EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY-NC 4.0

A systematic review of machine learning on clinical MALDI-TOF MS

Lucía Schmidt-Santiago iD, Alejandro Guerrero-López iD, Carlos Sevilla-Salcedo iD, David Rodríguez-Temporal iD, Belén Rodríguez-Sánchez iD, Vanessa Gómez-Verdejo iD

Briefings in Bioinformatics · 03.05.2026 · 27 (3)

DOI: 10.1093/bib/bbag208 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift Briefings in Bioinformatics, online erschienen am 08.05.2026. Verfasst von Lucía Schmidt-Santiago und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. Universidad, 30, E-28911 Leganés, Spain. Hauptthemen laut MEDLINE: Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization, Machine Learning, Bacteria. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 169 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Ministry of Science, Innovation and Universities-Agencia Estatal de Investigación, the Community of Madrid, European Union's Horizon Europe programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Spectrometry, Mass, Matrix-Assisted Laser Desorption-IonizationMachine LearningBacteriaHumansRandom Forest

Stichwörter der Autor:innen

MALDI-TOF MSantimicrobial resistancebacterial identificationbacterial typingdeep learningmachine learning

Autor:innen und Institutionen

  • Department of Signal Theory and Communications, Universidad Carlos III de Madrid, Avda. Universidad, 30, E-28911 Leganés, Spain.
  • Institute for Medical Microbiology, University of Zurich, Gloriastrasse 30, CH-8006 Zurich, Switzerland.
  • Department of Clinical Microbiology and Infectious Diseases, Gregorio Marañón Health Research Institute, Hospital General Universitario Gregorio Marañón, C. del Dr. Esquerdo 46, E-28007 Madrid, Spain.
  • Signal Processing Group, Gregorio Marañón Health Research Institute, Hospital General Universitario Gregorio Marañón, C. del Dr. Esquerdo 46, E-28007 Madrid, Spain.

ORCID-Profile: Lucía Schmidt-Santiago, Alejandro Guerrero-López, Carlos Sevilla-Salcedo, David Rodríguez-Temporal, Belén Rodríguez-Sánchez, Vanessa Gómez-Verdejo

Förderung

  • Ministry of Science, Innovation and Universities-Agencia Estatal de Investigación
  • the Community of Madrid
  • European Union's Horizon Europe programme
  • Marie Skłodowska-Curie Actions Postdoctoral Fellowship
  • Comunidad de Madrid's 2025 Cesar Nombela program
  • Ministry of Science, Innovation and Universities—Agencia Estatal de Investigación
  • European Union’s Horizon Europe programme
  • Comunidad de Madrid’s 2025 Cesar Nombela program

Zitieren

APA

Schmidt-Santiago, L., Guerrero-López, A., Sevilla-Salcedo, C., Rodríguez-Temporal, D., Rodríguez-Sánchez, B., & Gómez-Verdejo, V. (2026). A systematic review of machine learning on clinical MALDI-TOF MS. Briefings in Bioinformatics, 27(3). https://doi.org/10.1093/bib/bbag208

Vancouver

Schmidt-Santiago L, Guerrero-López A, Sevilla-Salcedo C, Rodríguez-Temporal D, Rodríguez-Sánchez B, Gómez-Verdejo V. A systematic review of machine learning on clinical MALDI-TOF MS. Briefings in Bioinformatics. 2026;27(3). doi:10.1093/bib/bbag208

BibTeX
@article{SchmidtSantiago2026,
  author = {Schmidt-Santiago, Lucía and Guerrero-López, Alejandro and Sevilla-Salcedo, Carlos and Rodríguez-Temporal, David and Rodríguez-Sánchez, Belén and Gómez-Verdejo, Vanessa},
  title = {A systematic review of machine learning on clinical MALDI-TOF MS},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {3},
  doi = {10.1093/bib/bbag208}
}
Kostenlos starten →