scholarly journals Machine Learning-Assisted Digital PCR and Melt Enables Broad Bacteria Identification and Pheno-Molecular Antimicrobial Susceptibility Test

2019 ◽  
Author(s):  
Pornpat Athamanolap ◽  
Kuangwen Hsieh ◽  
Christine M. O'Keefe ◽  
Ye Zhang ◽  
Samuel Yang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Susceptibility ◽  
Bacterial Species ◽  
Digital Pcr ◽  
Clinical Diagnostics ◽  
Diagnostic Tools ◽  
Quantitative Detection ◽  
Urine Specimen ◽  
Bacteria Identification ◽  
Susceptibility Profiles

Toward combating infectious diseases caused by pathogenic bacteria, there remains an unmet need for diagnostic tools that can broadly identify the causative bacteria and determine their antimicrobial susceptibilities from complex and even polymicrobial samples in a timely manner. To address this need, a microfluidic- and machine learning-based platform that performs broad bacteria identification (ID) and rapid yet reliable antimicrobial susceptibility testing (AST) is developed. Specifically, this new platform builds on "pheno-molecular AST", a strategy that transforms nucleic acid amplification tests (NAATs) into phenotypic AST through quantitative detection of bacterial genomic replication, and utilizes digital PCR and digital high-resolution melt (HRM) to quantify and identify bacterial DNA molecules. Bacterial species are identified using integrated experiment-machine learning algorithm via HRM profiles. Digital DNA quantification allows for rapid growth measurement that reflects susceptibility profiles of each bacterial species within only 30 min of antibiotic exposure. As a demonstration, multiple bacterial species and their susceptibility profiles in polymicrobial urine specimen were correctly identified with a total turnaround time of ~4 hours. With further development and clinical validation, this new platform holds the potential for improving clinical diagnostics and enabling targeted antibiotic treatments.

scholarly journals Antimicrobial Evaluation of Bacterial Isolates from Urine Specimen of Patients with Complaints of Urinary Tract Infections in Awka, Nigeria

2016 ◽  
Vol 2016 ◽  
pp. 1-6 ◽  
Author(s):  
Perpetua A. Ekwealor ◽  
Malachy C. Ugwu ◽  
Ifeanyi Ezeobi ◽  
George Amalukwe ◽  
Belinda C. Ugwu ◽  
...  
Keyword(s):  
Urinary Tract ◽  
Urinary Tract Infections ◽  
Antimicrobial Susceptibility ◽  
Bacterial Species ◽  
Resistance Index ◽  
Diffusion Method ◽  
Urine Specimen ◽  
Anambra State ◽  
Tract Infections ◽  
Susceptibility Patterns

Urinary tract infections (UTIs) account for one of the major reasons for most hospital visits and the determination of the antimicrobial susceptibility patterns of uropathogens will help to guide physicians on the best choice of antibiotics to recommend to affected patients. This study is designed to isolate, characterize, and determine the antimicrobial susceptibility patterns of the pathogens associated with UTI in Anambra State Teaching Hospital, Amaku, Anambra State, Nigeria. Clean catch urine samples of inpatient and outpatient cases of UTI were collected and bacteriologically analyzed using standard microbiological procedures. Antibiogram was done by the Kirby-Bauer disc diffusion method. The most prevalent isolates wereS. aureus(28%),E.coli(24.6%), andS. saprophyticus(20%). The antibacterial activities of the tested agents were in the order of Augmentin < Ceftazidime < Cefuroxime < Cefixime < Gentamicin < Ofloxacin < Ciprofloxacin < Nitrofurantoin. It was found that all the organisms were susceptible in varying degrees to Nitrofurantoin, Ciprofloxacin, and Ofloxacin. It was also observed that all the bacterial species exceptStreptococcusspp. have a Multiple Antibiotic Resistance Index (MARI) greater than 0.2. For empiric treatment of UTIs in Awka locality, Nitrofurantoin, Ciprofloxacin, and Ofloxacin are the first line of choice.

scholarly journals First data on antimicrobial susceptibility patterns of Moraxella catarrhalis isolates in Lebanon

