Using Machine Learning to Predict Antimicrobial Resistance―A Literature Review

Sakagianni, Aikaterini; Koufopoulou, Christina; Feretzakis, Georgios; Kalles, Dimitris; Verykios, Vassilios S.; Myrianthefs, Pavlos; Fildisis, Georgios

doi:10.3390/antibiotics12030452

Cited by 35 publications

(31 citation statements)

References 67 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, prediction tools can be applied at the point of prescription (eg, assessment for risk of antimicrobial resistance) and alerted to the prescriber [ 30 , 31 ]. As part of AS workflow, outlying prescriptions—such as meropenem for a patient with a low risk for gram-negative resistant infection—can be alerted during PAF and streamlined on the prioritization tool, eliminating unnecessary reviews of appropriate meropenem.…”

Section: Approaches To Initiative/alert Prioritizationmentioning

confidence: 99%

Improving the Efficiency of Antimicrobial Stewardship Action in Acute Care Facilities

Heil,

Justo,

Bork

2023

Open Forum Infectious Diseases

View full text Add to dashboard Cite

Inpatient antimicrobial stewardship (AS) programs are quality improvement programs tasked with improving antibiotic practices by augmenting frontline providers’ antibiotic prescription. Prospective audit and feedback (PAF) and pre-authorization (PRA) are essential activities in the hospital that can be resource-intensive for AS teams. Improving efficiency in AS activities is needed when there are limited resources or when programs are looking to expand other tasks beyond PAF and PRA, such as broad education or guideline development. Guidance on the creation and maintenance of alerts for the purpose of PAF reviews, modifications of antibiotic restrictions for PRA polices, and overall initiative prioritization strategies are reviewed. In addition, daily prioritization tools such as the tiered approach, scoring systems and regression modeling, are available for stewards to prioritize their daily workflow. Using these tools and guidance, AS programs can be productive and impactful in the face of resource limitation or competing priorities in the hospital.

show abstract

Section: Approaches To Initiative/alert Prioritizationmentioning

confidence: 99%

Improving the Efficiency of Antimicrobial Stewardship Action in Acute Care Facilities

Heil,

Justo,

Bork

2023

Open Forum Infectious Diseases

View full text Add to dashboard Cite

show abstract

“…Our analysis showed promising results for direct MIC prediction, and we identified RF and GBT models as top performers with cross-validated MSE scores on log 2 transformed MIC values of 0.25±0.03 and 0.28±0.05, respectively. Even though only a limited number of studies have explored MIC prediction of disinfectants from genomic data, making comparisons difficult, tree-based models show good performance and are commonly used for similar prediction tasks [15,16,38,39].…”

Section: Discussionmentioning

confidence: 99%

Quantitative prediction of disinfectant tolerance inListeria monocytogenesusing whole genome sequencing and machine learning

Gmeiner,

Ivanova,

Kamau Njage

et al. 2023

Preprint

View full text Add to dashboard Cite

Listeria monocytogenesis a potentially severe disease-causing bacteria mainly transmitted through food. This pathogen is of great concern for public health and the food industry in particular. Many countries have implemented thorough regulations, and some have even set ‘zero-tolerance’ thresholds for particular food products to minimise the risk ofL. monocytogenesoutbreaks. This emphasises that proper sanitation of food processing plants is of utmost importance. Consequently in recent years, there has been an increased interest inL. monocytogenestolerance to disinfectants used in the food industry. Even though many studies are focusing on laboratory quantification ofL. monocytogenestolerance, the possibility of predictive models remains poorly studied.Within this study, we explore the prediction of tolerance and minimum inhibitory concentrations (MIC) using whole genome sequencing (WGS) and machine learning (ML). We used WGS data and MIC values to quaternary ammonium compound (QAC) disinfectants from 1649L. monocytogenesisolates to train different ML predictors.Our study shows promising results for predicting tolerance to QAC disinfectants using WGS and machine learning. We were able to train high-performing ML classifiers to predict tolerance with balanced accuracy scores up to 0.97±0.02. For the prediction of MIC values, we were able to train ML regressors with mean squared error as low as 0.07±0.02. We also identified several new genes related to cell wall anchor domains, plasmids, and phages, putatively associated with disinfectant tolerance inL. monocytogenes.The findings of this study are a first step towards prediction ofL. monocytogenestolerance to QAC disinfectants used in the food industry. In the future, predictive models might be used to monitor disinfectant tolerance in food production and might support the conceptualisation of more nuanced sanitation programs.AUTHOR SUMMARYMicrobial contamination challenges food safety by potentially transmitting harmful microbes such as bacteria to consumers.Listeria monocytogenesis an example of such a bacteria, which is primarily transmitted through food and can cause severe diseases in at-risk groups. Fortunately, strict food safety regulations and stringent cleaning protocols are in place to prevent the transmission ofListeria monocytogenes. However, in recent years, there has been an increase in tolerance towards disinfectants used in the food industry, which can reduce their effectiveness. In this study, we used genome sequencing and phenotypic data to train machine learning models that can accurately predict whether individualListeria monocytogenesisolates are tolerant to selected disinfectants. We were able to train models that are not only able to distinguish sensitive/tolerant isolates but also can predict different degrees of tolerance to disinfectants. Further, we were able to report a set of genes that were important for the machine learning prediction and could give information about possible tolerance mechanisms. In the future, similar predictive models might be used to guide cleaning and disinfection protocols to facilitate maximum effectiveness.

show abstract

“…ML facilitates efficient information analysis, aiding in decision-making on vast medical and scientific data. With advancements in computing capabilities, ML enables the development of predictive applications [80]. ML algorithms are crucial in medical research, particularly in addressing antibiotic resistance (AMR) [81].…”

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

Using Machine Learning to Predict Antimicrobial Resistance―A Literature Review

Cited by 35 publications

References 67 publications

Improving the Efficiency of Antimicrobial Stewardship Action in Acute Care Facilities

Improving the Efficiency of Antimicrobial Stewardship Action in Acute Care Facilities

Quantitative prediction of disinfectant tolerance inListeria monocytogenesusing whole genome sequencing and machine learning

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

Contact Info

Product

Resources

About