Background: With increasing antibiotic resistance and regulation, the issue of antibiotic combination has been emphasised. However, antibiotic combination prescribing lacks a rapid identification of feasibility, while its risk of drug interactions is unclear.

Methods: We conducted statistical descriptions on 16 101 antibiotic coprescriptions for inpatients with bacterial infections from 2015 to 2023. By integrating the frequency and effectiveness of prescriptions, we formulated recommendations for the feasibility of antibiotic combinations. Initially, a machine learning algorithm was utilised to optimise grading thresholds and habits for antibiotic combinations. A feedforward neural network (FNN) algorithm was employed to develop antibiotic combination recommendation model (ACRM). To enhance interpretability, we combined sequential methods and DrugBank to explore the correlation between antibiotic combinations and drug interactions.

Results: A total of 55 antibiotics, covering 657 empirical clinical antibiotic combinations were used for ACRM construction. Model performance on the test dataset showed AUROCs of 0.589-0.895 for various antibiotic recommendation classes. The ACRM showed satisfactory clinical relevance with 61.54-73.33% prediction accuracy in a new independent retrospective cohort. Antibiotic interaction detection showed that the risk of drug interactions was 29.2% for strongly recommended and 43.5% for not recommended. A positive correlation was identified between the level of clinical recommendation and the risk of drug interactions.

Conclusions: Machine learning modelling of retrospective antibiotic prescriptions habits has the potential to predict antibiotic combination recommendations. The ACRM plays a supporting role in reducing the incidence of drug interactions. Clinicians are encouraged to adopt such systems to improve the management of antibiotic usage and medication safety.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijantimicag.2024.107122DOI Listing

Publication Analysis

Top Keywords

antibiotic combinations
20
antibiotic combination
16
antibiotic
15
machine learning
12
risk drug
12
drug interactions
12
drug
6
combinations prediction
4
prediction based
4
based machine
4

Similar Publications

Background: Regenerative endodontics requires an innovative delivery system to release antibiotics/growth factors in a sequential trend. This study focuses on developing/characterizing a thermoresponsive core-shell hydrogel designed for targeted drug delivery in endodontics.

Methods: The core-shell chitosan-alginate microparticles were prepared by electrospraying to deliver bone morphogenic protein-2 for 14 days and transforming growth factor-beta 1 (TGF-β1) for 7-14 days.

View Article and Find Full Text PDF

Probiotics, defined as viable microorganisms that enhance host health when consumed through the diet, exert their effects through mechanisms such as strengthening the immune system, enhancing resistance to infectious diseases, and improving tolerance to stressful conditions. Driven by a growing market, research on probiotics in aquaculture is a burgeoning field. However, the identification of new probiotics presents a complex challenge, necessitating careful consideration of both the safety and efficacy of the microorganisms employed.

View Article and Find Full Text PDF

Characterization and functionality of 1003 isolated from chicken cecum against .

Front Cell Infect Microbiol

December 2024

Postdoctoral Research Workstation, Heilongjiang Academy of Agricultural Sciences, Harbin, China.

Lactic acid bacteria are widely regarded as safe alternatives to antibiotics in livestock and poultry farming and have probiotic potential. () is a prominent component of pigeon crop microbiota; however, its function is unknown. In this study, a strain of 1003 from pigeon cecum was identified by combining whole genome sequencing and phenotypic analysis, and its safety and probiotic properties were studied.

View Article and Find Full Text PDF

Background: Recurrent caries were attributed to the lack of antibacterial properties of the dental materials. Silver nanoparticles (AgNPs) and calcium fluoride nanoparticles (CaF2NPs) are broad-spectrum antibacterial agents. The object of the study was to investigate the antibacterial properties of composite-incorporated AgNPs and CaF2NPs on .

View Article and Find Full Text PDF

A Case Report of Meningitis Caused by Biovar 3.

Infect Drug Resist

December 2024

State International Joint Research Center for Animal Health Breeding, College of Animal Science and Technology, Shihezi University, Shihezi, People's Republic of China.

Background: Brucellosis, a major endemic disease in northern China, is contracted by zoonosis of . We report a case of meningitis caused by biovar 3.

Case Presentation: A 46-year-old man was hospitalized at a local medical facility due to symptoms of fever, soreness, and weakness on April 16, 2021.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!