Advanced machine learning for estimating vascular occlusion percentage in patients with ischemic heart disease and periodontitis.

Objective: The study aimed to assess the efficacy of advanced machine learning algorithms in estimating the percentage of vascular occlusion in ischemic heart disease (IHD) cases with periodontitis. Methods: This study involved 300 IHD patients aged 45 to 65 with stage III periodontitis undergoing coronary angiograms. Dental and periodontal examinations assessed various factors. Coronary angiograms categorized patients into three groups based on artery stenosis. Clinical data were processed, outliers were identified, and machine learning algorithms were applied for analysis using the orange tool, including confusion matrices and receiver operating characteristic (ROC) curves for assessment. Results: The results showed that Random Forest, Naïve Bayes, and Neural Networks were 97 %, 84 %, and 92 % accurate, respectively. Random Forest did exceptionally well in identifying the severity of conditions, with 95.70 % accuracy for mild cases, 84.80 % for moderate cases, and a perfect 100.00 % for severe cases. Conclusions: The current study, using Periodontal Inflammatory Surface Area (PISA) scores, revealed that the Random Forest model accurately predicted the percentage of vascular occlusion.

Phytochemical Targeting of Nerve Growth Factor by Thymoquinone and Cuscutin: A Molecular Dynamics Simulation Study.

Background Nerve growth factor (NGF) is a novel target of pain therapeutics for oral cancer, and it plays a main role in the nociception of chronic pain. Surgery, along with chemotherapy or radiotherapy, is the gold standard for treating patients, but the side effects are significant as well. Newer effective interventions with natural phytochemicals could improve patient compliance and enhance the quality of life among patients with oral cancer. A literature search revealed a positive correlation between NGF and oral cancer pain. Nigella sativa (N. sativa) and Cuscuta reflexa (C. reflexa) have proven anticancer effects, but their activity with NGF is unexplored. Aims and objectives We aimed to identify the potential phytochemicals in N. sativa and C. reflexa. We also checked the NGF-blocking activity of the phytochemicals. Molecular docking and molecular dynamic (MD) simulations evaluated the binding energy and stability between the NGF protein and selected phytochemical ligands. Materials and methods We obtained protein NGF structure from UniProt (ID: 4EDX, P01138, Beta-nerve growth factor), ligand (thymoquinone) structure using PubChem ID: 10281, and ligand (cuscutin) structure using PubChem ID: 66065. Maestro protein (Schrödinger Inc., Mannheim, Germany) was used for molecular docking. Desmond Simulation Package (Schrödinger Inc., Mannheim, Germany) was used to model MD for 100 nanoseconds (ns). We have assessed the interaction between the protein and ligands by root mean square deviation (RMSD) values.  Results The interaction of thymoquinone and cuscutin with NGF was assessed. While interacting with thymoquinone, there was mild fluctuation from 0.6 Å to 2.5 Å up to 80 ns and ended up at 4.8 Å up to 100 ns. While interacting with cuscutin, mild fluctuation was seen from 0.8 Å to 4.8 Å till 90 ns and ended at 6.4 Å up to 100 ns. We found a stable interaction between our drug combination and the NGF receptor. Conclusion We have identified a stable interaction between thymoquinone, cuscutin, and NGF by our MD simulations. Hence, it could be used as an NGF inhibitor for pain relief and to control tumor progression. Further in vitro and in vivo evaluations of this novel drug combination with phytochemicals will help us understand their biological activities and potential clinical applications in oral cancer therapeutics.

Weighted Gene Co-expression Network Analysis (WGCNA) of Wnt Signaling Related to Periodontal Ligament Formation: A Bioinformatics-Based Analysis.

