants which included field epidemiologists, national health agencies, and academic groups; they had an overwhelming response from future data scientist generations, for whom the usability and practicality of the tools was a key factor in learning about analysis and control of infectious diseases. Individuals demonstrated an interest for broadening knowledge in tools that allows them to respond adequately to the next pandemic.

In the second year, the training team will reach more remote communities to test materials and comprehend the challenges of online and offline training to be included in the development of the e-learning platform.

Developing Software for data analytics:

Using information from the initial findings of the socio-technical characterization and training teams, coordinated by Geraldine Gómez at Javeriana and Mauricio Santos at Uniandes, the software development teams are building the first six R libraries. These aim at providing essential tools for improving basic outbreak analytics, surveillance, and reporting in Latin America and the Caribbean. The software development process is iterative and builds from a close working relationship with local agencies, such as secretaries of health, to ensure the tools are in line with their needs. 

One of the tools, sivirep, already had its first end users test with public health workers in Bogota. These end-user tests validate usability and relevance and will allow the packages to reach larger communities. During the second year, the team will continue co-developing R packages reaching other communities in the region. Three of the tools (sivirep, serofoi and epiCo) were part of the showcase at the LSHTM in April 2023.

Exploring the potential of the data science ecosystem with three different lines of action has taught us that engaging our community of users is vital for success. This ongoing engagement and iterative development practices help us understand users’ interaction with the system, and their training needs are critical for adoption. Our first year of TRACE-LAC has underscored that developing high-quality, open-source, human-centered tools for outbreak analytics by using best practices and adhering to the Epiverse-TRACE community values, is crucial to build a trustworthy and thriving data ecosystem.

The post One year on of Epiverse TRACE-LAC: Exploring the data science and health ecosystem in Latin America and the Caribbean appeared first on data.org.

In June 2022, the Epiverse TRACE community established blueprints for software development, considering not only technical elements (such as coding conventions) but also crucially, human interactions and the experience of participating in an open-source community. Incentivizing Collaborative and Open Research (ICOR)—a nonprofit initiative that seeks to facilitate and reward open science and collaboration—is working with us on tracking and measuring our goals toward this vision.

Metrics will become targets: make sure they mean something

An inspiration for our discussion were the metrics and analytics being developed for open-source community health by our colleagues at Community Health Analytics in Open Source Software (CHAOSS). They believe that metrics selected for one’s community will inevitably become targets, which means that the values underpinning the chosen metrics are critical. This was the impetus to begin formally defining the values we wished to inform the metrics for gauging the initiative’s collective success.

Securing collective buy-in of core values

The selection of Epiverse TRACE core values involved the following stepwise actions, which took place over four months:

• Team audit of project documentation and discussions to date, plus a review of CHAOSS focus areas as a potential library of metrics to employ
• Draft documentation of values derived from the audit, indicating for each the purpose and potential metrics and data collection measures
• Circulation of draft document to the full Epiverse TRACE staff: 40 individuals with diverse backgrounds across four academic institutions and our funding partner, data.org
• In-depth interrogation of potential values, taking place over several weeks, with additional values proposed
  For example, an exploration of  the concepts of usability versus utility led to the determination that both were distinctive and crucial
• Clarification and selection session, attended virtually by Epiverse TRACE staff across all partner sites, narrowed core values to 13 possibilities with the aim of selecting 7 to 8
• Final vote by team members resulting in a list of 8 core values selected and adopted

Epiverse TRACE community core values

The following list of values will represent the Epiverse-TRACE community, with metrics built out accordingly:

1. Inclusion – ensuring that our community spaces are inclusive and welcoming to all.
2. Sustainability of the ecosystem beyond the project’s grand-funded lifetime.
3. Reciprocity – operating from a stance of give and take.
4. Practicality of Epiverse TRACE tools and materials for end users – both in terms of usefulness and usability.
5. Quality within the code development process.
6. Timeliness of the tools developed (e.g., on a regular basis).
7. Accountability to our community, our funders and each other.
8. Environmentally conscious – taking steps as a project to minimise the negative consequences of our actions on the climate.

Next steps: metrics, communication, and ongoing assessment

We must now define appropriate metrics for capturing these values, taking care to incorporate both ‘hard’ and ‘soft’ measures. For example, when considering inclusion, in addition to recording the identity of those in attendance at virtual events and seminars, taking into account those who do or don’t feel empowered to speak.