10.3823/833 ◽  
2019 ◽  
Vol 9 (2) ◽  
Author(s):  
Monzer Hamze ◽  
Marwan Osman ◽  
Hassan Mallat ◽  
Marcel El Achkar
Keyword(s):  
Nalidixic Acid ◽  
Antimicrobial Susceptibility ◽  
Moraxella Catarrhalis ◽  
Antibiotic Susceptibility ◽  
Bacterial Pathogen ◽  
Diagnostic Tools ◽  
Flight Mass Spectrometry ◽  
High Level ◽  
Susceptibility Profiles ◽  
Susceptibility Patterns

Background. Moraxella catarrhalis is an important bacterial pathogen. Although national data have shown an increase in the levels of antimicrobial resistance in clinical settings in Lebanon, there is a lack of data regarding this human pathogen. This study aimed to determine for the first time the antimicrobial susceptibility profiles of M. catarrhalis isolates in Lebanon. Methods. A total of 34 M. catarrhalis strains were isolated from clinical specimens during the period from November 2010 to March 2019. Bacterial identification was carried out using matrix assisted laser desorption ionization–time of flight mass spectrometry. Antibiotic susceptibility of all isolates was performed according the recommendations of the European Committee on Antimicrobial Susceptibility Testing (EUCAST). Results. A total of 34 non-duplicated M. catarrhalis strains were isolated from nose (n=19), ear (n=7), sputum (n=5), blood (n=1), eye (n=1), and throat (n=1) of patients referred to Nini Hospital in Tripoli, North governorate of Lebanon. Regarding antibiotic susceptibility rates, the percent susceptibility is 100% to the majority of antibiotics, except ampicillin (7.4%), trimethoprim-sulfamethoxazole (85.3%), nalidixic acid (85.3%), and ciprofloxacin (97.1%). Conclusion. To our knowledge, this study is the first investigation regarding the antimicrobial susceptibility patterns of M. catarrhalis isolates in Lebanon. In addition to the high level of resistance to ampicillin, our findings showed the emergence of resistance to trimethoprim-sulfamethoxazole, nalidixic acid and ciprofloxacin. Even if this study provides useful information to develop effective empirical treatment, we recommend the implementation of reliable diagnostic tools to guide appropriate treatment.

scholarly journals Qualitative And Quantitative Detection of Surgical Pathogenic Microorganisms Escherichia Coli and Staphylococcus Aureus Based on ddPCR System

2020 ◽  
Author(s):  
Tiantian Zhang ◽  
Zhiqiang Niu ◽  
Feng Wu ◽  
Zongkun Chen ◽  
Jun xu ◽  
...  
Keyword(s):  
Escherichia Coli ◽  
Staphylococcus Aureus ◽  
Bacterial Species ◽  
Digital Pcr ◽  
Quantitative Detection ◽  
Detection Accuracy ◽  
Pathogenic Microorganisms ◽  
Detection Rates ◽  
Blood Samples ◽  
And Staphylococcus Aureus

Abstract Bacterial culture and drug susceptibility testing are used to identify bacteria associated with infections. Nevertheless, the process requires several days from collection to the identification of bacterial species and drug resistance patterns. The digital PCR system is a rapidly developing quantitative detection technology widely used in many fields, including pathogenic microorganism detection, early diagnosis of tumor markers, and analysis of gene expression with its advantages. The purpose of this study was to use a droplet digital PCR system to identify bacteria in blood samples, to explore its ability to identify common pathogenic microorganisms. We designed primers and probes for Escherichia coli and Staphylococcus aureus specific genes for the ddPCR system to identify in blood samples mixed with both organisms. The system had extremely high detection accuracy in samples and the detection rate of E. coli was 13.1–21.4% and that of S. aureus was 50–88.3%. The system identified blood samples containing both bacteria, with detection rates of 18.1%–97%. The ddPCR system qualitatively and quantitatively measured common pathogenic microorganisms in blood samples with high sensitivity and accuracy, providing rapid and accurate detection of pathogenic microorganisms.

scholarly journals Qualitative and quantitative detection of surgical pathogenic microorganisms Escherichia coli and Staphylococcus aureus based on ddPCR system

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Tiantian Zhang ◽  
Zhiqiang Niu ◽  
Feng Wu ◽  
Zongkun Chen ◽  
Jun Xu ◽  
...  
Keyword(s):  
Biomarker Discovery ◽  
Bacterial Species ◽  
Screening Method ◽  
Digital Pcr ◽  
Copy Number Variations ◽  
Quantitative Detection ◽  
Detection Accuracy ◽  
Detection Rates ◽  
Blood Samples ◽  
E Coli

