Artificial intelligence in optimizing antimicrobial therapy for gastro-renal disorders
- 1Faculty of Medicine, Lucian Blaga University of Sibiu
Abstract
Antimicrobial therapy remains central to the management of gastrointestinal and urinary tract infections, yet its effectiveness is increasingly compromised by antimicrobial resistance and antibiotic-induced microbiome disruption. These challenges are particularly pronounced in gastro-renal settings, where recurrent infections, altered drug absorption and impaired renal clearance generate substantial pharmacokinetic variability and narrow therapeutic margins. Empiric, guideline-based regimens may therefore contribute to treatment failure, resistance selection, and disease recurrence. Artificial intelligence (AI) and machine learning offer novel opportunities to optimize antimicrobial therapy by integrating clinical, microbiological and multi-omics data to predict resistance, guide antibiotic selection and dosing, and support antimicrobial stewardship. However, clinical translation remains limited by data heterogeneity, insufficient prospective validation, regulatory constraints, and the need for continued human oversight. This review synthesizes current AI-driven strategies relevant to gastro-renal infections, highlighting shared pathophysiological challenges, practical clinical applications and key limitations. An integrated framework for AI-assisted antimicrobial optimization is proposed to enhance therapeutic efficacy while mitigating antimicrobial resistance and preserving microbiome integrity.
Related
- Advancing antimicrobial stewardship in Africa through responsible artificial intelligence implementation
- Artificial intelligence and antimicrobial stewardship: From clinical decision support to public health action-On behalf of APUA
- Artificial Intelligence in the Fight Against Antimicrobial Resistance: Applications in Diagnosis, Susceptibility Prediction, Precision Dosing, and Antibiotic Discovery.
- Towards artificial intelligence based preoperative dosimetry for liver 90 Y selective internal radiation therapy
- Toward Enactive Artificial Intelligence
BibTeX
@article{stoia2026artificial,
title = {{Artificial intelligence in optimizing antimicrobial therapy for gastro-renal disorders}},
author = {Oana Stoia and Paula Anderco and Teona Badiu and Samuel Bogdan Todor and Cristian Ichim},
journal = {Frontiers in Cellular and Infection Microbiology},
year = {2026},
month = may,
doi = {10.3389/fcimb.2026.1792361},
url = {https://doi.org/10.3389/fcimb.2026.1792361},
note = {CC BY},
}
RIS
TY - JOUR
TI - Artificial intelligence in optimizing antimicrobial therapy for gastro-renal disorders
AU - Oana Stoia
AU - Paula Anderco
AU - Teona Badiu
AU - Samuel Bogdan Todor
AU - Cristian Ichim
PY - 2026
DA - 2026/05/25
JO - Frontiers in Cellular and Infection Microbiology
DO - 10.3389/fcimb.2026.1792361
UR - https://doi.org/10.3389/fcimb.2026.1792361
AB - Antimicrobial therapy remains central to the management of gastrointestinal and urinary tract infections, yet its effectiveness is increasingly compromised by antimicrobial resistance and antibiotic-induced microbiome disruption. These challenges are particularly pronounced in gastro-renal settings, where recurrent infections, altered drug absorption and impaired renal clearance generate substantial pharmacokinetic variability and narrow therapeutic margins. Empiric, guideline-based regimens may therefore contribute to treatment failure, resistance selection, and disease recurrence. Artificial intelligence (AI) and machine learning offer novel opportunities to optimize antimicrobial therapy by integrating clinical, microbiological and multi-omics data to predict resistance, guide antibiotic selection and dosing, and support antimicrobial stewardship. However, clinical translation remains limited by data heterogeneity, insufficient prospective validation, regulatory constraints, and the need for continued human oversight. This review synthesizes current AI-driven strategies relevant to gastro-renal infections, highlighting shared pathophysiological challenges, practical clinical applications and key limitations. An integrated framework for AI-assisted antimicrobial optimization is proposed to enhance therapeutic efficacy while mitigating antimicrobial resistance and preserving microbiome integrity.
SN - 2235-2988
ER -