Seminars in thrombosis and hemostasis最新文献

{"title":"Machine Learning and Deep Learning in Deep Vein Thrombosis: A Narrative Review of Clinical Applications for Diagnosis, Risk Prediction, and Outcome Management.","authors":"Hyun Yong Lee, Sangchul Yun, Eol Choi, Hana Jin, Heangjin Ohe, Sungwoo Cho, Moon Gu Lee","doi":"10.1055/a-2954-8867","DOIUrl":"https://doi.org/10.1055/a-2954-8867","url":null,"abstract":"<p><strong>Abstract: </strong>Machine learning (ML) and deep learning (DL) are increasingly applied across the clinical spectrum of deep vein thrombosis (DVT), from AI-guided ultrasound diagnosis to perioperative and inpatient risk prediction, but methodological progress has outpaced clinical translation. We aimed to narratively synthesize ML and DL applications in DVT across eight clinical domains and assess their performance and translational readiness. We performed a structured literature search of PubMed, Web of Science, and Scopus (January 2019-April 2026) using predefined disease and technology term blocks restricted to Title/Abstract fields. Of 492 records identified, 250 eligible publications were retained as the synthesis pool. Representative studies were purposively selected for detailed appraisal, prioritizing those with external validation, prospective design, or clear linkage to clinical workflows. AI applications span AI-guided ultrasound diagnosis, CT/MRI-based imaging, perioperative risk prediction, medical/ICU risk prediction, cancer-associated DVT, post-thrombotic syndrome and pulmonary embolism outcome prediction, and natural language processing (NLP)/large language model-based surveillance or decision support. Reported AUROC values are frequently high; however, external validation is uncommon, calibration metrics and decision-curve analysis are rarely reported, and prospective implementation studies are scarce. A randomized trial in medical inpatients demonstrated reduced hospital-acquired venous thromboembolism with AI-driven decision support, and AI-guided ultrasound pathways have shown near-expert diagnostic performance when used by non-expert operators. AI shows substantial promise for improving DVT diagnosis, risk stratification, and outcome prediction, but most models remain insufficiently validated for routine use. Prospective multicenter evaluation, standardized reporting of calibration and clinical utility, and structured oversight frameworks will be essential for safe deployment.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148991295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lipoprotein(a) and All-Cause Mortality: Paradox or Arithmetic?","authors":"Giuseppe Lippi, Fabian Sanchis-Gomar","doi":"10.1055/a-2952-2375","DOIUrl":"https://doi.org/10.1055/a-2952-2375","url":null,"abstract":"","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148970943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Do Advanced Hemostatic Assays Improve Prediction of Incident Deep Vein Thrombosis after Hip Fracture Surgery?","authors":"Lara Gianesello, Rossella Marcucci, Anna Maria Gori, Bingwen Eugene Fan, Mauro Panigada","doi":"10.1055/a-2952-2418","DOIUrl":"https://doi.org/10.1055/a-2952-2418","url":null,"abstract":"","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148970991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advances from Traditional Clinical Decision Support Tools to Machine Learning Applications in Primary Prevention of Thromboembolic Disorders.","authors":"Ermioni Oikonomou, Nikolaos Tsaftaridis, Alex C Spyropoulos, Mark Goldin","doi":"10.1055/a-2946-5165","DOIUrl":"https://doi.org/10.1055/a-2946-5165","url":null,"abstract":"<p><strong>Abstract: </strong>Primary thromboprophylaxis for arterial and venous thromboembolism (VTE) still presents many challenges, as patient- and disease-specific risk factors complicate risk assessment and necessitate tailored strategies. To tackle this, multiple thromboembolism risk assessment models have been developed and validated, with machine learning (ML) models now emerging. Some ML models have been integrated into electronic health record (EHR)-based clinical decision support systems (CDSS) to improve guideline adherence and optimize appropriate anticoagulant use. We conducted a narrative review exploring the intersection of ML and clinical decision support (CDS) in primary thromboprophylaxis for VTE and stroke prevention in atrial fibrillation. Traditional risk assessment models integrated into EHR-based CDS have improved thromboprophylaxis rates and, in some studies, reduced thrombotic events. More comprehensive CDS strategies, such as the deployment of an EHR-agnostic CDS incorporating the IMPROVE-DD score for venous thromboprophylaxis, have demonstrated broader clinical impact, with reductions in both venous and arterial thromboembolism. With advances in artificial intelligence, ML-based risk prediction models for both venous and arterial thromboembolism have demonstrated superior discriminative performance compared with traditional models, predominantly in internal validation studies. Furthermore, their integration into active CDSS represents a promising strategy to improve thromboprophylaxis. However, most ML models lack external validation, remaining susceptible to overfitting and limiting generalizability. ML models integrated into active CDS hold much promise given their enhanced predictive performance, ability to integrate high-dimensional data and capture complex nonlinear interactions. Nevertheless, further work is needed to establish clinical utility through prospective outcome studies, ensure generalizability via external validation, and achieve integration into real clinical workflows.