Each of the core values will be embedded in our discussions, communications, and documentation. Embodying them will require accountability – i.e., admitting errors and making unpopular or difficult decisions. However, we anticipate that our systematic community approach will ameliorate these difficulties.

And as our community grows, there will be periodic reviews to capture new insights and wider perspectives, as well as to question the continuing relevance of each value. We see this as an ongoing conversation, one which we hope will be as engaging as the discussions to date.

To get involved with the community, please complete this short form.

The post Epiverse TRACE: A Values-based Approach to Open-Source Ecosystems appeared first on data.org.

The problem? The tools to collect, clean, and analyze the data can vary dramatically from nation to nation and aren’t always interoperable, making it incredibly difficult to contextualize and understand local, regional, and global data as a whole. 

That’s where Epiverse comes in.

Launched by data.org in 2021, Epiverse is a global collaborative working to develop a trustworthy data analysis ecosystem dedicated to getting ahead of the next public health crisis. Specifically, Epiverse is empowering academia, governments, multilateral organizations, and others with open-source, privacy-preserving tools to derive new insights from data.

But even in an ecosystem as strong and robust as Epiverse, a good map is key. Outbreak analysts need to combine many tools to clean, describe, and analyze data to inform operations—all under considerable time pressure. 

“When trying to go from raw information to actionable intel, analysts face huge gaps to jump over and bridges to build,” says Senior Analyst Avinash Laddha. Together with Epiverse Software Design and Implementation Lead Thibaut Jombart, Laddha has created the Epiverse CONNECT Map, a regularly-updated visualization of the actual and potential relationships between different open-source outbreak analytics tools and health information management systems. 

Launching this map signals data.org’s commitment to the CONNECT pillar of Epiverse, focused on supporting and engaging with the global communities that sustain the data-driven technology focused on innovation and global health equity.

“There are many outbreak analytics tools out there and some connect with each other seamlessly, but many do not,” Laddha continues. “It’s a lot to remember when choosing which suite of tools best suits your goals.” 

For instance, take a data analyst who wants to forecast vaccine effectiveness. That analyst may have the perfect analysis tool in mind, but if they use a tool to collect and clean data that doesn’t connect to this analysis tool, they may have to spend countless hours reconfiguring data, at best. At worst, they have to start over again.

The Epiverse CONNECT Map helps with decision-making from the very beginning. Analysts can quickly choose a suite of tools and understand how the architecture should be built, saving valuable time and reducing the chances of error. “I knew this visualization could help data practitioners make very targeted and informed contributions to boost the performance of the suite of tools as a whole,” says Laddha.

Early positive feedback from the community indicates that Laddha was right. “But this is only the start of what can be a good community-driven resource,” he notes. “There are many connections (both actual and potential) that are still missing from the map.”

To continue collecting those connections, Epiverse, powered by data.org, invites you to submit your favorite tools and systems that you think should be on the map via a short form.

“Epiverse is incredibly fortunate to be part of the larger global health ecosystem,” says Laddha. “We know there are many minds focused on these challenges, and  hope that the Epiverse CONNECT Map will reduce duplication and improve coordination with the ultimate goal of improved global health outcomes.” 

The post Connecting the Dots of Outbreak Analytics appeared first on data.org.

Frustrated by the lack of research, development, and talent investment happening on the African continent, a group of data scientists got together in 2017 to shift the paradigm. 

Led by Dr. Vukosi Marivate, they launched Deep Learning Indaba, an event and organization to strengthen African machine learning. Now five years later, the event has exploded in popularity and credibility, attracting hundreds of students and professionals from 33 countries and spawning professional convenings and organizations that are building talent capacity, developing new solutions, and working toward a shared mission of a more inclusive and equitable landscape for data science.  

Ibrahim Mahgoub is the program director for Epiverse at data.org, a global collaborative working to develop a trustworthy data analysis ecosystem dedicated to getting ahead of the next public health crisis. Through the generous support of The Rockefeller Foundation, Mahgoub traveled to Tunisia to attend and moderate the final panel at Deep Learning Indaba. We caught up with him to learn more about how this Indaba—a Zulu word for a gathering or meeting—is advancing the field of data science.  

Ibrahim, you’re still on the ground in Tunisia as we speak. What are your impressions of your first Deep Learning Indaba event?  

It has been an incredible trip, sitting in on deep dive sessions around deep learning and absorbing so much rich technical content. It has been a humbling experience being around so many genius mathematicians, both those established in their careers and those learning and preparing to enter the field. Beyond that, though, it has been especially interesting to hear the individual stories about how people came to Indaba and their growth journeys as they have advanced this work alongside their peers.  

