67.6% of Latin American physicians' queries on Arkangel AI seek management, diagnosis, or work-up support across 20 countries

PreprintmedRxiv 2026 · 1 min read
Queries on management, differential diagnosis, or work-up
67.6%
Management plan 35.6%, differential diagnosis 20.6%, work-up and test selection 11.4%
Queries analyzed
235,803
9,443 physicians in 20 countries, May 2025–June 2026
Activation rate
84.4%
Registered physicians who submitted at least one query

medRxiv preprint: 235,803 queries from 9,443 physicians in 20 countries show search centred on clinical decision support.

This retrospective query-log study describes what Latin American physicians ask a semantic clinical search platform developed by Arkangel AI. Over 13 months, from May 2025 to June 2026, the analysis covered 235,803 queries from 9,443 physicians in 20 countries, classified into a 10-category clinical taxonomy and reported following STROBE.

The activation rate was 84.4%, and each physician submitted a mean of 29.6 queries, with broadly similar volume across countries. Management plan (35.6%), differential diagnosis (20.6%), and work-up and test selection (11.4%) together accounted for 67.6% of queries, and this hierarchy held in all 17 countries with enough volume for country-level analysis. The study is descriptive and does not measure clinical accuracy or patient outcomes; it is a preprint not yet peer reviewed.

Results at a glance

The headline numbers from the paper, in plain language.

How the model performed

Higher is better

Data: Management plan 35.6%, differential diagnosis 20.6%, work-up and test selection 11.4% · Registered physicians who submitted at least one query — medRxiv 2026

Show the numbers as a table
MetricValueWhat it means
Queries on management, differential diagnosis, or work-up67.6%Management plan 35.6%, differential diagnosis 20.6%, work-up and test selection 11.4%
Queries analyzed235,8039,443 physicians in 20 countries, May 2025–June 2026
Activation rate84.4%Registered physicians who submitted at least one query

How to cite

Katherine Monsalve, María Camila Villa, Natalia Castaño-Villegas, Jose Zea, Laura Velásquez. Clinical Information Needs Among Latin American Physicians: A Multi-Country Analysis of Semantic Clinical Search. medRxiv. 2026. https://doi.org/10.64898/2026.06.26.26356340

@article{monsalve2026clinical,
  title     = {{Clinical Information Needs Among Latin American Physicians: A Multi-Country Analysis of Semantic Clinical Search}},
  author    = {Katherine Monsalve and María Camila Villa and Natalia Castaño-Villegas and Jose Zea and Laura Velásquez},
  journal   = {medRxiv},
  year      = {2026},
  doi       = {10.64898/2026.06.26.26356340},
  url       = {https://www.medrxiv.org/content/10.64898/2026.06.26.26356340v1},
  note      = {Preprint}
}

More research from Arkangel AI

All research →

For hospitals and insurers

Validate these results at your institution

We run the model on your own clinical records with your team, under your privacy and governance rules.

Start a research partnership
Read paperCite