Machine learning for microbial identification and antimicrobial susceptibility testing on MALDI-TOF mass spectra: a systematic review

Using machine learning models to predict the dose-effect curve of municipal wastewater for zebrafish embryo toxicity

Municipal wastewater substantially contributes to aquatic ecological risks. Assessing the toxicity of municipal wastewater through dose-effect curves is challenging owing to the time-consuming, labor-intensive, and costly nature of biological assays. This study developed machine learning models to predict wastewater dose-effect curves for zebrafish embryos. The influent and effluent samples from 176 wastewater treatment plants in China were analyzed to collect water quality data, including information on seven chemical parameters and the toxic effects on zebrafish embryos at eight relative enrichment factors (REFs) of wastewater. Using Spearman's rank correlation coefficient and the max-relevance and min-redundancy algorithm, the parameters of ammonium nitrogen content and toxic effect values at REFs of 2 and 25 (REF2 and REF25), were identified as crucial input features from 15 variables. Decision tree, random forest, and gradient-boosted decision tree (GBDT) models were developed. Among these, GBDT exhibited the best performance, with an average R2 value of 0.91 and an average mean absolute percentage error (MAPE) of 27.91 %. Integrating the dose-effect curve pattern into the machine learning model considerably optimized the GBDT model, reaching a minimum MAPE of 14.74 %. The developed model can accurately determine the dose-effect curves of actual wastewater, reducing at least 75 % of the experimental workload. These findings provide a valuable tool for assessing zebrafish embryo toxicity in municipal wastewater management. This study indicates that combining environmental expertise and machine learning models allows for a scientific assessment of the potential toxic risks in wastewater, providing new perspectives and approaches for environmental policy development.

The application of machine learning in clinical microbiology and infectious diseases

With the development of artificial intelligence(AI) in computer science and statistics, it has been further applied to the medical field. These applications include the management of infectious diseases, in which machine learning has created inroads in clinical microbiology, radiology, genomics, and the analysis of electronic health record data. Especially, the role of machine learning in microbiology has gradually become prominent, and it is used in etiological diagnosis, prediction of antibiotic resistance, association between human microbiome characteristics and complex host diseases, prognosis judgment, and prevention and control of infectious diseases. Machine learning in the field of microbiology mainly adopts supervised learning and unsupervised learning, involving algorithms from classification and regression to clustering and dimensionality reduction. This Review explains crucial concepts in machine learning for unfamiliar readers, describes machine learning's current applications in clinical microbiology and infectious diseases, and summarizes important approaches clinicians must be aware of when evaluating research using machine learning.

Accelerating antimicrobial stewardship: An AI-CDSS approach to combating multidrug-resistant pathogens in the era of increasing resistance

OBJECTIVES

The World Health Organization has identified Klebsiella pneumoniae (KP) and Pseudomonas aeruginosa (PA) as significant public health threats owing to high antibiotic resistance. Traditional antibiotic susceptibility testing (AST) methods, crucial for determining the most suitable treatment regimen, typically require approximately 48-96 h (2-4 days) to yield results, including bacterial culture, rapid identification via matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS), and subsequent AST, which is too long for urgent clinical decisions. Here, we developed an artificial intelligence-clinical decision support system (AI-CDSS) utilizing machine learning to analyze MALDI-TOF MS data for antibiotic resistance prediction for these pathogens.

METHODS

From 165,299 bacterial specimens, we selected 12,967 KP and 9,429 PA cases. Predictive models, the core of the AI-CDSS, were built using advanced machine learning algorithms, such as the random forest classifier (RFC) and light gradient boosting machine (LGBM), with GridSearchCV and 5-fold cross-validation optimization and robustness.

RESULTS

Both the RFC and LGBM models demonstrated strong predictive performance, with area under the curve values predominantly ranging from 0.91 to 0.95. Sensitivity, specificity, positive predictive value, and negative predictive value primarily exceeded 80 %, ensuring reliable detection of resistance patterns. The AI-CDSS was designed to provide real-time, clinically actionable recommendations, enabling targeted antibiotic selection up to one day faster than conventional AST.

CONCLUSIONS

Integrating MALDI-TOF MS with machine learning in AI-CDSS significantly enhanced clinical decision-making, representing a major advancement in the rapid management of infectious diseases and antimicrobial stewardship.

MALDI-TOF mass spectrometry combined with machine learning algorithms to identify protein profiles related to malaria infection in human sera from Côte d'Ivoire

BACKGROUND

In sub-Saharan Africa, Plasmodium falciparum is the most prevalent species of malaria parasites. In endemic areas, malaria is mainly diagnosed using microscopy or rapid diagnostic tests (RDTs), which have limited sensitivity, and microscopic expertise is waning in non-endemic regions. Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) is nowadays the standard method in routine microbiology laboratories for bacteria and fungi identification in high-income countries, but is rarely used for parasite detection. This study aims to employ MALDI-TOF MS for identifying malaria by distinguishing P. falciparum-positive from P. falciparum-negative sera.

METHODS

Sera were obtained from 282 blood samples collected from non-febrile, asymptomatic people aged 5 to 58 years in southern Côte d'Ivoire. Infectious status and parasitaemia were determined by both RDTs and microscopy, followed by a categorization into two groups (P. falciparum-positive and P. falciparum-negative samples). MALDI-TOF MS analysis was carried out by generating protein spectra profiles from 131 Plasmodium-positive and 94 Plasmodium-negative sera as the training set. Machine learning (ML) algorithms were employed for distinguishing P. falciparum-positive from P. falciparum-negative samples. Subsequently, a subset of 57 sera (42 P. falciparum-positive and 15 P. falciparum-negative) was used as the validation set to evaluate the best two of the four models trained.

RESULTS

MALDI-TOF MS was able to generate good-quality spectra from both P. falciparum-positive and P. falciparum-negative serum samples. High similarities between the protein spectra profiles did not allow for distinguishing the two groups using principal component analysis (PCA). When four supervised ML algorithms were tested by tenfold cross-validation, P. falciparum-positive sera were discriminated against P. falciparum-negative sera with a global accuracy ranging from 73.28% to 81.30%, while sensitivity ranged from 70.23% to 83.97%. The independent test performed with a subset of 57 serum samples showed accuracies of 85.96% and 89.47%, and sensitivities of 90.48% and 92.86%, respectively, for LightGBM and RF.

CONCLUSION

MALDI-TOF MS combined with ML might be applied for detection of protein profiles related to P. falciparum malaria infection in human serum samples. Additional research is warranted for further optimization such as specific biomarkers detection or using other ML models.

Metagenomics studies in aquaculture systems: Big data analysis, bioinformatics, machine learning and quantum computing

The burgeoning field of aquaculture has become a pivotal contributor to global food security and economic growth, presently surpassing capture fisheries in aquatic animal production as evidenced by recent statistics. However, the dense fish populations inherent in aquaculture systems exacerbate abiotic stressors and promote pathogenic spread, posing a risk to sustainability and yield. This study delves into the transformative potential of metagenomics, a method that directly retrieves genetic material from environmental samples, in elucidating microbial dynamics within aquaculture ecosystems. Our findings affirm that metagenomics, bolstered by tools in big data analytics, bioinformatics, and machine learning, can significantly enhance the precision of microbial assessment and pathogen detection. Furthermore, we explore quantum computing's emergent role, which promises unparalleled efficiency in data processing and model construction, poised to address the limitations of conventional computational techniques. Distinct from metabarcoding, metagenomics offers an expansive, unbiased profile of microbial biodiversity, revolutionizing our capacity to monitor, predict, and manage aquaculture systems with high accuracy and adaptability. Despite the challenges of computational demands and variability in data standardization, this study advocates for continued technological integration, thereby fostering resilient and sustainable aquaculture practices in a climate of escalating global food requirements.

