Search Results (513)

Artificial intelligence (AI) and machine learning (ML) are transforming the landscape of rheumatological and systemic inflammatory disease management, offering unprecedented capacity to integrate complex, multidimensional data for diagnostic support, disease monitoring, and therapeutic decision-making. This comprehensive narrative review, based on a non-systematic literature search of PubMed/MEDLINE and Google Scholar combined with the authors’ clinical expertise, provides a clinically oriented synthesis of current and emerging AI applications across the full spectrum of immune-mediated inflammatory diseases—including rheumatoid arthritis, systemic lupus erythematosus, vasculitis, inflammatory bowel disease, psoriatic arthritis, systemic sclerosis, inflammatory myopathies, and sarcoidosis—with particular attention to applications that have demonstrated or are approaching clinical utility. We discuss deep learning-based image analysis, natural language processing of electronic health records, multi-omic biomarker discovery, and the application of Fourier transform-based signal processing to biological time series as a novel approach to continuous disease monitoring. Fourier transform methods—already foundational in MRI reconstruction, cardiac electrophysiology, and clinical neurophysiology—are here systematically extended to rheumatological and inflammatory disease signals, including accelerometry, electromyography, heart rate variability, and longitudinal biomarker time series. The phenomenon of large language model hallucination—particularly critical in rare inflammatory diseases—is addressed alongside retrieval-augmented generation as a mitigation strategy. We further argue that AI-driven methods do not merely improve the interpretation of clinical data, but fundamentally expand what is observable—with profound epistemological implications for clinical knowledge transmitted through generations of medical tradition. Ethical considerations and future directions toward precision inflammatory disease medicine are outlined. Full article

Pulmonary hypertension (PH) is a heterogeneous clinical syndrome in which similar haemodynamic abnormalities may arise from distinct vascular, cardiac, pulmonary, thromboembolic, and molecular mechanisms. This complexity limits the ability of conventional classifications and risk scores to fully capture individual disease trajectories and treatment responses. Artificial intelligence (AI) offers a framework for integrating clinical data, electrocardiography, multimodal imaging, invasive haemodynamics, biomarkers, and multi-omics information across the PH care pathway. This review summarises current applications of machine learning and deep learning in early detection, diagnostic referral, right-ventricular and pulmonary vascular phenotyping, molecular endotyping, risk stratification, and therapeutic decision support. Available studies show promising results for AI-assisted electrocardiographic screening, automated echocardiographic and cardiac magnetic resonance analysis, computed tomography (CT)-based phenotyping, and multimodal prognostic modelling. True multi-omics integration in PH remains limited to discovery studies and has not yet yielded externally validated endotype or treatment-response classifiers. Evidence maturity is task-dependent: screening and phenotyping span several PH groups, whereas validated risk tools, molecular endotyping, and pathway-directed therapy remain predominantly PAH-based, particularly in idiopathic/heritable PAH. However, most evidence remains retrospective, derives from selected referral populations, and lacks robust external or prospective validation. No AI-based model currently supports routine drug selection or autonomous clinical decision-making. Future progress will require harmonised multicentre datasets and standardised acquisition protocols, transparent and interpretable models, and prospective studies demonstrating meaningful clinical benefit. AI should therefore be viewed as an emerging decision-support tool that may strengthen precision medicine in PH while complementing clinical expertise across diagnosis, phenotyping, risk assessment, and therapeutic stratification pathways. Full article

Osteosarcopenia, defined as the coexistence of low bone mass and sarcopenia, is a multifactorial condition influenced by molecular crosstalk between bone and muscle. Growing evidence suggests that this interaction contributes to disease progression and highlights the need for integrated diagnostic and therapeutic approaches. Artificial intelligence (AI) is emerging as an important tool for the clinical management of osteosarcopenia, with potential applications in risk prediction, early diagnosis, evaluation of adverse outcomes such as fractures and falls, imaging analysis, and personalized treatment planning through machine learning and deep learning algorithms or with the support of large language models. This narrative review summarizes current evidence on the pathophysiological mechanisms underlying osteosarcopenia, with particular emphasis on the molecular mediators involved, and examines the current and potential applications of AI in its clinical assessment and management. By integrating advances in musculoskeletal biology with AI-driven approaches, this review highlights emerging opportunities to improve early detection, optimize clinical decision-making, and support the development of precision medicine strategies for patients with osteosarcopenia. Full article

