EClinicalMedicine最新文献

{"title":"Impact of delayed cord clamping on respiratory distress in late preterm and early term infants in elective cesarean section: a single centre, phase Ⅲ, randomised controlled trial.","authors":"Tingting Wang, Silu Wang, Ming Zhou, Yi Duan, Wei Chen, Liping Pan, Zhen Li, Jianguo Zhou, Jiang-Qin Liu","doi":"10.1016/j.eclinm.2025.103126","DOIUrl":"https://doi.org/10.1016/j.eclinm.2025.103126","url":null,"abstract":"<p><strong>Background: </strong>Delayed cord clamping (DCC) has the potential to alleviate respiratory distress by augmenting blood volume and oxygenation, although there is currently a lack of direct evidence to support this. Late preterm and early term infants born via elective cesarean section (CS) are known to be more vulnerable to the neonatal respiratory distress (NRD). This study was designed to examine the effect of DCC on NRD of these infants.</p><p><strong>Methods: </strong>Conducted from January 1, 2019 to January 31, 2024 at Shanghai First Maternity and Infant Hospital, this single-centre, phase Ⅲ, open-label randomised controlled trial included newborns delivered via elective CS between 34⁺⁰ and 38⁺⁶ weeks of gestation. Participants were excluded if fetus had suspected or confirmed congenital malformations, metabolic diseases, intrauterine growth restriction, late fetal heart rate deceleration or fetal distress. Pregnant women and their infants were randomised into immediate cord clamping (ICC) within 10 s of birth or DCC for 60 s and stratified by late preterm or early term. The primary outcome was the incidence of NRD which was defined as requiring oxygen or airway pressure support within the first 24 h of life. This study was approved from the Ethics Committee of Shanghai First Maternity and Infant Hospital, School of Medicine, Tongji University (KS 18126, KS1947). Chinese Clinical Trial Registry (ChiCTR1800017865), registered on August 18th, 2018.</p><p><strong>Findings: </strong>Of 2610 randomised women, 1418 neonates were included in the DCC group and 1419 in the ICC group. The mean maternal age for both groups was 33 (4) years, and all mothers were of Han ethnicity. The mean gestational age of the neonates was 37.9 (0.9) weeks in both groups. NRD occurred in 119 (8.4%) in DCC versus 135 (9.5%) in ICC (Adjusted Relative Risk [aRR] 0.93, 95% CI 0.75-1.14). There were no significant differences in infant and maternal adverse events such as low Apgar score (aRR 0.74, 95% CI 0.25-2.19), hypothermia (aRR 1.00, 95% CI 0.89-1.12), hypoglycemia (aRR 1.04, 95% CI 0.77-1.38), maternal intrapartum massive bleeding (aRR 0.96, 95% CI 0.76-1.19), or the requirement for transfusion (aRR 0.34, 95% CI 0.10-1.15).</p><p><strong>Interpretation: </strong>Delayed cord clamping was safe for both mothers and infants in late preterm and early term delivered by elective cesarean section, while it did not reduce the risk of early respiratory diseases.</p><p><strong>Funding: </strong>This trial was funded by Shanghai Municipal Health Commission, China in 2019 (201940140) and National Natural Science Foundation of China in 2022 (82204047).</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103126"},"PeriodicalIF":9.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909439/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable deep learning algorithm for identifying cerebral venous sinus thrombosis-related hemorrhage (CVST-ICH) from spontaneous intracerebral hemorrhage using computed tomography.","authors":"Kai-Cheng Yang, Yunzhi Xu, Qing Lin, Li-Li Tang, Jia-Wei Zhong, Hong-Na An, Yan-Qin Zeng, Ke Jia, Yujia Jin, Guoshen Yu, Feng Gao, Li Zhao, Lu-Sha Tong","doi":"10.1016/j.eclinm.2025.103128","DOIUrl":"https://doi.org/10.1016/j.eclinm.2025.103128","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Misdiagnosis of hemorrhage secondary to cerebral venous sinus thrombosis (CVST-ICH) as arterial-origin spontaneous intracerebral hemorrhage (sICH) can lead to inappropriate treatment and the potential for severe adverse outcomes. The current practice for identifying CVST-ICH involves venography, which, despite being increasingly utilized in many centers, is not typically used as the initial imaging modality for ICH patients. The study aimed to develop an explainable deep learning model to quickly identify ICH caused by CVST based on non-contrast computed tomography (NCCT).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The study population included patients diagnosed with CVST-ICH and other spontaneous ICH from January 2016 to March 2023 at the Second Affiliated Hospital of Zhejiang University, Taizhou First People's Hospital, Taizhou Hospital, Quzhou Second People's Hospital, and Longyan First People's Hospital. A transfer learning-based 3D U-Net with segmentation and classification was proposed and developed only on admission plain CT. Model performance was assessed using the area under the curve (AUC), sensitivity, and specificity metrics. For further evaluation, the average diagnostic performance of nine doctors on plain CT was compared with model assistance. Interpretability methods, including Grad-CAM++, SHAP, IG, and occlusion, were employed to understand the model's attention.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;An internal dataset was constructed using propensity score matching based on age, initially including 102 CVST-ICH patients (median age: 44 [29, 61] years) and 683 sICH patients (median age: 65 [52, 73] years). After matching, 102 CVST-ICH patients and 306 sICH patients (median age: 50 [40, 62] years) were selected. An external dataset consisted of 38 CVST-ICH and 119 sICH patients from four other hospitals. Validation showed AUC 0·94, sensitivity 0·96, and specificity 0·8 for the internal testing subset; AUC 0·85, sensitivity 0·87, and specificity 0·82 for the external dataset, respectively. The discrimination performance of nine doctors interpreting CT images significantly improved with the assistance of the proposed model (accuracy 0·79 vs 0·71, sensitivity 0·88 vs 0·81, specificity 0·75 vs 0·68, &lt;i&gt;p&lt;/i&gt; &lt; 0·05). Interpretability methods highlighted the attention of model to the features of hemorrhage edge appearance.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;The present model demonstrated high-performing and robust results on discrimination between CVST-ICH and spontaneous ICH, and aided doctors' diagnosis in clinical practice as well. Prospective validation with larger-sample size is required.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/strong&gt;The work was funded by the National Key R&D Program of China (2023YFE0118900), National Natural Science Foundation of China (No.81971155 and No.81471168), the Science and Technology Department of Zhejiang Province (LGJ22H180004), Medical and Health Science and Technology Project of Zhejiang Pr","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103128"},"PeriodicalIF":9.6,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11909457/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effects of lifestyle interventions on mental health in children and adolescents with overweight or obesity: a systematic review and meta-analysis.","authors":"Jiali Zhou, Yuan Song, Jiayao Ying, Chenhao Zhang, Jing Wu, Shiyi Shan, Jindian Zha, Liying Zhou, Wenhan Xiao, Peige Song","doi":"10.1016/j.eclinm.2025.103121","DOIUrl":"https://doi.org/10.1016/j.eclinm.2025.103121","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Childhood obesity and mental health disorders are increasingly prevalent. While lifestyle interventions are widely recognized as effective for managing obesity in children and adolescents, their effects on mental health remain unclear. This study aimed to systematically evaluate the effects of lifestyle interventions on mental health outcomes among children and adolescents with overweight or obesity.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;In this systematic review and meta-analysis, we searched five databases (PubMed, Embase, MEDLINE, CENTRAL and CINAHL) for relevant randomised controlled trials (RCTs) or non-randomised studies of interventions (NRSIs) published from database inception to December 7, 2024, without language restrictions. Lifestyle interventions are defined as structured programs that promote health-related behavioural changes across diverse domains, such as physical activity, dietary adjustments, cognitive training, and psychosocial support. We included studies that assessed the effects of lifestyle interventions on mental health outcomes among children and adolescents with overweight or obesity. Two reviewers independently screened records for eligibility, extracted study-level data and assessed risk of bias of RCTs and NRSIs via the revised Cochrane Risk of Bias Tool for randomised controlled trials (RoB 2) and the Risk of Bias in Non-randomised Studies-of Interventions (ROBINS-I), and certainty of the evidence by the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) approach. RCTs were prioritized as the primary source of evidence, while NRSIs served as supplementary evidence. A random-effects meta-analysis model was performed to calculate pooled standardized mean differences (SMDs) and 95% confidence intervals (CIs). Subgroup analyses stratified by age, body mass index (BMI) category, intervention type, theoretical framework, duration, and World Bank income region, were further conducted to identify potential sources of heterogeneity. The review protocol was registered in PROSPERO, CRD42024571061.