Predicting the clinical outcome of oral potentially malignant disorders using transcriptomic-based molecular pathology

Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: A systematic review

BACKGROUND

Oral Potentially Malignant Disorders (OPMDs) refer to a heterogenous group of clinical presentations with heightened rate of malignant transformation. Identification of risk levels in OPMDs is crucial to determine the need for active intervention in high-risk patients and routine follow-up in low-risk ones. Machine learning models has shown tremendous potential in several areas of dentistry that strongly suggest its application to estimate rate of malignant transformation of precancerous lesions.

METHODS

A comprehensive literature search was performed on Pubmed/MEDLINE, Web of Science, Scopus, Embase, Cochrane Library database to identify articles including machine learning models and algorithms to predict malignant transformation in OPMDs. Relevant bibliographic data, study characteristics, and outcomes were extracted for eligible studies. Quality of the included studies was assessed through the IJMEDI checklist.

RESULTS

Fifteen articles were found suitable for the review as per the PECOS criteria. Amongst all studies, highest sensitivity (100%) was recorded for U-net architecture, Peaks Random forest model, and Partial least squares discriminant analysis (PLSDA). Highest specificity (100%) was noted for PLSDA. Range of overall accuracy in risk prediction was between 95.4% and 74%.

CONCLUSION

Machine learning proved to be a viable tool in risk prediction, demonstrating heightened sensitivity, automation, and improved accuracy for predicting transformation of OPMDs. It presents an effective approach for incorporating multiple variables to monitor the progression of OPMDs and predict their malignant potential. However, its sensitivity to dataset characteristics necessitates the optimization of input parameters to maximize the efficiency of the classifiers.

Immunophenotypic and Gene Expression Analyses of the Inflammatory Microenvironment in High-Grade Oral Epithelial Dysplasia and Oral Lichen Planus

BACKGROUND

Oral lichen planus (OLP) and oral epithelial dysplasia (OED) present diagnostic challenges due to clinical and histologic overlap. This study explores the immune microenvironment in OED, hypothesizing that immune signatures could aid in diagnostic differentiation and predict malignant transformation.

METHODS

Tissue samples from OED and OLP cases were analyzed using immunofluorescence/immunohistochemistry (IF/IHC) for CD4, CD8, CD163/STAT1, and PD-1/PDL-1 expression. RNA-sequencing was performed on the samples, and data was subjected to CIBERSORTx analysis for immune cell composition. Gene Ontology analysis on the immune differentially expressed genes was also conducted.

RESULTS

In OED, CD8 + T-cells infiltrated dysplastic epithelium, correlating with dysplasia severity. CD4 + lymphocytes increased in the basal layer. STAT1/CD163 + macrophages correlated with CD4 + intraepithelial distribution. PD-1/PDL-1 expression varied. IF/IHC analysis revealed differential immune cell composition between OED and OLP. RNA-sequencing identified upregulated genes associated with cytotoxic response and immunosurveillance in OED. Downregulated genes were linked to signaling, immune cell recruitment, and tumor suppression.

CONCLUSIONS

The immune microenvironment distinguishes OED and OLP, suggesting diagnostic potential. Upregulated genes indicate cytotoxic immune response in OED. Downregulation of TRADD, CX3CL1, and ILI24 implies dysregulation in TNFR1 signaling, immune recruitment, and tumor suppression. This study contributes to the foundation for understanding immune interactions in OED and OLP, offering insights into future objective diagnostic avenues.

Bridging the gap between omics research and dental practice

AIM

The burgeoning field of omics research has witnessed exponential growth in both medicine and dentistry. However, despite more than a decade of advancements, clinical dentistry, particularly in Low- and Middle-Income Countries (LMICs), has seen limited progress in integrating omics-based approaches into routine practice. This review aims to provide a comprehensive overview of the integration of omics approaches in dentistry, focusing on the challenges and opportunities for translating research findings into clinical practice.

