Biomarkers

Periodontitis is a multifactorial inflammatory disease characterized by progressive destruction of the periodontal supporting tissues, resulting from complex interactions between microbial biofilm and host immune responses. Conventional diagnostic approaches, including periodontal probing and radiographic evaluation, are limited by examiner variability and challenges in interpreting multiple interacting risk factors. In recent years, Artificial Intelligence (AI) has emerged as a promising adjunct in periodontology, enhancing diagnostic precision, risk assessment, and personalized treatment planning. AI applications in clinical periodontology include Natural Language Processing (NLP) for structured data extraction and improved clinical documentation, as well as machine learning and deep learning models for radiographic and clinical analysis. Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs) have demonstrated high accuracy in detecting periodontal bone loss, classifying disease severity, identifying implant systems, and predicting disease progression. Integration of radiographic, clinical, and multi-omics datasets further supports comprehensive risk profiling and precision-based care. Additionally, AI-assisted biomarker analysis using saliva and gingival crevicular fluid shows potential for non-invasive early detection. Emerging technologies such as smartphone-based monitoring systems, AI-enabled oral hygiene devices, and augmented/virtual reality–based educational tools enhance patient engagement and professional training. Despite challenges including data privacy concerns, ethical considerations, high implementation costs, and limited large-scale clinical validation, AI represents a valuable assistive technology that strengthens clinical decision-making and advances personalized periodontal care. This article aims to comprehensively discuss the current applications of artificial intelligence in periodontology, highlighting recent advancements, clinical implications, limitations, and future perspectives for integrating AI into routine periodontal practice. Keywords: Periodontitis; Artificial Intelligence; Deep Learning; Convolutional Neural Networks; Artificial Neural Networks; Natural Language Processing; Periodontal Diagnosis; Radiographic Analysis; Biomarkers;

Cancer stem cells (CSCs) represent a critical subpopulation driving tumor initiation, progression, metastasis, and therapeutic resistance. Their remarkable plasticity and ability to self-renew underlie cancer’s resilience and recurrence following conventional treatments. Recent advances in liquid biopsy technology have transformed cancer diagnostics by enabling the minimally invasive detection and dynamic monitoring of tumor-derived materials, including circulating tumor cells, cell-free nucleic acids, and exosomes. This review synthesizes the current landscape of CSC biomarkers, encompassing classical surface markers, epigenetic and metabolic signatures, and emerging multi-omic molecular profiles. We assess how these biomarkers are integrated into advanced liquid biopsy platforms, evaluating their diagnostic sensitivity and specificity as well as their clinical utility in tracking CSC dynamics throughout cancer progression and therapy. Technical challenges such as isolating rare CSC populations and distinguishing CSC-specific signals from normal stem cells are addressed, alongside developments in single-cell analysis, computational modeling, and multiplexed marker assays enhancing biomarker precision. Furthermore, we highlight the tumor microenvironment’s role in modulating CSC phenotypes and implications for biomarker reliability. By bridging foundational CSC biology with cutting-edge technologies in liquid biopsy, this review outlines translational strategies to better detect, characterize, and target CSCs, ultimately striving to improve outcomes by overcoming therapeutic resistance and reducing cancer relapse.

Biomarkers provide a dynamic and powerful approach to understand the spectrum of various diseases with applications in observational and analytic epidemiology, randomised clinical trials, screening and diagnosis and prognosis. In the recent years knowledge about biomarkers has increased tremendously providing great opportunities for improving the management of patients by enhancing the efficacy of detection and efficacy of treatment. This review provides a brief account on various biomarkers for diagnosis, prognosis and therapeutic purposes, which include markers already in clinical practice as well as various upcoming biomarkers.