Journal Article

Confidence-based prediction of antibiotic resistance at the patient level

Inda-Díaz, Juan S., Helldal, Lisa, Svensson, Lennart, Lokrantz, Anna, Johnning, Anna, Sjöberg, Anders, Kristiansson, Erik, Hessel, Magnus, Jirstrand, Mats

2026

Overview

Improved diagnostic tools are vital for maintaining efficient treatment of antibiotic-resistant bacteria and for reducing antibiotic overconsumption. In our research, we introduce a new deep learning-based method capable of predicting untested antibiotic resistance phenotypes. The method uses transformers, a powerful artificial intelligence (AI) technique that efficiently leverages both antibiotic susceptibility tests (AST) and patient data simultaneously. The model produces predictions that can be used as time- and cost-efficient alternatives to results from cultivation-based diagnostic assays. Significantly, our study highlights the potential of AI technologies to address the increasing prevalence of antibiotic-resistant bacterial infections.

• Publisher: American Society for Microbiology,American Society for Microbiology (ASM)
• Subject: Anti-Bacterial Agents - pharmacology / Anti-Bacterial Agents - therapeutic use / Antibacterial Susceptibility Testing / Antibacterial Therapy / Antibiotic Resistance / Antibiotic Resistance and Stewardship / Antibiotic Susceptibility Testing / Antibiotics / Antimicrobial Resistance / Antimicrobial Susceptibility Testing / Artificial intelligence / Bacteria / Bacteria - drug effects / Bacterial infections / Bacterial Infections - diagnosis / Bacterial Infections - drug therapy / Bacterial Infections - microbiology / Bacteriology / Basic Medicine / Carbapenems / Cephalosporins / Clinical Detection of Resistance / Clinical Microbiology and Infectious Diseases / Computational Biology / Confidence / conformal prediction / Deep Learning / Detection and Diagnostics of Resistance / Diagnostic Techniques / diagnostics / Drug resistance / Drug Resistance, Bacterial / E coli / Europe / Humans / Infectious diseases / Laboratory Techniques / Medicinska och farmaceutiska grundvetenskaper / Microbial Pathogenesis and Immunology / Microbial Physiology and Genetics / Microbial Sensitivity Tests - methods / Natural language processing / Neural networks / Pathogens / Phenotypes / Predictions / Public Health Microbiology / Quinolones / Research Article / Resistance in Healthcare Settings / transformers