What makes Deep Learning Indaba different from other convenings? 

Indaba is not an industry conference organized by specific applications but rather people coming together across the continent to decide how to shape skill sets across various industry-types. This approach enables them to bring together some of the brightest minds in the world. 

Tell us a little about the panel that data.org hosted as part of the event. 

Sponsored by The Rockefeller Foundation, ours was the final session before the awards ceremony and it was such a powerful way to end the event. We had an incredible line-up of speakers, featuring Bayo Adekanmbi, the chief transformation officer at MTN Nigeria, Africa’s largest telecommunication company; Dr. Bubacarr Bah, an associate professor and head of data science Medical Research Council Unit The Gambia at the London School of Hygiene & Tropical Medicine; Dr. Agnes Kiragga, a research scientist and technical lead for data science at the African Population and Health Research Centre; and Indaba’s founder, Dr. Vukosi Marivate, who is also an associate professor and ABSA Chair of Data Science at the University of Pretoria. Each of these leaders has experience transforming organizations by harnessing data and building data science capacity, and we tapped into that expertise for a really robust discussion on how we can collectively chart a course forward to invest in, support, and expand data talent across Africa. 

Across Indaba’s sessions, are there any particular topics or priorities that stand out as most compelling? 

Natural language processing is a big topic of conversation here and is a growing area of research for artificial intelligence. It has such diverse applications, from fighting misinformation to enhancing virtual assistant technology. We need to teach computers how to understand language independently and not in an English-only context. Without natural language processing, AI can’t achieve maximum impact in low- and middle-income countries. Solutions need to be designed with the communities they’re intended to serve – and this is the meta-message of all these scholars and professionals coming together. There is both an opportunity to nurture this diverse and inclusive community of data practitioners, and a need to do so to solve the world’s pressing problems effectively.  

As you connect with leaders at Indaba, what do you most want them to know about Epiverse? 

Epiverse is trying to save people time. The big problem with disease outbreaks is you do not have time to build an entire stack of software to help you understand what is going on and what is going to happen next. So, we’re creating toolkits and open-source resources—informed by proven best practices—to save everyone crucial time that they cannot afford to lose in a crisis.  

How is the work of the Indaba community in line with the work and goals of data.org?  

We all believe in working with local data talent to develop resources deployed globally in order to engage more people in data for good. You can’t just parachute into places with ideas designed in a silo. For data science for social impact to be meaningful, solutions need to be co-created and they need to be open and accessible to all.  

Any parting thoughts?  

On our closing panel, we had people from hailing from the Gambia, Nigeria, South Africa, and Uganda – and I, myself, was born and raised in Egypt. The opportunity to develop data talent across the continent – for industry and social sector – is remarkable. Our recent Workforce Wanted report estimates that 3.5 M jobs in data for social impact (DSI) jobs worldwide have the potential to be created and filled by 2032. My hope is that a large number of them to be created in Africa, and to use that talent to drive high-impact projects like Epiverse.  

The post data.org Explores and Advances AI Solutions at Deep Learning Indaba appeared first on data.org.

When we first launched Epiverse in September 2021, we knew that without standardized, interoperable outbreak analytics tools, the virus would continue to undermine public health, particularly in low-and middle-income countries. The urgency we felt a year ago has not waned. With the fast-evolving COVID-19 variants, as well as the recent Monkeypox outbreak and resurgence of Polio, an initiative like Epiverse isn’t just needed — it’s imperative.

Over the past year, we’ve laid the groundwork by forging partnerships that bolster our efforts around the world — but this is only the beginning.

A Strong Foundation for Progress

Epiverse started as an interdisciplinary collaborative of experts advising on a concept that prioritized open-source, co-created software with the goal of strengthening and expanding the capabilities of infectious disease epidemiology. In the time since, Epiverse has evolved from a concept into a growing community, supported by philanthropic partners like Wellcome and The Rockefeller Foundation, the Alfred P. Sloan Foundation, and Canada’s International Development Research Centre. 

Global academic partners include the London School of Hygiene & Tropical Medicine (LSHTM), the LSHTM’s MRC Unit the Gambia, as well as Colombia’s Universidad de los Andes (Uniandes) and Pontificia Universidad Javeriana (Javeriana) have broadened the initiative’s reach and fortified its technical and epidemiological bench. We’ve also had the benefit of consulting with leading voices across a multitude of sectors through our Expert Advisory Committee while recruiting best-in-class mathematicians like Dr. Bubacarr Bah, advocates for open technology like Ibrahim Mahgoub, and innovative data scientists and technologists like Dr. Thibaut Jombart and Dr. Uyi Stewart.

This year, we also launched our inaugural package of Epiverse TRACE tools and developed the Epiverse TRACE Blueprint — a guide to our socio-technical approach to software development. In addition, we joined the Digital Public Goods Alliance to ensure that our technologies continue to be freely and easily accessible around the world.

We believe these partnerships and associations will yield a ripple of benefits for years to come. The Epiverse collaborative is not just committed to advancing data science in epidemiology — it is also committed to providing the wider social impact sector with new opportunities and resources, and ultimately building capacity in the regions that need it the most. 

Placing Humanity at the Center of Epiverse

While innovative science and technology get much of the spotlight, Epiverse cannot exist without its open-source community of contributors and users. Our outbreak analytics tools are already reimagining the open-source, collaborative process by setting guidelines that prioritize the community, and engaging and soliciting feedback from the people driving its co-creation and design.

For Epiverse, a human-centered design approach is critical to the initiative’s impact. By the end of this year, we will have engaged with health ministries and agencies in 15 countries who are providing localized expertise to inform our continued piloting, refining, and co-creating the Epiverse software ecosystem.

For me, the most encouraging news — aside from our growing community of funders, scientists, technologists, and health experts — continues to be that we are only getting started. As we look ahead, we are excited about our thriving partnerships, continued co-creation, and deepening social impact. But perhaps most importantly, we are grateful and inspired by the strength of our collaborative global community who are making sustained, meaningful impact through the kind of collaborative and equitable work that we only imagined as ‘possible’ when we began just one year ago. 

The post A Year in the Epiverse: Building an Ecosystem of Co-Created Progress appeared first on data.org.

Working in outbreak analytics for over a decade, the emergence of an initiative such as Epiverse was the long-awaited opportunity to radically change the way we use data to better prepare for and respond to disease outbreaks. For the first time, substantial resources have been unlocked to develop a much-needed, robust, high-quality ecosystem of software tools for analyzing epidemic data. 

Unlocking resources was just the first step of our ambitious project in which, to be successful, we will need to (re)invent the way we develop outbreak analytics tools or Epiverse TRACE tools. To date, infectious disease epidemiology (IDE) researchers have had little incentive to build software tools. The few groups who managed to dedicate time and effort to such endeavors were often working in competition with each other rather than collectively. These groups often lacked time, training, and resources for developing software to industry standards.  

Outbreak analytics involves a large number of stakeholders including academics, public health officers, field epidemiologists, modelers, and research software engineers. Similarly, Epiverse TRACE involves multiple teams covering different aspects of outbreak analytics, ranging from descriptive field epidemiology to more complex IDE modeling and automated data pipelines. To develop a coherent software ecosystem for outbreak analytics, we will need to ensure consistent, high-quality standards for coding, testing, and documentation, as well as ground rules for collaboration and interacting with our user base across all teams.  

Building a Software Ecosystem for People 

Thankfully, the open-source software (OSS) community has faced many of these challenges, and we can learn from their experience. This realization prompted our Epiverse team to organize a workshop this past June in London, where we were lucky to welcome world experts in R software development as well as from the wider OSS community. Based on the robust workshop discussions and contributions from the broader community, we created the Epiverse TRACE Blueprint for software development. 

Epiverse TRACE Blueprint aims to lay out best practices we will strive to implement when developing our ecosystem of open-source tools for outbreak analytics. One could expect such a document to be almost entirely focused on technical aspects, such as modular coding, unit testing, code coverage statistics, or generally implementing continuous integration. And while all these topics are indeed covered in the blueprint, they remained, surprisingly, secondary. Working together and drawing on our collective experience, we realized that the most important determinants of a successful OSS project are first and foremost about humans, and how they interact.  

The Blueprint is both an amalgamation of our community’s best practices and a commitment to championing and deploying these tried and true development conventions. A pervasive theme in the blueprint relates to interactions between users and developers. We take the stance that OSS development is intrinsically a co-creation process in which developers work hand-in-hand with end-users to ensure that tools address genuine needs faced by outbreak analysts. This involves not only using lean and agile collaboration frameworks, but also giving due recognition to all types of contributions, and investing extensively in documentation, training, and building capacity.  

