Antibiotic resistance poses a significant threat in in-patient settings with high mortality. Using MIMIC-III data, we generated Sentence-BERT embeddings from clinical notes and applied Neural Networks and XGBoost to predict antibiotic susceptibility. XGBoost achieved an average F1 score of 0.86, while Neural Networks scored 0.84. This study is among the first to use document embeddings for predicting antibiotic resistance, offering a novel pathway for improving antimicrobial stewardship.
@article{arxiv.2509.14283,
title = {Predicting Antibiotic Resistance Patterns Using Sentence-BERT: A Machine Learning Approach},
author = {Mahmoud Alwakeel and Michael E. Yarrington and Rebekah H. Wrenn and Ethan Fang and Jian Pei and Anand Chowdhury and An-Kwok Ian Wong},
journal= {arXiv preprint arXiv:2509.14283},
year = {2025}
}