Malignant Transformation Of Oral Leukoplakia Research Articles

Cover Image

The cover image is based on the Original Article The role of differentiated dysplasia in the prediction of malignant transformation of oral leukoplakia by Leon J. Wils et al., https://doi.org/10.1111/jop.13483. Image Credit: Wim Vos.image

The role of differentiated dysplasia in the prediction of malignant transformation of oral leukoplakia.

Oral leukoplakia is the most common oral potentially malignant disorder. Malignant transformation of oral leukoplakia occurs at an annual rate of 1%-7%. WHO-defined classic epithelial dysplasia is an important predictor of malignant transformation of oral leukoplakia, but we have previously shown in a proof of concept study that prediction improves by incorporation of an architectural pattern of dysplasia, also coined as differentiated dysplasia. We aimed to analyze this finding in a larger cohort of patients. For this retrospective study 176 oral leukoplakia patients were included. Biopsies for all patients were assessed for the presence of dysplasia and analyzed for cytokeratin 13 and 17 expression. Moreover, the inter-observer agreement for the diagnosis of differentiated dysplasia was determined. In total, 33 of 176 patients developed oral squamous cell carcinoma during follow-up. Presence of classic epithelial dysplasia increased cancer risk two-fold (HR = 2.18, p = 0.026). Lesions without classic epithelial dysplasia could be further risk-stratified by the presence of differentiated dysplasia (HR = 7.36, p < 0.001). Combined classic epithelial and differentiated dysplasia imparted a seven-fold increased risk of malignant transformation (7.34, p = 0.001). Inter-observer agreement for the diagnosis of dysplasia, including differentiated dysplasia, was moderate (κ = 0.56, p < 0.001). This study emphasizes the importance of the recognition of the architectural pattern of differentiated dysplasia as a separate entity for risk prediction of malignant transformation of oral leukoplakia. Presence of any pattern of dysplasia results in accurate prediction of malignant transformation risk of oral leukoplakia.

Comprehensive bioinformatics analysis combined with experimental validation to screen biomarkers for malignant transformation of oral leukoplakia

Oral leukoplakia (OLK) is the most common potentially malignant disorders in the oral cavity. This study aimed to screen the key genes of OLK malignant transformation using the Gene Expression Omnibus (GEO) database and experiments. In this study, the GEO database was employed to screen OLK malignant transformation-related genes, which were subsequently identified with a series of bioinformatic analyses. External validation showed that the model based on LAPTM4B, NR3C1, and COX6A1 had high accuracy in diagnosing OLK malignant transformation. Furthermore, the DMBA-induced potentially malignant disorders and OSCC models in vivo and real-time PCR experiment in vitro further verified the database analysis results. In conclusion, three key genes (LAPTM4B, NR3C1, and COX6A1) were screened as potential biomarkers for the diagnosis and treatment of OLK malignant transformation.

Evaluation of salivary Chemerin in oral leukoplakia, oral squamous cell carcinoma and healthy controls

Introduction: Chemerin is a multifunctional chemoattractant cytokine, encoded by RARRES2 gene. Its role in oral carcinogenesis is largely unexplored. Study was undertaken to evaluate the role of salivary chemerin as a potential biomarker in the early diagnosis of oral cancer and to elucidate the clinicopathologic and prognostic significance of chemerin in different grades of Oral Squamous Cell Carcinoma (OSCC) and oral leukoplakia. Materials and Methods: The study comprised 96 subjects, divided into 3 groups, each consisting of 32 subjects. These groups were clinically and histopathologically diagnosed with OSCC, oral leukoplakia, and healthy controls, respectively. The whole unstimulated saliva (1.5 mL) was collected from the subjects using passive drool technique and immediately centrifuged at 3000 rpm for 10 minutes. The salivary chemerin level was estimated using the competitive sandwich enzyme-linked immunosorbent assay method. The statistical analysis was performed using R software EZR version 1.32. Independent t-tests, analysis of variance tests, and Scheffe Multiple Comparisons were carried out to compare quantitative parameters. A receiver operating characteristic (ROC) curve was plotted to assess diagnostic accuracy of salivary chemerin. Results: Significantly higher levels of salivary chemerin were observed in OSCC and oral leukoplakia patients compared to healthy controls (P &lt; 0.05). The study further established an increase in salivary chemerin concentration in different histological grades of OSCC and oral leukoplakia. ROC curve analysis suggested that salivary chemerin is a highly sensitive and specific indicator for early screening and detection of oral leukoplakia and OSCC. Conclusion: Salivary chemerin can be considered as a reliable and specific indicator for the early screening and detection of oral leukoplakia and OSCC and a highly sensitive biomarker which may aid in detection of malignant transformation of oral leukoplakia.