Another core theme that emerged from the blueprint relates to how developers should interact amongst themselves. We believe that the key to success resides in teamwork rather than individual coding prowess. By having team members review each other’s code constantly and move across different projects regularly, we will better distribute code ownership, share technical knowledge among developers, and standardize code practices. And while we will benefit from the wider OSS community, we will also give back by engaging with developers through free software forums and workshops, highlighting individual contributors, and amplifying up-and-coming initiatives. 

It’s not news that human interactions are at the core of software development. In fact, Donald Knuth acknowledged this in his seminal work on literate programming nearly four decades ago in 1984: “Let us change our traditional attitude to the construction of programs: Instead of imagining that our main task is to instruct a computer what to do, let us concentrate rather on explaining to human beings what we want a computer to do.” Since then, the OSS community has made tremendous progress recognizing the importance of human interactions as a key part of software development, as illustrated by projects like the Community Health Analytics Open Source Software (CHAOSS) initiative. What is new is the potential for bringing this approach more systematically and comprehensively to epidemiology in a way that recognizes all contributions and creates infrastructure the global community can draw on. It is our hope that by bringing people together, fostering an inclusive, welcoming community, and championing high coding and documentation standards, Epiverse TRACE will deliver on its ambitious and vital mission to improve epidemic response and human lives across the globe. 

The post Placing People at the Cornerstone of Software Development appeared first on data.org.

Not only did existing tools fail to offer the speed and precision necessary to slow the spread of the virus, but COVID-19 also exploited a key flaw in our health systems – they are simply not designed for everyone to get sick at once. All over the world, epidemiologists were desperate for accurate, timely data and analytic software. In response, they built customized tools and models that aided localized efforts but failed to offer a coordinated and equitable global response. 

Though the pandemic looks very different from region to region today, timely, accurate data and globally interoperable software remain crucial elements for epidemic preparedness and response. And yet, most epidemiologists are still left to operate without them.  

Enter Epiverse  

Last fall, data.org launched Epiverse with a commitment to creating a more connected and informed epidemiological community geared toward disrupting global health inequities. The initiative grew from deep-dive discussions with stakeholders in public health, data science, data privacy, and open-source software who collectively identified the need for a global initiative dedicated to empowering the teams working tirelessly to respond to current epidemics and prepare for future ones.  

Since then, we’ve centered our work around the widely recognized Digital Development Principles to deliver on Epiverse’s three key pillars:  

1. Epiverse TRACE – a digital public good of interoperable software and tools that will globally transform epidemic response  

2. Epiverse BUILD – opportunities for inclusive, interdisciplinary co-creation and design on some of the field’s biggest challenges and inhibitors of progress  

3. Epiverse CONNECT – the global community sustaining the data-driven technology committed to innovation and global health equity  

TRACEing the Root of the Problem 

Epiverse TRACE addresses a wide range of needs in global infectious disease response to better understand and prepare for the evolution of an outbreak. Our tools will focus on everything from viral outbreak reconstruction to long-term forecasting. TRACE will also create game-changing opportunities for field epidemiologists with academic institutions, social impact organizations, and ministries of health alike to use data to better explain the past, understand the present, and envision the future.  

Data is often collected in different formats creating technical barriers to entry and inflexibility across different software tools. However, TRACE tools will eliminate that by interpreting data derived from common digital public goods – software used by community health workers to collect data from the field – as well as data obtained from health information systems and government bodies. This interoperability will allow teams from around the world to communicate efficiently and effectively and is essential for a coordinated global response. Looking ahead—and leveraging future partnerships and collaborations—we aim to paint a more complete and accurate epidemiological picture by incorporating non-traditional data, like commercial and environmental data, using privacy-preserving technology.

Some of this work is well underway. Our inaugural TRACE partners at The London School of Hygiene and Tropical Medicine (LSHTM) are currently focused on developing and testing tools in data cleaning, short-term outbreak reconstruction, and long-term forecasting/modeling. Their colleagues at LSHTM’s Medical Research Council Unit in the Gambia have also partnered with us to increase access in the region and ensure that data science tools are inclusive and relevant to low-to-middle income countries. Most recently, we launched a two-pronged approach in Colombia to strengthen epidemic response. The University of Javeriana is focused on enhancing service delivery tools deployed in field epidemiology, and the University of Los Andes is developing interoperable decision-making tools for response management.  