A rapid and simple MALDI-TOF MS lipid profiling method for differentiating Mycobacterium ulcerans from Mycobacterium marinum

Mycobacterium ulcerans, a slow-growing nontuberculous mycobacterium, causes Buruli ulcer, a neglected tropical disease. Distinguishing M. ulcerans from related species, including Mycobacterium marinum, poses challenges with respect to making accurate identifications. In this study, we developed a rapid and simple identification method based on mycobacterial lipid profiles and used matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) to analyze the lipid profiles of M. ulcerans (n = 35) and M. marinum (n = 19) isolates. Bacterial colonies pre-cultured on 2% Ogawa egg slants for 2 months were collected, and total lipids were extracted using an MBT Lipid Xtract kit. Spectra were obtained in negative ion mode using a MALDI Biotyper Sirius system, with ClinProTools v3.0 being used to analyze the spectra based on the application of three algorithms (genetic algorithm [GA], supervised neural network [SNN], and quick classifier [QC)]). Cross-validation was performed using a 20% leave-out set randomly selected from the samples. Models generated using GA, SNN, and QC showed cross-validation values of 100%, 100%, and 97.9%, respectively, and all algorithms achieved 100% recognition capability values. Our findings indicate that MALDI-TOF analysis of lipid profiles can accurately differentiate two mycobacterial species (M. ulcerans and M. marinum) that are difficult to distinguish using conventional protein-targeting methods.IMPORTANCEBuruli ulcer, caused by Mycobacterium ulcerans, is a neglected tropical disease. However, distinguishing M. ulcerans from related species, including Mycobacterium marinum, presents certain challenges. In this study, we demonstrate the utility of a rapid yet simple method for differentiating isolates of these mycobacteria based on their lipid profiles using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. This new approach can accurately identify species that are otherwise difficult to distinguish using conventional techniques. This represents a significant diagnostic advance for clinical laboratories, in that it enables a more rapid and precise identification, thereby leading to earlier treatment initiation and more appropriate treatment regimens for infections caused by these bacteria.

Predicting Antimicrobial Class Specificity of Small Molecules Using Machine Learning

While the useful armory of antibiotic drugs is continually depleted due to the emergence of drug-resistant pathogens, the development of novel therapeutics has also slowed down. In the era of advanced computational methods, approaches like machine learning (ML) could be one potential solution to help reduce the high costs and complexity of antibiotic drug discovery and attract collaboration across organizations. In our work, we developed a large antimicrobial knowledge graph (AntiMicrobial-KG) as a repository for collecting and visualizing public in vitro antibacterial assay. Utilizing this data, we build ML models to efficiently scan compound libraries to identify compounds with the potential to exhibit antimicrobial activity. Our strategy involved training seven classic ML models across six compound fingerprint representations, of which the Random Forest trained on the MHFP6 fingerprint outperformed, demonstrating an accuracy of 75.9% and Cohen's Kappa score of 0.68. Finally, we illustrated the model's applicability for predicting the antimicrobial properties of two small molecule screening libraries. First, the EU-OpenScreen library was tested against a panel of Gram-positive, Gram-negative, and Fungal pathogens. Here, we unveiled that the model was able to correctly predict more than 30% of active compounds for Gram-positive, Gram-negative, and Fungal pathogens. Second, with the Enamine library, a commercially available HTS compound collection with claimed antibacterial properties, we predicted its antimicrobial activity and pathogen class specificity. These results may provide a means for accelerating research in AMR drug discovery efforts by carefully filtering out compounds from commercial libraries with lower chances of being active.

Freeze-Thaw Imaging for Microorganism Classification Assisted with Artificial Intelligence

Fast and cost-effective microbial classification is crucial for clinical diagnosis, environmental monitoring, and food safety. However, traditional methods encounter challenges including intricate procedures, skilled personnel needs, and sophisticated instrumentations. Here, we propose a cost-effective microbe classification system, also termed freeze-thaw-induced floating pattern of AuNPs (FTFPA), coupled with artificial intelligence, which is capable of identifying microbes at a cost of $0.0023 per sample. Specifically, FTFPA utilizes AuNPs for coincubation with microbes, resulting in distinct patterns upon freeze-thawing due to their weak interaction. These patterns are digitized to train models that distinguish nine microbes in various tasks. The positive sample detection model achieved an F1 score of 0.976 (n = 194), while the multispecies classification task reached a macro F1 score of 0.859 (n = 1728). To address scalability and lightweight requirements across diverse classification scenarios, we categorized microbes based on species classification levels. The macro F1 score of the hierarchical model (n = 5184), order level model (n = 5184), Enterobacteriales level model (n = 2550), and Bacillales level model (n = 1974) was 0.854, 0.907, 0.958, and 0.843. In summary, our method is user-friendly, requiring only simple equipment, is easy to operate, and convenient, providing a platform for microbial identification.

Pre-trained Maldi Transformers improve MALDI-TOF MS-based prediction

For the last decade, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been the reference method for species identification in clinical microbiology. Hampered by a historical lack of open data, machine learning research towards models specifically adapted to MALDI-TOF MS remains in its infancy. Given the growing complexity of available datasets (such as large-scale antimicrobial resistance prediction), a need for models that (1) are specifically designed for MALDI-TOF MS data, and (2) have high representational capacity, presents itself. Here, we introduce Maldi Transformer, an adaptation of the state-of-the-art transformer architecture to the MALDI-TOF mass spectral domain. We propose the first self-supervised pre-training technique specifically designed for mass spectra. The technique is based on shuffling peaks across spectra, and pre-training the transformer as a peak discriminator. Extensive benchmarks confirm the efficacy of this novel design. The final result is a model exhibiting state-of-the-art (or competitive) performance on downstream prediction tasks. In addition, we show that Maldi Transformer's identification of noisy spectra may be leveraged towards higher predictive performance. All code supporting this study is distributed on PyPI and is packaged under: https://github.com/gdewael/maldi-nn.

Human Dignity and Artificial Intelligence in Healthcare: A Basis for a Catholic Ethics on AI

The rise of artificial intelligence (AI) has caught the attention of the world as it challenges the status quo on human operations. As AI has dramatically impacted education, healthcare, industry, and economics, a Catholic ethical study of human dignity in the context of AI in healthcare is presented in this article. The debates regarding whether AI will usher well or doom the dignity of humankind are occasioned by increasing developments of technology in patient care and medical decision-making. This paper draws from Catholic ethics, especially the concepts of inherent human dignity, the sanctity of human life, and morality in the medical field. It talks about using AI to upgrade healthcare outcomes without losing the essential humanity of human dignity in medical practice. It also touches on the most likely ethical issues: the morality of AI-related decisions and the depersonalization of health care. Finally, it provides a framework that brings AI development in tandem with a Catholic vision of human dignity and supports a healthcare system that caters to the common good but correctly respects the irreplaceable value of the human person and highlights moral responsibility.

An antimicrobial drug recommender system using MALDI-TOF MS and dual-branch neural networks

Timely and effective use of antimicrobial drugs can improve patient outcomes, as well as help safeguard against resistance development. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) is currently routinely used in clinical diagnostics for rapid species identification. Mining additional data from said spectra in the form of antimicrobial resistance (AMR) profiles is, therefore, highly promising. Such AMR profiles could serve as a drop-in solution for drastically improving treatment efficiency, effectiveness, and costs. This study endeavors to develop the first machine learning models capable of predicting AMR profiles for the whole repertoire of species and drugs encountered in clinical microbiology. The resulting models can be interpreted as drug recommender systems for infectious diseases. We find that our dual-branch method delivers considerably higher performance compared to previous approaches. In addition, experiments show that the models can be efficiently fine-tuned to data from other clinical laboratories. MALDI-TOF-based AMR recommender systems can, hence, greatly extend the value of MALDI-TOF MS for clinical diagnostics. All code supporting this study is distributed on PyPI and is packaged at https://github.com/gdewael/maldi-nn.

Accurate prediction of antimicrobial resistance and genetic marker of Staphylococcus aureus clinical isolates using MALDI-TOF MS and machine learning - across DRIAMS and Taiwan database

BACKGROUND

The use of matrix-assisted laser desorption/ionisation-time-of-flight mass spectra (MALDI-TOF MS) with machine learning (ML) has been explored for predicting antimicrobial resistance. This study evaluates the effectiveness of MALDI-TOF MS paired with various ML classifiers and establishes optimal models for predicting antimicrobial resistance and the presence of mecA gene among Staphylococcus aureus.

MATERIALS AND METHODS

Antimicrobial resistance against tier 1 antibiotics and MALDI-TOF MS of S. aureus were analysed using data from the Database of Resistance against Antimicrobials with MALDI-TOF Mass Spectrometry (DRIAMS) and one medical centre (CS database). Five ML classifiers were used to analyse performance metrics. The Shapley value quantified the predictive contribution of individual features.

