Back

AMROrbit: Reimagining AMR Stewardship through an Open Source, Dynamic, Actionable Scorecard from Routine Microbiology Data

Kaur, J.; Tiju, N. A.; Pendyala, R.; Vairamuthu, M.; Gupta, A.; Sethi, T.

2025-06-06 infectious diseases
10.1101/2025.06.05.25328985 medRxiv
Show abstract

We present AMROrbit scorecard, an explainable model and an open-sourced tool leveraging routine microbiology data to enable data-driven AMR stewardship and surveillance. We built the scorecard on a global dataset of 229 antibiotic-microorganism-sample combinations collected across 84 countries using robust statistical models combined with an intuitive phase-space visualization of the amplitude and velocity of AMR trajectories. AMROrbit revealed rising resistance in 61.6% of combinations and spiraling-out trajectories in 18.1% of countries, signaling an urgent need for proactive data-driven stewardship in these areas.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.