METHODS

we conducted a literature review using key databases to provide a brief overview of the history of genomics in dentistry. Additionally, we summarised recent breakthroughs in omics relevant to oral health practitioners, emphasising the inadequate translation of omics research into clinical practice.

RESULTS

Despite significant growth in omics research in both medicine and dentistry, its translation into routine clinical practice in dentistry remains limited. We summarise recent breakthroughs in omics and highlight the gap between research advancements and clinical implementation.

DISCUSSION AND CONCLUSION

The integration of omics approaches holds promise for enhancing diagnostics, personalised treatment strategies, and preventive measures in dental practice, ushering in a new era of precision oral healthcare. However, several challenges, including infrastructure limitations, cost-effectiveness, and education gaps, hinder the widespread adoption of omics-based approaches in clinical dentistry. A strong commitment to transforming dentistry is required to embrace this transition. This shift has the potential to revolutionise oral healthcare by advancing precision diagnostics and treatment strategies tailored to individual patient needs.

Leveraging artificial intelligence for perioperative cancer risk assessment of oral potentially malignant disorders

Oral potentially malignant disorders (OPMDs) are mucosal conditions with an inherent disposition to develop oral squamous cell carcinoma. Surgical management is the most preferred strategy to prevent malignant transformation in OPMDs, and surgical approaches to treatment include conventional scalpel excision, laser surgery, cryotherapy, and photodynamic therapy. However, in reality, since all patients with OPMDs will not develop oral squamous cell carcinoma in their lifetime, there is a need to stratify patients according to their risk of malignant transformation to streamline surgical intervention for patients with the highest risks. Artificial intelligence (AI) has the potential to integrate disparate factors influencing malignant transformation for robust, precise, and personalized cancer risk stratification of OPMD patients than current methods to determine the need for surgical resection, excision, or re-excision. Therefore, this article overviews existing AI models and tools, presents a clinical implementation pathway, and discusses necessary refinements to aid the clinical application of AI-based platforms for cancer risk stratification of OPMDs in surgical practice.

Immuno-oncologic signature of malignant transformation in oral squamous cell carcinoma

OBJECTIVE

The purpose of this study is to identify the immuno-oncologic (IO) signature at the surgical tumor margin (TM) of oral squamous cell carcinoma (OSCC) that is involved in the process of malignant transformation.

STUDY DESIGN

Under institutional review board approval, TM of 73 OSCC were investigated using immunohistochemistry for the immune biomarker, programmed death ligand-1 (PD-L1). NanoString 770 IO-focused gene set was analyzed in 5 pairs of TM and invasive tumor (T). PD-L1 regulation in response to interferon-gamma (IFN-γ) was investigated in an oral potentially malignant cell line (OPMC).

RESULTS

Programmed death ligand-1 expression in the epithelial margin directly correlated with its expression in the underlying immune cells (P = .0082). Differential gene expression showed downregulation of PD-L1 and IFN-γ 6 gene signature in the TM relative to T pair.CD8 and macrophages were higher in TM. CNTFR, LYZ, C7, RORC, and FGF13 downregulation in T relative to TM. TDO2, ADAM12, MMP1, LAMC2, MB21D1, TYMP, OASL, COL5A1, exhausted_CD8, Tregs,and NK_CD56dim were upregulated in T relative to TM. Finally, IFN-γ induced upregulation of PD-L1 in the OPMC.

CONCLUSIONS

Our work suggests a role for IFN-γ in PD-L1 upregulation in OPMC and presents novel IO transcriptional signatures for frankly invasive OSCC relative to TM.