RESULTS

The LightGBM demonstrated superior performance in predicting antimicrobial resistance for most tier 1 antibiotics among oxacillin-resistant S. aureus (ORSA) compared with all S. aureus and oxacillin-susceptible S. aureus (OSSA) in both databases. In DRIAMS, Multilayer Perceptron (MLP) was associated with excellent predictive performance, expressed as accuracy/AUROC/AUPR, for clindamycin (0.74/0.81/0.90), tetracycline (0.86/0.87/0.94), and trimethoprim-sulfamethoxazole (0.95/0.72/0.97). In the CS database, Ada and Light Gradient Boosting Machine (LightGBM) showed excellent performance for erythromycin (0.97/0.92/0.86) and tetracycline (0.68/0.79/0.86). Mass-to-charge ratio (m/z) features of 2411-2414 and 2429-2432 correlated with clindamycin resistance, whereas 5033-5036 was linked to erythromycin resistance in DRIAMS. In the CS database, overlapping features of 2423-2426, 4496-4499, and 3764-3767 simultaneously predicted the presence of mecA and oxacillin resistance.

CONCLUSION

The predictive performance of antimicrobial resistance against S. aureus using MALDI-TOF MS depends on database characteristics and the ML algorithm selected. Specific and overlapping mass spectra features are excellent predictive markers for mecA and specific antimicrobial resistance.

A new fusion strategy for rapid strain differentiation based on MALDI-TOF MS and Raman spectra

Typing of bacterial subspecies is urgently needed for the diagnosis and efficient treatment during disease outbreaks. Physicochemical spectroscopy can provide a rapid analysis but its identification accuracy is still far from satisfactory. Herein, a novel feature-extractor-based fusion-assisted machine learning strategy has been developed for high accuracy and rapid strain differentiation using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and Raman spectroscopy. Based on this fusion approach, rapid and reliable identification and analysis can be performed within 24 hours. Validation on a panel of important pathogens comprising Staphylococcus aureus, Klebsiella pneumoniae, Escherichia coli, and Acinetobacter baumannii showed that the identification accuracies of k-nearest neighbors (KNNs), support vector machines (SVMs) and artificial neural networks (ANNs) were 100%. In particular, when benchmarked against a MALDI-TOF MS spectral dataset, the new approach improved the identification accuracy of Acinetobacter baumannii from 87.67% to 100%. This work demonstrates the effectiveness of combining MALDI-TOF MS and Raman spectroscopy fusion data in pathogenic bacterial subtyping.

Machine learning and matrix-assisted laser desorption/ionization time-of-flight mass spectra for antimicrobial resistance prediction: A systematic review of recent advancements and future development

BACKGROUND

The use of matrix-assisted laser desorption/ionization time-of-flight mass spectra (MALDI-TOF MS) combined with machine learning techniques has recently emerged as a method to address the public health crisis of antimicrobial resistance. This systematic review, conducted following Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines, aims to evaluate the current state of the art in using machine learning for the detection and classification of antimicrobial resistance from MALDI-TOF mass spectrometry data.

METHODS

A comprehensive review of the literature on machine learning applications for antimicrobial resistance detection was performed using databases such as Web Of Science, Scopus, ScienceDirect, IEEE Xplore, and PubMed. Only original articles in English were included. Studies applying machine learning without using MALDI-TOF mass spectra were excluded.

RESULTS

Forty studies met the inclusion criteria. Staphylococcus aureus, Klebsiella pneumoniae and Escherichia coli were the most frequently cited bacteria. The antibiotics resistance most studied corresponds to methicillin for S. aureus, cephalosporins for K. pneumoniae, and aminoglycosides for E. coli. Random forest, support vector machine and logistic regression were the most employed algorithms to predict antimicrobial resistance. Additionally, seven studies reported using artificial neural networks. Most studies reported metrics such as accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (AUROC) above 0.80.

CONCLUSIONS

Our study indicates that random forest, support vector machine, and logistic regression are effective for predicting antimicrobial resistance using MALDI-TOF MS data. Recent studies also highlight the potential of deep learning techniques in this area. We recommend further exploration of deep learning and multi-label supervised learning for comprehensive antibiotic resistance prediction in clinical practice.

Classification of Latilactobacillus sakei subspecies based on MALDI-TOF MS protein profiles using machine learning models

Latilactobacillus sakei is an important bacterial species used as a starter culture for fermented foods; however, two subspecies within this species exhibit different properties in the foods. Matrix-assisted laser desorption/ionization-time of flight mass spectrometer (MALDI-TOF MS) is the gold standard for microbial fingerprinting. However, the resolution power is down to the species level. This study was to combine MALDI-TOF mass spectra and machine learning to develop a new method to identify two L. sakei subspecies (L. sakei subsp. sakei and L. sakei subsp. carnosus) and non-L. sakei species. Totally, 227 strains were collected, with 908 spectra obtained via on- and off-plate protein extraction. Only 68.7% of strains were correctly identified at the subspecies level in the Biotyper database; however, a high level of performance was observed from the machine learning models. Partial least squares-discriminant analysis (PLS-DA), principal component analysis-K-nearest neighbor (PCA-KNN), and support vector machine (SVM) demonstrated 0.823, 0.914, and 0.903 accuracies, respectively, whereas the random forest (RF) achieved an accuracy of 0.954, with an area under the receiver operating characteristic (AUROC) curve of 0.99, outperforming the other algorithms in distinguishing the subspecies. The machine learning proved to be a promising technique for the rapid and high-resolution classification of L. sakei subspecies using MALDI-TOF MS.

IMPORTANCE

Latilactobacillus sakei plays a significant role in the realm of food bacteria. One particular subspecies of L. sakei is employed as a protective agent during food fermentation, whereas another strain is responsible for food spoilage. Hence, it is crucial to precisely differentiate between the two subspecies of L. sakei. In this study, machine learning models based on protein mass peaks were developed for the first time to distinguish L. sakei subspecies. Furthermore, the efficacy of three commonly used machine learning algorithms for microbial classification was evaluated. Our results provide the foundation for future research on developing machine learning models for the classification of microbial species or subspecies. In addition, the developed model can be used in the food industry to monitor L. sakei subspecies in fermented foods in a time- and cost-effective method for food quality and safety.

Artificial intelligence-clinical decision support system for enhanced infectious disease management: Accelerating ceftazidime-avibactam resistance detection in Klebsiella pneumoniae

BACKGROUND

Effective and rapid diagnostic strategies are required to manage antibiotic resistance in Klebsiella pneumonia (KP). This study aimed to design an artificial intelligence-clinical decision support system (AI-CDSS) using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and machine learning for the rapid detection of ceftazidime-avibactam (CZA) resistance in KP to improve clinical decision-making processes.

METHODS

Out of 107,721 bacterial samples, 675 specimens of KP with suspected multi-drug resistance were selected. These specimens were collected from a tertiary hospital and four secondary hospitals between 2022 and 2023 to evaluate CZA resistance. We used MALDI-TOF MS and machine learning to develop an AI-CDSS with enhanced speed of resistance detection.

RESULTS

Machine learning models, especially light gradient boosting machines (LGBM), exhibited an area under the curve (AUC) of 0.95, indicating high accuracy. The predictive models formed the core of our newly developed AI-CDSS, enabling clinical decisions quicker than traditional methods using culture and antibiotic susceptibility testing by a day.

CONCLUSIONS

The study confirms that MALDI-TOF MS, integrated with machine learning, can swiftly detect CZA resistance. Incorporating this insight into an AI-CDSS could transform clinical workflows, giving healthcare professionals immediate, crucial insights for shaping treatment plans. This approach promises to be a template for future anti-resistance strategies, emphasizing the vital importance of advanced diagnostics in enhancing public health outcomes.

Prediction of antimicrobial resistance of Klebsiella pneumoniae from genomic data through machine learning

Antimicrobials, such as antibiotics or antivirals are medications employed to prevent and treat infectious diseases in humans, animals, and plants. Antimicrobial Resistance occurs when bacteria, viruses, and parasites no longer respond to these medicines. This resistance renders antibiotics and other antimicrobial drugs ineffective, making infections challenging or impossible to treat. This escalation in drug resistance heightens the risk of disease spread, severe illness, disability, and mortality. With datasets now containing hundreds or even thousands of pathogen genomes, machine learning techniques are on the rise for predicting antibiotic resistance in pathogens, prediction based on gene content and genome composition. Aim of this work is to combine and incorporate machine learning methods on bacterial genomic data to predict antimicrobial resistance, we will focus on the case of Klebsiella pneumoniae in order to support clinicians in selecting appropriate therapy.

Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra

Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for detection of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa, a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern β-lactam/β-lactamase inhibitor drugs, namely, ceftazidime/avibactam and ceftolozane/tazobactam. For these drugs, the model demonstrated area under the receiver operating characteristic curve (AUROC) of 0.869 and 0.856, specificity of 0.925 and 0.897, and sensitivity of 0.731 and 0.714, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional feature engineering approaches, the dynamic binning method yielded highest performance in 7 of 10 antimicrobials. Moreover, we showcased the efficacy of transfer learning in enhancing the AUROC performance for 8 of 11 antimicrobials. By assessing the contribution of features to the model's prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa.IMPORTANCEPseudomonas aeruginosa is a key bacterial pathogen that causes significant global morbidity and mortality. Antimicrobial resistance (AMR) emerges rapidly in P. aeruginosa and is driven by complex mechanisms. Drug-resistant P. aeruginosa is a major challenge in clinical settings due to limited treatment options. Early detection of AMR can guide antibiotic choices, improve patient outcomes, and avoid unnecessary antibiotic use. Matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS) is widely used for rapid species identification in clinical microbiology. In this study, we repurposed mass spectra generated by MALDI-TOF and used them as inputs for artificial intelligence approaches to successfully predict AMR in P. aeruginosa for multiple key antibiotic classes. This work represents an important advance toward using MALDI-TOF as a rapid AMR diagnostic for P. aeruginosa in clinical settings.

Applying Machine Learning for Antibiotic Development and Prediction of Microbial Resistance

Antimicrobial resistance (AMR) poses a serious threat to human health worldwide. It is now more challenging than ever to introduce a potent antibiotic to the market considering rapid emergence of antimicrobial resistance, surpassing the rate of antibiotic drug discovery. Hence, new approaches need to be developed to accelerate the rate of drug discovery process and meet the demands for new antibiotics, while reducing the cost of their development. Machine learning holds immense promise of becoming a useful tool, especially since in the last two decades, exponential growth has occurred in computational power and biological big data analytics. Recent advancements in machine learning algorithms for drug discovery have provided significant clues for potential antibiotic classes. Apart from discovery of new scaffolds, the machine learning protocols will significantly impact prediction of AMR patterns and drug metabolism. In this review, we outline power of machine learning in antibiotic drug discovery, metabolic fate, and AMR prediction to support researchers engaged and interested in this field.

Machine Learning Assisted MALDI Mass Spectrometry for Rapid Antimicrobial Resistance Prediction in Clinicals

Antimicrobial susceptibility testing (AST) plays a critical role in assessing the resistance of individual microbial isolates and determining appropriate antimicrobial therapeutics in a timely manner. However, conventional AST normally takes up to 72 h for obtaining the results. In healthcare facilities, the global distribution of vancomycin-resistant Enterococcus fecium (VRE) infections underscores the importance of rapidly determining VRE isolates. Here, we developed an integrated antimicrobial resistance (AMR) screening strategy by combining matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS) with machine learning to rapidly predict VRE from clinical samples. Over 400 VRE and vancomycin-susceptible E. faecium (VSE) isolates were analyzed using MALDI-MS at different culture times, and a comprehensive dataset comprising 2388 mass spectra was generated. Algorithms including the support vector machine (SVM), SVM with L1-norm, logistic regression, and multilayer perceptron (MLP) were utilized to train the classification model. Validation on a panel of clinical samples (external patients) resulted in a prediction accuracy of 78.07%, 80.26%, 78.95%, and 80.54% for each algorithm, respectively, all with an AUROC above 0.80. Furthermore, a total of 33 mass regions were recognized as influential features and elucidated, contributing to the differences between VRE and VSE through the Shapley value and accuracy, while tandem mass spectrometry was employed to identify the specific peaks among them. Certain ribosomal proteins, such as A0A133N352 and R2Q455, were tentatively identified. Overall, the integration of machine learning with MALDI-MS has enabled the rapid determination of bacterial antibiotic resistance, greatly expediting the usage of appropriate antibiotics.

Rapid determination of antibiotic susceptibility of clinical isolates of Escherichia coli by SYBR green I/Propidium iodide assay

Infections caused by pathogenic Escherichia coli are a serious threat to human health, while conventional antibiotic susceptibility tests (AST) have a long turn-around time, and rapid antibiotic susceptibility methods are urgently needed to save lives in the clinic, reduce antibiotic misuse and prevent emergence of antibiotic-resistant bacteria. We optimized and validated the feasibility of a novel rapid AST based on SYBR Green I and Propidium Iodide (SGPI-AST) for E. coli drug susceptibility test. A total of 112 clinical isolates of E. coli were collected and four antibiotics (ceftriaxone, cefoxitin, imipenem, meropenem) were selected for testing. Bacterial survival rate of E. coli was remarkably linearly correlated with S value at different OD600 values. After optimizing the antibiotic concentrations, the sensitivity and specificity of SGPI-AST reached 100%/100%, 97.8%/100%, 100%/100% and 98.4%/99% for ceftriaxone, cefoxitin, imipenem and meropenem, respectively, and the corresponding concordances of the SGPI-AST with conventional AST were 1.000, 0.980, 1.000 and 0.979, respectively. The SGPI-AST can rapidly and accurately determine the susceptibility of E. coli clinical isolates to multiple antibiotics in 60 min, and has the potential to be applied to guide the precise selection of antibiotics for clinical management of infections caused by pathogenic E. coli.

Rapid detection of ceftriaxone-resistant Salmonella by matrix-assisted laser desorption-ionization time-of-flight mass spectrometry combined with the ratio of optical density

BACKGROUND

The increased resistance rate of Salmonella to third-generation cephalosporins represented by ceftriaxone (CRO) may result in the failure of the empirical use of third-generation cephalosporins for the treatment of Salmonella infection in children. The present study was conducted to evaluate a novel method for the rapid detection of CRO-resistant Salmonella (CRS).

METHODS

We introduced the concept of the ratio of optical density (ROD) with and without CRO and combined it with matrix-assisted laser desorption-ionization time-of-flight mass spectrometry (MALDI-TOF MS) to establish a new protocol for the rapid detection of CRS.

RESULTS

The optimal incubation time and CRO concentration determined by the model strain test were 2 h and 8 µg/ml, respectively. We then conducted confirmatory tests on 120 clinical strains. According to the receiver operating characteristic curve analysis, the ROD cutoff value for distinguishing CRS and non-CRS strains was 0.818 [area under the curve: 1.000; 95% confidence interval: 0.970-1.000; sensitivity: 100.00%; specificity: 100%; P < 10- 3].

CONCLUSIONS

In conclusion, the protocol for the combined ROD and MALDI-TOF MS represents a rapid, accurate, and economical method for the detection of CRS.

Multiplex Detection of Foodborne Pathogens using 3D Nanostructure Swab and Deep Learning-Based Classification of Raman Spectra

Proactive management of foodborne illness requires routine surveillance of foodborne pathogens, which requires developing simple, rapid, and sensitive detection methods. Here, a strategy is presented that enables the detection of multiple foodborne bacteria using a 3D nanostructure swab and deep learning-based Raman signal classification. The nanostructure swab efficiently captures foodborne pathogens, and the portable Raman instrument directly collects the Raman signals of captured bacteria. a deep learning algorithm has been demonstrated, 1D convolutional neural network with binary labeling, achieves superior performance in classifying individual bacterial species. This methodology has been extended to mixed bacterial populations, maintaining accuracy close to 100%. In addition, the gradient-weighted class activation mapping method is used to provide an investigation of the Raman bands for foodborne pathogens. For practical application, blind tests are conducted on contaminated kitchen utensils and foods. The proposed technique is validated by the successful detection of bacterial species from the contaminated surfaces. The use of a 3D nanostructure swab, portable Raman device, and deep learning-based classification provides a powerful tool for rapid identification (≈5 min) of foodborne bacterial species. The detection strategy shows significant potential for reliable food safety monitoring, making a meaningful contribution to public health and the food industry.

