Lactoferrin-modified niclosamide lipid nanocarriers reprogram ferroptosis and antioxidant networks for breast cancer suppression.

Covalent organic frameworks (COFs) have emerged as a versatile class of crystalline reticular materials distinguished by their high surface area, permanent porosity, and atomically precise structural tunability. Their modular synthesis enables precise control over pore size, geometry, and surface functionality, while offering excellent chemical stability and intrinsic biocompatibility. These attributes make COFs uniquely suited for applications as precision nanocarriers in targeted drug delivery. Recent advances demonstrate that COFs can encapsulate therapeutic agents with high loading efficiency and facilitate controlled, stimuli-responsive release profiles. Furthermore, the incorporation of targeting moieties through linker design or post-synthetic modification enables site-specific delivery, minimizing off-target cytotoxicity and enhancing therapeutic efficacy-particularly in oncological contexts. This review critically evaluates the current landscape of COF-based drug delivery systems, detailing structural design strategies, loading and release mechanisms, and functionalization approaches for precision targeting. We also highlight key challenges-such as scalable synthesis, pharmacokinetics, and in vivo stability-and outline promising research directions toward the clinical translation of COF nanocarriers for personalized medicine.

The review has comprehensively examined the therapeutic potential of phytoconstituents in the treatment of arthritis with specific emphasis being given to diosgenin as a promising natural molecule. Arthritis is a significant health concern in the world, with its two most common types; Osteoarthritis and rheumatoid arthritis, becoming the causes of disability, and expensive to manage in the long run. Even though disease-modifying anti-rheumatic drugs and biologics have helped to better the patient outcomes, their side effects, high treatment cost, and inaccessibility demonstrate the necessity of safer and cheaper alternatives. The pharmacological significance of the root steroidal sapogenin, diosgenin, as a derivative of the species Dioscorea, that exhibits strong anti-inflammatory effects with clearly defined, molecular-based, mechanisms, is highlighted in this manuscript. Diosgenin suppresses cartilage destruction because of matrix metalloproteinases, the NF-kB signaling pathway as well as the major pro-inflammatory cytokines, TNF-a, IL-1b, and IL-6. It also has chondroprotective action to maintain the integrity of the extracellular matrix, increase levels of type II collagen and aggrecan, and decrease the expression of MMP-3 and MMP-13 by about 65-85% in the presence of inflammation. The challenges to clinical translation associated with formulation which are discussed in the review include the very low aqueous solubility of diosgenin (0.95 ug/mL) and oral bioavailability (< 7%). It addresses the use of the advanced delivery systems, including lipid nanoparticles, vesicular carriers and amorphous solid dispersions, which have demonstrated a 2.55-fold increase in bioavailability and also have the potential to improve therapeutic efficacy. Crucially, this review uniquely integrates these bioavailability enhancement strategies with diosgenin's underlying molecular mechanisms, illustrating how optimised delivery systems are essential to fully unlock its therapeutic potential. Despite robust preclinical evidence supporting its anti-arthritic and chondroprotective actions, clinical investigations remain scarce, with only a few small studies and none directly evaluating diosgenin for arthritis outcomes. Overall, this review emphasises the need for well-designed clinical trials to validate the therapeutic promise of diosgenin and related phytoconstituents, paving the way for safer, accessible, and multi-targeted natural interventions for arthritis management.