Objectives: To synthesize current evidence regarding advances in periodontal diagnosis and therapy, with emphasis on molecular biomarkers, omics technologies, microbiome profiling, digital imaging, and artificial intelligence-based analytical models that support the transition toward precision periodontology. Methods: This narrative review examines contemporary evidence on emerging molecular, microbiological, and digital technologies applied to periodontal diagnosis, prognostic assessment, and therapeutic planning. The review includes studies addressing salivary and gingival crevicular fluid biomarkers, microbiome characterization, omics approaches, cone-beam computed tomography, three-dimensional imaging, machine-learning algorithms, and personalized periodontal therapies. Relevant literature was identified through searches in major biomedical databases, including PubMed/MEDLINE, Scopus, and Web of Science, focusing on studies published on periodontal diagnostics, biomarkers, digital technologies, artificial intelligence, and precision medicine approaches in periodontology. Results: Peer-reviewed articles addressing innovative diagnostic and therapeutic approaches in periodontology were considered. Priority was given to studies evaluating clinical applicability, diagnostic performance, prognostic utility, and personalized treatment strategies integrating molecular and digital technologies. Conclusions: Emerging molecular and digital technologies are reshaping periodontal diagnosis and therapy by improving disease detection, risk prediction, and individualized treatment planning. Biomarkers, omics technologies, microbiome profiling, and artificial intelligence-assisted imaging may enhance diagnostic precision and clinical decision-making. These developments support the implementation of precision periodontology; however, challenges related to biomarker validation, algorithm standardization, cost, and accessibility remain barriers to routine clinical adoption. Further research is necessary to validate these approaches and facilitate their integration into periodontal practice. The integration of biomarkers, omics technologies, advanced imaging, and artificial intelligence may improve early periodontal diagnosis, prognostic assessment, and personalized treatment planning. These innovations support the transition toward precision periodontology and have the potential to enhance clinical decision-making, treatment outcomes, and long-term periodontal health in routine dental practice. Full article

Background/Objectives: Immune-mediated inflammatory skin diseases (IMSDs), including psoriasis, atopic dermatitis, and systemic sclerosis, are chronic relapsing disorders that impose substantial physical, psychological, and economic burdens. Current assessment relies largely on subjective clinical scoring and conventional imaging modalities that provide limited functional information. This structured narrative review evaluates photoacoustic imaging (PAI) as a non-invasive optical-ultrasound technique for morphological and functional assessment in IMSDs. Methods: We searched PubMed studies published from January 2017 to December 2025 using terms related to photoacoustic imaging, optoacoustic mesoscopy, psoriasis, atopic dermatitis, systemic sclerosis, contact dermatitis, and immune-mediated inflammatory skin disease. Studies were narratively synthesized by disease, PAI modality, comparator, outcome, and translational limitation. Main Findings: PAI can map vascular and pigment-related optical absorption and estimate oxygenation, blood volume, and selected structural biomarkers. In psoriasis, atopic dermatitis, and systemic sclerosis, PAI-derived measures have been associated with clinical severity, subclinical vascular or epidermal changes, and treatment response. However, most available studies are small, single-center, heterogeneous, or based on prototype systems, and several biomarkers still require histopathological and external validation. Conclusions: Current evidence supports PAI as a feasible research and potential adjunctive assessment tool for IMSDs rather than an established replacement for standard clinical, histopathological, or imaging methods. Standardized protocols, validation across skin phototypes, cost-effective devices, and prospective multicenter studies are required before routine clinical adoption. Full article