Artificial Intelligence-Clinical Decision Support System in Infectious Disease Control: Combatting Multidrug-Resistant Klebsiella pneumoniae with Machine Learning

Purpose

The World Health Organization has identified Klebsiella pneumoniae (KP) as a significant threat to global public health. The rising threat of carbapenem-resistant Klebsiella pneumoniae (CRKP) leads to prolonged hospital stays and higher medical costs, necessitating faster diagnostic methods. Traditional antibiotic susceptibility testing (AST) methods demand at least 4 days, requiring 3 days on average for culturing and isolating the bacteria and identifying the species using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), plus an extra day for interpreting AST results. This lengthy process makes traditional methods too slow for urgent clinical situations requiring rapid decision-making, potentially hindering prompt treatment decisions, especially for fast-spreading infections such as those caused by CRKP. This research leverages a cutting-edge diagnostic method that utilizes an artificial intelligence-clinical decision support system (AI-CDSS). It incorporates machine learning algorithms for the swift and precise detection of carbapenem-resistant and colistin-resistant strains.

Patients and Methods

We selected 4307 KP samples out of a total of 52,827 bacterial samples due to concerns about multi-drug resistance using MALDI-TOF MS and Vitek-2 systems for AST. It involved thorough data preprocessing, feature extraction, and machine learning model training fine-tuned with GridSearchCV and 5-fold cross-validation, resulting in high predictive accuracy, as demonstrated by the receiver operating characteristic and area under the curve (AUC) scores, laying the groundwork for our AI-CDSS.

Results

MALDI-TOF MS analysis revealed distinct intensity profiles differentiating CRKP and susceptible strains, as well as colistin-resistant Klebsiella pneumoniae (CoRKP) and susceptible strains. The Random Forest Classifier demonstrated superior discriminatory power, with an AUC of 0.96 for detecting CRKP and 0.98 for detecting CoRKP.

Conclusion

Integrating MALDI-TOF MS with machine learning in an AI-CDSS has greatly expedited the detection of KP resistance by approximately 1 day. This system offers timely guidance, potentially enhancing clinical decision-making and improving treatment outcomes for KP infections.

Identification of Escherichia coli strains using MALDI-TOF MS combined with long short-term memory neural networks

The current study aims to develop a new technique for the precise identification of Escherichia coli strains, utilizing matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) combined with a long short-term memory (LSTM) neural network. A total of 48 Escherichia coli strains were isolated and cultured on tryptic soy agar medium for 24 hours for the generation of MALDI-TOF MS spectra. Eight hundred MALDI-TOF MS spectra were obtained per strain, resulting in a database of 38,400 spectra. Fifty percent of the data was utilized for LSTM neural network training, with fine-tuned parameters for strain-level identification. The other half served as the test set to assess model performance. Traditional PCA dimension reduction of MALDI-TOF MS spectra indicated 47 out of 48 strains to be unclassifiable. In contrast, the LSTM neural network demonstrated remarkable efficacy. After 20 training epochs, the model achieved a loss value of 0.0524, an accuracy of 0.999, a precision of 0.985, and a recall of 0.982. When tested on the unseen data, the model attained an overall accuracy of 92.24%. The integration of MALDI-TOF MS and LSTM neural network markedly enhances the identification of Escherichia coli strains. This innovative approach offers an effective and accurate tool for MALDI-TOF MS-based strain-level identification, thus expanding the analytical capabilities of microbial diagnostics.

Advances of machine learning-assisted small extracellular vesicles detection strategy

Detection of extracellular vesicles (EVs), particularly small EVs (sEVs), is of great significance in exploring their physiological characteristics and clinical applications. The heterogeneity of sEVs plays a crucial role in distinguishing different types of cells and diseases. Machine learning, with its exceptional data processing capabilities, offers a solution to overcome the limitations of conventional detection methods for accurately classifying sEV subtypes and sources. Principal component analysis, linear discriminant analysis, partial least squares discriminant analysis, XGBoost, support vector machine, k-nearest neighbor, and deep learning, along with some combined methods such as principal component-linear discriminant analysis, have been successfully applied in the detection and identification of sEVs. This review focuses on machine learning-assisted detection strategies for cell identification and disease prediction via sEVs, and summarizes the integration of these strategies with surface-enhanced Raman scattering, electrochemistry, inductively coupled plasma mass spectrometry and fluorescence. The performance of different machine learning-based detection strategies is compared, and the advantages and limitations of various machine learning models are also evaluated. Finally, we discuss the merits and limitations of the current approaches and briefly outline the perspective of potential research directions in the field of sEV analysis based on machine learning.

Tackling the Antimicrobial Resistance "Pandemic" with Machine Learning Tools: A Summary of Available Evidence

Antimicrobial resistance is recognised as one of the top threats healthcare is bound to face in the future. There have been various attempts to preserve the efficacy of existing antimicrobials, develop new and efficient antimicrobials, manage infections with multi-drug resistant strains, and improve patient outcomes, resulting in a growing mass of routinely available data, including electronic health records and microbiological information that can be employed to develop individualised antimicrobial stewardship. Machine learning methods have been developed to predict antimicrobial resistance from whole-genome sequencing data, forecast medication susceptibility, recognise epidemic patterns for surveillance purposes, or propose new antibacterial treatments and accelerate scientific discovery. Unfortunately, there is an evident gap between the number of machine learning applications in science and the effective implementation of these systems. This narrative review highlights some of the outstanding opportunities that machine learning offers when applied in research related to antimicrobial resistance. In the future, machine learning tools may prove to be superbugs' kryptonite. This review aims to provide an overview of available publications to aid researchers that are looking to expand their work with new approaches and to acquaint them with the current application of machine learning techniques in this field.

Distinguishing methicillin-resistant Staphylococcus aureus from methicillin-sensitive strains by combining Fe3O4 magnetic nanoparticle-based affinity mass spectrometry with a machine learning strategy

Pathogenic bacteria, including drug-resistant variants such as methicillin-resistant Staphylococcus aureus (MRSA), can cause severe infections in the human body. Early detection of MRSA is essential for clinical diagnosis and proper treatment, considering the distinct therapeutic strategies for methicillin-sensitive S. aureus (MSSA) and MRSA infections. However, the similarities between MRSA and MSSA properties present a challenge in promptly and accurately distinguishing between them. This work introduces an approach to differentiate MRSA from MSSA utilizing matrix-assisted laser desorption ionization mass spectrometry (MALDI-MS) in conjunction with a neural network-based classification model. Four distinct strains of S. aureus were utilized, comprising three MSSA strains and one MRSA strain. The classification accuracy of our model ranges from ~ 92 to ~ 97% for each strain. We used deep SHapley Additive exPlanations to reveal the unique feature peaks for each bacterial strain. Furthermore, Fe3O4 MNPs were used as affinity probes for sample enrichment to eliminate the overnight culture and reduce the time in sample preparation. The limit of detection of the MNP-based affinity approach toward S. aureus combined with our machine learning strategy was as low as ~ 8 × 103 CFU mL-1. The feasibility of using the current approach for the identification of S. aureus in juice samples was also demonstrated.

MSDeepAMR: antimicrobial resistance prediction based on deep neural networks and transfer learning

Introduction

Antimicrobial resistance (AMR) is a global health problem that requires early and effective treatments to prevent the indiscriminate use of antimicrobial drugs and the outcome of infections. Mass Spectrometry (MS), and more particularly MALDI-TOF, have been widely adopted by routine clinical microbiology laboratories to identify bacterial species and detect AMR. The analysis of AMR with deep learning is still recent, and most models depend on filters and preprocessing techniques manually applied on spectra.

Methods

This study propose a deep neural network, MSDeepAMR, to learn from raw mass spectra to predict AMR. MSDeepAMR model was implemented for Escherichia coli, Klebsiella pneumoniae, and Staphylococcus aureus under different antibiotic resistance profiles. Additionally, a transfer learning test was performed to study the benefits of adapting the previously trained models to external data.

Results

MSDeepAMR models showed a good classification performance to detect antibiotic resistance. The AUROC of the model was above 0.83 in most cases studied, improving the results of previous investigations by over 10%. The adapted models improved the AUROC by up to 20% when compared to a model trained only with external data.