Percutaneous puncture techniques have been widely adopted across various domains of modern clinical interventional therapy due to their high diagnostic specificity, minimal invasiveness, and rapid postoperative recovery. However, the nonholonomic kinematics arising from the interaction between flexible needles and soft tissues, combined with the complexity of human anatomical structures, pose significant challenges to robot-assisted flexible needle insertion. To address these challenges, this paper proposes an improved rapidly-exploring random tree (RRT) path planning algorithm incorporating soft actor critic (SAC)-guided sampling. By integrating SAC-guided sampling strategies, the algorithm offers effective sampling guidance for path planning, significantly reducing the randomness of the search process, minimizing the generation of invalid nodes, accelerating convergence, and improving both path quality and planning efficiency. A hybrid sampling strategy is employed to balance global exploration and local exploitation capabilities, thereby enhancing adaptability and planning performance in complex anatomical environments. Furthermore, a navigation and positioning robot is integrated to autonomously guide the needle toward the target, thereby improving the autonomy of the insertion procedure. Target insertion experiments demonstrate an error of 0.97 ± 0.41 mm in synthetic biomimetic tissue, demonstrating strong potential for clinical translation.

Recently, inflammatory cytokine profiles have been linked to suicide risk in adolescents with non-suicidal self-injury, highlighting a promising biological dimension of suicide risk assessment. Clinical translation of the cytokine profiles into practice will require frontline engagement of the workforce. Mental health nurses are frequently the most accessible professionals in schools, communities, and low-resource settings and are prime candidates to bridge this gap. By integrating psychosocial evaluation with emerging biomarker data, they can deliver systematic risk assessment, continuous monitoring, and timely intervention. This role would not replace psychiatric expertise; it would extend the reach of psychiatric services, embedding suicide prevention across the continuum of care. For health systems, nurse-led integration may enhance capacity, equity, and resilience in responding to adolescent suicide risk. This editorial demonstrates that empowering nurses to operationalize biomarker-informed strategies is needed for advancing effective and sustainable suicide prevention in this vulnerable population.

Prostate cancer (PC) treatment is limited by resistance mechanisms and cumulative toxicities, necessitating novel therapeutic strategies. While curcumin and piperine exhibit potent anticancer properties, their clinical utility is severely compromised by poor bioavailability and rapid metabolism. This review critically analyzes the preclinical and clinical landscape of curcumin and piperine nanoformulations (CPN) for the treatment of PC. We utilized PubMed and Scopus (2000-2025) to evaluate molecular mechanisms, focusing on CYP17A1 inhibition, PI3K/Akt/mTOR signaling, and ferroptosis. The report examines the physicochemical properties of nanocarriers, including PLGA and liposomes, and addresses translational barriers such as the heterogeneity of the Enhanced Permeability and Retention (EPR) effect, stromal density, and risks associated with piperine-mediated drug - drug interactions. While nano-encapsulation enhances the therapeutic index of curcumin, clinical translation remains stalled by a reliance on passive targeting and insufficient manufacturing scalability. Future success depends on shifting from 'beaker' synthesis to microfluidic production (Quality by Design) and adopting active targeting (e.g. PSMA-directed delivery) to penetrate the prostate stroma. Without these strategic pivots and biomarker-driven trials, CPNs risk remaining an academic curiosity rather than evolving into a viable clinical intervention.

Type I interferons (IFN-I) are central to pathogenesis and monitoring of systemic lupus erythematosus (SLE), yet clinically accessible biomarkers remain limited. Building on prior validation of membrane-bound SIGLEC-1 (mbSIGLEC-1), we conducted a proof-of-concept study to evaluate soluble SIGLEC-1 (sSIGLEC-1) as a useful IFN-I biomarker in SLE. The study prospectively enrolled 61 SLE patients and 100 blood donors as controls. In SLE patients, disease activity indices (DAI) and routine SLE and IFN biomarkers (IFNα, IP-10, mbSIGLEC-1) were assessed longitudinally. sSIGLEC-1 was measured using chemiluminescence immunoassay; a cohort-specific threshold was defined by ROC analysis. Cross-sectional correlations between DAIs and biomarkers were analysed in all patients, longitudinal analyses included 23 patients over 57 visits. Flare-predictive value was evaluated in 27 patients with quiescent disease over 180 days. We determined a threshold for sSIGLEC-1 at 4.55 ng/ml (sensitivity: 70.49%, specificity: 90%). Cross-sectionally, sSIGLEC-1 correlated with mbSIGLEC-1 (r = 0.67, p< 0.001), BILAG (r = 0.37, p= 0.004) and SLEDAI (r = 0.36, p= 0.005). sSIGLEC-1 and mbSIGLEC-1 showed high sensitivity in moderate (sSIGLEC-1: 76%; mbSIGLEC-1: 84%) and severe (both: 100%) disease activity. sSIGLEC-1 correlated positively with IFN-α (r = 0.35; p= 0.006) and IP-10 (r = 0.57; p< 0.001), with similar results for mbSIGLEC-1. Longitudinally, changes in BILAG correlated to changes in sSIGLEC-1 (r = 0.36; p= 0.014) and mbSIGLEC-1 (r = 0.38; p= 0.009). Analysing flare-predictive ability, neither sSIGLEC-1 nor mbSIGLEC-1 showed significant results. Our study supports sSIGLEC-1 as a reliable and scalable biomarker of IFN-I activity in SLE. Its performance and compatibility with routine assays make it a strong candidate for clinical translation and broader application in IFN-I-driven diseases.

