About WHO
Our primary role is to direct and coordinate international health within the United Nations system. Our main areas of work are health systems; health through the life-course; noncommunicable and communicable diseases; preparedness, surveillance and response; and corporate services.Activities by WHO
PulseSatellite: A collaboration tool using human-AI interaction to analyse satellite imagery
Africa, Asia and the Pacific BangladeshSomalia
PulseSatellite is a collaborative satellite image analysis tool that leverages neural network models that can be retrained on-the-fly and adapted to specific humanitarian contexts and geographies. The tool has models for mapping structures in refugee settlements, roof density detection, and flood mapping.
We are also working closely with UNOSAT to develop benchmark datasets for shelter (refugee camp) mapping, building footprint detection and damage assessment. We plan to use these to test many of the available well trained and top-performing models, but in the context of UN-focused datasets (e.g. with more of a Global South and development context than many of the standard machine learning benchmarks) and make this available as a service to the UN system.
Operational contexts are rapidly changing, meaning that AI models may not always perform well. Through using a human-in-the-loop approach we have found that models can be adapted to such changing settings, however, this still requires (sometimes significant) manual intervention from analysts.
The Global Initiative on AI for Health (GI-AI4H)
GlobalThe launch of the GI-AI4H is a landmark moment of harnessing the potential of AI in health. This transition was and is possible thanks to the commitment of three key United Nations agencies, the World Health Organization (WHO), the International Telecommunication Union (ITU), and the World Intellectual Property Organization (WIPO) to enable, facilitate and implement the adoption of AI-based technologies for health. The setting up of the GI-AI4H moves beyond the traditional boundaries of individual organizations. It is a testament to the recognition that addressing the complex challenges and opportunities presented by AI in health requires a multidimensional and collaborative approach. By pooling their joint expertise and resources the initiative aims at becoming a powerful force aligned to two core objectives: Firstly, the GI-AI4H is dedicated to ensuring innovation and global accessibility to AI solutions across healthcare services. In leveraging AI, WHO envisions a future where innovative technologies bridge gaps in healthcare delivery, making essential services accessible to everyone, especially in low- and middle-income countries (LMIC). Secondly, the promotion of ethical and equitable advancements in health AI technology. Recognizing the potential risks and disparities associated with AI from its inception in policymaking to the implementation on the ground, the initiative places a strong emphasis on ensuring that technological progress is accompanied by principles of fairness, inclusivity, and ethical considerations. This commitment underscores the intention to create a healthcare landscape where the benefits of AI are equitably distributed, leaving no one behind.
Activity Type Research/Reports/AssessmentsFocus Group on Artificial Intelligence for Health (FG-AI4H)
Global Not ApplicableThe FG-AI4H was run from 2018 to 2023 as a collaboration between ITU and WHO and pioneered a standardized assessment framework for the evaluation of AI-based methods for health, diagnosis, triage and treatment decisions. It developed 36 deliverables providing developers guidance under four pillars: (1) ethics, (2) regulations, (3) technology and (4) clinical evaluation and 15 use cases. Its work is continued under the Global Initiative on AI for Health co-organized by ITU, WHO and WIPO, expanding the guidance to a wider audience, countries and regulators in particular.
Activity Type Research/Reports/AssessmentsPolicy/Regulatory GuidanceNetworks/Mentorship/ExchangeOnline radio monitoring for public health social listening and beyond
AfricaA radio monitoring pipeline was developed to 'listen' to online radio stations, transcribe the audio using machine learning speech-to-text models, and analyze the content using NLP methods. The dashboard is used by infodemic managers and decision-makers to inform public health interventions.
Activity Type AI Tools/SolutionsResearch/Reports/Assessments