Discussion

This study demonstrate the potential of the MSDeepAMR model to predict antibiotic resistance and their use on external MS data. This allow the extrapolation of the MSDeepAMR model to de used in different laboratories that need to study AMR and do not have the capacity for an extensive sample collection.

Brave New World of Artificial Intelligence: Its Use in Antimicrobial Stewardship-A Systematic Review

Antimicrobial resistance (AMR) is a growing public health problem in the One Health dimension. Artificial intelligence (AI) is emerging in healthcare, since it is helpful to deal with large amounts of data and as a prediction tool. This systematic review explores the use of AI in antimicrobial stewardship programs (ASPs) and summarizes the predictive performance of machine learning (ML) algorithms, compared with clinical decisions, in inpatients and outpatients who need antimicrobial prescriptions. This review includes eighteen observational studies from PubMed, Scopus, and Web of Science. The exclusion criteria comprised studies conducted only in vitro, not addressing infectious diseases, or not referencing the use of AI models as predictors. Data such as study type, year of publication, number of patients, study objective, ML algorithms used, features, and predictors were extracted from the included publications. All studies concluded that ML algorithms were useful to assist antimicrobial stewardship teams in multiple tasks such as identifying inappropriate prescribing practices, choosing the appropriate antibiotic therapy, or predicting AMR. The most extracted performance metric was AUC, which ranged from 0.64 to 0.992. Despite the risks and ethical concerns that AI raises, it can play a positive and promising role in ASP.

MALDI-TOF as a powerful tool for identifying and differentiating closely related microorganisms: the strange case of three reference strains of Paenibacillus polymyxa

Accurate identification and typing of microbes are crucial steps in gaining an awareness of the biological heterogeneity and reliability of microbial material within any proprietary or public collection. Paenibacillus polymyxa is a bacterial species of great agricultural and industrial importance due to its plant growth-promoting activities and production of several relevant secondary metabolites. In recent years, matrix-assisted laser desorption ionisation time-of-flight mass spectrometry (MALDI-TOF MS) has been widely used as an alternative rapid tool for identifying, typing, and differentiating closely related strains. In this study, we investigated the diversity of three P. polymyxa strains. The mass spectra of ATCC 842T, DSM 292, and DSM 365 were obtained, analysed, and compared to select discriminant peaks using ClinProTools software and generate classification models. MALDI-TOF MS analysis showed inconsistent results in identifying DSM 292 and DSM 365 as belonging to P. polimixa species, and comparative analysis of mass spectra revealed the presence of highly discriminatory biomarkers among the three strains. 16S rRNA sequencing and Average Nucleotide Identity (ANI) confirmed the discrepancies found in the proteomic analysis. The case study presented here suggests the enormous potential of the proteomic-based approach, combined with statistical tools, to predict and explore differences between closely related strains in large microbial datasets.

Rapid discrimination of Bifidobacterium longum subspecies based on MALDI-TOF MS and machine learning

Although MALDI-TOF mass spectrometry (MS) is widely known as a rapid and cost-effective reference method for identifying microorganisms, its commercial databases face limitations in accurately distinguishing specific subspecies of Bifidobacterium. This study aimed to explore the potential of MALDI-TOF MS protein profiles, coupled with prediction methods, to differentiate between Bifidobacterium longum subsp. infantis (B. infantis) and Bifidobacterium longum subsp. longum (B. longum). The investigation involved the analysis of mass spectra of 59 B. longum strains and 41 B. infantis strains, leading to the identification of five distinct biomarker peaks, specifically at m/z 2,929, 4,408, 5,381, 5,394, and 8,817, using Recurrent Feature Elimination (RFE). To facilate classification between B. longum and B. infantis based on the mass spectra, machine learning models were developed, employing algorithms such as logistic regression (LR), random forest (RF), and support vector machine (SVM). The evaluation of the mass spectrometry data showed that the RF model exhibited the highest performace, boasting an impressive AUC of 0.984. This model outperformed other algorithms in terms of accuracy and sensitivity. Furthermore, when employing a voting mechanism on multi-mass spectrometry data for strain identificaton, the RF model achieved the highest accuracy of 96.67%. The outcomes of this research hold the significant potential for commercial applications, enabling the rapid and precise discrimination of B. longum and B. infantis using MALDI-TOF MS in conjunction with machine learning. Additionally, the approach proposed in this study carries substantial implications across various industries, such as probiotics and pharmaceuticals, where the precise differentiation of specific subspecies is essential for product development and quality control.

Multimodal learning in clinical proteomics: enhancing antimicrobial resistance prediction models with chemical information

MOTIVATION

Large-scale clinical proteomics datasets of infectious pathogens, combined with antimicrobial resistance outcomes, have recently opened the door for machine learning models which aim to improve clinical treatment by predicting resistance early. However, existing prediction frameworks typically train a separate model for each antimicrobial and species in order to predict a pathogen's resistance outcome, resulting in missed opportunities for chemical knowledge transfer and generalizability.

RESULTS

We demonstrate the effectiveness of multimodal learning over proteomic and chemical features by exploring two clinically relevant tasks for our proposed deep learning models: drug recommendation and generalized resistance prediction. By adopting this multi-view representation of the pathogenic samples and leveraging the scale of the available datasets, our models outperformed the previous single-drug and single-species predictive models by statistically significant margins. We extensively validated the multi-drug setting, highlighting the challenges in generalizing beyond the training data distribution, and quantitatively demonstrate how suitable representations of antimicrobial drugs constitute a crucial tool in the development of clinically relevant predictive models.

AVAILABILITY AND IMPLEMENTATION

The code used to produce the results presented in this article is available at https://github.com/BorgwardtLab/MultimodalAMR.

Promising potential of machine learning-assisted MALDI-TOF MS as an effective detector for Streptococcus suis serotype 2 and virulence thereof

IMPORTANCE

To the best of our knowledge, this study reveals a strong correlation between mass spectra pattern and virulence phenotype among S. suis for the first time. In order to make the findings applicable and to excavate the intrinsic information in the spectra, the classifiers based on the machine learning algorithms were established, and RF (Random Forest)-based models have achieved an accuracy of over 90%. Overall, this study will pave the way for virulent SS2 (Streptococcus suis serotype 2) rapid detection, and the important findings on the association between genotype and mass spectrum may provide a new idea for the genotype-dependent detection of specific pathogens.

Deep learning and single-cell phenotyping for rapid antimicrobial susceptibility detection in Escherichia coli

The rise of antimicrobial resistance (AMR) is one of the greatest public health challenges, already causing up to 1.2 million deaths annually and rising. Current culture-based turnaround times for bacterial identification in clinical samples and antimicrobial susceptibility testing (AST) are typically 18-24 h. We present a novel proof-of-concept methodological advance in susceptibility testing based on the deep-learning of single-cell specific morphological phenotypes directly associated with antimicrobial susceptibility in Escherichia coli. Our models can reliably (80% single-cell accuracy) classify untreated and treated susceptible cells for a lab-reference fully susceptible E. coli strain, across four antibiotics (ciprofloxacin, gentamicin, rifampicin and co-amoxiclav). For ciprofloxacin, we demonstrate our models reveal significant (p < 0.001) differences between bacterial cell populations affected and unaffected by antibiotic treatment, and show that given treatment with a fixed concentration of 10 mg/L over 30 min these phenotypic effects correlate with clinical susceptibility defined by established clinical breakpoints. Deploying our approach on cell populations from six E. coli strains obtained from human bloodstream infections with varying degrees of ciprofloxacin resistance and treated with a range of ciprofloxacin concentrations, we show single-cell phenotyping has the potential to provide equivalent information to growth-based AST assays, but in as little as 30 min.

Discrimination between hypervirulent and non-hypervirulent ribotypes of Clostridioides difficile by MALDI-TOF mass spectrometry and machine learning

Hypervirulent ribotypes (HVRTs) of Clostridioides difficile such as ribotype (RT) 027 are epidemiologically important. This study evaluated whether MALDI-TOF can distinguish between strains of HVRTs and non-HVRTs commonly found in Europe. Obtained spectra of clinical C. difficile isolates (training set, 157 isolates) covering epidemiologically relevant HVRTs and non-HVRTs found in Europe were used as an input for different machine learning (ML) models. Another 83 isolates were used as a validation set. Direct comparison of MALDI-TOF spectra obtained from HVRTs and non-HVRTs did not allow to discriminate between these two groups, while using these spectra with certain ML models could differentiate HVRTs from non-HVRTs with an accuracy >95% and allowed for a sub-clustering of three HVRT subgroups (RT027/RT176, RT023, RT045/078/126/127). MALDI-TOF combined with ML represents a reliable tool for rapid identification of major European HVRTs.

