English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Objectives Microbial antibiotic resistance remains a serious public health problem worldwide. Conventional culture-based techniques are time-taking procedures; therefore, there is need for new approaches for detecting bacterial resistance. The aim of this study was to assess antibiotic resistance of  Escherichia coli  by analyzing biochemical parameters with machine learning systems without using antibiogram. Material and methods In this article, machine learning systems such as K-Nearest Neighbors, Artificial Neural Networks (ANN), Support Vector Machine and Decision Tree Learning were used to investigate whether  E. coli  is sensitive or resistant to antibiotics. The study was conducted based on the clinical records of 103 patients who were previously diagnosed with  E. coli  infection, including CBC and complete UA results, and CRP values. Results The accuracy rates of antibiotic resistance/susceptibility detected by ANN were as follows: Amikacin (96.0%), Ampicillin (77%), Ceftazidime (62%), Cefixime (63%), Cefotaxime (68%), Colistin (95%), Ciprofloxacin (76%), Cefepime (70%), Ertapenem (96%), Nitrofurantoin (90%), Phosphomycin (98%), Gentamicin (84%), Levofloxacin (98%), Piperacillin-Tazobactam (92%), and Trimethoprim-Sulfadiazine (79%). Conclusions The study determined the antibiotic resistance of  E. coli  with less time and cost compared to conventional culture-based methods machine learning based model contributes positively to artificial intelligence (AI) supported decision-making processes in laboratory medicine.

Is it possible to determine antibiotic resistance of E. coli by analyzing laboratory data with machine learning?