Ferroptosis in cancer toward molecular insights and clinical translation in pancreatic cancer.

Nanozymes are enzyme-mimicking nanomaterials that are promising for diverse biomedical applications; they enable stable, tunable, and multifunctional cancer therapies via exploiting tumor microenvironment (TME) cues to regulate reactive oxygen species (ROS) and catalytic activities locally, aided by state-of-the-art fabrication methods and artificial intelligence (AI)-assisted designs. This review summarizes recent developments in nanozyme-based cancer therapy, focusing on the underlying catalytic mechanisms, material classifications, and their multimodality integration for cancer treatment. It further examines oxidase (OXD), peroxidase (POD), catalase (CAT), and superoxide dismutase (SOD)-like nanozymes in chemodynamic (CDT), photothermal (PTT), photodynamic (PDT), sonodynamic (SDT), immune and starvation therapies (ST), emphasizing single-atom, multimetallic, biomimetic, and AI-assisted design strategies of nanozymes. Single-atom and multimetallic nanozymes offer superior catalytic precision, atom efficiency, and programmable pathways over conventional nanomaterials. While AI-assisted design accelerates discovery of optimal compositions and therapeutic environment compatibility, enabling controlled ROS generation and TME responsiveness and hence enhancing tumor selectivity and therapeutic efficacy, their combination may represent a transformative direction for precision cancer therapy. Despite encouraging progress, challenges related to in vivo specificity, long-term biosafety, scalable synthesis, and clinical translation remain. Addressing these issues through interdisciplinary innovation will be critical for advancing next-generation intelligent nanozyme platforms toward clinical oncology.

The review aims to comprehensively examine the anticancer potential of diosgenin, a natural steroidal sapogenin, in the context of hepatocellular carcinoma (HCC). It highlights the underlying mechanisms of action, discusses diosgenin's limitations in bioavailability, and evaluates nanotechnology-based drug delivery systems designed to enhance its therapeutic efficacy. This review was conducted through a structured and comprehensive literature screening process to ensure thorough coverage of relevant studies. Publications were retrieved from PubMed, Scopus, and Web of Science databases using keywords such as "diosgenin," "hepatocellular carcinoma," "liver cancer," "nanocarrier," "drug delivery," and "phytochemicals" applied individually and in various combinations. The search encompassed articles published between 2000 and 2025, with priority given to peer-reviewed English-language studies. Out of more than 300 records initially identified, approximately 125 studies met the inclusion criteria addressing diosgenin's pharmacodynamics, molecular mechanisms, and nanotechnology-based delivery systems. Diosgenin exerts anti-HCC effects through multiple pathways including PI3K/Akt, NF-κB/STAT3, MAPK, and mitochondrial apoptosis signaling. While its low solubility and poor bioavailability limit clinical application, nanocarriers have significantly improved drug stability, sustained release, and targeted tumor delivery. Among them, niosomes and carbon nanotubes showed notable efficacy, with diosgenin-loaded niosomes reducing HepG2 cell viability, and carbon nanotubes demonstrating synergistic tumor inhibition when co-loaded with ferulic acid. Diosgenin-based liposomes also enhanced the effect of doxorubicin, increasing apoptosis and reducing tumor burden in vivo. Diosgenin represents a promising multi-targeted agent for liver cancer therapy, especially when combined with advanced drug delivery systems. These diosgenin loaded nanocarriers overcome pharmacokinetic limitations and significantly improve therapeutic outcomes through enhanced tumor targeting and synergistic effects with chemotherapeutic agents. However, successful clinical translation requires addressing key regulatory, ethical, and manufacturing challenges, including standardization of nanocarrier formulations, large-scale reproducibility, and long-term safety evaluation. Overall, diosgenin-based nanocarriers show promising potential for clinical translation, offering safer and more targeted therapeutic options for HCC.

The emergence of organoids has received widespread attention for faithful recapitulation of physiological and pathological conditions, together with overcoming the major bottleneck of extrapolating laboratory findings from model systems to human organs. Organoid technologies are one of the most revolutionary breakthroughs in the fields of regenerative medicine and biomedical research. These three-dimensional (3D) micro-organ models are derived from stem cells and tissue derivatives, and can highly simulate the structure and function of parental organs, which thus open up unprecedented avenues for understanding organogenesis, disease modeling, drug screening and individualized therapeutics. In this review, we comprehensively elaborate on the core principles and key elements of organoid construction, and the multidisciplinary integration with the advanced technologies. Simultaneously, we systematically summarize their applications in disease modeling and pharmaceutical research, together with the landscape of organoid-based observational and interventional clinical trials in regenerative medicine. Furthermore, we put forward the outstanding prospects and challenges in organoid-based precise diagnosis and treatment applications. In particular, the long-standing key issues in the field such as vascularization and maturity, standardization and reproducibility, biobank and ethical considerations, and the emerging interdisciplinary integrations. Collectively, we outline the state-of-the-art renewal in organoid-guided precision medicine and regenerative medicine, which will benefit the following investigations in development biology and clinical translation.

Ulcerative Colitis (UC) treatments often lack target specificity and have significant side effects. A key pathological driver is the excessive necroptosis of intestinal epithelial cells (IECs), which disrupts the gut barrier. To address this, we designed an intelligent oral theranostic nanoplatform, CurN@I, to dismantle the necroptosis-inflammation axis. CurN@I consists of a barium sulfate (BaSO4) core for computed tomography (CT) imaging, encapsulated within a pH-responsive silk protein nanosponge. This scaffold is co-loaded with a necroptosis inhibitor (Necrostatin-1s, Nec-1s) and an antioxidant (demethoxycurcumin, DMC). The nanostructure is condensed in the acidic stomach but swells at the neutral pH of the inflamed intestine for localized drug release. Its negative surface charge facilitates durable electrostatic adhesion to the inflamed mucosa. In murine UC models, oral CurN@I significantly outperformed first-line clinical drugs. Mechanistic analysis showed it inhibits IEC necroptosis, alleviates oxidative stress, promotes barrier regeneration, and reshapes the gut microbiome. This work presents a non-invasive, targeted oral strategy that integrates diagnosis with multi-faceted therapy to restore intestinal homeostasis, demonstrating strong potential for clinical translation.

