Bacterial identification, antimicrobial resistance prediction, and strain typification are critical tasks in clinical microbiology, essential for guiding patient treatment and controlling the spread of infectious diseases. While machine learning (ML) has shown immense promise in enhancing Matrix-Assisted Laser Desorption/Ionization-Time of Flight Mass Spectrometry (MALDI-TOF MS) applications for these tasks, there is currently no comprehensive review that fully addresses this from a technical ML perspective. To address this gap, we systematically reviewed 115 studies published between 2004 and 2025, focusing on key ML aspects such as data size and balance, preprocessing pipelines, model selection and evaluation, open-source data, and code availability. Our analysis highlights the predominant use of classical ML models like Random Forest and Support Vector Machines, alongside emerging interest in deep learning approaches for handling complex, high-dimensional data. Despite significant progress, challenges such as inconsistent preprocessing workflows, reliance on black-box models, limited external validation, and insufficient open-source resources persist, hindering transparency, reproducibility, and broader adoption. This review offers actionable insights to enhance ML-driven bacterial diagnostics, advocating for standardized methodologies, greater transparency, and improved data accessibility. In addition, we provide guidelines on how to approach ML for MALDI-TOF MS analysis, helping researchers navigate key decisions in model development and evaluation.

Multi-objective Bayesian optimization (MOBO) is a powerful framework for optimizing black-box functions with conflicting objectives and costly evaluations. A key component in MOBO is the probabilistic surrogate model used to guide the search for the optimum. A simple approach is to use independent Gaussian processes (GPs), one per objective. A more powerful method is to use multi-output GPs, such as those based on the intrinsic coregionalization model (ICM), to exploit correlations between objectives. However, with this model, often independent observation noise across objectives is assumed, which ignores part of the correlation structure. In this work, we isolate and analyze the role of observational noise in MOBO with ICM-based multi-output GPs. We consider models that can capture correlations in the observational noise, and study how the presence and structure of noise affect the joint predictive distribution, the considered acquisition function, and ultimately the optimization performance.Through theoretical analysis and extensive synthetic and real-world experiments, we show that multi-output GPs can significantly improve optimization efficiency when the evaluations are noisy. Importantly, however, when the evaluations are noiseless, we observe, both theoretically and empirically, only small gains by considering multi-output GPs, and cheaper independent GPs may be preferred. Furthermore, our synthetic experiments show that explicitly modeling noise correlations provides additional advantages when the objectives themselves are negatively correlated. In real-world problems, however, we have observed mixed results regarding modeling noise correlations. There are small gains in an ensemble benchmark and clearer gains, similar to those observed in the synthetic experiments, in a neural-network benchmark. These findings provide practical insights into when and how to use ICMs for MOBO.

BACKGROUND: Clostridioides difficile is a major cause of hospital-acquired diarrhea and a driver of nosocomial outbreaks, yet rapid, accurate ribotype identification remains challenging. We sought to develop a MALDI-TOF MS-based workflow coupled with machine learning to distinguish epidemic toxigenic ribotypes (RT027 and RT181) from other strains in real time. RESULTS: We analyzed MALDI-TOF spectra from 379 clinical isolates collected across ten Spanish hospitals and identified seven discriminant biomarker peaks. Two peaks (2463 and 4993 m/z) were uniquely associated with RT027, while combinations of five additional peaks reliably identified RT181. Our classifiers-implemented both in the commercial Clover MSDAS platform and the open-access AutoCdiff web tool-achieved up to 100% balanced accuracy in ribotype assignment and proved robust in real-time outbreak simulations. CONCLUSIONS: This study demonstrates that MALDI-TOF MS combined with tailored machine learning can deliver rapid, high-precision ribotype identification for C. difficile. The freely available AutoCdiff models ( https://bacteria.id ) offer an immediately deployable solution for clinical laboratories, with the potential to enhance outbreak surveillance and control.

This paper introduces a novel approach to learn multi-task regression models with constrained architecture complexity. The proposed model, named RFF-BLR, consists of a randomised feedforward neural network with two fundamental characteristics: a single hidden layer whose units implement the random Fourier features that approximate an RBF kernel, and a Bayesian formulation that optimises the weights connecting the hidden and output layers. The RFF-based hidden layer inherits the robustness of kernel methods. The Bayesian formulation enables promoting multioutput sparsity: all tasks interplay during the optimisation to select a compact subset of the hidden layer units that serve as common non-linear mapping for every tasks. The experimental results show that the RFF-BLR framework can lead to significant performance improvements compared to the state-of-the-art methods in multitask nonlinear regression, especially in small-sized training dataset scenarios.

Adaptive learning is necessary for nonstationary environments where the learning machine needs to forget past data distribution. Efficient algorithms require a compact model update to not grow in computational burden with the incoming data and with the lowest possible computational cost for online parameter updating. Existing solutions only partially cover these needs. Here, we propose the first adaptive sparse Gaussian process (GP) able to address all these issues. We first reformulate a variational sparse GP (VSGP) algorithm to make it adaptive through a forgetting factor. Next, to make the model inference as simple as possible, we propose updating a single inducing point of the SGP model together with the remaining model parameters every time a new sample arrives. As a result, the algorithm presents a fast convergence of the inference process, which allows an efficient model update (with a single inference iteration) even in highly nonstationary environments. Experimental results demonstrate the capabilities of the proposed algorithm and its good performance in modeling the predictive posterior in mean and confidence interval estimation compared to state-of-the-art approaches.