Knockdown of PGC1α suppresses dysplastic oral keratinocytes proliferation through reprogramming energy metabolism

Oral potentially malignant disorders (OPMDs) are precursors of oral squamous cell carcinoma (OSCC). Deregulated cellular energy metabolism is a critical hallmark of cancer cells. Peroxisome proliferator-activated receptor-gamma coactivator-1 alpha (PGC1α) plays vital role in mitochondrial energy metabolism. However, the molecular mechanism of PGC1α on OPMDs progression is less unclear. Therefore, we investigated the effects of knockdown PGC1α on human dysplastic oral keratinocytes (DOKs) comprehensively, including cell proliferation, cell cycle, apoptosis, xenograft tumor, mitochondrial DNA (mtDNA), mitochondrial electron transport chain complexes (ETC), reactive oxygen species (ROS), oxygen consumption rate (OCR), extracellular acidification rate (ECAR), and glucose uptake. We found that knockdown PGC1α significantly inhibited the proliferation of DOKs in vitro and tumor growth in vivo, induced S-phase arrest, and suppressed PI3K/Akt signaling pathway without affecting cell apoptosis. Mechanistically, downregulated of PGC1α decreased mtDNA, ETC, and OCR, while enhancing ROS, glucose uptake, ECAR, and glycolysis by regulating lactate dehydrogenase A (LDHA). Moreover, SR18292 (an inhibitor of PGC1α) induced oxidative phosphorylation dysfunction of DOKs and declined DOK xenograft tumor progression. Thus, our work suggests that PGC1α plays a crucial role in cell proliferation by reprograming energy metabolism and interfering with energy metabolism, acting as a potential therapeutic target for OPMDs.

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.

Proceedings of the North American Society of Head and Neck Pathology Companion Meeting, New Orleans, LA, March 12, 2023: Oral Cavity Dysplasia: Why Does Histologic Grading Continue to be Contentious?

Head and neck squamous cell carcinoma (HNSCC) is the world's 6th most common malignancy. Oral cavity SCC (OCSCC) represents approximately one third of the HNSCC cases diagnosed annually in the United States. Despite therapeutic advances, OCSCC is frequently lethal, with a modest 5-year survival. Because OCSCC is often preceded by premalignant lesions, it is an ideal disease for screening initiatives. The conventional visual and tactile exam (CVTE), coupled with a tissue biopsy, remains the gold standard. However, CVTE alone cannot reliably differentiate between reactive/inflammatory and dysplastic lesions. Further, the histologic diagnosis of dysplasia is subjective in nature and a highly imperfect predictor of malignant transformation. This prognostic uncertainty creates a significant clinical management dilemma-watchful waiting with increased patient psychological and economic burdens versus unnecessary aggressive treatment. As such, the development and validation of novel diagnostic platforms such as Artificial Intelligence (AI) and prognostic molecular biomarkers may help address these critical unmet clinical needs.

The Role of Different Immunocompetent Cell Populations in the Pathogenesis of Head and Neck Cancer-Regulatory Mechanisms of Pro- and Anti-Cancer Activity and Their Impact on Immunotherapy