Introduction The Wnt signaling pathway is crucial for tooth development, odontoblast differentiation, and dentin formation. It interacts with epithelial cadherin (E-cadherin) and beta-catenin in tooth development and periodontal ligament (PDL) formation. Dysregulation of Wnt signaling is linked to periodontal diseases, requiring an understanding of therapeutic interventions. Weighted gene co-expression network analysis (WGCNA) can identify co-expressed gene modules. Our study aims to identify hub genes in WGCNA analysis of Wnt signaling-based PDL formation. Methods The study used a microarray dataset GSE201313 from the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus to analyze the impact of DMP1 expression on XLH dental pulp cell differentiation and PDL formation. The standardized dataset was used for WGCNA analysis, which generated a co-expression network by calculating pairwise correlations between genes and constructing an adjacency matrix. The topological overlap matrix (TOM) was transformed into a hierarchical clustering tree and then cut into modules or clusters of highly interconnected genes. The module eigengene (ME) was calculated for each module, and the genes within this module were identified as hub genes. Gene ontology (GO) and KEGG pathway enrichment analysis were performed to gain insights into the biological functions of the hub genes. The integrated Differential Expression and Pathway analysis (iDEP) tool (http://bioinformatics.sdstate.edu/idep/; South Dakota State University, Brookings, USA) was used for WGCNA analysis. Results The study used the WGCNA package to analyze 1,000 differentially expressed genes, constructing a gene co-expression network and generating a hierarchical clustering tree and TOM. The analysis reveals a scale-free topology fitting index R2 and mean connectivity for various soft threshold powers, with an R2 value of 5. COL6A1, MMP3, BGN, COL1A2, and FBN2 are hub genes implicated in PDL development. Conclusion The study identified key hub genes, including COL6A1, MMP3, BGN, and FBN2, crucial for PDL formation, tissue remodeling, and cell-matrix interactions, guiding future therapeutic strategies.

AI-based 3D-QSAR model of FDA-approved repurposed drugs for inhibiting sclerostin.

BACKGROUND: Wnt activation promotes bone formation and prevents bone loss. The Wnt pathway antagonist sclerostin and additional anti-sclerostin antibodies were discovered as a result of the development of the monoclonal antibody romosozumab. These monoclonal antibodies greatly increase the risk of cardiac arrest. Three-dimensional quantitative structure-activity relationships (3D-QSAR) predicts biological activities of ligands based on their three-dimensional features by employing powerful chemometric investigations such as artificial neural networks (ANNs) and partial least squares (PLS). OBJECTIVE: In this study, ligand-receptor interactions were investigated using 3D-QSAR Comparative molecular field analysis (CoMFA). Estimates of steric and electrostatic characteristics in CoMFA are made using Lennard-Jones and Coulomb potentials. METHODS: To identify the conditions necessary for the activity of these molecules, fifty Food and Drug Administration (FDA)-approved medications were chosen for 3D-QSAR investigations and done by CoMFA. For QSAR analysis, there are numerous tools available. This study employed Open 3D-QSAR for analysis due to its simplicity of use and capacity to produce trustworthy results. Four tools were used for the analysis on this platform: Py-MolEdit, Py-ConfSearch, and Py-CoMFA. RESULTS: Maps that were generated were used to determine the screen's r2 (Coefficient of Multiple Determinations) value and q2 (correlation coefficient). These numbers must be fewer than 1, suggesting a good, trustworthy model. Cross-validated (q2) 0.532 and conventional (r2) correlation values of 0.969 made the CoMFA model statistically significant. The model showed that hydroxamic acid inhibitors are significantly more sensitive to the steric field than the electrostatic field (70%) (30%). This hypothesis states that steric (43.1%), electrostatic (26.4%), and hydrophobic (20.3%) qualities were important in the design of sclerostin inhibitors. CONCLUSION: With 3D-QSAR and CoMFA, statistically meaningful models were constructed to predict ligand inhibitory effects. The test set demonstrated the model's robustness. This research may aid in the development of more effective sclerostin inhibitors that are synthesised using FDA-approved medications.

Artificial Intelligence (AI)-Based Detection of Anaemia Using the Clinical Appearance of the Gingiva.

