A Scoping Review of Infrared Spectroscopy and Machine Learning Methods for Head and Neck Precancer and Cancer Diagnosis and Prognosis
Ein Scoping Review zu Infrarotspektroskopie und Machine-Learning-Methoden für Diagnose und Prognose von Präkanzer und Krebs im Kopf-Hals-Bereich
Cancers · 26.02.2025 · 17 (5) · 796
DOI: 10.3390/cancers17050796 ↗Auf einen Blick
14 Studien untersuchten die Kombination von Infrarotspektroskopie und Machine Learning für Diagnose und Prognose von Kopf-Hals-Präkanzer und -krebs. Für orale Krebsdiagnostik wurden hohe Sensitivität, Spezifität und Genauigkeit berichtet.
Fragestellung
Wie werden Machine-Learning-Methoden mit Infrarotspektroskopie für Diagnose und Prognose von Kopf-Hals-Präkanzer und -krebs eingesetzt?
Methode
Scoping Review; Suche in MEDLINE, Embase und Scopus bis 14. Januar 2024.
Ergebnisse
14 Studien erfüllten die Kriterien. Genutzt wurden u. a. FTIR, ATR-FTIR, Nahinfrarot- und Synchrotron-IR-Mikrospektroskopie sowie LDA, SVM und weitere ML-Methoden.
Einschränkungen
Begrenzte Stichprobengrößen schränken die Generalisierbarkeit ein.
Schlussfolgerung der Autor:innen
Die Kombination von Infrarotspektroskopie und ML zeigt ein vielversprechendes Potenzial für Diagnose und Prognose von Kopf-Hals-Präkanzer und -krebs.
Kernaussagen
- 14 Studien zu IR-Spektroskopie plus ML bei Kopf-Hals-Präkanzer und -krebs
- Für orale Krebsdiagnostik wurden Sensitivität und Spezifität bis 100 % berichtet
- Die Autor:innen nennen begrenzte Stichprobengrößen als Einschränkung
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Übersichtsarbeit in der Zeitschrift Cancers, online erschienen am 26.02.2025. Verfasst von Shahd A Alajaji und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oncology and Diagnostic Sciences, School of Dentistry, University of Maryland, 650 W. Baltimore Street, 7 Floor, Baltimore, MD 21201, U…. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDCR NIH HHS, NIH/National Institute of Dental and Craniofacial Research.
Abstract (Originalsprache)
Objectives
This scoping review aimed to provide both researchers and practitioners with an overview of how machine learning (ML) methods are applied to infrared spectroscopy for the diagnosis and prognosis of head and neck precancer and cancer.
Methods
A subject headings and keywords search was conducted in MEDLINE, Embase, and Scopus on 14 January 2024, using predefined search algorithms targeting studies that integrated infrared spectroscopy and ML methods in head and neck precancer/cancer research. The results were managed through the COVIDENCE systematic review platform.
Results
Fourteen studies met the eligibility criteria, which were defined by IR spectroscopy techniques, ML methodology, and a focus on head and neck precancer/cancer research involving human subjects. The IR spectroscopy techniques used in these studies included Fourier transform infrared (FTIR) spectroscopy and imaging, attenuated total reflection-FTIR, near-infrared spectroscopy, and synchrotron-based infrared microspectroscopy. The investigated human biospecimens included tissues, exfoliated cells, saliva, plasma, and urine samples. ML methods applied in the studies included linear discriminant analysis (LDA), principal component analysis with LDA, partial least squares discriminant analysis, orthogonal partial least squares discriminant analysis, support vector machine, extreme gradient boosting, canonical variate analysis, and deep reinforcement neural network. For oral cancer diagnosis applications, the highest sensitivity and specificity were reported to be 100%, the highest accuracy was reported to be 95–96%, and the highest area under the curve score was reported to be 0.99. For oral precancer prognosis applications, the highest sensitivity and specificity were reported to be 84% and 79%, respectively.
Conclusions
This review highlights the promising potential of integrating infrared spectroscopy with ML methods for diagnosing and prognosticating head and neck precancer and cancer. However, the limited sample sizes in existing studies restrict generalizability of the study findings. Future research should prioritize larger datasets and the development of advanced ML models to enhance reliability and robustness of these tools.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oncology and Diagnostic Sciences, School of Dentistry, University of Maryland, 650 W. Baltimore Street, 7 Floor, Baltimore, MD 21201, USA.
- Department of Oral Medicine and Diagnostic Sciences, College of Dentistry, King Saud University, Riyadh 12371, Saudi Arabia.
- Division of Artificial Intelligence Research, University of Maryland School of Dentistry, Baltimore, MD 21201, USA.
- Department of Restorative Dentistry, Rutgers School of Dental Medicine, Newark, NJ 07103, USA.
- Department of Oral and Craniofacial Sciences, School of Dentistry, University of Missouri Kansas City, Kansas City, MO 64108, USA.
- University of Maryland Marlene and Stewart Greenebaum Comprehensive Cancer Center, Baltimore, MD 21201, USA.
ORCID-Profile: Shahd A Alajaji, Yong Wang, Ahmed S Sultan, Rong Wang
Förderung
- NIDCR NIH HHS
- NIH/National Institute of Dental and Craniofacial Research
Zitieren
APA
Alajaji, S. A., Sabzian, R., Wang, Y., Sultan, A. S., & Wang, R. (2025). A Scoping Review of Infrared Spectroscopy and Machine Learning Methods for Head and Neck Precancer and Cancer Diagnosis and Prognosis. Cancers, 17(5), 796. https://doi.org/10.3390/cancers17050796
Vancouver
Alajaji SA, Sabzian R, Wang Y, Sultan AS, Wang R. A Scoping Review of Infrared Spectroscopy and Machine Learning Methods for Head and Neck Precancer and Cancer Diagnosis and Prognosis. Cancers. 2025;17(5):796. doi:10.3390/cancers17050796
BibTeX
@article{Alajaji2025,
author = {Alajaji, Shahd A and Sabzian, Roya and Wang, Yong and Sultan, Ahmed S and Wang, Rong},
title = {A Scoping Review of Infrared Spectroscopy and Machine Learning Methods for Head and Neck Precancer and Cancer Diagnosis and Prognosis},
journal = {Cancers},
year = {2025},
volume = {17},
number = {5},
pages = {796},
doi = {10.3390/cancers17050796}
}
EUVIMED