Head and neck squamous cell carcinoma (HNSCC) is one of the most aggressive and heterogeneous groups of human neoplasms. HNSCC is characterized by high morbidity, accounting for 3% of all cancers, and high mortality with ~1.5% of all cancer deaths. It was the most common cancer worldwide in 2020, according to the latest GLOBOCAN data, representing the seventh most prevalent human malignancy. Despite great advances in surgical techniques and the application of modern combinations and cytotoxic therapies, HNSCC remains a leading cause of death worldwide with a low overall survival rate not exceeding 40-60% of the patient population. The most common causes of death in patients are its frequent nodal metastases and local neoplastic recurrences, as well as the relatively low response to treatment and severe drug resistance. Much evidence suggests that the tumour microenvironment (TME), tumour infiltrating lymphocytes (TILs) and circulating various subpopulations of immunocompetent cells, such regulatory T cells (CD4+CD25+Foxp3+Tregs), cytotoxic CD3+CD8+ T cells (CTLs) and CD3+CD4+ T helper type 1/2/9/17 (Th1/Th2/Th9/Th17) lymphocytes, T follicular helper cells (Tfh) and CD56dim/CD16bright activated natural killer cells (NK), carcinoma-associated fibroblasts (CAFs), myeloid-derived suppressor cells (MDSCs), tumour-associated neutrophils (N1/N2 TANs), as well as tumour-associated macrophages (M1/M2 phenotype TAMs) can affect initiation, progression and spread of HNSCC and determine the response to immunotherapy. Rapid advances in the field of immuno-oncology and the constantly growing knowledge of the immunosuppressive mechanisms and effects of tumour cancer have allowed for the use of effective and personalized immunotherapy as a first-line therapeutic procedure or an essential component of a combination therapy for primary, relapsed and metastatic HNSCC. This review presents the latest reports and molecular studies regarding the anti-tumour role of selected subpopulations of immunocompetent cells in the pathogenesis of HNSCC, including HPV+ve (HPV+) and HPV-ve (HPV-) tumours. The article focuses on the crucial regulatory mechanisms of pro- and anti-tumour activity, key genetic or epigenetic changes that favour tumour immune escape, and the strategies that the tumour employs to avoid recognition by immunocompetent cells, as well as resistance mechanisms to T and NK cell-based immunotherapy in HNSCC. The present review also provides an overview of the pre- and clinical early trials (I/II phase) and phase-III clinical trials published in this arena, which highlight the unprecedented effectiveness and limitations of immunotherapy in HNSCC, and the emerging issues facing the field of HNSCC immuno-oncology.

Transcriptomic analysis predicts the risk of progression of premalignant lesions in human tongue

The 5-year survival rate for patients with oral squamous cell carcinomas (SCC), including tongue SCC, has not significantly improved over the last several decades. Oral potentially malignant disorders (OPMD), including oral dysplasias, are oral epithelial disorders that can develop into oral SCCs. To identify molecular characteristics that might predict conversion of OPMDs to SCCs and guide treatment plans, we performed global transcriptomic analysis of human tongue OPMD (n = 9) and tongue SCC (n = 11) samples with paired normal margin tissue from patients treated at Weill Cornell Medicine. Compared to margin tissue, SCCs showed more transcript changes than OPMDs. OPMDs and SCCs shared some altered transcripts, but these changes were generally greater in SCCs than OPMDs. Both OPMDs and SCCs showed altered signaling pathways related to cell migration, basement membrane disruption, and metastasis. We suggest that OPMDs are on the path toward malignant transformation. Based on patterns of gene expression, both OPMD and tongue SCC samples can be categorized into subclasses (mesenchymal, classical, basal, and atypical) similar to those seen in human head and neck SCC (HNSCC). These subclasses of OPMDs have the potential to be used to stratify patient prognoses and therapeutic options for tongue OPMDs. Lastly, we identified a gene set (ELF5; RPTN; IGSF10; CRMP1; HTR3A) whose transcript changes have the power to classify OPMDs and SCCs and developed a Firth logistic regression model using the changes in these transcripts relative to paired normal tissue to validate pathological diagnosis and potentially predict the likelihood of an OPMD developing into SCC, as data sets become available.

Transcriptional analysis highlights three distinct immune profiles of high-risk oral epithelial dysplasia

Oral potentially malignant disorders (OPMD) are precursors of oral squamous cell carcinoma (OSCC), and the presence of oral epithelial dysplasia (OED) in OPMD confers an increased risk of malignant transformation. Emerging evidence has indicated a role for the immune system in OPMD disease progression; however, the underlying immune mechanisms remain elusive. In this study, we used immune signatures established from cancer to delineate the immune profiles of moderate and severe OED, which are considered high-risk OPMD. We demonstrated that moderate and severe OEDs exhibit high lymphocyte infiltration and upregulation of genes involved in both immune surveillance (major histocompatibility complex-I, T cells, B cells and cytolytic activity) and immune suppression (immune checkpoints, T regulatory cells, and tumor-associated macrophages). Notably, we identified three distinct subtypes of moderate and severe OED: immune cytotoxic, non-cytotoxic and non-immune reactive. Active immune surveillance is present in the immune cytotoxic subtype, whereas the non-cytotoxic subtype lacks CD8 immune cytotoxic response. The non-immune reactive subtype showed upregulation of genes involved in the stromal microenvironment and cell cycle. The lack of T cell infiltration and activation in the non-immune reactive subtype is due to the dysregulation of CTNNB1, PTEN and JAK2. This work suggests that moderate and severe OED that harbor the non-cytotoxic or non-immune reactive subtype are likely to progress to cancer. Overall, we showed that distinct immune responses are present in high-risk OPMD, and revealed targetable pathways that could lead to potential new approaches for non-surgical management of OED.

