Comprehensive geographic data are essential to accurately model geographic accessibility to healthcare and to guide equitable health system planning and implementation. In low-income countries, however, incomplete road and building data in global databases such as OpenStreetMap (OSM) limit the precision and operational applications of geographic accessibility models. Following a successful pilot in one district of Madagascar, we evaluated the scalability of an exhaustive mapping approach to produce highly granulated household-level accessibility estimates at regional and national levels. Using satellite imagery and the OSM platform, we mapped all buildings, roads, footpaths, and rice fields across seven additional districts in southeastern Madagascar. We estimated travel routes, distance and travel time between each household and the nearest primary health center (PHC) or community health site (CHS) using the OSM Routing Machine, combined with predictions of travel speed from a locally calibrated statistical model. We then assessed population density and mapping completeness for roads and buildings in our study area and across Madagascar using AI-generated reference datasets (Microsoft and Facebook/MapWithAI) and estimated corresponding mapping times. Finally, we estimated the resources required in person-years to scale this approach across Madagascar using two different extrapolation methods. Nearly one and a half million buildings and 197,000 km of footpaths were added to OSM across the eight mapped districts, for a total area of about 30,200 km2. Between 24 % and 65 % of the population lived within one hour of a PHC depending on the district, and 87 %–99 % lived within one hour of a CHS. Most Malagasy districts were classified as having low completeness for both buildings and roads. Scaling up the approach to cover the entire country would require between 220 and 350 person-years depending on the extrapolation method and assumptions used. Mapping an entire country with sufficient detail to precisely model healthcare accessibility for every household is feasible but resource-intensive. Combining human mapping, participatory approaches, and AI-assisted datasets can substantially improve OSM completeness and generate actionable, high-resolution travel-time data for health planning. Our findings provide a roadmap for Madagascar and other countries seeking to develop national-scale geospatial infrastructure for sustainable development and universal health coverage.

The authors have declared no competing interest.

The first phase was supported by a grant from the Institut de Recherche pour le Développement (IRD Coup de Pouce, "MAGIE" project) and internal funding from Pivot. The second phase was conducted as part of the RISE project (Research, Innovation, Surveillance, and Evaluation), funded by the United States Agency for International Development (USAID) and the President's Malaria Initiative (PMI). The third phase was supported by internal funding from the NGO Pivot.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

N/A

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes