European Journal of Clinical Investigation最新文献

{"title":"Prediction of major outcomes in patients with malignant hypertension using machine learning: A report from the West Birmingham malignant hypertension registry.","authors":"Antonios A Argyris, Hironori Ishiguchi, Yang Chen, Yalin Zheng, Alena Shantsila, Eduard Shantsila, D Gareth Beevers, Gregory Y H Lip","doi":"10.1111/eci.70052","DOIUrl":"https://doi.org/10.1111/eci.70052","url":null,"abstract":"<p><strong>Background: </strong>Malignant hypertension (MHT) is a rare, yet severe condition with high morbidity and mortality. We aimed to assess the potential of machine learning (ML) algorithms in forecasting prognostic outcomes in MHT patients.</p><p><strong>Methods: </strong>Data from the West Birmingham MHT Registry were used. We evaluated the efficacy of 9 ML algorithms, CatBoost, Decision Tree (DT), Light-Gradient Boosting Machine (LightGBM), K-Nearest Neighbours (KNN), Logistic Regression (LR), Multi-Layer Perceptron (MLP), Random Forest (RF), Support Vector Machine (SVM) and XGBoost in predicting a composite outcome of all-cause mortality/dialysis. Evaluation metrics included the area under the receiver operating characteristic curve (AUC) and F1 score. SHapley Additive exPlanations values were employed to quantify the importance of each feature.</p><p><strong>Results: </strong>The cohort comprised 385 individuals with MHT (mean age 48 ± 13 years, 66% male). During a median follow-up of 11 (interquartile range: 3-18) years, 282 patients (73%) experienced the composite outcome. Among 24 demographic and clinical variables, 16 were selected into the ML models. The SVM, LR, and MLP models exhibited robust predictive performance, achieving AUCs of .81 (95% CI: .70-.90), .82 (95% CI: .71-.92) and .81 (95% CI: .71-.90), respectively. Furthermore, these models demonstrated high F1 scores (SVM: .75, LR: .80. MLP: .75). Age, smoking, follow-up systolic blood pressure, and baseline creatinine were commonly identified as primary prognostic features in both SVM and LR models.</p><p><strong>Conclusions: </strong>The application of ML algorithms facilitates effective prediction of prognostic outcomes in MHT patients, illustrating their potential utility in clinical decision-making through more targeted risk stratification and individualised patient care.</p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":" ","pages":"e70052"},"PeriodicalIF":4.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143981234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Phenotypic patterns of metabolic dysfunction-associated steatotic liver disease in type 2 diabetes: The impact of insulin.","authors":"Queralt Martín-Saladich, Rafael Simó, Andreea Ciudin, Julia Baguña, Clara Ramirez-Serra, Santiago Aguadé-Bruix, Albert Roque, Maria N Pizzi, Hug Cuéllar, Nuria Roson-Gradaille, Miguel A González Ballester, Juan M Pericàs, José Raul Herance","doi":"10.1111/eci.70050","DOIUrl":"https://doi.org/10.1111/eci.70050","url":null,"abstract":"<p><strong>Background: </strong>Metabolic dysfunction-associated steatotic liver disease (MASLD) often leads to hepatic insulin resistance (IR), yet its link to liver-specific insulin-mediated glucose uptake (IGLU) in type 2 diabetes (T2D) remains unclear. We aimed to explore this MASLD-T2D relationship, addressing organ-specific IR for personalized management and risk prevention.</p><p><strong>Methods: </strong>This cross-sectional study included 41 T2D participants enrolled in a clinical trial (NCT02248311) undergoing biochemical analyses, anthropometric measurements and [¹⁸F]FDG-PET/CT imaging before and after hyperinsulinemic euglycemic clamp (HEC).</p><p><strong>Findings: </strong>Two MASLD-T2D phenotypes were identified according to their IGLU patterns, that is, with low (HepGluc[+], n = 21) and with high (HepGluc[-], n = 20) hepatic response to insulin. HepGluc[+] participants exhibited increased systemic IR (HOMA-IR, p = .012), inflammation (interleukin 6, p = .005); alanine and aspartate aminotransferase ALT, AST (p = .015 and p = .007); gamma-glutamyl transferase GGT (p = .019) and steatosis markers (liver volume, p = .006); NAFLD liver fat score, p = .0017; hepatic steatosis index, p = .02; fatty liver index, p = .008; liver stiffness measurements (LSM) (p = .049). No statistical differences in serum-based liver fibrosis scores were shown. To identify MASLD-T2D phenotypes in a friendly manner, the MASLD-T2D score based on support vector machines was developed using AST, ALT and GGT (AUC = .83), as well as with MASLD indices including LSM and NAFLD liver fat score (AUC = .90).</p><p><strong>Implications: </strong>Two new MASLD-T2D phenotypes have been identified, HepGluc[+] and HepGluc[-], according to IGLU patterns, with HepGluc[+] being more deleterious due to higher systemic IR, steatosis and inflammation. Phenotypes can be identified using a new function, the MASLD-T2D score.