TDP-43 proteinopathies, encompassing amyotrophic lateral sclerosis (ALS), frontotemporal lobar degeneration (FTLD), and limbic-predominant age-related TDP-43 encephalopathy (LATE), represent a heterogeneous spectrum of devastating neurodegenerative disorders. For decades, the diverse clinical presentations of these diseases have complicated antemortem diagnosis and hindered the development of disease-modifying therapies. However, recent breakthroughs in basic science are beginning to address these clinical barriers, although substantial hurdles to practical clinical application remain. Structural elucidation via cryo-electron microscopy (Cryo-EM) has shattered the single-protein amyloid dogma by revealing that TDP-43 can form hetero-amyloid filaments with ANXA11, thereby providing a molecular basis for pathological strain diversity. Concurrently, the pathogenic focus has shifted toward nuclear loss of function, which triggers a systemic “RNA crisis” characterized by aberrant alternative polyadenylation (APA) and cryptic exon inclusion (e.g., STMN2, UNC13A). Crucially, this metabolic collapse is profoundly exacerbated by patient-specific genetic risk factors, acting synergistically in a “two-hit” model of neurodegeneration. To translate these findings to the clinic, next-generation diagnostic tools are emerging. Integrating neuron-derived extracellular vesicle (EV) isolation with Seed Amplification Assays (SAAs) holds promise to help overcome the structural camouflage that limits current PET imaging, potentially offering ultra-sensitive, functional strain identification in biofluids. While these structural and diagnostic milestones provide a strong foundation for precision medicine, major challenges in assay standardization and clinical validation must be addressed. Advanced therapeutic strategies—namely, splice-switching antisense oligonucleotides (ASOs) that directly restore RNA metabolism, combined with the targeted suppression of neuronal hyperexcitability—are now entering clinical trials. This review synthesizes how decoding the structural and RNA-metabolic complexities of TDP-43 is paving a promising pathway from bench to bedside, while critically discussing current translational limitations. Full article

Mesoporous silica nanoparticles (MSNs) have emerged as versatile nanocarriers for biomedical applications because of their unique physicochemical properties, including high surface area, large pore volume, excellent drug-loading capacity, controllable biodegradation, and facile surface functionalization. These characteristics have enabled the development of advanced drug delivery systems with enhanced therapeutic efficacy, targeted delivery, improved bioavailability, and reduced systemic toxicity. Recent advances in MSN synthesis, physicochemical properties, surface engineering, and functionalization strategies have significantly improved their biological performance and therapeutic potential. In particular, integrating polymers, lipids, and liposomes with MSN platforms has enhanced colloidal stability, circulation time, cellular uptake, and target specificity, thereby facilitating efficient, stimuli-responsive drug delivery. This review highlights MSN-based drug delivery systems in cancer therapy, where multifunctional nanocarriers enable site-specific delivery, controlled drug release, enhanced tumor accumulation, and reduced off-target effects. The review discusses the expanding roles of MSNs in antimicrobial therapy, wound healing, tissue engineering, and regenerative medicine, emphasizing their ability to promote localized therapeutic delivery, immunomodulation, angiogenesis, and tissue regeneration. The review discusses the diagnostic and theragnostic capabilities of MSNs for disease imaging and monitoring. It also critically evaluates current challenges related to biocompatibility, biodegradation, toxicity, biological barriers, large-scale manufacturing, clinical translation, and regulatory considerations. This review provides a comprehensive overview of recent progress, current limitations, and future opportunities for MSN-based platforms in targeted drug delivery and advanced biomedical applications, supporting their continued advancement toward clinical translation and precision medicine. Full article

AI-generated synthetic media are evolving from tools of digital manipulation into a practical antidote for persistent challenges in digital health implementation. However, the computational capabilities that characterise these technologies, their applications and downstream health-related benefits remain fragmented and insufficiently synthesised. This systematic review identified the computational capabilities that characterise AI-generated synthetic media in health, examined their applications and benefits, and developed an integrative framework linking these domains. Twenty-four studies published between 2021 and 31 May 2026 were included. Methodological quality was assessed using the Mixed Methods Appraisal Tool (MMAT) and findings were synthesised through thematic analysis. The synthesis revealed an integrated set of capabilities spanning photorealistic medical-image generation, modality-specific synthesis of clinical images and physiological signals, synthetic non-image health-data creation, preservation of statistical distributions, temporal patterns and clinical relationships, generation of diverse, novel and non-memorised samples and controlled transformation of medical and audiovisual content. Privacy-oriented synthesis and deepfake detection emerged as distinct components supporting privacy-conscious data use, clinical verification and healthcare safety. These demonstrated capabilities were linked to empirically evaluated and indicated applications, including data augmentation, AI model training, diagnostic model development, privacy-oriented health-data sharing, medical education, patient-facing communication, therapeutic support, clinical safety, health-system analytics and planning. The resulting Computational Capability–Application–Benefit (CAB) Framework conceptualises synthetic media as an evidence-graded pathway distinguishing demonstrated computational capabilities, evaluated health-related applications and reported, indicated or potential downstream benefits requiring further validation. AI-generated synthetic media, therefore, represent an emerging computational infrastructure with potential to support safer, privacy-conscious, adaptive and data-intensive healthcare. Full article