Malignant transformation rate of oral leukoplakia in the past 20 years: A systematic review and meta-analysis.

This meta-analysis aimed to assess the rate of malignant transformation (MT) of oral leukoplakia (OL) and to study potential risk factors for the MT of OL into oral squamous cell carcinoma (OSCC). We performed a bibliographic search on nine electronic databases, including PubMed, MEDLINE, and Wanfang Data, for data on the MT rate of OL. Possible risk factors were calculated using Comprehensive Meta-Analysis and Open Meta [Analyst] software. The pooled proportion of OL MT for the total population described in the 26 selected studies was 7.20% (95% confidence interval: 5.40-9.10%). Nonhomogeneous type lesions, higher grades of dysplasia, the location of the lesion (tongue and multifocal), and female sex had significant effects on the MT of OL. OL tended to develop into OSCC (7.2%), and those with significant MT risk factors should be subjected to regular follow-up and observation. However, we require large-scale prospective studies to validate these results, together with unified clinicopathological diagnostic criteria, standardized risk factor recording/assessment methods, and long-term follow-up guidelines.

Potential noninvasive biomarkers for the malignant transformation of oral leukoplakia: A systematic review and meta-analysis.

The rising cancer incidence in patients with oral leukoplakia (OL) highlights the importance of identifying potential biomarkers for high-risk individuals and lesions because these biomarkers are useful in developing personalized management strategies for OL patients. This study systematically searched and analyzed the literature on potential saliva and serum biomarkers for OL malignant transformation. PubMed and Scopus were searched for studies published up to April 2022. The primary outcome of this study was the difference in biomarker concentrations in saliva or serum samples from healthy control (HC), OL and oral cancer (OC) populations. Cohen's d with 95% credible interval was calculated and pooled using the inverse variance heterogeneity method. A total of seven saliva biomarkers were analyzed in this paper, including interleukin-1alpha, interleukin-6 (IL-6), interleukin-6-8, tumor necrosis factor alpha (TNF-α), copper, zinc, and lactate dehydrogenase. IL-6 and TNF-α exhibited statistically significant deviations in comparisons between HC versus OL and OL versus OC. A total of 13 serum biomarkers were analyzed, including IL-6, TNF-α, C-reactive protein, total cholesterol, triglycerides, high-density lipoproteins, low-density lipoproteins, albumin, protein, β2-microglobulin, fucose, lipid-bound sialic acid (LSA), and total sialic acid (TSA). LSA and TSA exhibited statistically significant deviations in comparisons between HC versus OL and OL versus OC. IL-6 and TNF-α in saliva have strong predictive values for OL deterioration, and LSA and TSA concentration levels in serum also have the potential to serve as biomarkers for OL deterioration.

A systems biology approach to uncover key genes and pathways mediating progression of leukoplakia to primary oral squamous cell carcinoma

ObjectiveOral squamous cell carcinoma (OSCC) counts for 90% of pathology in oral cavity cancer. Oral leukoplakia is the most frequent type of pre-invasive lesion leading to OSCC. An integrated bioinformatics analysis was performed to determine key genes and pathways deregulated in the malignant transformation of leukoplakia to primary OSCC. MethodsDifferentially expressed genes (DEGs) were determined in early OSCC compared to oral leukoplakia. A protein-protein interaction (PPI) network was constructed, clusters and hubs in the PPI network were identified, and prognostic hub genes in head and neck squamous cell carcinoma and OSCC were determined. The validation study was conducted for three of the markers at the protein level using the immunohistochemistry (IHC) assay. ResultsA total of 901 DEGs in primary OSCC compared to leukoplakia were identified. Also, 113 hub genes were determined in the PPI network. Twenty-two hubs were linked with the prognosis of HNSCC patients. The combination of seven genes including PLAU, FADD, SERPINE1, FOSL1, PLAUR, FST, and THBS1 illustrated the most considerable prognostic impact in HNSCC. IRF1 and MAP2K6 were the main TF and protein kinase involved in the malignant transformation of oral leukoplakia to primary OSCC. The most significant pathways and biological processes deregulated in primary OSCC were associated with the immune system. IHC study confirmed the upregulation of PLAU, SERPINE1, and SPP1 in primary OSCC. ConclusionsThe present results unraveled more details underlying the mechanisms involved in the malignant transformation of oral leukoplakia and may help the prognosis of patients with primary OSCC.

