Lab profile
About LiGHT
LiGHT is an international laboratory that advances open-access and implementable AI for global health and humanitarian response. The lab co-develops, validates, and scales trustworthy AI and data solutions with NGOs and frontline teams to improve health and humanitarian outcomes, particularly in complex and low-resource environments. Their work combines engineering, evaluation, and implementation science to build AI systems that work in the real world through participatory design, distributed ownership, and open science principles.
01 · Research focus
Research areas and highlights
Topics and recent work as stated on the lab’s own site.
- IMCI-PlusAn interdisciplinary, Pan-African-European Union research initiative which aims to improve the management of childhood pneumonia by pioneering the use of point-of-care lung ultrasound in everyday clinical practice and policy.
- MOOVEA global, expert-led initiative that enables clinicians, humanitarian actors, and local experts to evaluate AI models against the realities of their own settings through a progressive clinical validation pathway from hypothetical scenarios to randomized controlled trials.
- CADLUS4TBAn EDCTP3-funded research project bringing together partners across Africa and Europe to improve tuberculosis diagnosis through AI-driven computer-assisted lung ultrasound in Benin, Mali and South Africa.
- MeditronMeditronFO (Fully Open) is the first fully open medical specialist LLM, and outperforms Medgemma on open ended clinical evaluations.
- ultr-AIMultimodal foundation models integrating text, images, signals, and clinical data.
- MoDNModular Clinical Decision Support Networks (MoDN) is a novel decision tree composed of feature-specific neural network modules that creates dynamic personalised representations of patients and can make multiple predictions of diagnoses and features, updatable at each step of a consultation.
- MoBayesMoBayes constructs an explicit clinical knowledge base, then iteratively gathers evidence through LLM-parsed patient dialogue and updates beliefs with Bayesian inference, outperforming much larger standalone LLM doctors at a fraction of the cost.
- MultiModNMultiModN explores modular neural architectures for multimodal, multi-task learning, with a focus on interpretable fusion across heterogeneous data sources, supporting robust prediction even when some information is missing not at random.
- DISCODIStributed COllaborative Learning enables building and training AI models without sharing any data through machine learning directly in the browser.
- mmoreMassive Multimodal Open RAG & Extraction (mmore) pipeline to personalize LLMs with a diverse corpus of multimodal inputs.
- Talk2YourDataTalk2yourdata enables natural language querying of DHIS2 health data.
- OneScopeA multi-parameter smart stethoscope.
02 · People
Leadership and researchers
People listed on the lab’s team pages, by role.
03 · Research intelligence
Research Intelligence evidence
Publications, grants and clinical trials linked to the lab’s researchers in Health AI Central’s research data.
Publications & preprints
- [AI-assisted radiology in the management of respiratory infections].Revue medicale suisse · 2026
- Unpacking the Unreliability of Interrater Reliability of Pediatric Auscultation.Hospital pediatrics · 2025
- How are fast tracks organized in adult and pediatric emergency departments in Switzerland? A cross-sectional survey.BMC health services research · 2025
04 · Updates
Updates and lab news
News and events from the lab’s own site.
No news has been collected from the lab’s site yet.
05 · Official presence
Lab sources and channels
The lab’s own pages and accounts.
06 · Related
Related labs and centers
Labs at the same institution and labs working on similar topics.