AbstractBacterial culture and drug susceptibility testing are used to identify pathogen infections. Nevertheless, the process requires several days from collection to the identification of bacterial species and drug-resistance patterns. The digital PCR system is a rapidly developing quantitative detection technology widely applied to molecular diagnosis, including copy number variations, single nucleotide variant analysis, cancer biomarker discovery, and pathogen identification. This study aimed to use a droplet digital PCR system to identify bacteria in blood samples and explore its ability to identify pathogen in bacteremia. Then, we designed primers and probes of SWG-9 and COA gene for E. coli and S. aureus to identify in blood samples with the ddPCR system. The system had demonstrated extremely high detection accuracy in blood samples, and the detection rate of E. coli was 13.1–21.4%, and that of S. aureus was 50–88.3%. Finally, blood samples containing both E. coli and S. aureus were tested to evaluate further the accuracy and applicability of this method, indicating the detection rates range from 18.1% to 97%. The ddPCR system is highly promising as a qualitatively and quantitatively screening method for rapidly detecting pathogen.

scholarly journals Use of Machine Learning to Investigate the Quantitative Checklist for Autism in Toddlers (Q-CHAT) towards Early Autism Screening

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 574
Author(s):  
Gennaro Tartarisco ◽  
Giovanni Cicceri ◽  
Davide Di Pietro ◽  
Elisa Leonardi ◽  
Stefania Aiello ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Performance ◽  
Behavioral Science ◽  
Autistic Traits ◽  
Classification Performance ◽  
Recursive Feature Elimination ◽  
Diagnostic Tools ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Autism Screening

In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM–recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.

scholarly journals Patient-Specific Predictive Antibiogram in Decision Support for Empiric Antibiotic Treatment

2020 ◽  
Vol 41 (S1) ◽  
pp. s521-s522
Author(s):  
Debarka Sengupta ◽  
Vaibhav Singh ◽  
Seema Singh ◽  
Dinesh Tewari ◽  
Mudit Kapoor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Antimicrobial Resistance ◽  
Model Building ◽  
Medical Center ◽  
Bacterial Species ◽  
Model Performance ◽  
The United States ◽  
Patient Specific ◽  
Gradient Boosting ◽  
Comparative Performance

Background: The rising trend of antibiotic resistance imposes a heavy burden on healthcare both clinically and economically (US$55 billion), with 23,000 estimated annual deaths in the United States as well as increased length of stay and morbidity. Machine-learning–based methods have, of late, been used for leveraging patient’s clinical history and demographic information to predict antimicrobial resistance. We developed a machine-learning model ensemble that maximizes the accuracy of such a drug-sensitivity versus resistivity classification system compared to the existing best-practice methods. Methods: We first performed a comprehensive analysis of the association between infecting bacterial species and patient factors, including patient demographics, comorbidities, and certain healthcare-specific features. We leveraged the predictable nature of these complex associations to infer patient-specific antibiotic sensitivities. Various base-learners, including k-NN (k-nearest neighbors) and gradient boosting machine (GBM), were used to train an ensemble model for confident prediction of antimicrobial susceptibilities. Base learner selection and model performance evaluation was performed carefully using a variety of standard metrics, namely accuracy, precision, recall, F1 score, and Cohen &kappa;. Results: For validating the performance on MIMIC-III database harboring deidentified clinical data of 53,423 distinct patient admissions between 2001 and 2012, in the intensive care units (ICUs) of the Beth Israel Deaconess Medical Center in Boston, Massachusetts. From ~11,000 positive cultures, we used 4 major specimen types namely urine, sputum, blood, and pus swab for evaluation of the model performance. Figure 1 shows the receiver operating characteristic (ROC) curves obtained for bloodstream infection cases upon model building and prediction on 70:30 split of the data. We received area under the curve (AUC) values of 0.88, 0.92, 0.92, and 0.94 for urine, sputum, blood, and pus swab samples, respectively. Figure 2 shows the comparative performance of our proposed method as well as some off-the-shelf classification algorithms. Conclusions: Highly accurate, patient-specific predictive antibiogram (PSPA) data can aid clinicians significantly in antibiotic recommendation in ICU, thereby accelerating patient recovery and curbing antimicrobial resistance.Funding: This study was supported by Circle of Life Healthcare Pvt. Ltd.Disclosures: None

scholarly journals Temporal Variations in Patterns of Clostridioides difficile Strain Diversity and Antibiotic Resistance in Thailand