Development of a Pathomics-Based Model for the Prediction of Malignant Transformation in Oral Leukoplakia

Accurate prognostic stratification of oral leukoplakia (OLK) with risk of malignant transformation into oral squamous cell carcinoma is crucial. We developed an objective and powerful pathomics-based model for the prediction of malignant transformation in OLK using hematoxylin and eosin (H&E)-stained images. In total, 759 H&E-stained images from multicenter cohorts were included. A training set (n = 489), validation set (n = 196), and testing set (n = 74) were used for model development. Four deep learning methods were used to train and validate the model constructed using H&E-stained images. Pathomics features generated through deep learning combined with machine learning algorithms were used to develop a pathomics-based model. Immunohistochemical staining of Ki67, p53, and PD-L1 was used to interpret the black box of the model. Pathomics-based models predicted the malignant transformation of OLK (validation set area under curve [AUC], 0.899; testing set AUC, 0.813) and significantly identified high-risk and low-risk populations. The prediction performance of malignant transformation from dysplasia grading (validation set AUC, 0.743) was lower than that of the pathomics-based model. The expressions of Ki67, p53, and PD-L1 were correlated with various pathomics features. The pathomics-based model accurately predicted the malignant transformation of OLK and may be useful for the objective and rapid assessment of the prognosis of patients with OLK.

MALIGNANT TRANSFORMATION OF ORAL LEUKOPLAKIA – A REVIEW

Oral Leukoplakia is one of the most common oral premalignant lesions and dened as white patch or plaque that does not rub off clinically identied as another entity. Etiological factors are smoking, viral and fungal agent and specic nutrients and deciency may have role in the development and progression. Clinically it can be classied as homogenous and non-homogenous. It most seen on buccal mucosa and lateral border of tongue. Malignant transformation of oral leukoplakia is about 5-18%. A higher chance of it transformation has been seen in non-homogeneous, high risk anatomic structures such as the oor of the mouth or the tongue, as well as a history of non-smoking. It can be diagnosed by biopsy, toluidine blue staining or lugol s iodine and exfoliative cytology. Management is surgical excision, cryosurgery, CO2 laser, retinoids, photodynamic therapy

A meta-analysis reveals the protein profile associated with malignant transformation of oral leukoplakia.

The search for biomarkers associated with oral leukoplakia malignant transformation is critical for early diagnosis and improved prognosis of oral cancer patients. This systematic review and meta-analysis aimed to assess protein-based markers potentially associated with malignant transformation of oral leukoplakia. Five database and the grey literature were searched. In total, 142 studies were included for qualitative synthesis, where 173 proteins were investigated due to their potential role in malignant progression from oral leukoplakia (OL) to oral squamous cell carcinoma (OSCC). The abundance of these proteins was analyzed in fixed tissues and/or biofluid samples, mainly by immunohistochemistry and ELISA, and 12 were shared by both samples. Enrichment analysis revealed that the differential abundant proteins are mostly involved with regulation of cell death, regulation of cell proliferation, and regulation of apoptotic process. Also, these proteins are mainly expressed in the extracellular region (55.5%), cell surface (24.8%), and vesicles (49.1%). The meta-analysis revealed that the proteins related to tumor progression, PD-L1, Mdm2, and Mucin-4 were significantly associated with greater abundance in OSCC patients, with an Odds Ratio (OR) of 0.12 (95% CI: 0.04-0.40), 0.44 (95% CI: 0.24-0.81), and 0.18 (95% CI: 0.04-0.86), respectively, with a moderate certainty of evidence. The results indicate a set of proteins that have been investigated across OSCC initiation and progression, and whose transcriptional expression is associated with clinical characteristics relevant to the prognosis and aggressiveness. Further verification and validation of this biomarkers set are strongly recommended for future clinical application.