Microenvironment in Oral Potentially Malignant Disorders: Multi-Dimensional Characteristics and Mechanisms of Carcinogenesis

Oral potentially malignant disorders (OPMDs) are a group of diseases involving the oral mucosa and that have a risk of carcinogenesis. The microenvironment is closely related to carcinogenesis and cancer progression by regulating the immune response, cell metabolic activities, and mechanical characteristics. Meanwhile, there are extensive interactions between the microenvironments that remodel and provide favorable conditions for cancer initiation. However, the changes, exact roles, and interactions of microenvironments during the carcinogenesis of OPMDs have not been fully elucidated. Here, we present an updated landscape of the microenvironments in OPMDs, emphasizing the changes in the immune microenvironment, metabolic microenvironment, mechanical microenvironment, and neural microenvironment during carcinogenesis and their carcinogenic mechanisms. We then propose an immuno–metabolic–mechanical–neural interaction network to describe their close relationships. Lastly, we summarize the therapeutic strategies for targeting microenvironments, and provide an outlook on future research directions and clinical applications. This review depicts a vivid microenvironment landscape and sheds light on new strategies to prevent the carcinogenesis of OPMDs.

Molecular Signatures of Tumour and Its Microenvironment for Precise Quantitative Diagnosis of Oral Squamous Cell Carcinoma: An International Multi-Cohort Diagnostic Validation Study

BACKGROUND

Heterogeneity in oral potentially malignant disorder (OPMD) poses a problem for accurate prognosis that impacts on treatment strategy and patient outcome. A holistic assessment based on gene expression signatures from both the tumour cells and their microenvironment is necessary to provide a more precise prognostic assessment than just tumour cell signatures alone.

METHODS

We reformulated our previously established multigene qPCR test, quantitative Malignancy Index Diagnostic System (qMIDS) with new genes involved in matrix/stroma and immune modulation of the tumour microenvironment. An algorithm calculates and converts a panel of 16 gene mRNA expression levels into a qMIDS index to quantify risk of malignancy for each sample.

RESULTS

The new qMIDS^V2 assay was validated in a UK oral squamous cell carcinoma (OSCC) cohort (n = 282) of margin and tumour core samples demonstrating significantly better diagnostic performance (AUC = 0.945) compared to previous qMIDS^V1 (AUC = 0.759). Performance of qMIDS^V2 were independently validated in Chinese (n = 35; AUC = 0.928) and Indian (n = 95; AUC = 0.932) OSCC cohorts. Further, 5-year retrospective analysis on an Indian dysplastic lesion cohort (n = 30) showed that qMIDS^V2 was able to significantly differentiate between lesions without transformation and those with malignant transformation.

CONCLUSIONS

This study validated a novel multi-gene qPCR test on a total of 535 tissue specimens from UK, China and India, demonstrating a rapid minimally invasive method that has a potential application for dysplasia risk stratification. Further study is required to establish if qMIDS^V2 could be used to improve OPMD patient management, guide treatment strategy and reduce oral cancer burden.