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148920932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond Accuracy: Why Replacing Traditional Scores with AI in Thrombosis Care Creates New Ethical and Regulatory Obligations.","authors":"Vasiliki Danilatou, Deepa J Arachchillage","doi":"10.1055/a-2943-7750","DOIUrl":"https://doi.org/10.1055/a-2943-7750","url":null,"abstract":"<p><strong>Abstract: </strong>Clinical prediction scores have been central to thrombosis and hemostasis practice for decades, providing transparent, interpretable, and validated approaches to risk assessment. Increasingly, artificial intelligence (AI)-based predictive models are being developed to improve risk stratification by integrating large, complex datasets and identifying patterns beyond conventional statistical models. However, improved predictive performance alone does not determine clinical value, and AI introduces new ethical, regulatory, and governance challenges. This narrative review compares traditional thrombosis risk scores and AI-based predictive models, focusing on methodological differences, ethical considerations, regulatory requirements, and the competencies clinicians require for responsible implementation. Traditional scores benefit from simplicity, transparency, and ease of clinical interpretation but have important limitations, including modest predictive performance, limited adaptability, potential bias, and uncertain evidence that score-guided management improves outcomes compared with clinical judgment alone. Many of the concerns currently associated with AI-based risk prediction, including bias, generalizability, validation, and monitoring, also exist within traditional prediction models but have historically received less regulatory attention. AI-based models offer potential advantages through dynamic risk prediction, integration of multimodal data, and improved predictive accuracy; however, they introduce additional challenges related to explainability, data governance, privacy, cybersecurity, accountability, reproducibility, and postdevelopment surveillance. AI should be viewed as an evolution of clinical decision support rather than a replacement for established approaches or clinical expertise. Safe implementation requires robust validation, continuous monitoring, human oversight, transparent governance frameworks, and clinician AI literacy.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":""},"PeriodicalIF":4.2,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148888536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Editorial Compilation-Part XIX.","authors":"Emmanuel J Favaloro, Leonardo Pasalic, Bingwen Eugene Fan, Giuseppe Lippi","doi":"10.1055/a-2775-7368","DOIUrl":"https://doi.org/10.1055/a-2775-7368","url":null,"abstract":"","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":"52 6","pages":"613-617"},"PeriodicalIF":4.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148797752","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Clinical Response to Elevated Lipoprotein(a): Practical Approach for Risk Management in the Absence of Targeted Therapies.","authors":"Fabian Sanchis-Gomar, Giuseppe Lippi","doi":"10.1055/a-2768-2477","DOIUrl":"10.1055/a-2768-2477","url":null,"abstract":"<p><strong>Abstract: </strong>Lipoprotein(a) (Lp(a)) is a genetically determined, lifelong cardiovascular risk factor strongly associated with atherosclerotic cardiovascular disease (ASCVD) despite optimal low-density lipoprotein cholesterol (LDL-C) lowering. The current management is challenged by the absence of outcome-proven Lp(a)-specific therapies. Statins, ezetimibe, bempedoic acid, and lifestyle interventions have little or no effect on Lp(a). Statins may modestly raise levels; niacin is now contraindicated as it has not been shown to reduce cardiovascular or all-cause mortality, while PCSK9 (Proprotein Convertase Subtilisin/Kexin type 9) inhibitors and inclisiran reduce Lp(a) concentrations by approximately 20 to 30%, though this effect remains secondary to their LDL-C-lowering effect. The only U.S. Food and Drug Administration (FDA)-approved therapy specifically addressing Lp(a) is lipoprotein apheresis, which reduces Lp(a) levels by 60 to 75%, but is restricted to specific patient populations due to invasiveness, high cost, and limited availability. Future promise lies in RNA-based therapies, including antisense oligonucleotides (pelacarsen) and small-interfering RNAs (olpasiran, lepodisiran, SLN360), which achieve 80 to 95% sustained Lp(a) reductions. Large outcome trials will determine whether this biochemical efficacy translates into tangible clinical benefits. Current guidelines now recommend one-time lifetime Lp(a) measurement, treating ≥125 nmol/L (≥50 mg/dL) as a risk-enhancing factor. High or extreme elevations, especially with ASCVD, mandate aggressive LDL-C lowering, optimization of modifiable risk factors, family cascade screening, and apheresis or referral to RNA-therapy trials in select cases. Thus, while therapeutic options remain limited, systematic measurement and risk stratification are ethically justified to prepare for the imminent arrival of Lp(a)-targeted therapies.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":"653-666"},"PeriodicalIF":4.