FGFR1 is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

Fibroblast growth factor receptor 1 is a potential prognostic factor for tongue squamous cell carcinoma and is associated with oral epithelial dysplasia grade in oral leukoplakia. Thirty cases of tongue squamous cell carcinoma and 30 cases of oral leukoplakia were analyzed. Fibroblast growth factor receptor 1 and phosphorylated Akt protein expression were analyzed by immunohistochemistry and quantified using a digital algorithm. Fibroblast growth factor receptor 1 gene amplification was analyzed by fluorescent in situ hybridizationin the tongue squamous cell carcinoma cases. Clinical appearance and dysplasia grade were correlated with oral leukoplakia malignant transformation. Oral leukoplakia cases presenting high fibroblast growth factor receptor 1 expression showed a higher risk of malignant transformation (p=0.016, HR: 7.3, 95% CI: 1.4-37.4). Phosphorylated Akt showed faint to no expression in oral leukoplakia, which did not correlate with dysplasia grade or malignant transformation. High expression of fibroblast growth factor receptor 1 and phosohorylated Akt were associated with poor overall survival and disease-free survival in tongue squamous cell carcinoma, although only fibroblast growth factor receptor 1 expression was significantly associated with poor overall survival (p=0.024; HR: 4.9, 95% CI: 1.2-19.9). Cases presenting double fibroblast growth factor receptor 1/phosphorylated Akt overexpression (n=8) showed markedly impaired overall survival (p=0.020; HR: 6.4, 95% CI: 1.3-31.1) and disease-free survival (p=0.001, HR: 13.0, 95% CI: 3.0-55.7). Fibroblast growth factor receptor 1 amplification was observed in 16.6% of tongue squamous cell carcinoma cases, being correlated with vascular and neural invasion (p=0.001 and 0.017, respectively), but not with fibroblast growth factor receptor 1 protein expression, overall survival, or disease-free survival. Fibroblast growth factor receptor 1 protein expression is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

Elucidating the Genetic Landscape of Oral Leukoplakia to Predict Malignant Transformation.

Oral leukoplakia is the most common oral potentially malignant disorder with an annual malignant transformation rate of 1% to 5%. Consequently, oral leukoplakia patients have a 30% to 50% lifetime risk to develop oral squamous cell carcinoma. Although risk factors for malignant transformation of oral leukoplakia have been investigated, no definitive risk stratification model has been proposed. Next-generation sequencing can elucidate the genetic landscape of oral leukoplakia, which may be used to predict the risk for malignant transformation. We investigated a retrospective cohort of 89 oral leukoplakia patients, and analyzed their oral leukoplakia lesions for the presence of genomic copy-number alterations and mutations in genes associated with oral squamous cell carcinoma. In 25 of 89 (28%) patients, oral squamous cell carcinoma developed during follow-up. Seventy-nine of 89 (89%) oral leukoplakias harbored at least one genetic event. Copy-number alterations were present in 61 of 89 (69%) oral leukoplakias, most commonly gains of chromosome regions 8q24 (46%) and 20p11 (20%) and loss of 13q12 (19%). Mutations were present in 59 of 89 (66%) oral leukoplakias, most commonly in TP53 (28%), FAT1 (20%), and NOTCH1 (13%). Genetic data were combined with the presence of dysplasia to generate a prediction model, identifying three groups with a distinct risk for malignant transformation. We provide an extensive description of genetic alterations in oral leukoplakia and its relation to malignant transformation. On the basis of our data we provide a model for the prediction of malignant transformation of oral leukoplakia using dysplasia and genetic markers.

SNAI2 promotes the malignant transformation of oral leukoplakia by modulating p-EMT.

Snail family transcriptional repressor 2 (SNAI2) is a key regulator of partial epithelial-mesenchymal transition (p-EMT) and is associated with tumorigenesis. Whether SNAI2 promotes oral leukoplakia (OLK) malignant transformation by modulating p-EMT is unclear. This study utilized two clinical datasets (GSE26549 and GSE85195) from the Gene Expression Omnibus database, cytological experiments, and a 4-nitroquinoline 1-oxide-induced mice model to explore the role of SNAI2 in OLK malignant transformation. The clinical cohort found SNAI2, as a risk factor (HR=2.50, 95% CI: 1.08-5.79, p=0.033), could promote OLK malignant transformation (p=0.012). Cytological experiments indicated that SNAI2 overexpression promoted DOK cell proliferation, invasion, migration, and increase the protein expression of p-EMT relative signatures, whereas SNAI2 silencing has opposite effects. Furthermore, the mice model and clinical datasets demonstrated the expression of SNAI2 and p-EMT relative signatures were increased with OLK malignant transformation. And SNAI2 was strongly correlated with p-EMT. Besides, co-expressed genes of SNAI2 were also enriched in p-EMT relative biological processes and signaling pathways. p-EMT plays a significant role in promoting the OLK malignant transformation. As an important regulator of p-EMT, SNAI2 could be a target to block the OLK malignant transformation.