Introduction Human mesenchymal stem/stromal cells (hMSCs) hold significant regenerative potential due to their anti-inflammatory and pro-angiogenic secretome. Three-dimensional (3D) hMSC aggregates secrete extracellular vesicles (EVs) with enhanced immunomodulatory properties compared to 2D cultures. However, the clinical translation of hMSC-EVs remains limited by low production yield. This study investigates scalable EV generation from 3D hMSC aggregates in a novel Vertical-Wheel Bioreactor (VWBR), leveraging shear stress-mediated biochemical cues to enhance EV biogenesis and cargo relevant to nerve regeneration. Methods Bone marrow-derived hMSCs were cultured as 3D aggregates in VWBRs and exposed to two different culture media—αMEM/FBS (serum-containing) and DMEM/F12/B27 (serum-free)—under three agitation speeds (25, 40, and 64 rpm). Metabolite analysis and qRT-PCR were performed to assess metabolic activity and EV biogenesis, focusing on ESCRT machinery markers. EVs were isolated and evaluated for yield, size, markers, and microRNA cargo. Functional assays were conducted to measure the effects on EVs on Schwann cells under LPS-induced neural inflammation. Results VWBR culture resulted in increased expression of EV biogenesis genes and glycolytic pathway markers compared to static culture. The αMEM/FBS (serum-containing) condition was more robust than DMEM/F12/B27 (serum-free) condition. EV yield (EV number per cell) increased by 3-10 fold (in serum-containing medium) in VWBR compared to static culture, with particle sizes ranging from 120-180 nm and appropriate EV marker expression. microRNA-sequencing showed upregulation of miR-29a-3p, miR-451a, miR-224-5p, miR-16-5p, miR-133a-3p, and miR-143-3p, indicating enhanced EV biogenesis, metabolic reprogramming, and immunomodulatory potential. Functionally, VWBR-derived EVs modulated inflammatory gene expression in Schwann cells exposed to LPS. Discussion VWBR-driven hydrodynamics promotes EV biogenesis from 3D hMSC aggregates, improving metabolic activity, EV cargo relevance, and functional efficacy. The resulting EVs exhibit therapeutic cargo capable of modulating neural inflammation. These findings advance understanding of dynamic aggregation on metabolic cues and EV production, demonstrating a scalable strategy for generating therapeutically potent hMSC-EVs for neuropathic and regenerative applications.

Acne vulgaris is a prevalent chronic inflammatory skin disease, for which topical pharmacotherapy remains challenging due to the skin barrier and complex pathological mechanisms. In recent years, micro/nanocarrier‐based dermal delivery systems have emerged as novel strategies to overcome these barriers. These carriers can significantly enhance local drug bioavailability, targeting precision, and therapeutic duration. Furthermore, by integrating functionally complementary carriers, synergistic effects can be achieved across spatial, temporal, and biological dimensions, offering a systematic intervention for this multifactorial condition. However, the clinical translation of such technologies is still hindered by several challenges, including scalable manufacturing processes, long‐term safety evaluation, reliable preclinical models, and harmonized regulatory standards. Looking forward, the convergence of multiomics diagnostics and digital manufacturing is expected to advance intelligent closed‐loop systems capable of real‐time sensing and adaptive regulation, thereby enabling truly personalized and precise treatment. This progress will shift acne management from symptomatic control toward modulation of the underlying pathology.

Precision in assessing neurological function after stroke is key to optimizing the efficacy of rehabilitation. Functional near-infrared spectroscopy (fNIRS) provides a highly ecologically valid assessment of cortical activation and functional reorganization after stroke by monitoring cortical hemodynamic changes during different tasks. However, the current fNIRS task paradigm lacks systematic integration for standardized design and clinical translation strategies, and fragmented evidence is difficult to converge into actionable practice guidelines. To fill this gap, this paper systematically reviews the application of fNIRS in motor, cognitive, language, and dual-task paradigms in stroke rehabilitation research. It reveals the clinical value of different paradigms for neurological function assessment and proposes adaptive task designs that fit the functional characteristics of patients with stroke. This study emphasizes the importance of personalized and ecological paradigms, providing a theoretical basis and practical reference for subsequent standardized research on fNIRS task paradigms and developing clinical application standards.

