Parametric Models for Predicting Gram-negative Antibiotic Susceptibility Phenotype: A Brief Report
Garg, A.; Graham, C.; Daneman, N.; MacFadden, D.
Show abstract
Predicted probabilities of antibiotic susceptibility to known or suspected pathogens can be used to support antibiotic selection. Patient demographic, clinical, and prior microbiologic history can be used to generate location-specific prediction models. For three Canadian tertiary care institutions we fit and evaluated models for predicting Gram-negative antibiotic susceptibilities to common antimicrobial agents based on previously established model structures. A web-based application was developed to permit visualization of antibiotic susceptibility predictions and support antibiotic decision-making.
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Protocol For Human Evaluation of Artificial Intelligence Chatbots in Clinical Consultations 93%
- An accurate and interpretable model for antimicrobial resistance in pathogenic Escherichia coli from livestock and companion animal species 93%
- A Risk Prediction and Clinical Guidance System for Evaluating Patients with Recurrent Infections. 92%
Similar papers in this journal
- Predicting the causative pathogen among children with pneumonia using a causal Bayesian network 93%
- Tracking Pseudomonas aeruginosa transmissions due to environmental contamination after discharge in ICUs using mathematical models 91%
- Risk factors for fluoroquinolone- and macrolide-resistance among swine Campylobacter coli using multi-layered chain graphs 91%
Similar papers in this journal
- Revealing antibiotic cross-resistance patterns in hospitalized patients through Bayesian network modelling 94%
- Estimating the cost of antibiotic use on future collateral resistance: a retrospective comparison of cefuroxime versus cefazolin and amoxicillin/clavulanate 91%
- Optimal dosing of cefotaxime and desacetylcefotaxime for critically ill paediatric patients. Can we use microsampling? 90%
Similar papers in this journal
- Modeling physician variability to prioritize relevant medical record information 92%
- Framework for Identifying Drug Repurposing Candidates from Observational Healthcare Data 92%
- Determining prescriptions in electronic health care (EHR) data: methods for development of standardised, reproducible drug codelists 92%
"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.