Audio or visual data analysis tasks usually have to deal with high-dimensional and nonnegative signals. However, most data analysis methods suffer from overfitting and numerical problems when data have more than a few dimensions needing a dimensionality reduction preprocessing. Moreover, interpretability about how and why filters work for audio or visual applications is a desired property, especially when energy or spectral signals are involved. In these cases, due to the nature of these signals, the nonnegativity of the filter weights is a desired property to better understand its working. Because of these two necessities, we propose different methods to reduce the dimensionality of data while the nonnegativity and interpretability of the solution are assured. In particular, we propose a generalized methodology to design filter banks in a supervised way for applications dealing with nonnegative data, and we explore different ways of solving the proposed objective function consisting of a nonnegative version of the orthonormalized partial least-squares method. We analyze the discriminative power of the features obtained with the proposed methods for two different and widely studied applications: texture and music genre classification. Furthermore, we compare the filter banks achieved by our methods with other state-of-the-art methods specifically designed for feature extraction.

During the past years solar radiation prediction has become increasingly relevant among the scientific community and Machine Learning techniques have proven to be a useful tool to automatically learn an accurate prediction model. In this paper, we move one step further and try to gain interpretability during the learning process by introducing a novel feature selection approach. Our method trains a set of bootstrapped SVR classifiers to detect those features that are informative for the prediction task. This way we obtain a more robust set of selected features compared to other selection methods. This allows us to detect in a multivariate fashion not only the features needed to solve the prediction task, but also those that are informative for the problem at hand. The application of this algorithm to a Weather Research and Forecasting model, and its comparison to some state of the art tools, shows the advantages of the proposed method both in terms of resistance to overfitting, selection consistency and interpretability, while at the same time improving performance in terms of prediction accuracy.

Orthonormalized partial least squares (OPLS) is a popular multivariate analysis method to perform supervised feature extraction. In this paper, we propose a novel scheme to solve Orthonormalized Partial Least Squares (OPLS) that can be easily modified to include additional constraints over the input data projection vectors. This scheme is used to implement an OPLSmethod with sparsity constraints (SOPLS), which allows to obtain more interpretable projection vectors that depend only on a few of the original input variables. The discriminative power of the sparse features extracted by SOPLS is analyzed on a benchmark of classification problems, where the method shows very competitive performance in terms of classification error.

In this brief, we propose to increase the capabilities of standard real AdaBoost (RAB) architectures by replacing their linear combinations with a fusion controlled by a gate with fixed kernels. Experimental results in a series of well-known benchmark problems support the effectiveness of this approach in improving classification performance. Although the need for cross-validation processes obviously leads to higher training requirements and more computational effort, the operation load is never much higher; in many cases it is even lower than that of competitive RAB schemes.

This paper introduces a new support vector machine (SVM) formulation to obtain sparse solutions in the primal SVM parameters, providing a new method for feature selection based on SVMs. This new approach includes additional constraints to the classical ones that drop the weights associated to those features that are likely to be irrelevant. A ν-SVM formulation has been used, where ν indicates the fraction of features to be considered. This paper presents two versions of the proposed sparse classifier, a 2-norm SVM and a 1-norm SVM, the latter having a reduced computational burden with respect to the first one. Additionally, an explanation is provided about how the presented approach can be readily extended to multiclass classification or to problems where groups of features, rather than isolated features, need to be selected. The algorithms have been tested in a variety of synthetic and real data sets and they have been compared against other state of the art SVM-based linear feature selection methods, such as 1-norm SVM and doubly regularized SVM. The results show the good feature selection ability of the approaches.

This work explores the possibility of improving the performance of Real Adaboost ensemble classifiers by replacing their standard linear combination of learners by a gating scheme. This more powerful fusion method is defined following the epoch-by-epoch construction of boosting ensembles. Preliminary experimental results support the potential of this new approach.

Progressively emphasizing samples that are difficult to classify correctly is the base for the recognized high performance of real Adaboost (RA) ensembles. The corresponding emphasis function can be written as a product of a factor that measures the quadratic error and a factor related to the proximity to the classification border; this fact opens the door to explore the potential advantages provided by using adjustable combined forms of these factors. In this paper, we introduce a principled procedure to select the combination parameter each time a new learner is added to the ensemble, just by maximizing the associated edge parameter, calling the resulting method the dynamically adapted weighted emphasis RA (DW-RA). A number of application examples illustrates the performance improvements obtained by DW-RA.

The recent interest in combining neural networks has produced a variety of techniques. This paper deals with boosting methods, in particular, real AdaBoost schemes built up with radial basis function networks. Real Adaboost emphasis function can be divided into two different terms, the first only focus on the quadratic error of each pattern and the second only takes into account its "proximity" to the boundary. Incorporating to this fixed emphasis function an additional degree of freedom, that allows us to weight these two terms, and also to select the radial basis functions centroids according to the emphasized regions, we show performance improvements: an error rate reduction, a faster convergence, and overfitting robustness.