Epigenetic analysis, especially DNA methylation profiling of plasma cell-free DNA (cfDNA), has recently emerged as a promising clinical tool. Choosing the right analytical method is crucial for working with limited cfDNA, ensuring cost-effectiveness, and supporting clinical translation. While bisulfite-based methods have long been the standard for methylation analysis, enzymatic conversion is a potential alternative. However, their comparative performance for cfDNA remains unclear. In this study, we compared enzymatic (EM-Seq) and bisulfite-based (cfRRBS and cfMethyl-seq) methods. EM-Seq showed higher mapping efficiency, broader genomic coverage, and captured more CpGs at low coverage thresholds, while the bisulfite methods had higher conversion rates, lower costs, and better coverage of functional regions like promoters and exons. The bisulfite-based methods also demonstrated superior reproducibility. Overall, cfRRBS offered the best balance of cost, accuracy, and reproducibility. Our findings fill a key gap in cancer epigenetics, outline the strengths and limitations of each method, and provide a practical guide for selecting cfDNA methylation profiling methods in liquid biopsy applications.

Background: Metabolic syndrome, a clinical condition defined by central obesity, impaired glucose regulation, elevated blood pressure, hypertriglyceridemia, and low high-density lipoprotein cholesterol across the lifespan, is now a major public health issue typically managed with lifestyle, behavioral, and dietary recommendations. However, “one-size-fits-all” recommendations often yield modest, heterogeneous responses and poor long-term adherence, creating a clinical need for more targeted and implementable preventive and therapeutic strategies. Objective: To synthesize evidence on how the gut microbiome can inform precision nutrition and exercise approaches for metabolic syndrome prevention and management, and to evaluate readiness for clinical translation. Key findings: The gut microbiome may influence cardiometabolic risk through microbe-derived metabolites and pathways involving short-chain fatty acids, bile acid signaling, gut barrier integrity, and low-grade systemic inflammation. Diet quality (e.g., Mediterranean-style patterns, higher fermentable fiber, or lower ultra-processed food intake) consistently relates to more favorable microbial functions, and intervention studies show that high-fiber/prebiotic strategies can improve glycemic control alongside microbiome shifts. Physical exercise can also modulate microbial diversity and metabolic outputs, although effects are typically subtle and may depend on baseline adiposity and sustained adherence. Emerging “microbiome-informed” personalization, especially algorithms predicting postprandial glycemic responses, has improved short-term glycemic outcomes compared with standard advice in controlled trials. Targeted microbiome-directed approaches (e.g., Akkermansia muciniphila-based supplementation and fecal microbiota transplantation) provide proof-of-concept signals, but durability and scalability remain key limitations. Conclusions: Microbiome-informed personalization is a promising next step beyond generic guidelines, with potential to improve adherence and durable metabolic outcomes. Clinical implementation will require standardized measurement, rigorous external validation on clinically meaningful endpoints, interpretable decision support, and equity-focused evaluation across diverse populations.

Cannabis sativa yields a wide range of bioactive compounds, including terpenes, flavonoids, and cannabinoids. Tetrahydrocannabinolic acid (THCA), cannabidiolic acid (CBDA), cannabigerolic acid (CBGA), and cannabichromenic acid (CBCA) are the acidic biosynthetic precursors of the neutral cannabinoids Δ9-tetrahydrocannabinol (THC) and cannabidiol (CBD), which have been the subject of much research. This review examines the biosynthesis, decarboxylation, molecular pharmacology, and therapeutic significance of acidic cannabinoids, intending to address a significant knowledge gap. Peer-reviewed literature from major scientific databases was used in a systematic narrative review with an emphasis on investigations of acidic cannabinoid chemistry, pharmacology, pharmacokinetics, and disease-specific applications. According to the reviewed data, acidic cannabinoids exhibit unique biological activities that distinguish them from their neutral counterparts. These include neuroprotective, anti-inflammatory, anticonvulsant, and anti-proliferative actions, which are mediated by molecular targets such as serotonin 5-HT1A receptors, cyclooxygenase-2 (COX-2), transient receptor potential (TRP) channels, and peroxisome proliferator-activated receptor-γ (PPARγ). Acidic cannabinoids are more appealing for therapeutic usage in children and the elderly, considering that they are not intoxicating like THC; however, this distinction applies primarily to non‑heated consumption. Chemical instability, low bioavailability, and a dearth of controlled human trials impede clinical translation despite their potential. According to the findings, acidic cannabinoids are an underutilized yet potentially valuable class of precision medicines. In this study, we outline existing understanding on acidic cannabinoids, discuss their production and transformation, and identify research needs that could influence cannabis science research.