ASSOCIATION OF FOXP3 WITH CLINICAL AND HISTOPATHOLOGICAL ASPECTS OF MALIGNANT TRANSFORMATION OF THE ORAL LEUKOPLAKIA

<h3>Objectives</h3> Oral leukoplakia (OL) is the most common potentially malignant lesion of the oral mucosa. Several factors are associated with increased risk of malignant transformation. The aim was to evaluate the expression of Foxp3+ cells in OL samples and their relationship with clinical and pathologic factors associated with the malignant transformation of OL. <h3>Study Design</h3> Twenty-five samples from patients diagnosed with OL were selected. Clinical data such as age, sex, and location were obtained from archives. The histopathologic degree was obtained, and immunohistochemistry was performed using anti-Foxp3. Ten fields from each slide were obtained and Foxp3+ cells were counted. The mean density was compared between groups and statistical analysis was applied. Normal oral mucosa (NOM) samples were used as control. <h3>Results</h3> Foxp3+ cells were increased in samples of smokers when compared to NOM samples (<i>P</i> < .05). Foxp3+ cells were increased in females (<i>P</i> < .05) and in OL samples with severe epithelial dysplasia when compared with samples of moderate epithelial dysplasia (<i>P</i> < .05). <h3>Conclusions</h3> The study suggests that the number of cells associated with modulation of immune response may be affected by clinical and histopathologic characteristics associated with malignant transformation of OL.

Autofluorescence imaging as a noninvasive tool of risk stratification for malignant transformation of oral leukoplakia: A follow-up cohort study

BackgroundThere is few longitudinal study on oral potentially malignant disorder (OPMDs) focusing on oral leukoplakia (OLK) with clinical endpoints to investigate the role of autofluorescence imaging (AFI) for surveilling the malignant transformation. MethodsBased on our previous prospective diagnostic study enrolled 517 OPMD patients, 184 OLK patients were retrieved to further investigate the role of AFI using VELscope in predicting malignant transformation. During a median follow-up period of 44 months, 19 (10.33%) developed into oral cancer. ResultsOLK patients were divided into loss of autofluorescence (LAF, n = 124) and retention of autofluorescence (RAF, n = 60) groups according to the results of AFI. Interestingly, difference between malignant transformation rate (MTR, 14.52%) of group LAF and overall MTR (10.33%) was not significant, but MTR (1.67%) of group RAF was significantly lower than overall MTR. Kaplan-Meier and Cox-regression analyses revealed that LAF could not directly distinguish the high-risk lesions, but RAF significantly discriminate the low-risk lesions. Importantly, time-dependent ROC curve analysis found that the sensitivity and negative predictive value (NPV) of AFI for the prediction of malignant transformation was 100% and 100% (2-year follow-up), 94.7% and 98.3% (5-year follow-up), respectively. Also, calibration curve and decision curve analyses showed high levels of predictive value and clinical relevance. ConclusionThis follow-up cohort study firstly evaluated AFI using VELscope for risk stratification of OLK malignant transformation. Whether conservative management is appropriate for OLK patients with RAF imaging due to minimal rate and risk of malignant transformation and great specificity and NPV is required to be further investigated.

Podoplanin Expression Independently and Jointly with Oral Epithelial Dysplasia Grade Acts as a Potential Biomarker of Malignant Transformation in Oral Leukoplakia.

Our aim was to evaluate the expression of biomarkers, CD44v6, CD147, EGFR, p53, p63, p73, p16, and podoplanin in oral leukoplakias (OL) and to assess their potential for prediction of malignant transformation (MT). We analyzed the expression of CD44v6, CD147, EGFR, p53, p63, p73, p16, and podoplanin by immunohistochemistry in 52 OL, comprised of 41 low-grade (LG) dysplasia and 11 high-grade (HG) cases. Twelve healthy normal tissues (NT) were also included. Univariate and multivariate analysis were performed to evaluate any association with MT. Variable expression among the studied markers was observed, with a significant increase of high expression from NT to LG and HG cases in CD44v6 (p = 0.002), P53 (p = 0.002), P73 (p = 0.043), and podoplanin (p < 0.001). In multivariate analysis, cases with high podoplanin score showed a significant increased risk of MT (HR of 10.148 (95% CI of 1.503–68.532; p = 0.017). Furthermore, podoplanin combined with binary dysplasia grade obtained a HR of 10.238 (95% CI of 2.06–50.889; p = 0.004). To conclude, CD44v6, p53, p73, and podoplanin showed an increasing expression along the natural history of oral carcinogenesis. Podoplanin expression independently or combined with dysplasia grade could be useful predictive markers of MT in OL.