Genetic Changes Driving Immunosuppressive Microenvironments in Oral Premalignancy

Oral premalignant lesions (OPLs) are the precursors to oral cavity cancers, and have variable rates of progression to invasive disease. As an intermediate state, OPLs have acquired a subset of the genomic alterations while arising in an oral inflammatory environment. These specific genomic changes may facilitate the transition to an immune microenvironment that permits malignant transformation. Here, we will discuss mechanisms by which OPLs develop an immunosuppressive microenvironment that facilitates progression to invasive cancer. We will describe how genomic alterations and immune microenvironmental changes co-evolve and cooperate to promote OSCC progression. Finally, we will describe how these immune microenvironmental changes provide specific and unique evolutionary vulnerabilities for targeted therapies. Therefore, understanding the genomic changes that drive immunosuppressive microenvironments may eventually translate into novel biomarker and/or therapeutic approaches to limit the progression of OPLs to potential lethal oral cancers.

The clinical utility of contemporary oral epithelial dysplasia grading systems

INTRODUCTION

Clinical management of oral potentially malignant disorders relies on accurate histopathological assessment of the presence and grade of oral epithelial dysplasia. Whilst adjunctive laboratory tests have provided useful prognostic information, none are in widespread clinical use. This study was performed to assess the clinical utility of two contemporary oral epithelial dysplasia grading systems.

METHODS

Patients were identified from a clinical database. Oral epithelial dysplasia grading was performed by three oral and maxillofacial pathologists blinded to clinical outcome using the WHO 2017 system and a binary classification. The primary outcome measure was the development of oral squamous cell carcinoma, termed 'malignant transformation'.

RESULTS

131 cases satisfied the inclusion criteria, of which 23 underwent malignant transformation. There was substantial inter-rater agreement between the study pathologists for both grading systems, measured using kappa statistics (κ = 0.753-0.784). However, there was only moderate agreement between the consensus WHO 2017 dysplasia grade for the study against the original grade assigned by a pool of six pathologists in the context of the clinical service (κ = 0.491). Higher grade categories correlated with an increased risk of developing cancer using both grading systems.

CONCLUSION

This study demonstrates that the WHO 2017 and binary grading systems are reproducible between calibrated pathologists and that consensus reporting is likely to improve the consistency of grading. The WHO and binary systems were prognostically comparable. We recommend that institutions implement consensus oral epithelial dysplasia grading and prospectively audit the effectiveness of risk stratifying their patients with oral potentially malignant disorders. (249 words).

The upregulation of oncogenic miRNAs in swabbed samples obtained from oral premalignant and malignant lesions

OBJECTIVES

Oncogenic miRNAs upregulated in OSCC play a range of versatile roles in oral carcinogenesis. Oral potentially malignant disorders (OPMDs) are the antecedent lesions to oral squamous carcinoma (OSCC) and they require a definitive diagnosis and early intervention. This study hypothesizes the presence of aberrant oncogenic miRNA expression in swabbed oral lesions.

MATERIALS AND METHODS

The expression of miR-21, miR-31, miR-134, miR-146a, and miR-211 in swabbed samples from 36 dysplastic or hyperplastic OPMDs and 10 OSCCs, relative to respective normal mucosa within the same patient, is analyzed with qRT-PCR to develop a diagnosis.

RESULTS

Upregulation of all tested miRNAs in OPMD and OSCC samples comparing to controls is found to have occurred. Receiver operating characteristics curve analysis shows that miR-31 gives the best diagnostic accuracy of 0.91 when differentiating OPMD/OSCC from controls. An analysis of miR-134 and miR-211 expression allows the discrimination of the dysplastic state associated with OPMD, while the use of expression of the combined miRNAs further improves the analytical performances when identifying the dysplastic state. The concordant upregulation of miR-21, miR-31, and miR-146a is found to occur during an early stage of OSCC carcinogenesis.

CONCLUSION

This study demonstrates the upregulation of multiple oncogenic miRNAs in swabbed OPMD and OSCC samples. miRNA expression in swabbed collectives enables the differentiation between normal mucosa and OPMD/OSCC, independent of their histopathological severity.

CLINICAL RELEVANCE

This conventional and convenient sampling tool, when coupled with an assessment of miR-31 expression, would seem to be an adjuvant approach to the diagnosis of OPMD and OSCC.