Antibiotics ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 714
Author(s):  
Supapit Wongkuna ◽  
Tavan Janvilisri ◽  
Matthew Phanchana ◽  
Phurt Harnvoravongchai ◽  
Amornrat Aroonnual ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Antimicrobial Susceptibility ◽  
Reference Strain ◽  
Toxin Production ◽  
Temporal Variations ◽  
Toxin Gene ◽  
Data Sets ◽  
Clostridioides Difficile ◽  
Life Threatening ◽  
Susceptibility Profiles

Clostridioides difficile has been recognized as a life-threatening pathogen that causes enteric diseases, including antibiotic-associated diarrhea and pseudomembranous colitis. The severity of C. difficile infection (CDI) correlates with toxin production and antibiotic resistance of C. difficile. In Thailand, the data addressing ribotypes, toxigenic, and antimicrobial susceptibility profiles of this pathogen are scarce and some of these data sets are limited. In this study, two groups of C. difficile isolates in Thailand, including 50 isolates collected from 2006 to 2009 (THA group) and 26 isolates collected from 2010 to 2012 (THB group), were compared for toxin genes and ribotyping profiles. The production of toxins A and B were determined on the basis of toxin gene profiles. In addition, minimum inhibitory concentration of eight antibiotics were examined for all 76 C. difficile isolates. The isolates of the THA group were categorized into 27 A−B+CDT− (54%) and 23 A-B-CDT- (46%), while the THB isolates were classified into five toxigenic profiles, including six A+B+CDT+ (23%), two A+B+CDT− (8%), five A−B+CDT+ (19%), seven A−B+CDT− (27%), and six A−B−CDT− (23%). By visually comparing them to the references, only five ribotypes were identified among THA isolates, while 15 ribotypes were identified within THB isolates. Ribotype 017 was the most common in both groups. Interestingly, 18 unknown ribotyping patterns were identified. Among eight tcdA-positive isolates, three isolates showed significantly greater levels of toxin A than the reference strain. The levels of toxin B in 3 of 47 tcdB-positive isolates were significantly higher than that of the reference strain. Based on the antimicrobial susceptibility test, metronidazole showed potent efficiency against most isolates in both groups. However, high MIC values of cefoxitin (MICs 256 μg/mL) and chloramphenicol (MICs ≥ 64 μg/mL) were observed with most of the isolates. The other five antibiotics exhibited diverse MIC values among two groups of isolates. This work provides evidence of temporal changes in both C. difficile strains and patterns of antimicrobial resistance in Thailand.

scholarly journals Rapid bacteria identification using structured illumination microscopy and machine learning

2017 ◽  
Vol 11 (01) ◽  
pp. 1850007 ◽  
Author(s):  
Yingchuan He ◽  
Weize Xu ◽  
Yao Zhi ◽  
Rohit Tyagi ◽  
Zhe Hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optical Microscopy ◽  
Pathogenic Bacteria ◽  
Morphological Features ◽  
Structured Illumination ◽  
Structured Illumination Microscopy ◽  
Standard Pattern ◽  
Bacteria Identification ◽  
Detection And Identification ◽  
Combined Use

Traditionally, optical microscopy is used to visualize the morphological features of pathogenic bacteria, of which the features are further used for the detection and identification of the bacteria. However, due to the resolution limitation of conventional optical microscopy as well as the lack of standard pattern library for bacteria identification, the effectiveness of this optical microscopy-based method is limited. Here, we reported a pilot study on a combined use of Structured Illumination Microscopy (SIM) with machine learning for rapid bacteria identification. After applying machine learning to the SIM image datasets from three model bacteria (including Escherichia coli, Mycobacterium smegmatis, and Pseudomonas aeruginosa), we obtained a classification accuracy of up to 98%. This study points out a promising possibility for rapid bacterial identification by morphological features.

Sign in / Sign up

Export Citation Format

Share Document