Rapid AMR prediction in Pseudomonas aeruginosa combining MALDI-TOF MS with DNN model

BACKGROUND

Pseudomonas aeruginosa is a significant clinical pathogen that poses a substantial threat due to its extensive drug resistance. The rapid and precise identification of this resistance is crucial for effective clinical treatment. Although matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has been used for antibiotic susceptibility differentiation of some bacteria in recent years, the genetic diversity of P. aeruginosa complicates population analysis. Rapid identification of antimicrobial resistance (AMR) in P. aeruginosa based on a large amount of MALDI-TOF-MS data has not yet been reported. In this study, we employed publicly available datasets for P. aeruginosa, which contain data on bacterial resistance and MALDI-TOF-MS spectra. We introduced a deep neural network model, synergized with a strategic sampling approach (SMOTEENN) to construct a predictive framework for AMR of three widely used antibiotics.

RESULTS

The framework achieved area under the curve values of 90%, 85%, and 77% for Tobramycin, Cefepime, and Meropenem, respectively, surpassing conventional classifiers. Notably, random forest algorithm was used to assess the significance of features and post-hoc analysis was conducted on the top 10 features using Cohen's d. This analysis revealed moderate effect sizes (d = 0.5-0.8) in Tobramycin and Cefepime models. Finally, putative AMR biomarkers were identified in this study.

CONCLUSIONS

This work presented an AMR prediction tool specifically designed for P. aeruginosa, which offers a hopeful pathway for clinical decision-making.

Artificial intelligence, machine learning and deep learning: Potential resources for the infection clinician

BACKGROUND

Artificial intelligence (AI), machine learning and deep learning (including generative AI) are increasingly being investigated in the context of research and management of human infection.

OBJECTIVES

We summarise recent and potential future applications of AI and its relevance to clinical infection practice.

METHODS

1617 PubMed results were screened, with priority given to clinical trials, systematic reviews and meta-analyses. This narrative review focusses on studies using prospectively collected real-world data with clinical validation, and on research with translational potential, such as novel drug discovery and microbiome-based interventions.

RESULTS

There is some evidence of clinical utility of AI applied to laboratory diagnostics (e.g. digital culture plate reading, malaria diagnosis, antimicrobial resistance profiling), clinical imaging analysis (e.g. pulmonary tuberculosis diagnosis), clinical decision support tools (e.g. sepsis prediction, antimicrobial prescribing) and public health outbreak management (e.g. COVID-19). Most studies to date lack any real-world validation or clinical utility metrics. Significant heterogeneity in study design and reporting limits comparability. Many practical and ethical issues exist, including algorithm transparency and risk of bias.

CONCLUSIONS

Interest in and development of AI-based tools for infection research and management are undoubtedly gaining pace, although the real-world clinical utility to date appears much more modest.

Rapid identification of Salmonella serovars Enteritidis and Typhimurium using whole cell matrix assisted laser desorption ionization - Time of flight mass spectrometry (MALDI-TOF MS) coupled with multivariate analysis and artificial intelligence

Salmonella is a common food-borne pathogen with Enteritidis and Typhimurium being among the most important serovars causing numerous outbreaks. A rapid method was investigated to identify these serovars using whole-cell MALDI-TOF MS coupled with multivariate analysis and artificial intelligence and 113 Salmonella strains, including 38 Enteritidis (SE), 38 Typhimurium (ST) and 37 strains from 32 other Salmonella serovars (SG). Datasets of ions (presence/absence) with high discriminative power were created using newly developed criteria and subject to multivariate analyses and eight artificial intelligence (AI) tools. Principal Component Analysis based on 55 or 88 selected ions separated SE, ST and SG without overlap on the first three principal components. Datasets were partitioned using five partitioning methods with 70% of samples for AI model training and 30% for validation. Of the eight AI models evaluated, high performance (HP) SVM and HP Neural were the top performers, identified three serovar groups 97% correctly on average (range 82%-100%) according to the validation results. Selection of serovar specific ions facilitated differentiation of serotypes using unsupervised model PCA and improved the accuracy of classification using AI significantly (p < 0.01). MALDI-TOF MS incorporated with advanced data processing and classification tools is a promising method to allow rapid identification of Salmonella serovars of concern in routine diagnostic laboratories.

Effect of Tryptic Digestion on Sensitivity and Specificity in MALDI-TOF-Based Molecular Diagnostics through Machine Learning

The digestion of protein into peptide fragments reduces the size and complexity of protein molecules. Peptide fragments can be analyzed with higher sensitivity (often > 102 fold) and resolution using MALDI-TOF mass spectrometers, leading to improved pattern recognition by common machine learning algorithms. In turn, enhanced sensitivity and specificity for bacterial sorting and/or disease diagnosis may be obtained. To test this hypothesis, four exemplar case studies have been pursued in which samples are sorted into dichotomous groups by machine learning (ML) software based on MALDI-TOF spectra. Samples were analyzed in 'intact' mode in which the proteins present in the sample were not digested with protease prior to MALDI-TOF analysis and separately after the standard overnight tryptic digestion of the same samples. For each case, sensitivity (sens), specificity (spc), and the Youdin index (J) were used to assess the ML model performance. The proteolytic digestion of samples prior to MALDI-TOF analysis substantially enhanced the sensitivity and specificity of dichotomous sorting. Two exceptions were when substantial differences in chemical composition between the samples were present and, in such cases, both 'intact' and 'digested' protocols performed similarly. The results suggest proteolytic digestion prior to analysis can improve sorting in MALDI/ML-based workflows and may enable improved biomarker discovery. However, when samples are easily distinguishable protein digestion is not necessary to obtain useful diagnostic results.

Revolutionizing healthcare: the role of artificial intelligence in clinical practice

INTRODUCTION

Healthcare systems are complex and challenging for all stakeholders, but artificial intelligence (AI) has transformed various fields, including healthcare, with the potential to improve patient care and quality of life. Rapid AI advancements can revolutionize healthcare by integrating it into clinical practice. Reporting AI's role in clinical practice is crucial for successful implementation by equipping healthcare providers with essential knowledge and tools.

RESEARCH SIGNIFICANCE

This review article provides a comprehensive and up-to-date overview of the current state of AI in clinical practice, including its potential applications in disease diagnosis, treatment recommendations, and patient engagement. It also discusses the associated challenges, covering ethical and legal considerations and the need for human expertise. By doing so, it enhances understanding of AI's significance in healthcare and supports healthcare organizations in effectively adopting AI technologies.

MATERIALS AND METHODS

The current investigation analyzed the use of AI in the healthcare system with a comprehensive review of relevant indexed literature, such as PubMed/Medline, Scopus, and EMBASE, with no time constraints but limited to articles published in English. The focused question explores the impact of applying AI in healthcare settings and the potential outcomes of this application.

RESULTS

Integrating AI into healthcare holds excellent potential for improving disease diagnosis, treatment selection, and clinical laboratory testing. AI tools can leverage large datasets and identify patterns to surpass human performance in several healthcare aspects. AI offers increased accuracy, reduced costs, and time savings while minimizing human errors. It can revolutionize personalized medicine, optimize medication dosages, enhance population health management, establish guidelines, provide virtual health assistants, support mental health care, improve patient education, and influence patient-physician trust.

CONCLUSION

AI can be used to diagnose diseases, develop personalized treatment plans, and assist clinicians with decision-making. Rather than simply automating tasks, AI is about developing technologies that can enhance patient care across healthcare settings. However, challenges related to data privacy, bias, and the need for human expertise must be addressed for the responsible and effective implementation of AI in healthcare.