</p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":" ","pages":"e70050"},"PeriodicalIF":4.4,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144004570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to ‘Association Between Exposure to Air Pollution and Blood Lipids in the General Population of Spain’","authors":"","doi":"10.1111/eci.70047","DOIUrl":"10.1111/eci.70047","url":null,"abstract":"<p>Valdés S, Doulatram-Gamgaram V, Maldonado-Araque C, García-Escobar E, García-Serrano S, Oualla-Bachiri W, García-Vivanco M, Garrido JL, Gil V, Martín-Llorente F, Calle-Pascual A, Castaño L, Delgado E, Menéndez E, Franch-Nadal J, Gaztambide S, Girbés J, Chaves FJ, Galán-García JL, Aguilera-Venegas G, Vallvé JC, Amigó N, Guardiola M, Ribalta J, Rojo-Martínez G. Association between exposure to air pollution and blood lipids in the general population of Spain. <i>Eur J Clin Invest</i>. 2024;54(2):e14101.</p><p>In paragraph 4 of the ‘Funding Information’ section, the text ‘European Regional Development Fund (ERDF) “A way to build Europe”’, was incorrect. This should have read ‘funded by ISCIII and cofounded by the European Union’.</p><p>We apologize for this error.</p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":"55 7","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/eci.70047","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144063187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy and safety of RNA interference therapeutics in transthyretin cardiac amyloidosis: A systematic review and meta-analysis","authors":"Shehroze Tabassum,&nbsp;Farhan Naeem,&nbsp;Mohamed Saad Rakab,&nbsp;Abdul Mannan Khan Minhas,&nbsp;Ramesh Daggubati,&nbsp;M. Chadi Alraies","doi":"10.1111/eci.70049","DOIUrl":"10.1111/eci.70049","url":null,"abstract":"<p>RNAi therapeutics represent a promising advancement in the treatment of ATTR-CM, offering significant benefits over placebo. It demonstrated substantial improvements in survival, functional capacity, and quality of life, alongside a marked reduction in BNP levels and GLS—critical biomarkers of disease progression. These findings underscore the potential of RNAi therapy to alter the disease trajectory and improve patient outcomes.\u0000 <figure>\u0000 <div><picture>\u0000 <source></source></picture><p></p>\u0000 </div>\u0000 </figure></p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":"55 7","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144063188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Concerns regarding interpretation in systematic review of exercise and endothelial glycocalyx.","authors":"Craig Bolger, David B Pyne, Andrew J McKune","doi":"10.1111/eci.70048","DOIUrl":"https://doi.org/10.1111/eci.70048","url":null,"abstract":"","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":" ","pages":"e70048"},"PeriodicalIF":4.4,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143987988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nutrition, cognition and chronic kidney disease: A comprehensive review of interactions and interventions","authors":"Mehmet Kanbay,&nbsp;Lasin Ozbek,&nbsp;Mustafa Guldan,&nbsp;Sama Mahmoud Abdel-Rahman,&nbsp;Uluman Sisman,&nbsp;Francesca Mallamaci,&nbsp;Carmine Zoccali","doi":"10.1111/eci.70045","DOIUrl":"https://doi.org/10.1111/eci.70045","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Cognitive impairment is a prevalent complication in chronic kidney disease (CKD), ranging from mild deficits in early stages to more severe conditions, such as mild cognitive impairment and dementia in advanced stages. CKD patients exhibit reduced performance in memory, attention, language, visuospatial abilities and executive functions.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results and Discussion</h3>\u0000 \u0000 <p>Contributing factors include uraemic toxins, structural brain changes, blood–brain barrier dysfunction, anaemia and comorbidities like diabetes mellitus. Malnutrition, affecting nearly half of CKD patients, exacerbates cognitive decline through inflammation, oxidative stress and protein-energy wasting. Nutritional deficiencies, particularly in protein, vitamin D, B vitamins, omega-3 fatty acids and antioxidants, are linked to impaired cognition. Emerging evidence highlights the role of the gut–brain axis, with gut-derived uraemic toxins and microbiome alterations contributing to cognitive dysfunction. Processed foods and microplastics further compound risks by promoting inflammation and neurotoxicity. Dialysis and kidney transplantation offer opportunities for cognitive recovery, though challenges remain, particularly in haemodialysis patients. Nutritional interventions, including tailored protein intake, micronutrient supplementation and dietary counselling, are critical for mitigating cognitive decline. Addressing CKD comorbidities, such as anaemia and diabetes through targeted nutritional and pharmacological strategies, improves outcomes. Integrating psychological and social support enhances quality of life, given the high prevalence of anxiety and depression in CKD patients.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Future research should focus on personalized nutrition, gut microbiota modulation and routine cognitive assessments to optimise care. A holistic approach combining medical, nutritional and psychosocial strategies is essential for improving cognitive and overall health in CKD patients.