Background and aim Millions suffer from anaemia worldwide, and systemic disorders like anaemia harm oral health. Anaemia is linked to periodontitis as certain inflammatory cytokines produced during periodontal inflammation can depress erythropoietin production leading to the development of anemia. Thus, detecting and treating it is crucial to tooth health. Hence, this study aimed to evaluate three different machine-learning approaches for the automated detection of anaemia using clinical intraoral pictures of a patient's gingiva. Methodology Orange was employed with squeeze net embedding models for machine learning. Using 300 intraoral clinical photographs of patients' gingiva, logistic regression, neural network, and naive Bayes were trained and tested for prediction and detection. Accuracy was measured using a confusion matrix and receiver operating characteristic (ROC) curve. Results In the present study, three convolutional neural network (CNN)-embedded machine-learning algorithms detected and predicted anaemia. For anaemia identification, naive Bayes had an area under curve (AUC) of 0.77, random forest plot had an AUV of 0.78, and logistic regression had 0.85. Thus, the three machine learning methods detected anaemia with 77%, 78%, and 85% accuracy, respectively. Conclusion Using artificial intelligence (AI) with clinical intraoral gingiva images can accurately predict and detect anaemia. These findings need to be confirmed with larger samples and additional imaging modalities.

Weighted Gene Co-expression Network Analysis of the Inflammatory Wnt Signaling Reveals Biomarkers Related to Bone Formation.

Background and aim Osteocytes regulate bone metabolism and balance through various mechanisms, including the Wnt (Wingless-related integration site signal transduction) signaling pathway. Weighted gene co-expression network analysis (WGCNA) is a computational method to identify functionally related genes based on expression patterns, especially in the Wnt-beta-catenin and osteo-regenerative pathways. This study aims to analyze gene modules of the Wnt signaling pathway from WGCNA analysis. Methods The study used a microarray dataset from the GEO (GSE228306) to analyze differential gene expression in human primary monocytes. The study standardized datasets using Robust Multi-Array Average (RMA) expression measure and Integrated Differential Expression and Pathway (IDEP) analysis tool, building a co-expression network for group-specific component (GC) genes. Results The study uses WGCNA to identify co-expression modules with dysregulated mRNAs, revealing enrichment in Wnt-associated pathways and top hub-enriched genes like colony-stimulating factor 3 (CSF3), interleukin-6 (IL-6), IL-23 subunit alpha (IL23A), suppressor of cytokine signaling 1 (SOCS1), and C-C motif chemokine ligand 19 (CCL19). Conclusion WGCNA analysis of the Wnt signaling pathway will involve functional annotation, network visualization, validation, integration with other omics data, and addressing method limitations for better understanding.

Effect of microbubble as local drug delivery system in endodontic management - An In-Vitro study.

Background and Objectives: Microbubbles (MBs) are gas or vapor-filled cavities inside liquids with sizes ranging from 2 to 3 µm. Recently, MBs have shown great promise in nanomedicine owing to their high encapsulation efficiency, targeted drug release, improved biocompatibility, and longer blood circulation. Furthermore, they are more suitable for focusing on particular body regions and are safer and non-invasive. MBs generators are used to create bubbles in fluid dynamics, chemistry, medicine, agriculture, and the environment. Drug delivery using MBs increases penetration without causing systemic toxicity. In this study, we examined whether the use of microbubbles as a local drug-delivery mechanism increases tubular penetration of endodontic medications and irrigant. Materials and Methods: An Enterococcus faecalis culture was added to 38 dentin cylinders of single-rooted teeth. Samples were divided into the experimental and control groups that received a triple antibiotic paste with and without MB infusion (n = 19 in each group), respectively. After 14 days, the number of live bacteria in the samples was determined using confocal laser scanning microscopy. Results: After 14 days of contact with the medication, the percentages of live and dead bacteria were assessed. Results show that Group 2 (Triple antibiotic infused micro bubble) showed significantly (P < 0.05) higher antibacterial efficacy than Group 1 (TAP). Conclusion: In this study, the antibacterial efficacy was significantly higher in the experimental group than in the control group. Therefore, within the limitations of the study it can be said that MB infusion is a viable technique to improve root canal disinfection. Hence, it can be considered as a novel technique for local drug delivery systems in endodontic management.