Crohn's Disease Prediction Using Sequence Based Machine Learning Analysis of Human Microbiome

Human microbiota refers to the trillions of microorganisms that inhabit our bodies and have been discovered to have a substantial impact on human health and disease. By sampling the microbiota, it is possible to generate massive quantities of data for analysis using Machine Learning algorithms. In this study, we employed several modern Machine Learning techniques to predict Inflammatory Bowel Disease using raw sequence data. The dataset was obtained from NCBI preprocessed graph representations and converted into a structured form. Seven well-known Machine Learning frameworks, including Random Forest, Support Vector Machines, Extreme Gradient Boosting, Light Gradient Boosting Machine, Gaussian Naïve Bayes, Logistic Regression, and k-Nearest Neighbor, were used. Grid Search was employed for hyperparameter optimization. The performance of the Machine Learning models was evaluated using various metrics such as accuracy, precision, fscore, kappa, and area under the receiver operating characteristic curve. Additionally, Mc Nemar's test was conducted to assess the statistical significance of the experiment. The data was constructed using k-mer lengths of 3, 4 and 5. The Light Gradient Boosting Machine model overperformed over other models with 67.24%, 74.63% and 76.47% accuracy for k-mer lengths of 3, 4 and 5, respectively. The LightGBM model also demonstrated the best performance in each metric. The study showed promising results predicting disease from raw sequence data. Finally, Mc Nemar's test results found statistically significant differences between different Machine Learning approaches.

Accurate noise-robust classification of Bacillus species from MALDI-TOF MS spectra using a denoising autoencoder

Bacillus strains are ubiquitous in the environment and are widely used in the microbiological industry as valuable enzyme sources, as well as in agriculture to stimulate plant growth. The Bacillus genus comprises several closely related groups of species. The rapid classification of these remains challenging using existing methods. Techniques based on MALDI-TOF MS data analysis hold significant promise for fast and precise microbial strains classification at both the genus and species levels. In previous work, we proposed a geometric approach to Bacillus strain classification based on mass spectra analysis via the centroid method (CM). One limitation of such methods is the noise in MS spectra. In this study, we used a denoising autoencoder (DAE) to improve bacteria classification accuracy under noisy MS spectra conditions. We employed a denoising autoencoder approach to convert noisy MS spectra into latent variables representing molecular patterns in the original MS data, and the Random Forest method to classify bacterial strains by latent variables. Comparison of the DAE-RF with the CM method using the artificially noisy test samples showed that DAE-RF offers higher noise robustness. Hence, the DAE-RF method could be utilized for noise-robust, fast, and neat classification of Bacillus species according to MALDI-TOF MS data.

Differentiation between Weissella cibaria and Weissella confusa Using Machine-Learning-Combined MALDI-TOF MS

Although Weissella cibaria and W. confusa are essential food-fermenting bacteria, they are also opportunistic pathogens. Despite these species being commercially crucial, their taxonomy is still based on inaccurate identification methods. In this study, we present a novel approach for identifying two important Weissella species, W. cibaria and W. confusa, by combining matrix-assisted laser desorption/ionization and time-of-flight mass spectrometer (MALDI-TOF MS) data using machine-learning techniques. After on- and off-plate protein extraction, we observed that the BioTyper database misidentified or could not differentiate Weissella species. Although Weissella species exhibited very similar protein profiles, these species can be differentiated on the basis of the results of a statistical analysis. To classify W. cibaria, W. confusa, and non-target Weissella species, machine learning was used for 167 spectra, which led to the listing of potential species-specific mass-to-charge (m/z) loci. Machine-learning techniques including artificial neural networks, principal component analysis combined with the K-nearest neighbor, support vector machine (SVM), and random forest were used. The model that applied the Radial Basis Function kernel algorithm in SVM achieved classification accuracy of 1.0 for training and test sets. The combination of MALDI-TOF MS and machine learning can efficiently classify closely-related species, enabling accurate microbial identification.

Antimicrobial resistance and machine learning: past, present, and future

Machine learning has become ubiquitous across all industries, including the relatively new application of predicting antimicrobial resistance. As the first bibliometric review in this field, we expect it to inspire further research in this area. The review employs standard bibliometric indicators such as article count, citation count, and the Hirsch index (H-index) to evaluate the relevance and impact of the leading countries, organizations, journals, and authors in this field. VOSviewer and Biblioshiny programs are utilized to analyze citation and co-citation networks, collaboration networks, keyword co-occurrence, and trend analysis. The United States has the highest contribution with 254 articles, accounting for over 37.57% of the total corpus, followed by China (103) and the United Kingdom (78). Among 58 publishers, the top four publishers account for 45% of the publications, with Elsevier leading with 15% of the publications, followed by Springer Nature (12%), MDPI, and Frontiers Media SA with 9% each. Frontiers in Microbiology is the most frequent publication source (33 articles), followed by Scientific Reports (29 articles), PLoS One (17 articles), and Antibiotics (16 articles). The study reveals a substantial increase in research and publications on the use of machine learning to predict antibiotic resistance. Recent research has focused on developing advanced machine learning algorithms that can accurately forecast antibiotic resistance, and a range of algorithms are now being used to address this issue.

Rapid identification of carbapenem-resistant Klebsiella pneumoniae based on matrix-assisted laser desorption ionization time-of-flight mass spectrometry and an artificial neural network model

BACKGROUND

Carbapenem-resistant Klebsiella pneumoniae (CRKP) is a clinically critical pathogen that causes severe infection. Due to improper antibiotic administration, the prevalence of CRKP infection has been increasing considerably. In recent years, the utilization of matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) has enabled the identification of bacterial isolates at the families and species level. Moreover, machine learning (ML) classifiers based on MALDI-TOF MS have been recently considered a novel method to detect clinical antimicrobial-resistant pathogens.

METHODS

A total of 2683 isolates (369 CRKP cases and 2314 carbapenem-susceptible Klebsiella pneumoniae [CSKP]) collected in the clinical laboratories of Taipei Medical University Hospital (TMUH) were included in this study, and 80% of data was split into the training data set that were submitted for the ML model. The remaining 20% of data was used as the independent data set for external validation. In this study, we established an artificial neural network (ANN) model to analyze all potential peaks on mass spectrum simultaneously.

RESULTS

Our artificial neural network model for detecting CRKP isolates showed the best performance of area under the receiver operating characteristic curve (AUROC = 0.91) and of area under precision-recall curve (AUPRC = 0.90). Furthermore, we proposed the top 15 potential biomarkers in probable CRKP isolates at 2480, 4967, 12,362, 12,506, 12,855, 14,790, 15,730, 16,176, 16,218, 16,758, 16,919, 17,091, 18,142, 18,998, and 19,095 Da.

CONCLUSIONS

Compared with the prior MALDI-TOF and machine learning studies of CRKP, the amount of data in our study was more sufficient and allowing us to conduct external validation. With better generalization abilities, our artificial neural network model can serve as a reliable screening tool for CRKP isolates in clinical practice. Integrating our model into the current workflow of clinical laboratories can assist the rapid identification of CRKP before the completion of traditional antimicrobial susceptibility testing. The combination of MADLI-TOF MS and machine learning techniques can support physicians in selecting suitable antibiotics, which has the potential to enhance the patients' outcomes and lower the prevalence of antimicrobial resistance.

MALDI-TOF/MS Profiling of Whole Saliva and Gingival Crevicular Fluid in Patients with the Invisalign System and Fixed Orthodontic Appliances

The movement of teeth by orthodontic treatment with the Invisalign (IN) system and fixed orthodontic appliances (FOA) is characterized by the reconstruction of periodontal ligaments, alveolar bone, and gingiva. A reflection of these phenomena can be found in the composition of gingival crevicular fluid (GCF). A total of 90 samples from 45 participants (45 whole saliva and 45 GCF), including 15 patients with FOA, 15 patients with IN, and 15 patients with oral health, were subjected to matrix-assisted laser desorption/ionization mass spectrometry (MALDI-TOF/MS) analysis. Mass fingerprints were generated for each sample. Three models were tested: a quick classifier (QC), a genetic algorithm (GA), and a supervised neural network (SNN). For both groups of samples (saliva and GCF), the GA model showed the highest recognition abilities of 88.89% (saliva) and 95.56% (GCF). Differences between the treated (FOA and IN) groups and the control group in saliva and GCF samples were determined using cluster analysis. In addition, we monitored the effect of long-term orthodontic treatment (after 6 months) in the lag phase of orthodontic tooth movement. The results show increased levels of inflammatory markers (α-defensins), which may indicate an ongoing inflammatory process even after 21 days from force application.