Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning
Abstract Oral cancer may arise from oral leukoplakia and oral lichenoid mucositis (oral lichen planus and oral lichenoid lesions) subtypes of oral potentially malignant disorders. As not all patients will develop oral cancer in their lifetime, the availability of malignant transformation predictive...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2023-03-01
|
Series: | Journal of Big Data |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40537-023-00714-7 |
_version_ | 1797853755251621888 |
---|---|
author | John Adeoye Mohamad Koohi-Moghadam Siu-Wai Choi Li-Wu Zheng Anthony Wing Ip Lo Raymond King-Yin Tsang Velda Ling Yu Chow Abdulwarith Akinshipo Peter Thomson Yu-Xiong Su |
author_facet | John Adeoye Mohamad Koohi-Moghadam Siu-Wai Choi Li-Wu Zheng Anthony Wing Ip Lo Raymond King-Yin Tsang Velda Ling Yu Chow Abdulwarith Akinshipo Peter Thomson Yu-Xiong Su |
author_sort | John Adeoye |
collection | DOAJ |
description | Abstract Oral cancer may arise from oral leukoplakia and oral lichenoid mucositis (oral lichen planus and oral lichenoid lesions) subtypes of oral potentially malignant disorders. As not all patients will develop oral cancer in their lifetime, the availability of malignant transformation predictive platforms would assist in the individualized treatment planning and formulation of optimal follow-up regimens for these patients. Therefore, this study aims to compare and select optimal machine learning (ML)-based models for stratifying the malignant transformation status of patients with oral leukoplakia and oral lichenoid mucositis. One thousand one hundred and eighty-seven patients with oral leukoplakia and oral lichenoid mucositis treated at three tertiary health institutions in Hong Kong, Newcastle UK, and Lagos Nigeria were included in the study. Demographic, clinical, pathological, and treatment-based factors obtained at diagnosis and during follow-up were used to populate and compare forty-six machine learning-based models. These were implemented as a set of twenty-six predictors for centers with substantial data quantity and fifteen predictors for centers with insufficient data. Two best models were selected according to the number of variables. We found that the optimal ML-based risk models with twenty-six and fifteen predictors achieved an accuracy of 97% and 94% respectively following model testing. Upon external validation, both models achieved a sensitivity, specificity, and F1-score of 1, 0.88, and 0.67 on consecutive patients treated after the construction of the models. Furthermore, the 15-predictor ML model for centers with reduced data achieved a higher sensitivity for identifying oral leukoplakia and oral lichenoid mucositis patients that developed malignancies in other treatment settings compared to the binary oral epithelial dysplasia system for risk stratification (0.96 vs 0.82). These findings suggest that machine learning-based models could be useful potentially to stratify patients with oral leukoplakia and oral lichenoid mucositis according to their risk of malignant transformation in different settings. |
first_indexed | 2024-04-09T19:55:52Z |
format | Article |
id | doaj.art-f18f545ec3b54e3c9ea5ba566b9c6927 |
institution | Directory Open Access Journal |
issn | 2196-1115 |
language | English |
last_indexed | 2024-04-09T19:55:52Z |
publishDate | 2023-03-01 |
publisher | SpringerOpen |
record_format | Article |
series | Journal of Big Data |
spelling | doaj.art-f18f545ec3b54e3c9ea5ba566b9c69272023-04-03T05:30:22ZengSpringerOpenJournal of Big Data2196-11152023-03-0110112410.1186/s40537-023-00714-7Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learningJohn Adeoye0Mohamad Koohi-Moghadam1Siu-Wai Choi2Li-Wu Zheng3Anthony Wing Ip Lo4Raymond King-Yin Tsang5Velda Ling Yu Chow6Abdulwarith Akinshipo7Peter Thomson8Yu-Xiong Su9Division of Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong KongDivision of Applied Oral Sciences and Community Dental Care, Faculty of Dentistry, The University of Hong KongDepartment of Orthopedics and Traumatology, Li Ka Shing Faculty of Medicine, The University of Hong KongDivision of Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong KongDepartment of Pathology, Queen Mary HospitalDivision of Otorhinolaryngology, Department of Surgery, Li Ka Shing Faculty of Medicine, The University of Hong KongDivision of Head and Neck Surgery, Department of Surgery, Li Ka Shing Faculty of Medicine, The