Prediction of Interactomic HUB Genes in Periodontitis With Acute Myocardial Infarction.

BACKGROUND: Acute myocardial infarction (AMI) risk correlates with C-reactive protein (CRP) levels, suggesting systemic inflammation is present well before AMI. Studying different types of periodontal disease (PD), extremely common in individuals at risk for AMI, has been one important research topic. According to recent research, AMI and PD interact via the systemic production of certain proinflammatory and anti-inflammatory cytokines, small signal molecules, and enzymes that control the onset and development of both disorders' chronic inflammatory reactions. This study uses machine learning to identify the interactome hub biomarker genes in acute myocardial infarction and periodontitis. METHODS: GSE208194 and GSE222883 were chosen for our research after a thorough search using keywords related to the study's goal from the gene expression omnibus (GEO) datasets. DEGs were identified from the GEOR tool, and the hub gene was identified using Cytoscape-cytohubba. Using expression values, Random Forest, Adaptive Boosting, and Naive Bayes, widgets-generated transcriptomics data, were labelled, and divided into 80/20 training and testing data with cross-validation. ROC curve, confusion matrix, and AUC were determined. In addition, Functional Enrichment Analysis of Differentially Expressed Gene analysis was performed. RESULTS: Random Forest, AdaBoost, and Naive Bayes models with 99%, 100%, and 75% AUC, respectively. Compared to RF, AdaBoost, and NB classification models, AdaBoost had the highest AUC. Categorization algorithms may be better predictors than important biomarkers. CONCLUSIONS: Machine learning model predicts hub and non-hub genes from genomic datasets with periodontitis and acute myocardial infarction.

Prediction of the Need for Anticonvulsants in the Management of Orofacial Neuropathic Pain Using Machine Learning.

Background and aim Orofacial neuropathic pain is a medical condition caused by a lesion or dysfunction of the nervous system and is one of the most challenging for dental clinicians to diagnose. Anticonvulsants, antidepressants, analgesics, nonsteroidal anti-inflammatory drugs, and other classes of medications are frequently used to treat this condition. Our study aimed to build a machine learning-based classifier to predict the need for anticonvulsant drugs in patients with orofacial neuropathic pain. Materials and methods A machine learning tool that was trained and tested on patients for predicting and detecting algorithms, which would in turn predict the need for anticonvulsants in the treatment of orofacial neuropathic pain, was employed in this study. Results Three machine learning algorithms successfully detected and predicted the need for anticonvulsants to treat patients with orofacial neuropathic pain. All three models showed a high accuracy, that is, 97%, 94%, and 89%, in predicting the need for anticonvulsants. Conclusion Machine learning algorithms can accurately predict the need for anticonvulsant drugs for treating orofacial neuropathic pain. Further research is needed to validate these findings using larger sample sizes and imaging modalities.

Graph neural networks-based prediction of drug gene association of P2X receptors in periodontal pain.

The P2X7 receptor, a member of the P2X receptor family, plays a crucial role in various physiological processes, particularly pain perception. Its expression across immune, neuronal, and glial cells facilitates the release of pro-inflammatory molecules, thereby influencing pain development and maintenance, as evidenced by its association with pulpitis in rats. Notably, P2X receptors such as P2X3 and P2X7 are pivotal in dental pain pathways, making them promising targets for novel analgesic interventions. Leveraging graph neural networks (GNNs) presents an innovative approach to model graph data, aiding in the identification of drug targets and prediction of their efficacy, complementing advancements in genomics and proteomics for therapeutic development. In this study, 921 drug-gene interactions involving P2X receptors were accessed through https://www.probes-drugs.org/. These interactions underwent meticulous annotation, preprocessing, and subsequent utilization to train and assess GNNs. Furthermore, leveraging Cytoscape, the CytoHubba plugin, and other bioinformatics tools, gene expression networks were constructed to pinpoint hub genes within these interactions. Through analysis, SLC6A3, SLC6A2, FGF1, GRK2, and PLA2G2A were identified as central hub genes within the context of P2X receptor-mediated drug-gene interactions. Despite achieving a 65 percent accuracy rate, the GNN model demonstrated suboptimal predictive power for gene-drug interactions associated with oral pain. Hence, further refinements and enhancements are imperative to unlock its full potential in elucidating and targeting pathways underlying oral pain mechanisms.