Autoimmune diseases are becoming increasingly prevalent and can cause multi-organ damage through dysregulated immune responses to self-antigens. This review aims to summarize the roles of annexin family proteins and annexin autoantibodies in the mechanisms of autoimmune diseases, as well as their potential diagnostic and therapeutic applications. A targeted PubMed search conducted on August 31, 2025, utilized annexin- and disease-related terms without year restrictions, focusing on English-language, peer-reviewed studies involving humans or recognized animal models.Evidence suggests that Annexin A1 (ANXA1) and formyl peptide receptor 2 (FPR2) signaling can influence inflammatory and T-cell responses. Additionally, Annexin A2 (ANXA2) is associated with organ-targeted injury, such as lupus nephritis (LN) in systemic lupus erythematosus (SLE), through its interactions with anti-double-stranded DNA antibodies (anti-dsDNA). Annexin A5 (ANXA5) serves as an anticoagulant phospholipid "shield," which can be compromised by antiphospholipid antibodies (aPLs), contributing to thrombosis and obstetric complications in antiphospholipid syndrome (APS) and increasing vascular risk in SLE. In rheumatoid arthritis (RA), ANXA1 exhibits context-dependent effects, while ANXA2 promotes synovial proliferation, invasion, and angiogenesis.Dysregulation of annexins has also been observed in primary Sjögren's syndrome (pSS), multiple sclerosis (MS), and systemic sclerosis (SSc). Additionally, the emerging utility of anti-ANXA1, anti-ANXA2, and anti-ANXA5 autoantibodies for phenotyping and risk stratification, including in seronegative antiphospholipid syndrome (SNAPS), highlights their clinical relevance. Overall, annexins and their autoantibodies represent promising biomarkers and therapeutic targets; however, the heterogeneity of assays and the limited availability of prospective multicenter data currently hinder clinical translation.

Fetal growth disorders, including both fetal growth restriction and macrosomia, remain major contributors to perinatal morbidity and long-term health risks in adulthood. While ultrasound is the most frequently employed technique for the diagnosis of intrauterine growth abnormalities, its efficacy is constrained by the operator’s experience and variable accuracy. This review explores the role of artificial intelligence (AI) in advancing the detection and management of fetal growth disorders. We conducted a comprehensive literature search of major databases to identify original and review articles addressing the use of AI in fetal growth restriction, small-for-gestational-age and large-for-gestational-age fetuses, as well as fetal macrosomia. The available evidence indicates that AI models combining maternal, fetal, and imaging data exhibit a level of accuracy comparable to that of experienced clinicians, while also enhancing operational efficiency and reducing variability. Emerging applications include automated biometry, prediction models based on biomarkers and Doppler indices, as well as deep learning algorithms applied directly to ultrasound scans. These methods not only enhance diagnostic precision but also expand access to high-quality prenatal care, particularly in low-resource settings. Nonetheless, most of the published studies remain limited by retrospective designs, small sample sizes, and a lack of external validation. Addressing these challenges, along with ethical, technical, and regulatory considerations, will be essential for clinical translation. In conclusion, AI has the potential to become a cornerstone of precision perinatal medicine by enabling earlier diagnosis, individualized monitoring, and thus improved outcomes for both mothers and infants.