Integrins are heterodimeric transmembrane receptors that mediate bidirectional signaling and regulate cell–cell and cell–extracellular matrix interactions. Integrin αvβ6 is an epithelial-associated integrin that has emerged as a promising molecular target for PET/CT imaging using integrin αvβ6-directed radiotracers such as ⁶⁸Ga-Trivehexin, and, most recently, for antibody–drug conjugate therapy in epithelial malignancies. Unexpected physiological and incidental uptake within the pituitary gland has been reported in integrin αvβ6-targeted PET studies, including uptake in morphologically normal pituitary glands and pituitary neuroendocrine tumors (PitNETs). However, the histological basis of integrin αvβ6 expression in the human pituitary gland remains poorly understood. The aim of this study is to characterize the immunohistochemical expression of integrin αvβ6 in normal human pituitary tissue and PitNETs and to evaluate its potential implications for integrin αvβ6-targeted imaging and theranostic applications. Five complete adult pituitary glands obtained at autopsy and 28 PitNETs were examined by immunohistochemistry for integrin αvβ6. Staining distribution, intensity, and cellular localization were assessed in the adenohypophysis, neurohypophysis, and Rathke’s cleft remnants. PitNETs were classified according to transcription factor expression (PIT1, TPIT, and SF1). Among the 28 PitNETs, 17 were SF1-lineage (60.7%), three were PIT1-lineage (10.7), two were TPIT-lineage (7.1%), three lacked a dominant transcription factor (10.7%), and three showed plurilineage expression (10.7%). Integrin αvβ6 expression was evaluated semiquantitatively according to staining intensity and the percentage of positive tumor cells. In normal pituitary glands, integrin αvβ6 immunoreactivity was predominantly membranous and localized to larger adenohypophyseal cells irrespective of transcription factor lineage or hormone phenotype. Strong expression was also observed in the epithelial lining cells of Rathke’s cleft remnants, whereas the neurohypophysis lacked detectable integrin αvβ6 expression. Among the 28 PitNETs, integrin αvβ6 expression was detected in 20 cases (71.4%). Positive tumors demonstrated variable staining intensity and extent, ranging from 20% to 100% positive tumor cells. By lineage, integrin αvβ6 expression was detected in 13 of 17 SF1-lineage tumors (76.5%), one of three PIT1-lineage tumors (33.3%), and zero of two TPIT-lineage tumors (0%). Additionally, all three tumors lacking a dominant transcription factor (100%) and all three plurilineage tumors (100%) demonstrated integrin αvβ6 expression. Eleven integrin αvβ6-positive tumors showed expression in ≥50% of tumor cells, and six exhibited strong or diffuse immunoreactivity. Integrin αvβ6 expression in adenohypophyseal cells and Rathke’s cleft remnants provides a histological explanation for physiological pituitary uptake observed on αvβ6-targeted PET/CT imaging. The high prevalence of integrin αvβ6 expression in PitNETs, particularly in a subset demonstrating strong and diffuse immunoreactivity, suggests potential applicability of integrin αvβ6-targeted molecular imaging and theranostic approaches, including both radioligand- and antibody-based strategies. However, these applications remain investigational and require further validation in preclinical and clinical studies. At the same time, physiological integrin αvβ6 expression in normal anterior pituitary tissue may limit imaging specificity and should be considered when developing integrin αvβ6-targeted radioligand therapies. Further clinicopathological and imaging correlation studies are warranted to define the diagnostic and therapeutic role of integrin αvβ6-targeted approaches in PitNETs. Full article

