Prediction of malignant transformation in oral epithelial dysplasia using machine learning.

Autor:	Ingham J; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom., Smith CI; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom., Ellis BG; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom., Whitley CA; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom., Triantafyllou A; Department of Pathology, Liverpool Clinical Laboratories, University of Liverpool, L69 3GA, United Kingdom., Gunning PJ; Department of Molecular and Clinical Cancer Medicine, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, L3 9TA, United Kingdom., Barrett SD; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom., Gardener P; Manchester Institute of Biotechnology, University of Manchester, M1 7DN, United Kingdom., Shaw RJ; Department of Molecular and Clinical Cancer Medicine, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, L3 9TA, United Kingdom.; Regional Maxillofacial Unit, Liverpool University Hospitals NHS Foundation Trust, Liverpool, L9 7AL, United Kingdom., Risk JM; Department of Molecular and Clinical Cancer Medicine, Institute of Systems, Molecular and Integrative Biology, University of Liverpool, L3 9TA, United Kingdom., Weightman P; Department of Physics, University of Liverpool, L69 7ZE, United Kingdom.
Jazyk:	angličtina
Zdroj:	IOP SciNotes [IOP SciNotes] 2022 Sep 01; Vol. 3 (3), pp. 034001. Date of Electronic Publication: 2022 Oct 07.
DOI:	10.1088/2633-1357/ac95e2
Abstrakt:	A machine learning algorithm (MLA) has been applied to a Fourier transform infrared spectroscopy (FTIR) dataset previously analysed with a principal component analysis (PCA) linear discriminant analysis (LDA) model. This comparison has confirmed the robustness of FTIR as a prognostic tool for oral epithelial dysplasia (OED). The MLA is able to predict malignancy with a sensitivity of 84 ± 3% and a specificity of 79 ± 3%. It provides key wavenumbers that will be important for the development of devices that can be used for improved prognosis of OED. (© 2022 The Author(s). Published by IOP Publishing Ltd.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu