Citation: López-Cortés, X.A.;
Matamala, F.; Venegas, B.; Rivera, C.
Machine-Learning Applications in
Oral Cancer: A Systematic Review.
Appl. Sci. 2022, 12, 5715. https://
doi.org/10.3390/app12115715
Academic Editors: Alberta Lucchese,
Dario Di Stasio and Gianrico
Spagnuolo
Received: 7 December 2021
Accepted: 31 May 2022
Published: 4 June 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
applied
sciences
Review
Machine-Learning Applications in Oral Cancer: A
Systematic Review
Xaviera A. López-Cortés
1,
* , Felipe Matamala
1
, Bernardo Venegas
2
and César Rivera
3
1
Department of Computer Sciences and Industries, Universidad Católica del Maule, Talca 3480112, Chile;
pipexmatamala@gmail.com
2
Department of Stomatology, Faculty of Health Sciences, Universidad de Talca, Talca 3460000, Chile;
bvenegas@utalca.cl
3
Department of Basic Biomedical Sciences, Faculty of Health Sciences, Universidad de Talca,
Talca 3460000, Chile; cerivera@utalca.cl
* Correspondence: xlopez@ucm.cl
Abstract: Over the years, several machine-learning applications have been suggested to assist in
various clinical scenarios relevant to oral cancer. We offer a systematic review to identify, assess,
and summarize the evidence for reported uses in the areas of oral cancer detection and prevention,
prognosis, pre-cancer, treatment, and quality of life. The main algorithms applied in the context of oral
cancer applications corresponded to SVM, ANN, and LR, comprising 87.71% of the total published
articles in the field. Genomic, histopathological, image, medical/clinical, spectral, and speech data
were used most often to predict the four areas of application found in this review. In conclusion,
our study has shown that machine-learning applications are useful for prognosis, diagnosis, and
prevention of potentially malignant oral lesions (pre-cancer) and therapy. Nevertheless, we strongly
recommended the application of these methods in daily clinical practice.
Keywords: oral cancer; OSCC; machine learning; applications
1. Introduction
Oral cancer has emerged as a serious public health issue across the world. According
to the literature, the global incidence, mortality, and disability-adjusted life years of this
disease increased by nearly 1.0-fold between 1990 and 2017 [1]. Based on the GLOBOCAN
estimates of incidence and mortality, 377,713 new cases and 177,757 deaths for lip and oral
cavity cancer were reported for the year 2020 [2]. Most oral cancers are squamous cell
carcinomas, which is an aggressive disease with a high tendency to metastasize locally and
to distant sites. It has a considerable impact on a patient’s life and on society as a whole.
Oral cancer has a 5-year overall survival rate of just approximately 51.7 percent due to
frequently late diagnosis [3].
The methods used for oral cancer diagnosis include the traditional anamnesis and
clinical examination, complemented with image and hematoxylin–eosin histopathologi-
cal analysis, the latter being the most common method [4,5]. Immunohistochemistry is
routinely used to distinguish the disease in more complex instances and to aid in disease
staging. For its examination, molecular approaches have been devised with the goal of
finding biomarkers that can anticipate early alterations. In situ hybridization, gel elec-
trophoresis and blotting, flow cytometry, mass spectrometry, polymerase chain reaction,
microarrays, Sanger sequencing, and next-generation sequencing are common techniques
employed in molecular diagnostics of oral squamous cell carcinomas [6].
In the practice of clinical medicine and in all health-related tasks, the diagnostic
process is critical. A correct diagnostic evaluation is essential for the effectiveness of disease
therapy. This diagnostic process is based on the interpretation of information supplied by
the patient in the anamnesis, as well as the clinician’s clinical examination, in addition to
Appl. Sci. 2022, 12, 5715. https://doi.org/10.3390/app12115715 https://www.mdpi.com/journal/applsci