The Functional Lumen Imaging Probe (EndoFLIP^®) system is an impedance-based technology providing real-time measurements of cross-sectional area (CSA) and intraballoon pressure across a luminal segment. Initially developed for esophagogastric junction (EGJ) evaluation in achalasia, the application of EndoFLIP has subsequently expanded to the assessment of both sphincteric and non-sphincteric regions throughout the gastrointestinal tract in a variety of clinical conditions, including eosinophilic esophagitis (EoE), post-fundoplication states, and gastroparesis. Its unique ability to be utilized in both the diagnostic and therapeutic settings, including the assessment of treatment response, makes it a valuable tool in the overall management of gastrointestinal motility disorders. The present review extends beyond a simple overview of EndoFLIP applications by providing a comprehensive evaluation of its performance in comparison with other diagnostic modalities, as well as the current knowledge gaps regarding its use. Study limitations and procedure-related aspects requiring further investigation are critically discussed, with the aim of supporting and guiding future research in this field. Full article

Theranostic nanoparticles, which integrate diagnostic imaging and therapeutic delivery within a single nanoplatform, represent a transformative paradigm in oncological nanomedicine. Despite substantial preclinical progress, the field faces persistent gaps in rational nanoparticle design informed by tumor biology, preclinical model fidelity, and clinical translation. This review critically synthesizes theranostic nanoparticle research across three underexplored domains. First, we examine tumor microenvironment features—reactive oxygen species dynamics, glutathione gradients, hypoxia, and proteasomal dysregulation—as mechanistic drivers of nanoparticle responsiveness. Second, we evaluate redox-responsive and proteasome-targeted nanoplatforms that exploit these cues for stimuli-triggered drug release and simultaneous imaging readout. Third, we address the unmet need for three-dimensional organoid and microfluidic tumor models as predictive preclinical testing environments, given the well-documented limitations of conventional two-dimensional cultures. Cancer subtype-specific applications are discussed for breast cancer, HPV-associated malignancies, colorectal cancer, and prostate cancer. Clinical translation barriers—including pharmacokinetic constraints, protein corona formation, immune clearance, anti-PEG antibodies, complement activation-related pseudoallergy, and FDA/EMA regulatory pathways—are addressed from a clinical oncology perspective. The review concludes with a research roadmap integrating proteomics-guided nanoparticle engineering, patient-derived organoid biobanks, and artificial intelligence-assisted design as priority areas for next-generation oncological theranostics. Full article

(1) Background: Pancreatic ductal adenocarcinoma remains one of the most lethal malignancies due to late diagnosis, aggressive tumor biology, and limited therapeutic options. Artificial intelligence has emerged as a promising tool to improve detection, risk stratification, and treatment planning. This study aims to review the current clinical applications of artificial intelligence in the management of pancreatic cancer and evaluate its translational potential. (2) Methods: A comprehensive literature search was conducted across major databases (PubMed/MEDLINE, Scopus, Web of science and Cochrane) for studies published between 2015 and 2026. Eligible studies included clinical investigations and systematic reviews reporting quantifiable outcomes related to diagnosis, staging, prognostication, and treatment response using artificial intelligence methods. (3) Results: A total of 24 studies were included, most of which were retrospective and utilized imaging, histopathology, and clinical datasets. Artificial intelligence demonstrated high diagnostic performance, particularly in imaging-based detection and lesion characterization, with several models achieving excellent accuracy. Applications in staging, surgical planning, and prognostication also showed promising results, although external validation and prospective data were limited. (4) Conclusions: Artificial intelligence has significant potential to enhance the management of pancreatic cancer, particularly as a decision-support tool. However, further prospective validation and integration into clinical workflows are required before widespread adoption. Full article

Neurofibromatosis type 1 (NF1) is a genetic tumor predisposition syndrome characterized by a substantial risk of developing peripheral nerve sheath tumors, including malignant peripheral nerve sheath tumors (MPNSTs), which occur in 8–13% of patients. Approximately 50% arise from plexiform neurofibromas (PNs) and 40% develop de novo, making them a major cause of premature mortality. Current clinical management is limited by the intrinsic shortcomings of standard imaging modalities: magnetic resonance imaging (MRI) and positron emission tomography/computed tomography (PET/CT), and tissue biopsy in distinguishing benign PNs from early malignant transformation, which remains a major clinical challenge. This progression follows a stepwise molecular continuum marked by cumulative genetic alterations and widespread epigenetic dysregulation. In this setting, liquid biopsy has emerged as a promising non-invasive approach to help fill these diagnostic gaps by enabling real-time molecular monitoring through the analysis of circulating tumor DNA (ctDNA) and other blood-based biomarkers. This review examines the current evidence supporting liquid biopsy applications in NF1 management, including early detection of MPNST, discrimination between benign and malignant lesions, mutational profiling for therapeutic targeting, and disease monitoring before and during treatment. We also discuss the current evidence on fragmentomics, methylomics and driver mutation profiling as tools to distinguish PNs from MPNSTs. Recent evidence suggests that liquid biopsy may help detect molecular changes associated with malignant transformation before clear clinical signs emerge, potentially opening an important window for intervention and supporting a shift towards a more molecularly informed surveillance model. Finally, this review considers the possible extension of liquid biopsy to other tumor types, including NF1-deficient breast cancer, and outlines a future management framework aimed at improving early diagnosis and personalized therapeutic intervention in this high-risk population. Full article

Epidermolysis bullosa (EB) comprises a group of rare inherited genodermatoses characterized by fragility and blistering of the skin and mucous membranes, chronic wounding, and significant morbidity including increased risk of squamous cell carcinoma in severe subtypes. Key unmet priorities include reducing diagnostic latency, establishing objective wound monitoring, enabling early detection of malignant transformation within chronic ulcerations, and developing therapies that durably modify disease progression. Artificial intelligence (AI) encompassing machine learning (ML), and deep learning (DL) is increasingly integrated into EB research and clinical practice to address these unmet needs. This structured narrative review synthesises current evidence on AI applications in EB spanning genetic diagnostics, wound assessment, inflammatory endotyping, drug repurposing, and emerging therapeutic technologies, and integrates evidence from registered clinical trials. In genomics, DL-based splicing prediction models and variant prioritisation frameworks accelerate pathogenic variant detection and reduce diagnostic latency. In wound care, convolutional neural networks-based platforms enable automated lesion segmentation and remote monitoring, while multimodal AI models predict healing trajectories and support stratification of wounds by chronicity. Computational transcriptomic analyses have identified candidate repurposing agents by reversing pathogenic gene expression signatures in EB tissue. Emerging convergence of AI with biosensors-integrated wound dressings and three-dimensional bioprinting of genetically corrected skin substitutes represents a transformative future direction. Translational barriers include limited EB-specific training datasets, algorithmic bias across diverse skin phototypes, the interpretability deficit of DL systems, and evolving regulatory frameworks for AI as a medical device. Expansion of internationally interoperable EB disease registries with standardised wound imaging protocols is identified as the single most impactful intervention to accelerate AI adoption. A minimum endpoint set for AI-assisted EB wound assessment, incorporating wound area trajectory, wound type classification, tissue composition, and paired patient-reported pain and itch scores, is proposed to standardise outcome reporting across future studies. Full article

In medicine, nanoparticles are used for various purposes, including theranostics, imaging, diagnostics, drug delivery, tissue regeneration and targeted cancer treatments, and to minimize the harmful side effects associated with conventional therapies. Target-specific biomolecules, such as silica nanoparticles (SiNPs) labeled with metallic radionuclides, are becoming increasingly popular. The choice of radionuclide is based on its nuclear properties. Silica has several advantages for nanoparticle synthesis, including high biocompatibility, the capacity for drug encapsulation due to its porous structure, and the potential for extensive surface functionalization, including radiolabeling for imaging and therapeutic applications. A radionuclide can be attached to a silica nanoparticle either directly or through the use of chelators or polymers. Additionally, the capability to encapsulate therapeutic agents within such systems offers significant potential for the development of targeted therapies. This study aims to provide a comprehensive overview of recent developments in the radiolabeling of silica-based nanoparticles, with a focus on their application in nuclear medicine, particularly in diagnostic imaging and targeted radionuclide therapy. Theranostics employs a range of imaging modalities to guide and monitor therapeutic interventions. Principal techniques include positron emission tomography (PET), single-photon emission computed tomography (SPECT), magnetic resonance imaging (MRI), and Optical Imaging (such as fluorescence and bioluminescence). These imaging methods enable precise visualization of pathological sites, facilitate tracking of therapeutic agent distribution, and permit real-time assessment of treatment efficacy. Full article