BUILDing + CONNECTing a Community of Co-Creation  

In our experience creating digital public goods, it takes great effort to strike a healthy balance between the desire to have widely-used tools and the aspiration for those same tools to be widely usable – a push and pull between broad utility and adaptability to specific use cases. In this case, the push and pull centers on timely data analysis and interoperable analytic software.  

Epiverse TRACE will minimize this tension by creating tools that are reflective of global need and driven by the insights gleaned from the interdisciplinary collaboration that began this effort.  

While TRACE serves to provide robust tools, Epiverse BUILD will bring the best and brightest together to co-create solutions. Currently, we are designing a challenge geared toward safely unlocking privacy preserved data to access new insights in our fight against infectious disease outbreaks.  As we look toward the future, BUILD will provide more opportunities where people can come together and innovate new technology.  

When developing open-source software, securing engagement, and cultivating a supportive developer community is a challenge. This is where Epiverse CONNECT will apply proven community-building tactics, like establishing dedicated community managers, convening spaces for conversations on progress in the field, and providing shared resources like data visualization maps to help developers and other community members navigate and collaborate within the ecosystem.  

Our work to strengthen partnerships on a global scale – particularly with low-to-middle income countries – brings us closer to co-creating an inclusive environment that supports an engaged developer community. It may seem obvious but crafting these intentional and fundamental pieces of community-building not only facilitate better, collaborative results—they also set a tone of respect and appreciation within the ecosystem, something that many open-source developers have been missing.   

Like everything else we do at data.org, Epiverse operates at the intersection of technology and its impact on humanity. This socio-technical approach is embedded in our methodology and reflected in our work.  

Digital public goods like Epiverse TRACE offer countries sovereignty over their software and inspire other collaborative efforts across the social sector. For now, we continue to focus on building the tools that are immediately needed in the regions most impacted by health inequities. We believe this work and community will extend far beyond this and ultimately serve as a blueprint for global social impact.  

The post Epiverse: A Trifecta for the Future of Epidemic Response appeared first on data.org.

Thibaut joins data.org as Software Design and Implementation Lead, responsible for system interoperability and automation across the Epiverse software packages. In this role, he will focus on building links within the Epiverse tools and with external collaborators and users, defining and implementing software design strategies, conducting research to maximize tool efficiency in outbreak response contexts, and serving as an advisor to relevant data.org programming. Working with the global collaborative of Epiverse building partners, Thibaut will lead the transformation of today’s epidemiological response tools, leveraging a robust and open software ecosystem.

Thibaut brings critical first-hand experience in outbreak responses, both as part of academic teams and in the field. Prior to joining data.org, Thibaut was an Associate Professor in outbreak analytics at the London School of Hygiene & Tropical Medicine (LSHTM) and served as a consultant for the World Health Organization. Thibaut worked on several outbreak responses as an academic, including pandemic influenza, MERS-CoV, or the COVID-19 pandemic, and has also been deployed with the WHO to the Democratic Republic of the Congo where he used data science to inform the response to Ebola outbreaks. Pertinent to his role at data.org, Thibaut is extensively involved in developing data science software and has authored or co-authored over twenty R packages. This software has attracted an expansive user base, with packages garnering approximately 540,000 downloads and over 6,000 citations. He is also the founder of the R Epidemics Consortium (RECON), a non-profit organization for the development of free, open-source analysis tools and training resources for the response to humanitarian crises.

“Open-source software holds the power to alleviate the procedural bottlenecks that slow down infectious disease response. Epiverse’s technology will ensure that the information generated by one epidemiological analysis can be used seamlessly in another. The inclusive open-source Epiverse community will deliver greater insights across the globe, empowering the production of better products, solutions, and ultimately health outcomes. I am delighted to help data.org lead this charge,” said Dr. Thibaut Jombart.

Thibaut holds a Ph.D. in biostatistics from the University of Lyon, France, and is a part-time senior lecturer in outbreak analytics at Imperial College London.

“Dr. Thibaut Jombart is a leading expert and contributor to the field of outbreak analytics, and we are thrilled to have him lead technology development across Epiverse,” said Ibrahim Mahgoub, Program Director, Epiverse. “His interdisciplinary expertise and boots-on-the-ground experience will provide a critical focus on interoperability and field effectiveness, ensuring that Epiverse tools enable responders to be more connected and informed.”

The post data.org Welcomes Software Design and Implementation Lead to Bolster Technology Strength and Community Engagement appeared first on data.org.