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145744067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Von Willebrand Disease Type 2A: An Update.","authors":"Omid Seidizadeh, Luciano Baronciani, Pier Mannuccio Mannucci, Flora Peyvandi","doi":"10.1055/a-2778-9989","DOIUrl":"10.1055/a-2778-9989","url":null,"abstract":"<p><strong>Abstract: </strong>Dysfunctional or quantitatively deficient von Willebrand factor (VWF) underlies von Willebrand disease (VWD), the most common inherited bleeding disorder. Type 2A VWD is a qualitative defect marked by impaired VWF-dependent platelet adhesion, typically reflected in disproportionately reduced ratios of platelet-dependent VWF activity to antigen (VWF activity/VWF:Ag) and collagen binding to antigen (VWF:CB/VWF:Ag). This phenotype results from a selective reduction or lack of high- and intermediate-molecular-weight multimers, which are essential for effective hemostasis under high shear stress. The lack of multimer arises from impaired multimer assembly and/or increased proteolytic cleavage of VWF by ADAMTS13. Clinically, type 2A tends to present with greater severity than other type 2 variants, manifesting as mucocutaneous bleeding, often including heavy menstrual bleeding, epistaxis, post-surgical bleeding and gastrointestinal hemorrhage from angiodysplasia. Diagnosis relies on functional assays and VWF multimer analysis, supported by genetic testing that identifies subtype-specific mutations affecting VWF multimeric structure and therefore its function. Type 2A is typically inherited in an autosomal dominant manner, with rare exceptions of autosomal recessive inheritance. Structural and molecular studies are continuing to elucidate how domain-specific variants disrupt multimeric structure and thus interactions with its ligands. Management is guided by bleeding severity and includes desmopressin (following responsiveness testing) and VWF replacement therapy. This review provides an in-depth update on type 2A VWD, covering its epidemiology, pathophysiology across distinct subtypes, clinical manifestations, diagnostic approach, molecular and structural insights, and current therapeutic strategies.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":"618-627"},"PeriodicalIF":4.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145843998","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Immunity in Immunothrombosis.","authors":"David Noone, Roger J S Preston, Gemma Leon","doi":"10.1055/a-2722-7189","DOIUrl":"10.1055/a-2722-7189","url":null,"abstract":"<p><strong>Abstract: </strong>Thrombosis is a comorbidity associated with autoimmune, allergic, and infectious conditions; however, the mechanistic basis for this elevated risk is poorly understood. The simultaneous activation of the immune and coagulation systems to assist in response to injury and efficient pathogen clearance, termed immunothrombosis, is typically described as a bidirectional interaction between the innate immune and coagulation systems. More recently, however, data have emerged highlighting the involvement of adaptive immune cells in this process. In this review, we discuss the role of adaptive immune cells in clot formation and resolution, and explore how the adaptive immune system modulates procoagulant activity in autoimmune diseases such as inflammatory bowel disease, systemic lupus erythematosus, and graft versus host disease; allergic disorders, such as dermatitis and asthma; infectious diseases, such as coronavirus disease 2019 (COVID-19) and human immunodeficiency virus (HIV); and ischemic conditions such as myocardial infarction and stroke.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":"667-682"},"PeriodicalIF":4.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145513756","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of ACR/EULAR Classification Criteria in Real Life: Thrombotic Patients Positive for Lupus Anticoagulant Only.","authors":"Vittorio Pengo, Luca Sarti, Daniela Poli, Piera Sivera, Doris Barcellona, Domenico Prisco, Attilia Maria Pizzini, Giuseppe Vercillo, Emilia Antonucci, Gualtiero Palareti","doi":"10.1055/a-2731-2213","DOIUrl":"10.1055/a-2731-2213","url":null,"abstract":"<p><strong>Abstract: </strong>Lupus anticoagulant (LA) positive only (negative anticardiolipin antibodies [aCL] and anti-β2 glycoprotein I antibodies [aβ2GPI]) thrombosis represents a clinical challenge. It is often unclear whether the cause of thrombosis is LA or whether other clinical conditions have led to an episode of venous thromboembolism (VTE) or arterial thromboembolism (ATE). Recent antiphospholipid syndrome (APS) classification criteria assign different scores to thrombotic events based on the presence of confounding risk factors. In the presence of strong associated risk factors, patients are not classified as having APS as a score less than 3 points is assigned to the clinical domain. This study evaluated patients LA positive only included in the group of APS in the START2 Antiphospholipid Registry. The aim of the study was to determine how many of them did not meet the new APS classification criteria due to the presence of associated risk factors. Of the 488 patients enrolled in the START Antiphospholipid Registry, 86 (18%) had LA positive only and 43 had a previous thromboembolic event (33 VTE and 10 ATE). Of the 33 patients with VTE (9%), 3 had a high-risk VTE profile and 2 had a high-risk ATE profile and did not meet the new classification criteria. The updated criteria appropriately limit the inclusion of patients with high-risk thrombotic profiles in APS research studies. Although risk factors and not LA may be the cause of thrombosis, the presence of LA can complicate treatment decisions in clinical practice.</p>","PeriodicalId":21673,"journal":{"name":"Seminars in thrombosis and hemostasis","volume":" ","pages":"741-745"},"PeriodicalIF":4.2,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145392587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}