scholarly journals Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders

Cancers ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 6054
Author(s):  
John Adeoye ◽  
Mohamad Koohi-Moghadam ◽  
Anthony Wing Ip Lo ◽  
Raymond King-Yin Tsang ◽  
Velda Ling Yu Chow ◽  
...  
Keyword(s):  
Clinical Practice ◽  
Malignant Transformation ◽  
Cross Validation ◽  
Machine Intelligence ◽  
Oral Leukoplakia ◽  
Time To Event ◽  
Oral Potentially Malignant Disorders ◽  
Oral Lichenoid Lesions ◽  
Potentially Malignant Disorders ◽  
Potentially Malignant

Machine-intelligence platforms for the prediction of the probability of malignant transformation of oral potentially malignant disorders are required as adjunctive decision-making platforms in contemporary clinical practice. This study utilized time-to-event learning models to predict malignant transformation in oral leukoplakia and oral lichenoid lesions. A total of 1098 patients with oral white lesions from two institutions were included in this study. In all, 26 features available from electronic health records were used to train four learning algorithms—Cox-Time, DeepHit, DeepSurv, random survival forest (RSF)—and one standard statistical method—Cox proportional hazards model. Discriminatory performance, calibration of survival estimates, and model stability were assessed using a concordance index (c-index), integrated Brier score (IBS), and standard deviation of the averaged c-index and IBS following training cross-validation. This study found that DeepSurv (c-index: 0.95, IBS: 0.04) and RSF (c-index: 0.91, IBS: 0.03) were the two outperforming models based on discrimination and calibration following internal validation. However, DeepSurv was more stable than RSF upon cross-validation. External validation confirmed the utility of DeepSurv for discrimination (c-index—0.82 vs. 0.73) and RSF for individual survival estimates (0.18 vs. 0.03). We deployed the DeepSurv model to encourage incipient application in clinical practice. Overall, time-to-event models are successful in predicting the malignant transformation of oral leukoplakia and oral lichenoid lesions.

scholarly journals Coetaneous Presentation of Oral Leukoplakia and Oral Submucous Fibrosis with High Grade Dysplasia and Its Management with Lasers: A Case Report

2021 ◽  
Vol 6 (08) ◽  
pp. 464-469
Author(s):  
Preethi R ◽  
Malarkodi T ◽  
Arvind Krishnamurthy ◽  
Aravind Warrier S
Keyword(s):  
Malignant Transformation ◽  
Oral Submucous Fibrosis ◽  
Oral Leukoplakia ◽  
High Grade Dysplasia ◽  
High Grade ◽  
Oral Potentially Malignant Disorders ◽  
Oral Epithelial Dysplasia ◽  
Potentially Malignant Disorders ◽  
Potentially Malignant ◽  
Submucous Fibrosis

Oral potentially malignant disorders (OPMD) are diverse lesions associated with an increased likelihood for malignant transformation to oral cancer. The most frequently encountered OPMD in clinical practice are Oral Leukoplakia and oral submucous fibrosis (OSMF). The use of tobacco is consistently linked with leukoplakia and areca/betel nut with OSMF. Histopathological features of oral epithelial dysplasia, its varying grades are of immense clinical significance to evaluate its ability for malignant transformation. We report a case of homogenous leukoplakia and OSMF, two oral potentially malignant disorders occurring at the same site with high-grade dysplasia and its management using lasers.

scholarly journals DNA Methylation Patterns in Saliva of Tobacco users with High-Risk Oral Potentially Malignant Disorders

2021 ◽  
pp. 129-137
Author(s):  
Mimansha Patel ◽  
Madhuri Nitin Gawande ◽  
Minal Shashikant Chaudhary ◽  
Alka Harish Hande
Keyword(s):  
Dna Methylation ◽  
High Risk ◽  
Malignant Transformation ◽  
Promoter Methylation ◽  
Genomic Dna ◽  
Premalignant Lesions ◽  
Oral Potentially Malignant Disorders ◽  
Potentially Malignant Disorders ◽  
Potentially Malignant ◽  
Methylation Patterns