</p>\u0000 </section>\u0000 </div>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":"55 6","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143938743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of immature granulocytes on the outcome of patients with decompensated cirrhosis.","authors":"Magdalini Adamantou, Dimitrios Glaros, Evangelinos Michelis, Apostolos Papageorgiou, Eleni Adamopoulou, Antonia Alevizou, Menelaos Athanasiadis, Eleni Pergantina, Vasiliki E Georgakopoulou, Vasileios Lekakis, Evangelos Cholongitas","doi":"10.1111/eci.70044","DOIUrl":"https://doi.org/10.1111/eci.70044","url":null,"abstract":"<p><strong>Background: </strong>Higher immature granulocyte levels have a predictive role in several clinical conditions, although data concerning cirrhosis are scarce. Reduced muscle mass is a known factor affecting the outcome of these patients. The aim of the study was to evaluate the association of immature granulocytes with muscle mass and their role in predicting the outcome (survival, death or liver transplantation) in patients with stable decompensated cirrhosis.</p><p><strong>Methods: </strong>We prospectively studied 210 patients with decompensated cirrhosis awaiting liver transplantation. Their clinical and laboratory characteristics were recorded, including complete blood count with immature granulocyte count and immature granulocyte percentage. The severity of liver disease was evaluated by estimating the Child-Turcotte-Pugh and MELD-sodium scores. Dual energy X-ray absorptiometry was used to quantify the total and regional lean mass, while mid-arm muscle circumference was used for the evaluation of upper limb muscle mass.</p><p><strong>Results: </strong>Immature granulocyte percentage was proved to be the only factor independently associated with transplant-free survival (Hazard Ratio: 1.98, 95% confidence interval [1.03-3.81], p = .04). Stratification of our cohort based on the best discriminative cut-off values of immature granulocyte count and percentage revealed significant differences in the outcome based on Kaplan-Meier curves, while immature granulocyte count and percentage were significantly associated with parameters of body composition.</p><p><strong>Conclusions: </strong>Higher immature granulocyte count and percentage have a significant prognostic role and are associated with worse outcome in patients with stable decompensated cirrhosis.</p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":" ","pages":"e70044"},"PeriodicalIF":4.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143974005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Total lesion glycolysis is a promising predictor of chemo-response in pancreatic cancer patients treated with neoadjuvant chemotherapy prior to surgery.","authors":"Sooin Byeon, Bridget Abbott, Paul Roach, Dale L Bailey, Angela Chou, Sarah Maloney, Anthony J Gill, Jaswinder Samra, Anubhav Mittal, Sumit Sahni","doi":"10.1111/eci.70046","DOIUrl":"https://doi.org/10.1111/eci.70046","url":null,"abstract":"<p><strong>Background: </strong>There has been increased use of neoadjuvant chemotherapy (NAC) in resectable pancreatic ductal adenocarcinoma (PDAC) patients. [¹⁸F]fluoro-2-deoxyglucose positron emission tomography/computed tomography (FDG-PET/CT) scan is being frequently used to determine treatment response in PDAC patients undergoing NAC. Maximum standardized uptake value (SUV_max) is conventionally used as an FDG-PET/CT parameter, but there are emerging parameters, such as total lesion glycolysis (TLG), which take into account mean standardized uptake (SUV_mean) and metabolic tumour volume (MTV). This study compared the ability of emerging FDG-PET/CT parameters (i.e. SUV_mean, MTV and TLG) to predict chemo-response compared to SUV_max.</p><p><strong>Methods: </strong>In this single centre, retrospective study, NAC-treated PDAC patients (n = 74) for whom both pre- and post-NAC FDG-PET/CT scans were available were recruited. All scans were imported to a single analysis platform and reanalysed. Chemo-response was determined by the assessment of percentage viable tumour cells in the tumour bed. Statistical analysis was performed on the data.</p><p><strong>Results: </strong>A significant correlation was observed between post-treatment FDG-PET/CT scan parameters and viable cancer cells in the tumour bed, with TLG showing a higher degree of correlation (r = .3131) compared to all other parameters (r = .2722-.3008). The percentage decrease in the TLG (post-NAC scan vs. pre-NAC scan) demonstrated the highest degree of correlation with viable cancer cells in the tumour bed (r = -.3444) and had a statistically significant (p = .0157) effect between NAC responders (Median = 80.57) and non-responders (Median = 65.16). The difference between TLG (post-NAC scan vs. pre-NAC scan) was shown to be an independent prognostic indicator for overall survival (hazard ratio = .5033, p = .0361).</p><p><strong>Conclusion: </strong>TLG was shown to be a superior predictor of chemo-response and patient prognosis compared to all other FDG-PET/CT parameters in PDAC patients treated with NAC.