Confidence-based prediction of antibiotic resistance at the patient level

TL;DR

A deep learning method predicts antibiotic resistance using patient data and existing test results, offering faster and more accurate diagnostics.

Contribution

A novel deep learning model using transformers to predict untested antibiotic resistance with uncertainty estimation.

Findings

The model achieved 93% average accuracy across bacterial species and antibiotics.

Predictive uncertainty was accurately estimated using conformal prediction.

Higher error rates were observed for penicillins and quinolones compared to other antibiotic classes.

Abstract

Rapid and accurate diagnostics of bacterial infections are necessary for efficient treatment of antibiotic-resistant pathogens. Cultivation-based methods, such as antibiotic susceptibility testing (AST), are limited by bacterial growth rates and seldom yield results before treatment needs to start, increasing patient risk and contributing to antibiotic overprescription. Here, we present a deep-learning method that leverages patient data and available AST results to predict antibiotic susceptibilities that have not yet been measured. After training on three million AST results from 30 European countries, the method achieved an average accuracy of 93% across bacterial species and antibiotics. It predicted susceptibility with an average major error rate below 5% for quinolones, cephalosporins, and carbapenems, and below 8% and 14% for aminoglycosides and penicillins, respectively. Furthermore, the model predicted resistance with an average very major error rate below 10% for cephalosporins, carbapenems, and aminoglycosides, but with higher very major error rates for penicillins and quinolones. We combined the method with conformal prediction and demonstrated accurate estimation of the predictive uncertainty at the patient level. Our results suggest that artificial intelligence-based decision support may offer new means to meet the growing burden of antibiotic resistance.

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.

Figures