Tracking Attacks on Health Care in Ukraine

DrivenData built a real-time, interactive map to visualize attacks on the Ukrainian health care system. The map will support partner efforts to provide aid, hold aggressors accountable in court, and increase public awareness.

The organizations¶

Insecurity Insight monitors incidents of violence worldwide using innovative open-source data collection and analysis. Their unique database supports decision makers at humanitarian agencies, nonprofits, and community organizations concerned with the protection of health workers, educators, and displaced populations.

Physicians for Human Rights combines medicine, science, and the law to document human rights violations and hold perpetrators accountable.

The challenge¶

Since the invasion of Ukraine in February 2022, there has been a targeted campaign of attacks on health care facilities and civilian infrastructure. Documenting these assaults is critical to provide effective aid and to prosecute aggressors for violating human rights law.

Insecurity Insight gathers information to support these efforts through information sharing with local organizations and open-source monitoring, which enables uniquely rapid response to dynamic conflicts. Insecurity Insight has been closely involved in tracking violence in Ukraine since the invasion began, but needed a more easily accessible tool to disseminate information quickly to those on the ground.

The approach¶

Insecurity Insight's Health Care at Risk map tracks incidence of violence against healthcare systems worldwide, but does not capture the specific details needed in the Ukrainian context nor provide information in real time. This project created an easy-to-use, up-to-date, interactive map of attacks on healthcare in Ukraine to support journalists, aid providers, and prosecutors.

To accomplish this, DrivenData:

Used open-source visualization tools like Nuxt, Vuetify, and Leaflet to build on existing best practices while also allowing for sufficient customization.
Connected the map directly to Insecurity Insight's database via an API, enabling real-time updates without any manual entry.
Deployed a prototype early and iterated quickly based on input from organizations with an understanding of the needs of key end users - those working to provide aid and hold aggressors accountable in court.

The map was developed alongside a coalition of organizations, including eyeWitness to Atrocities, Insecurity Insight, Media Initiative for Human Rights, Physicians for Human Rights, the Ukrainian Healthcare Center, and DLabs.AI.

The outcome¶

Over the course of just a few months, a full dashboard tracking attacks on health care in Ukraine was designed, developed, and deployed. The map is updated regularly and used to monitor the state of health care in Ukraine.

Screenshot of interactive map of attacks on health care in Ukraine when filtered for attacks on infrastructure. Source: www.attacksonhealthukraine.org

Users can:

Select any individual attack to see a short description, as well as any relevant images
Quickly view topline counts like number of attacks, clinics damaged, and health workers killed on either a desktop or a mobile phone
Filter the attacks by type of infrastructure and date range
Visualize how patterns of attacks have changed over time
View the map in either English of Ukrainian

To learn more, visit the map or read the corresponding report.

Our real-world impact

All projects

Partners: Max Planck Institute for Evolutionary Anthropology, Arcus Foundation, WILDLABS

Automating wildlife identification for research and conservation

Detected wildlife in images and videos—automatically and at scale—by building the winning algorithm from a DrivenData competition into an open source python package and a web application running models in the cloud.

Partners: Private sector, social sector

Building LLM solutions

Built solutions using LLMs for multiple real-world applications, across tasks including semantic search, summarization, named entity recognition, and multimodal analysis. Work has spanned research on state-of-the-art models tuned for specific use cases to production ready retrieval-augmented AI applications.

Partners: The World Bank, The Conflict and Environment Observatory

Identifying crop types using satellite imagery in Yemen

Used satellite imagery to identify crop extent, crop types and climate risks to agriculture in Yemen, informing World Bank development programs in the country after years of civil war.

Partners: IDEO.org

Illuminating mobile money experiences in Tanzania

Analyzed millions of mobile money records to uncover patterns in behavior, and then combined these insights with human-centered design to shape new approaches to delivering mobile money to low-income populations in Tanzania.

Partners: CABI Plantwise

Mining chat messages with plant doctors using language models

Automated recognition of agricultural entities (such as crops, pests, diseases, and chemicals) in WhatsApp and Telegram messages among plant doctors, enabling new ways to surface emerging trends and improve science-based guidance for smallholder farmers.

Partners: Data science company foundation

Matching students with schools where they are likely to succeed

Used machine learning to match students with higher education programs where they are more likely to get in and graduate based on their unique profile, with a focus on backgrounds traditionally less likely to attend college or apply to more competitive programs.