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;We identified 20,359 records, of which 26 studies (17 RCTs and nine NRSIs) involving 3511 children and adolescents with overweight or obesity were included. Mental health outcomes assessed included depression, anxiety, self-concept, self-efficacy, negative affect, quality of life, and emotional functioning. Lifestyle interventions evaluated encompassed physical activity, health education, emotion regulation, diet, and multicomponent approaches. Among RCTs, reductions in depression (SMD = -0.24, 95% CI: -0.39 to -0.10, &lt;i&gt;I-square&lt;/i&gt; [&lt;i&gt;I&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt;] = 0.0%) and improvements in quality of life (SMD = 0.24, 95% CI: 0.04-0.44, &lt;i&gt;I&lt;/i&gt; &lt;sup&gt;2&lt;/sup&gt; = 44.0%) were observed, with moderate certainty. Subgroup analyses revealed greater reductions in depression among adolescents and participants with obesity, in programs that involving multicomponent a","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103121"},"PeriodicalIF":9.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11906288/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647554","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance of an AI prediction tool for new-onset atrial fibrillation after coronary artery bypass grafting.","authors":"Hualong Ma, Dalong Chen, Weitao Lv, Qiuying Liao, Jingyi Li, Qinai Zhu, Ying Zhang, Lizhen Deng, Xiaoge Liu, Qinyang Wu, Xianliang Liu, Qiaohong Yang","doi":"10.1016/j.eclinm.2025.103131","DOIUrl":"https://doi.org/10.1016/j.eclinm.2025.103131","url":null,"abstract":"<p><strong>Background: </strong>There is lack of tools to predict new-onset postoperative atrial fibrillation (NOAF) after coronary artery bypass grafting (CABG). We aimed to develop and validate a novel AI-based bedside tool that accurately predicts predict NOAF after CABG.</p><p><strong>Methods: </strong>Data from 2994 patients who underwent CABG between March 2015 and July 2024 at two tertiary hospitals in China were retrospectively analyzed. 2486 patients from one hospital formed the derivation cohort, split 7:3 into training and test sets, while the 508 patients from a separate hospital formed the external validation cohort. A stacking model integrating 11 base learners was developed and evaluated using Accuracy, Precision, Recall, F1 score, and Area Under Curve (AUC). SHapley Additive exPlanations (SHAP) values were calculated and plotted to interpret the contributions of individual characteristics to the model's predictions.</p><p><strong>Findings: </strong>Seventy-seven predictive characteristics were analyzed. The stacking model achieved superior performance with AUCs 0·931 and F1 scores 0·797 in the independent external validation, outperforming CHA2DS2-VASc, HATCH, and POAF scores (AUC 0·931 vs. 0·713, 0·708, and 0·667; <i>p</i> < 0·05). SHAP value indicate that the importance of predictive features for NOAF, in descending order, include: Brain natriuretic peptide, Left ventricular end-diastolic diameter, Ejection fraction, BMI, β-receptor blockers, Duration of surgery, Age, Neutrophil percentage-to-albumin ratio, Myocardial infarction, Left atrial diameter, Hypertension, and smoking status. Subsequently, we constructed an easy-to-use bedside clinical tool for NOAF risk assessment leveraging these characteristics.</p><p><strong>Interpretation: </strong>The AI-based tool offers superior prediction of NOAF, outperforming three existing predictive tools. Future studies should further explore how various patient characteristics influence the timing of NOAF onset, whether early or late.</p><p><strong>Funding: </strong>This work was funded by Lingnan Nightingale Nursing Research Institute of Guangdong Province, and Guangdong Nursing Society (GDHLYJYZ202401).</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103131"},"PeriodicalIF":9.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11908608/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143647615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Online pharmacies: a double-edged sword.","authors":"eClinicalMedicine","doi":"10.1016/j.eclinm.2025.103133","DOIUrl":"https://doi.org/10.1016/j.eclinm.2025.103133","url":null,"abstract":"","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103133"},"PeriodicalIF":9.6,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11934860/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143709435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The diagnosis of mucormycosis by PCR in patients at risk: a systematic review and meta-analysis.","authors":"Lottie Brown, Lena