Can tissue biomarkers be used to determine the prognosis of oral leukoplakia lesions with regards to malignant transformation?

Design Systematic review looking at published studies which aimed to identify human tissue biomarkers which could predict malignant transformation of oral leukoplakia (OL) lesions.Case/control selection Articles were identified from PubMed, EBSCO and Cochrane library databases using combinations of keywords. Randomised clinical trials, case-control studies and prospective and retrospective cohort studies were included. All studies had to include follow-up data. There were no restrictions regarding gender, age groups, geographic origin, or year of publication. The selection process involved two of the researchers independently analysing titles and abstracts to identify articles for full-text reading. The same authors then read the articles identified for full-text reading, applying the eligibility criteria. If there was a disagreement with regards to the selection, a discussion was had until a consensus was reached.Data analysis Qualitative data was presented as reported from the primary studies. Quantitative analysis was not carried out due to the high heterogeneity across the studies.Results Forty-six studies were included within the systematic review. These studies identified a total of 3,783 patients with OL, of which 1,047 went on to develop oral cancer, giving an average malignant transformation incidence of 27.6%. Forty-nine different tissue biomarkers were evaluated among the included studies, with the p53 and podoplanin proteins and loss of heterozygosity the most frequently discussed.Conclusions Of the biomarkers studied, podoplanin and chromosomal loci abnormalities (such as loss of heterozygosity) would appear the most promising in being able to predict malignant transformation of OL lesions; however, further research is required.

Risk assessment of malignant transformation of oral leukoplakia in patients with previous oral squamous cell carcinoma

The aim of this study was to identify the risk factors associated with developing oral squamous cell carcinoma (OSCC) from surgically excised oral leukoplakia (OL) in patients with previous oral cavity cancer. Clinicopathological data of 84 patients who were treated for OL between July 2002 and July 2020 and who had previously received treatment for OSCC were reviewed retrospectively. The follow-up time ranged from 0.69 to 17.99 years (mean 6.78 ± 4.25 years). The overall cumulative malignant transformation rate was 25% and the annual transformation rate was 5.73%. Kaplan–Meier survival analysis and the log-rank test showed that Candida infection (P = 0.010) was a risk factor associated with malignant transformation. In the multivariate Cox regression analysis, tongue and floor of the mouth as the location of the leukoplakia (P = 0.039), multifocal lesions of OL (P = 0.047), and Candida infection (P = 0.018) were the three independent prognostic factors related to the development of OSCC from the treated OL. A cautious approach to OL of the tongue with Candida infection or multifocal disease in this group of patients would be appropriate.

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

Simple SummaryMouth cancer is the most common malignancy in the head-and-neck region. Usually, these tumors develop from white lesions in the mouth that appear long before cancer diagnosis. However, platforms that can estimate the time-factored risk of cancer occurring from these diseases and guide treatment and monitoring approaches are elusive. To this end, our study presents time-to-event models that are based on machine learning for prediction of the risk of malignancy from oral white lesions following pathological diagnosis as a function of time. These models displayed very satisfactory discrimination and calibration after multiple tests. To facilitate their preliminary use in clinical practice and further validation, we created a website supporting the use of these models to aid decision making.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.

MicroRNAs and their role in the malignant transformation of oral leukoplakia: a scoping review.

Background MiRNAs are small non-coding RNAs that regulate gene expression at the post-transcriptional level and have been associated with malignant transformation of oral epithelial precursor lesions such as oral leukoplakia. The aim was to perform a scoping review of the contemporary literature about the different roles of miRNAs during the malignant transformation of oral leukoplakia.Material and Methods We conducted a systematic search with the following MeSH terms: ‘oral leukoplakia’, ‘carcinoma in situ’, ‘microRNAs’, ‘mouth neoplasms’ and ‘epithelial–mesenchymal transition’ in PubMed/MEDLINE, EMBASE and SpringerLink.Results Fifteen articles were included for analysis, among which in vivo and in vitro articles were included. A total of 21 different miRNAs were found to be involved in the malignant transformation process of oral leukoplakia. Regarding their possible effects, 6 miRNAs were classified as oncogenic, 5 as tumour suppressors and 10 were related to epithelial–mesenchymal transition, invasion and migration.Conclusions Based on the current review, we concluded that miRNAs-21, 345, 181-b and 31* seem to be potential markers of malignant transformation of oral leukoplakia. However, further clinical prospective studies are needed in order to validate their utility as prognostic biomarkers. Key words:miRNAs, oral leukoplakia, oral squamous cell carcinoma, biomarkers, malignant transformation.