Utilization of Machine Learning Techniques for Identification of Escherichia Coli Based on Results of Bauer Kirby Antibiotic Susceptibility Testing

2021 ◽  
pp. 303-312
Author(s):  
Amel Spahić ◽  
Zerina Mašetić ◽  
Irma Mahmutović-Dizdarević ◽  
Monia Avdić
Keyword(s):  
Machine Learning ◽  
Escherichia Coli ◽  
Antibiotic Susceptibility ◽  
Susceptibility Testing ◽  
Machine Learning Techniques ◽  
Antibiotic Susceptibility Testing ◽  
Learning Techniques

scholarly journals Potential Role of Door Handles in the Spread of Drug Resistant Bacteria in Makerere University.

2021 ◽  
Author(s):  
◽  
Immaculate Nabawanuka
Keyword(s):  
Escherichia Coli ◽  
Antibiotic Susceptibility ◽  
Pathogenic Bacteria ◽  
Susceptibility Testing ◽  
Bacterial Load ◽  
Plate Count ◽  
Diffusion Method ◽  
Resistant Bacteria ◽  
Antibiotic Susceptibility Testing ◽  
Makerere University

Background: The transmission of diseases caused by pathogenic bacteria is still a threat. One of the potential sources of bacterial diseases is the door handles. This study aimed at isolating, identifying bacteria, determining total bacterial load, and determining antibiotic susceptibility patterns of bacteria obtained from door handles in Makerere university. Methodology:  A total of 60 samples randomly scattered within the university were swabbed and analyzed for bacterial growth. Samples were inoculated on MacConkey and blood agar and then incubated at 37 ºC for 24 hours. All sample isolates were sub cultured and identified based on macro and micromorphology, and standard biochemical tests. The establishment of the total bacterial load was done using the standard plate count method. Antibiotic susceptibility testing was done using the disc diffusion method on Muller Hilton agar. Results: The following bacterial species and genera were obtained from door handles, staphylococcus aureus (30.8%), Coagulase-negative staphylococcus (12.0%), Streptococcus species (24.2%), Escherichia coli (7.7%), Pseudomonas aeruginosa (14.3%), bacilli species (11.0%). The study showed that there was a significant difference in the prevalence of bacilli species (p= 0.017) and E. coli (p= 0.015) among the study group. The results from total bacterial count indicated that toilet door handles had the highest bacterial load compared to office door handles and classrooms. Antibiotic susceptibility testing of isolates showed that all bacteria were resistant and intermediately resistant to commonly used antibiotics except for Escherichia coli that was susceptible to amoxicillin Conclusion and recommendations: The study reveals that door handles are a considerable source of pathogenic bacteria thus play a major role in the transmission of diseases caused by such bacteria. Further studies could be done and different study groups could be included for example routinely opened doors and the doors which are not routinely opened.

scholarly journals Evaluation of an ultra-rapid antibiotic susceptibility testing method on positive blood cultures with Escherichia coli

2021 ◽  
Author(s):  
Özden Baltekin ◽  
Alexander T. A. Johnsson ◽  
Alicia Y. W. Wong ◽  
Kajsa Nilsson ◽  
Bêrivan Mert ◽  
...  
Keyword(s):  
Escherichia Coli ◽  
Rapid Method ◽  
Antibiotic Susceptibility ◽  
Susceptibility Testing ◽  
Blood Stream Infection ◽  
Agar Plate ◽  
Blood Cultures ◽  
Antibiotic Susceptibility Testing ◽  
Mortality And Morbidity ◽  
E Coli

Blood stream infection (BSI) is related to high mortality and morbidity. Early antimicrobial therapy is crucial in treating patients with BSI. The most common Gram-negative bacteria causing BSI is Escherichia coli. Targeted effective treatment of patients with BSI is only possible if it is based on antibiotic susceptibility testing (AST) data after blood culture positivity. However, there are very few methods available for rapid phenotypic AST and the fastest method takes 4 h. Here we analyzed the performance of a 30 min ultra-rapid method for AST of E. coli directly from positive blood cultures (BC). In total, 51 positive BC with E. coli were studied, and we evaluated the ultra-rapid method directly on positive BC as well as on E. coli colonies cultured on agar plates. The results obtained by the new method were compared with disk diffusion. The method provided accurate AST result in 30 min to Ciprofloxacin and Gentamicin for 92% and 84% of the positive BC samples, respectively. For E. coli isolates retrieved from agar plates, 86% and 96% of the AST results were accurate for Ciprofloxacin and Gentamicin, respectively, after 30 min of assay time. When time to result was modulated in-silico from 30 to 60 minutes for the agar plate samples, accuracy of AST results went up to 92% for Ciprofloxacin and to 100% for Gentamicin. The present study shows that the method is reliable and delivers ultra-rapid AST data in 30 minutes directly from positive BC and as well as from agar plates.

scholarly journals Machine Learning of Bacterial Transcriptomes Reveals Responses Underlying Differential Antibiotic Susceptibility

mSphere ◽  
2021 ◽  
Vol 6 (4) ◽  
Author(s):  
Anand V. Sastry ◽  
Nicholas Dillon ◽  
Amitesh Anand ◽  
Saugat Poudel ◽  
Ying Hefner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antibiotic Susceptibility ◽  
Clinical Microbiology ◽  
Susceptibility Testing ◽  
Patient Treatment ◽  
Antibiotic Susceptibility Testing ◽  
Drug Effectiveness ◽  
Treatment Regimens ◽  
Imminent Threat

Antibiotic resistance is an imminent threat to global health. Patient treatment regimens are often selected based on results from standardized antibiotic susceptibility testing (AST) in the clinical microbiology lab, but these in vitro tests frequently misclassify drug effectiveness due to their poor resemblance to actual host conditions.

scholarly journals Microfluidic detection of movements of Escherichia coli for rapid antibiotic susceptibility testing

Lab on a Chip ◽  
2018 ◽  
Vol 18 (5) ◽  
pp. 743-753 ◽  
Author(s):  
Vural Kara ◽  
Chuanhua Duan ◽  
Kalpana Gupta ◽  
Shinichiro Kurosawa ◽  
Deborah J. Stearns-Kurosawa ◽  
...  
Keyword(s):  
Escherichia Coli ◽  
Antibiotic Susceptibility ◽  
Susceptibility Testing ◽  
Antibiotic Susceptibility Testing ◽  
Bacterial Viability

Various nanomechanical movements of bacteria provide a signature of bacterial viability.

Using machine learning techniques to reduce data annotation time

2006 ◽  
Author(s):  
Christopher Schreiner ◽  
Kari Torkkola ◽  
Mike Gardner ◽  
Keshu Zhang
Keyword(s):  
Machine Learning ◽  
Machine Learning Techniques ◽  
Data Annotation ◽  
Learning Techniques

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

Sign in / Sign up

Export Citation Format

Share Document