Tschiderer, Alexandre Alanio, Rosemary A Barnes, Sharon C-A Chen, Massimo Cogliati, Mario Cruciani, J Peter Donnelly, Ferry Hagen, Catriona Halliday, Lena Klingspor, Katrien Lagrou, Willem Melchers, Laurence Millon, Florent Morio, Elena Salvador, Giacomo Stroffolini, Markus Ruhnke, Stephanie Toepfer, Karin van Dijk, Andrew M Borman, María José Buitrago, Rebecca Gorton, Jürgen Löffller, Riina Rautemaa-Richardson, Boualem Sendid, Peter Willeit, P Lewis White, Michaela Lackner","doi":"10.1016/j.eclinm.2025.103115","DOIUrl":"10.1016/j.eclinm.2025.103115","url":null,"abstract":"<p><strong>Background: </strong>This systematic review and meta-analysis aimed to examine the performance of polymerase chain reaction (PCR) assays for diagnosing mucormycosis.</p><p><strong>Methods: </strong>A standardised search was conducted from conception to December 3rd 2024 using PubMed, Embase, Global Health, and Cochrane library. Original studies that used PCR-based methods on any human specimen to diagnose mucormycosis were analysed for eligibility. Using a bivariate meta-analysis, the diagnostic performance of PCR was examined against the European Organisation for Research and Treatment of Cancer-Mycoses Study Group Education and Research Consortium 2020 (EORTC-MSGERC) definitions of proven and probable invasive mould disease, which was modified to include all patients at risk of mucormycosis. The study protocol was registered on the PROSPERO database (CRD42023478667).</p><p><strong>Findings: </strong>Of 4855 articles, a total of 30 met inclusion criteria, including 5920 PCR reactions on 5147 non-duplicate specimens from 819 cases of proven/probable mucormycosis and 4266 patients who did not meet the EORTC-MSGERC 2020 criteria. According to specimen type, sensitivity of PCR varied (p < 0.001) whereas specificity was similar (p = 0.662). Bronchoalveolar lavage fluid offered the highest sensitivity of 97.5% (95% CI 83.7-99.7%), specificity of 95.8% (95% CI 89.6-98.4%), positive likelihood ratio (LR+) of 23.5, and negative likelihood ratio (LR-) of 0.03. Tissue provided sensitivity of 86.4% (95% CI 78.9-91.5%), specificity of 90.6% (95% CI 78.1-96.3%), LR+ of 9.2, and LR- of 0.15. Blood provided reduced sensitivity of 81.6% (95% CI 70.1-89.4%), specificity of 95.5% (95% CI 87.4-98.5%), DOR of 95, LR+ of 18.3, and LR- of 0.19. Formalin-fixed paraffin-embedded specimens yielded the lowest sensitivity of 73.0% (95% CI 61.0-82.3%), highest specificity of 96.4% (CI 95% 87.5-99.0%), LR+ of 20.2, and LR- of 0.28. The covariates best explaining heterogeneity of the overall analysis were specimen type, study design (cohort <i>versus</i> case-control) and disease prevalence while patient population (COVID-19 <i>versus</i> other) and PCR (conventional <i>versus</i> quantitative) had less impact on heterogeneity.</p><p><strong>Interpretation: </strong>This meta-analysis confirms the high performance of PCR for diagnosing mucormycosis and supports the instatement of PCR detection of free-DNA in blood, BALF and tissue into future updated definitions and diagnostic guidelines for mucormycosis.</p><p><strong>Funding: </strong>None.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103115"},"PeriodicalIF":9.6,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905852/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Global Fund, Cervical Cancer, and HPV infections: what can low- and middle-income countries do to accelerate progress by 2030?","authors":"Runcie C W Chidebe, Alile Osayi, Julie S Torode","doi":"10.1016/j.eclinm.2025.103127","DOIUrl":"10.1016/j.eclinm.2025.103127","url":null,"abstract":"<p><p>The footprint of cervical cancer mirrors the impact of global inequity and inequality on the right to health for girls and women. While today, cervical cancer is a relatively rare cause of death in Europe, North America, and Australia, almost 94% of deaths in 2022 occurred in low- and middle-income countries (LMICs). Governments adopted the WHO global strategy to eliminate cervical cancer. Still, the stark reality is that many countries may not reach the 90:70:90 targets by 2030 without political commitment and a sense of urgency. We call for enhanced advocacy for the right to prevention services and political actions to mobilise global funding, local philanthropic support, and innovative financing. During the COVID-19 pandemic, an African coalition raised over $20 million to mitigate the impact of the pandemic. Positive lessons from this response should be replicated to save millions of women and girls at risk of cervical cancer in LMICs. There is a need for a global fund for cancer; regional blocs like the African Union need to recognise the disproportionate burden and establish continental funding mechanisms to enable high-burden countries to make crucial upfront health systems investments that will put their countries on the pathway to cervical cancer elimination.