Prediction of interactomic hub genes in PBMC cells in type 2 diabetes mellitus, dyslipidemia, and periodontitis.

BACKGROUND AND OBJECTIVE: In recent years, the complex interplay between systemic health and oral well-being has emerged as a focal point for researchers and healthcare practitioners. Among the several important connections, the convergence of Type 2 Diabetes Mellitus (T2DM), dyslipidemia, chronic periodontitis, and peripheral blood mononuclear cells (PBMCs) is a remarkable example. These components collectively contribute to a network of interactions that extends beyond their domains, underscoring the intricate nature of human health. In the current study, bioinformatics analysis was utilized to predict the interactomic hub genes involved in type 2 diabetes mellitus (T2DM), dyslipidemia, and periodontitis and their relationships to peripheral blood mononuclear cells (PBMC) by machine learning algorithms. MATERIALS AND METHODS: Gene Expression Omnibus datasets were utilized to identify the genes linked to type 2 diabetes mellitus(T2DM), dyslipidemia, and Periodontitis (GSE156993).Gene Ontology (G.O.) Enrichr, Genemania, and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways were used for analysis for identification and functionalities of hub genes. The expression of hub D.E.G.s was confirmed, and an orange machine learning tool was used to predict the hub genes. RESULT: The decision tree, AdaBoost, and Random Forest had an A.U.C. of 0.982, 1.000, and 0.991 in the R.O.C. curve. The AdaBoost model showed an accuracy of (1.000). The findings imply that the AdaBoost model showed a good predictive value and may support the clinical evaluation and assist in accurately detecting periodontitis associated with T2DM and dyslipidemia. Moreover, the genes with p-value < 0.05 and A.U.C.>0.90, which showed excellent predictive value, were thus considered hub genes. CONCLUSION: The hub genes and the D.E.G.s identified in the present study contribute immensely to the fundamentals of the molecular mechanisms occurring in the PBMC associated with the progression of periodontitis in the presence of T2DM and dyslipidemia. They may be considered potential biomarkers and offer novel therapeutic strategies for chronic inflammatory diseases.

Light gradient boosting-based prediction of quality of life among oral cancer-treated patients.

BACKGROUND AND INTRODUCTION: Statisticians rank oral and lip cancer sixth in global mortality at 10.2%. Mouth opening and swallowing are challenging. Hence, most oral cancer patients only report later stages. They worry about surviving cancer and receiving therapy. Oral cancer severely affects QOL. QOL is affected by risk factors, disease site, and treatment. Using oral cancer patient questionnaires, we use light gradient Boost Tree classifiers to predict life quality. METHODS: DIAS records were used for 111 oral cancer patients. The European Organisation for Research and Treatment of Cancer's QLQ-C30 and QLQ-HN43 were used to document the findings. Anyone could enroll, regardless of gender or age. The IHEC/SDC/PhD/OPATH-1954/19/TH-001 Institutional Ethical Clearance Committee approved this work. After informed consent, patients received the EORTC QLQ-C30 and QLQ-HN43 questionnaires. Surveys were in Tamil and English. Overall, QOL ratings covered several domains. We obtained patient demographics, case history, and therapy information from our DIAS (Dental Information Archival Software). Enrolled patients were monitored for at least a year. After one year, the EORTC questionnaire was retaken, and scores were recorded. This prospective analytical exploratory study at Saveetha Dental College, Chennai, India, examined QOL at diagnosis and at least 12 months after primary therapy in patients with histopathologically diagnosed oral malignancies. We measured oral cancer patients' quality of life using data preprocessing, feature selection, and model construction. A confusion matrix was created using light gradient boosting to measure accuracy. RESULTS: Light gradient boosting predicted cancer patients' quality of life with 96% accuracy and 0.20 log loss. CONCLUSION: Oral surgeons and oncologists can improve planning and therapy with this prediction model.

