Machine Learning for Antimicrobial Resistance Research and Drug Development

Shankarnarayan, Shamanth A.; Guthrie, Joshua D.; Charlebois, Daniel A.

doi:10.5772/intechopen.104841

Cited by 7 publications

(6 citation statements)

References 173 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One common challenge with ML models is their “black box” nature, which makes it difficult to understand how they arrive at their predictions 77 . This lack of interpretability hinders their adoption in clinical practice where transparency and trust are crucial.…”

Section: Discussionmentioning

confidence: 99%

Machine learning to identify clinically relevantCandidayeast species

Shankarnarayan,

Charlebois

2023

Preprint

View full text Add to dashboard Cite

BackgroundFungal infections, especially due toCandidaspecies, are on the rise. Multi-drug resistant organism such asCandida aurisare difficult and time consuming to identify accurately.Machine learning is increasingly being used in health care, especially in medical imaging. In this study, we evaluated the effectiveness of six convolutional neural networks (CNNs) to identify four clinically importantCandidaspecies.Materials and MethodsWet-mounted images were captured using bright field live-cell microscopy followed by separating single cells, budding cells, and cell group images which were then subjected to different machine learning algorithms (custom CNN, VGG16, ResNet50, InceptionV3, EfficientNetB0, and EfficientNetB7) to learn and predictCandidaspecies.ResultsAmong the six algorithms tested, the InceptionV3 model performed best in predictingCandidaspecies from microscopy images. All models performed poorly on raw images obtained directly from the microscope. The performance of all models increased when trained on single and budding cell images. The InceptionV3 model identified budding cells ofC. albicans, C. auris,C. glabrata(Nakaseomyces glabrata), andC. haemuloniiin 97.0%, 74.0%, 68.0%, and 66.0% cases, respectively. For single cells ofC. albicans, C. auris,C. glabrata, andC. haemuloniiInceptionV3 identified 97.0%, 73.0%, 69.0%, and 73.0% cases, respectively. The sensitivity and specificity of InceptionV3 were respectively 77.1% and 92.4%.ConclusionThis study provides proof of concept that microscopy images from wet mounted slides can be used to identifyCandidayeast species using machine learning quickly and accurately.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning to identify clinically relevantCandidayeast species

Shankarnarayan,

Charlebois

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The prediction of the resistance mechanism relies on the k-mer value, assessing its presence or absence. It is commonly applied in ML-based software like SET and classification and regression trees, which are rule-based learning algorithms [84]. In predicting carbapenem and co-trimoxazole resistance in MRSA, Acinetobacter baumannii, and Streptococcus pneumoniae, various ML methodologies, including adaptive boosting and gradient-boosting, have been successfully implemented [85,86].…”

Section: Forecasting Drug Resistance In S Aureus: a ML Paradigmmentioning

confidence: 99%

Emerging strategies and therapeutic innovations for combating drug resistance in Staphylococcus aureus strains: A comprehensive review

Gopikrishnan,

Haryini,

2024

J Basic Microbiol

View full text Add to dashboard Cite

In recent years, antibiotic therapy has encountered significant challenges due to the rapid emergence of multidrug resistance among bacteria responsible for life‐threatening illnesses, creating uncertainty about the future management of infectious diseases. The escalation of antimicrobial resistance in the post‐COVID era compared to the pre‐COVID era has raised global concern. The prevalence of nosocomial‐related infections, especially outbreaks of drug‐resistant strains of Staphylococcus aureus, have been reported worldwide, with India being a notable hotspot for such occurrences. Various virulence factors and mutations characterize nosocomial infections involving S. aureus. The lack of proper alternative treatments leading to increased drug resistance emphasizes the need to investigate and examine recent research to combat future pandemics. In the current genomics era, the application of advanced technologies such as next‐generation sequencing (NGS), machine learning (ML), and quantum computing (QC) for genomic analysis and resistance prediction has significantly increased the pace of diagnosing drug‐resistant pathogens and insights into genetic intricacies. Despite prompt diagnosis, the elimination of drug‐resistant infections remains unattainable in the absence of effective alternative therapies. Researchers are exploring various alternative therapeutic approaches, including phage therapy, antimicrobial peptides, photodynamic therapy, vaccines, host‐directed therapies, and more. The proposed review mainly focuses on the resistance journey of S. aureus over the past decade, detailing its resistance mechanisms, prevalence in the subcontinent, innovations in rapid diagnosis of the drug‐resistant strains, including the applicants of NGS and ML application along with QC, it helps to design alternative novel therapeutics approaches against S. aureus infection.

show abstract

“…By avoiding laboratory culture, genotypic methods promise to not only be quicker than phenotypic methods. Still, they may also shed light on the mechanisms underlying AMR, allow for the early detection of transmission events, and provide crucial ancillary information like bacterial strain and virulence factors [25][26][27][28].…”

Section: Application Of Machine Learning (Ml) In Amrmentioning

confidence: 99%

“…Several ML models are proposed in the literature to analyze the AMR [14], [16], [18], [19], [21], [23], [26], [27], [28], [29]. These works generally deployed the supervised and unsupervised ML models for the AMR analysis.…”

Section: Application Of Machine Learning (Ml) In Amrmentioning

confidence: 99%

Artificial Intelligence in Battle against Antimicrobial Resistance: Opportunities and Challenges

Debasish Swapnesh Kumar Nayak

2023

IJRITCC

View full text Add to dashboard Cite

Due to the overuse and abuse of antibiotics, antimicrobial resistance (AMR) poses a serious risk to socioeconomic development and public health. A paradigm shift is required to address this dilemma, and artificial intelligence (AI) appears as a possible remedy. AI, including machine learning (ML) and deep learning (DL), has demonstrated significant promise in several medical research fields, especially in the fight against AMR. Applications of AI in AMR use cutting-edge computational methods to analyze gene expression and whole-genome sequencing data, assisting in discovering infectious disease etiology and disease subtypes. These AI-driven systems have several advantages over more conventional ones, including less need for human involvement, more accuracy, and lower costs. However, they also encounter difficulties, such as inconsistent performance across datasets, with data volume critically influencing model efficacy. The accessibility and expense of high-throughput sequencing data, particularly next-generation sequencing data, also pose challenges to the wider application of AI models for AMR investigation. Despite these difficulties, AI has significant promise in the fight against AMR, and its advantages and disadvantages must be carefully considered in order to build successful tactics for dealing with this urgent worldwide problem. We assess research papers on AMR analysis using AI on various datasets and contrast the effectiveness of various AI models. We thoroughly reviewed the DL models used up to this point in the field of AMR, and we additionally discussed the challenges that come with deploying these approaches. This paper offers a thorough overview of AI's applications in AMR analysis, highlighting both its benefits and drawbacks.

show abstract

Machine Learning for Antimicrobial Resistance Research and Drug Development

Cited by 7 publications

References 173 publications

Machine learning to identify clinically relevantCandidayeast species

Machine learning to identify clinically relevantCandidayeast species

Emerging strategies and therapeutic innovations for combating drug resistance in Staphylococcus aureus strains: A comprehensive review

Artificial Intelligence in Battle against Antimicrobial Resistance: Opportunities and Challenges

Contact Info

Product

Resources

About