University of Hong KongDepartment of Oral and Maxillofacial Pathology and Biology, Faculty of Dental Sciences, University of LagosCollege of Medicine and Dentistry, James Cook UniversityDivision of Oral and Maxillofacial Surgery, Faculty of Dentistry, The University of Hong KongAbstract Oral cancer may arise from oral leukoplakia and oral lichenoid mucositis (oral lichen planus and oral lichenoid lesions) subtypes of oral potentially malignant disorders. As not all patients will develop oral cancer in their lifetime, the availability of malignant transformation predictive platforms would assist in the individualized treatment planning and formulation of optimal follow-up regimens for these patients. Therefore, this study aims to compare and select optimal machine learning (ML)-based models for stratifying the malignant transformation status of patients with oral leukoplakia and oral lichenoid mucositis. One thousand one hundred and eighty-seven patients with oral leukoplakia and oral lichenoid mucositis treated at three tertiary health institutions in Hong Kong, Newcastle UK, and Lagos Nigeria were included in the study. Demographic, clinical, pathological, and treatment-based factors obtained at diagnosis and during follow-up were used to populate and compare forty-six machine learning-based models. These were implemented as a set of twenty-six predictors for centers with substantial data quantity and fifteen predictors for centers with insufficient data. Two best models were selected according to the number of variables. We found that the optimal ML-based risk models with twenty-six and fifteen predictors achieved an accuracy of 97% and 94% respectively following model testing. Upon external validation, both models achieved a sensitivity, specificity, and F1-score of 1, 0.88, and 0.67 on consecutive patients treated after the construction of the models. Furthermore, the 15-predictor ML model for centers with reduced data achieved a higher sensitivity for identifying oral leukoplakia and oral lichenoid mucositis patients that developed malignancies in other treatment settings compared to the binary oral epithelial dysplasia system for risk stratification (0.96 vs 0.82). These findings suggest that machine learning-based models could be useful potentially to stratify patients with oral leukoplakia and oral lichenoid mucositis according to their risk of malignant transformation in different settings.https://doi.org/10.1186/s40537-023-00714-7Artificial intelligenceMachine learningOral leukoplakiaOral lichen planusOral lichenoid lesionsOral potentially malignant disorders |
spellingShingle | John Adeoye Mohamad Koohi-Moghadam Siu-Wai Choi Li-Wu Zheng Anthony Wing Ip Lo Raymond King-Yin Tsang Velda Ling Yu Chow Abdulwarith Akinshipo Peter Thomson Yu-Xiong Su Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning Journal of Big Data Artificial intelligence Machine learning Oral leukoplakia Oral lichen planus Oral lichenoid lesions Oral potentially malignant disorders |
title | Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
title_full | Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
title_fullStr | Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
title_full_unstemmed | Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
title_short | Predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
title_sort | predicting oral cancer risk in patients with oral leukoplakia and oral lichenoid mucositis using machine learning |
topic | Artificial intelligence Machine learning Oral leukoplakia Oral lichen planus Oral lichenoid lesions Oral potentially malignant disorders |
url | https://doi.org/10.1186/s40537-023-00714-7 |
work_keys_str_mv | AT johnadeoye predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT mohamadkoohimoghadam predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT siuwaichoi predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT liwuzheng predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT anthonywingiplo predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT raymondkingyintsang predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT veldalingyuchow predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT abdulwarithakinshipo predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT peterthomson predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning AT yuxiongsu predictingoralcancerriskinpatientswithoralleukoplakiaandorallichenoidmucositisusingmachinelearning |