</p>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":" ","pages":"e70046"},"PeriodicalIF":4.4,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143802849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Localization of accessory pathways in Wolff-Parkinson-white syndrome using ECG-based multi-task deep learning","authors":"Jasper Hennecken,&nbsp;Bauke K. O. Arends,&nbsp;Thomas Mast,&nbsp;Lukas Dekker,&nbsp;Pim van der Harst,&nbsp;Yuri Blaauw,&nbsp;Wolfgang Dichtl,&nbsp;Thomas Senoner,&nbsp;Rutger J. Hassink,&nbsp;Peter Loh,&nbsp;René van Es,&nbsp;Rutger R. van de Leur","doi":"10.1111/eci.14385","DOIUrl":"https://doi.org/10.1111/eci.14385","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Wolff-Parkinson-White syndrome is characterized by accessory atrioventricular pathways (AP) and atrio-ventricular re-entry arrhythmias. Catheter ablation approach and success are determined by AP location. Existing rule-based algorithms based on the electrocardiogram (ECG) are time consuming, prone to inter-observer variability and use delta wave polarity as a binary variable. To overcome these challenges, we propose a model based on a deep neural network (DNN).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>Patients with concealed pathways, multiple antegrade conducting pathways or without any sinus rhythm ECGs were excluded. AP location was determined based on electrophysiological testing during catheter ablation and categorized into right-sided, septal and left-sided APs. Multi-task learning with auxiliary identification of the presence of pre-excitation, parahisian pathways and locations where a transseptal puncture is potentially required was used to increase usability and performance. The DNN was compared to the Milstein and Arruda algorithms.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Between 1997 and 2023, 645 patients who underwent catheter ablation for an AP were included in the study. The model was developed using 1.394 ECGs from 567 patients. The DNN was tested using 78 ECGs in two independent cohorts. The model outperformed both the Milstein and Arruda algorithms with an area under the receiver operating characteristic curve (AUROC) of .92 (95% confidence interval: .88–.96) compared to the Arruda algorithm (AUROC of .80; <i>p</i> &lt;.001) and the Milstein algorithm (AUROC of .81; <i>p</i> &lt;.001).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>Our model showed excellent discriminatory performance in predicting the location of an accessory pathway while outperforming conventional techniques. Clinically, this tool can improve preoperative planning and risk stratification.</p>\u0000 </section>\u0000 </div>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":"55 S1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/eci.14385","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning for electrocardiogram interpretation: Bench to bedside","authors":"Bas B. S. Schots,&nbsp;Camila S. Pizarro,&nbsp;Bauke K. O. Arends,&nbsp;Marish I. F. J. Oerlemans,&nbsp;Dino Ahmetagić,&nbsp;Pim van der Harst,&nbsp;René van Es","doi":"10.1111/eci.70002","DOIUrl":"https://doi.org/10.1111/eci.70002","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Recent advancements in deep learning (DL), a subset of artificial intelligence, have shown the potential to automate and improve disease recognition, phenotyping and prediction of disease onset and outcomes by analysing various sources of medical data. The electrocardiogram (ECG) is a valuable tool for diagnosing and monitoring cardiovascular conditions.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>The implementation of DL in ECG analysis has been used to detect and predict rhythm abnormalities and conduction abnormalities, ischemic and structural heart diseases, with performance comparable to physicians. However, despite promising development of DL algorithms for automatic ECG analysis, the integration of DL-based ECG analysis and deployment of medical devices incorporating these algorithms into routine clinical practice remains limited.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>This narrative review highlights the applications of DL in 12-lead ECG analysis. Furthermore, we review randomized controlled trials that assess the clinical effectiveness of these DL tools. Finally, it addresses different key barriers to widespread implementation in clinical practice, including regulatory hurdles, algorithm transparency and data privacy concerns.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>By outlining both the progress and the obstacles in this field, this review aims to provide insights into how DL could shape the future of ECG analysis and enhance cardiovascular care in daily clinical practice.</p>\u0000 </section>\u0000 </div>","PeriodicalId":12013,"journal":{"name":"European Journal of Clinical Investigation","volume":"55 S1","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/eci.70002","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143786964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}