Background: “Oral Potentially Malignant Disorder (OPMD)” is a well-known symptom that, if untreated, can be carcinogenic. It includes leukoplakia, erythroplakia or erythroleukoplakia. One of the typical premalignant lesions of the oral cavity is “oral leukoplakias (OLs),” which frequently precedes “OSCCs.”OLs with dysplastic characteristics are considered to be at a higher risk of “malignant transformation.” So, early diagnosis of "oral squamous cell carcinomas (OSCCs)" is desperately required to enhance patient prognosis and quality of life (QOL).As a result, we examined the distinctive promoter methylation presence in high-risk OLs. Objectives: To detect, compare & correlate “DNA methylation” patterns in normal individuals, tobacco users without disease and tobacco users with the disease. Methodology: With the participants' full consent, 48 saliva samples were obtained and prepared. DNA isolation, restriction digestion of genomic DNA, extraction of restriction enzyme digested genomic DNA, Polymerase Chain Reaction (PCR), and Agarose Gel Electrophoresis (AGE) were all carried out. Expected results: This study will help us to assess the use of Saliva as an aid to identifying both high and low risk “Oral Potentially Malignant Disorders.” Conclusion: Peculiar promoter methylation of various genes was related to a high possibility of malignant transformation in OLs.

scholarly journals The role of interventional surgery in oral potentially malignant disorders

2014 ◽  
Vol 5 (2) ◽  
pp. 84-89 ◽  
Author(s):  
Peter Thomson
Keyword(s):  
Malignant Transformation ◽  
Scientific Literature ◽  
Squamous Carcinoma ◽  
Oral Potentially Malignant Disorders ◽  
Management Guidelines ◽  
Increased Risk ◽  
Potentially Malignant Disorders ◽  
Potentially Malignant ◽  
Rising Incidence

Oral potentially malignant disorders are mucosal diseases with a significantly increased risk of squamous carcinoma development – a lethal and deforming disease with rising incidence, especially in young people. Despite the ability to recognise pre-cancer disorders in patients, clinicians remain unable to predict individual mucosal lesion behaviour or quantify the risk of malignant transformation. No clear management guidelines exist and the available scientific literature is unable to answer the fundamental question: does early diagnosis and interventional management treat pre-cancer effectively and prevent malignant transformation?

scholarly journals Effect of smoking status and programmed death-ligand 1 expression on the microenvironment and malignant transformation of oral leukoplakia: A retrospective cohort study

PLoS ONE ◽  
2021 ◽  
Vol 16 (4) ◽  
pp. e0250359
Author(s):  
Takahiro Yagyuu ◽  
Naoki Funayama ◽  
Mitsuhiko Imada ◽  
Tadaaki Kirita
Keyword(s):  
Malignant Transformation ◽  
Smoking Status ◽  
Oral Leukoplakia ◽  
Oral Potentially Malignant Disorders ◽  
Programmed Death Ligand 1 ◽  
Programmed Death ◽  
Increased Risk ◽  
Potentially Malignant ◽  
Cd8 Cell ◽  
Smoking Group

Tobacco smoking is associated with an increased risk of oral leukoplakia and head and neck cancer. Although it has recently been reported that the establishment of an immunosuppressive microenvironment in oral potentially malignant disorders may lead to malignant transformation, it is unclear whether the microenvironments of oral potentially malignant disorders differ according to smoking status. We examined differences in programmed death-ligand 1 (PD-L1) expression and subepithelial CD163+ TAM and CD8+ cell/lymphocyte counts in the microenvironment of oral leukoplakia of smoking and non-smoking patients and investigated their associations with malignant transformation. Pathology reports and original biopsy request forms from 1995–2015 were retrospectively reviewed. Lesions clinically characterized as white plaques/lesions of the oral mucosa and pathologically diagnosed as oral epithelial dysplasia were included. Immunohistochemistry was performed to evaluate PD-L1 expression and subepithelial CD163+/CD8+ cell counts. The significance of prognostic factors in predicting malignant transformation was determined using Cox regression analysis. Statistical significance was defined as P<0.05. In total, 200 patients with oral leukoplakia were selected. The mean age at diagnosis was higher in non-smoking patients (n = 141; 66.9 years) than in smoking patients (n = 59; 60.5 years). The 5-year cumulative malignant transformation rate was higher in non-smoking patients than in smoking patients (9.3% vs. 3.0%, respectively). Oral leukoplakia was associated with significantly higher PD-L1 expression and increased numbers of subepithelial CD163+ cells in the non-smoking group compared with the smoking group. Non-smoking-related oral leukoplakia with positive PD-L1 expression was associated with a 6.97-fold (95% confidence interval: 2.14–22.7) increased risk of malignant transformation. The microenvironment of oral leukoplakia differed according to smoking status. A combination of smoking status and PD-L1 expression may predict malignant transformation in oral leukoplakia patients. This study highlights the importance of understanding the interaction between smoking and the microenvironment in oral leukoplakia.

Sign in / Sign up

Export Citation Format

Share Document