Therapeutic evaluation of titanium dioxide nanoparticles based herbal dental varnish derived from rosemary and ginger extracts:A comprehensive investigation into anti-inflammatory and antioxidant properties.

BACKGROUND: Titanium nanoparticles (NPs) offer promising applications in the treatment and prevention of inflammatory disorders due to their unique physicochemical characteristics. However, additional research is necessary to attain a thorough comprehension and validate the efficacy of this approach in dental practice. OBJECTIVE: This study scrutinizes the anti-inflammatory properties of a dental varnish infused with ginger and rosemary extracts mediated by titanium dioxide (TiO2) nanoparticles. METHODS: A herbal dental varnish was formulated by integrating ginger and rosemary extracts with titanium dioxide nanoparticles at concentrations of 10, 20, 30, 40, and 50 µL. Anti-inflammatory properties were assessed through Bovine Serum Albumin denaturation and membrane stabilization assays, comparing results with a control group. RESULTS: The results reveal concentration-dependent antioxidant and anti-inflammatory properties in the test group when compared to the control group. The BSA assay corroborates increased percent inhibition with rising titanium dioxide nanoparticle concentrations. In line with existing literature, titanium dioxide nanoparticles enhance dental material properties. CONCLUSION: The bioactive compounds in ginger and rosemary, such as phenolic compounds and terpenes, contribute to anti-inflammatory and antioxidant effects of the varnish. Additionally, the therapeutic potential of titanium dioxide nanoparticles in addressing inflammatory diseases underscores their significance in this formulation.

Artificial Intelligence: A Reliable Tool to Detect the Elongation of the Styloid Process.

Background Eagle's syndrome is characterized by the anomalous elongation of the styloid process. This condition is usually identified through the manual evaluation of orthopantomogram (OPG) images, which is time-consuming and can have interobserver variability. The application of Artificial intelligence (AI) in radiology is gaining importance and interest in recent years. The application of AI in detecting styloid process elongation is less explored, advocating for research in the same arena. Aim and objectives The study aimed to evaluate the accuracy of artificial intelligence in detecting styloid process elongation in digital OPGs and to compare the performance of the three different AI algorithms with that of the manual radiographic evaluation by the radiologist. Materials and methods A total of 400 digital OPGs were screened, and linear measurements of the styloid process length (ImageJ software (National Institute of Health, Maryland, USA)) were done for the identification of styloid process elongation by a single calibrated observer to finally include a processed image dataset including 169 images of the elongated styloid process and 200 images of the normal styloid process. A machine learning approach was used to detect the styloid process elongation using the three different AI models: logistic regression, neural network, and Naïve Bayes algorithms in Orange software (University of Ljubljana, Slovenia). Performance evaluation was done using the accuracy, sensitivity, specificity, precision, recall, F1 score, and AUC-ROC (area under the receiver operating characteristic) curve. Results Logistic regression and neural network algorithms depicted the highest accuracy of 100% with no false positives or false negatives, securing a score of 1.000 for all the metrics. However, the Naïve Bayes model demonstrated a fairly considerable accuracy, classifying 49 false positive images and 59 false negative images with an AUC (area under the curve) score of 78 %. Nevertheless, it performed better than random guessing. Conclusion Logistic regression and neural network algorithms accurately detected styloid process elongation similar to that of manual radiographic evaluation. The Naïve Bayes algorithm did not perform an accurate classification yet performed better than random guessing. AI holds a promising scope for its application in automatically detecting styloid process elongation in digital OPGs.