Predicting Antibiotic Resistance Patterns Using Sentence-BERT: A Machine Learning Approach

Abstract: 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. Introduction: Sepsis and septic shock are life threatening conditions, with mortality rates as high as 50 - 60%. [1] Delays in appropriate antibiotic administration lead to an 8% decrease in survival for every hour of delay, underscoring the need for prompt and precise treatment.