</p><p><strong>Funding: </strong>This study was not funded.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103127"},"PeriodicalIF":9.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905856/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence assisted identification of newborn auricular deformities via smartphone application.","authors":"Liu-Jie Ren, Rui-Jie Yang, Li-Li Chen, Shu-Yue Wang, Chen-Long Li, Yuan Huang, Tian-Yu Zhang, Yao-Yao Fu, Shuo Wang","doi":"10.1016/j.eclinm.2025.103124","DOIUrl":"10.1016/j.eclinm.2025.103124","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Auricular deformities are common in newborns and require early diagnosis and timely intervention. Several factors highlight the necessity of a machine learning-based diagnostic solution: the high prevalence of these conditions, the narrow time window for effective non-surgical treatment, limited medical resources, and the importance of both physical and mental well-being. This study presents a novel artificial intelligence (AI) model to identify and classify common sub-types of auricle deformities, using photos taken with mobile devices.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;The dataset was made up of the open-source dataset named BabyEar4k, which contains 3852 auricle images with diagnosis data, and another private dataset containing 104 microtia ears added from ENT Hospital of Fudan University. All the training photos were pre-processed to 800 × 800 RGB images, with the auricles located at the centers. The dataset was divided into two parts, 3835 samples for training/validation and 120 (20 for each class) for testing, i.e., the internal test dataset. 15% of the training data were used for validation during the training process. External validation was conducted on data from three centres across China (Xinjiang N = 252, Guizhou N = 186, and Fujian N = 252). The performance of the model was evaluated by comparative analyses with human volunteers. A prospective test set was collected in Shanghai (Obstetrics & Gynecology Hospital of Fudan University, from 2023/10/17 to 2023/12/29; N = 272). Given the significant variation in the distribution of sub-types, accuracy and weighted F1-score were chosen as primary evaluation metrics.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;Four different backbone architectures were evaluated: ResNet50, DenseNet121, EfficientNet, and RegNet. On the internal test set, the model achieved an accuracy of 0.83-0.85 for six-class classification and 0.94-0.98 for binary classification. ResNet50 backbone had the most consistent performance. Multi-center real-world data validation demonstrated satisfactory accuracy, with a range of 0.74-0.82 for six-class classification and 0.79-0.86 for normal/abnormal classification, indicating strong generalizability. In comparative analyses with volunteers, the professionals achieved an accuracy of 0.7-0.8 in the six-class classification task, while the related fellows scored 0.45-0.65, and the laypeople scored 0.45-0.55.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;The developed system offers an efficient and cost-effective solution for clinical applications, including early diagnosis of newborn auricular deformities, monitoring treatment progress, and educational purposes.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/strong&gt;This study was supported by Shanghai Science and Technology Innovation Action Plan (23Y21900200, 21DZ2200700, T-Y Zhang) and Medical Engineering Fund of Fudan University (Y-Y Fu). S Wang was supported by the Shanghai Sailing Program (22YF1409300) and China Computer Federation (C","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103124"},"PeriodicalIF":9.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905851/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bronchodilator responsiveness and future chronic airflow obstruction: a multinational longitudinal study.","authors":"Ben Knox-Brown, Fahad Algharbi, Octavia Mulhern, James Potts, Imed Harrabi, Christer Janson, Rune Nielsen, Dhiraj Agarwal, Andrei Malinovschi, Sanjay Juvekar, Miriam Denguezli, Thorarinn Gíslason, Rana Ahmed, Asaad Nafees, Parvaiz A Koul, Daniel Obaseki, Mahesh Padukudru Anand, Li Cher Loh, Hermínia Brites Dias, Fátima Rodrigues, David Mannino, Mohammed Elbiaze, Karima El Rhazi, Filip Mejza, Graham Devereux, Frits M E Franssen, Asma El Sony, Emiel Wouters, Mohammed Al Ghobain, Kevin Mortimer, Abdul Rashid, Rashid Osman, Michael Studnicka, Joao Cardoso, Peter Burney, Andre F S Amaral","doi":"10.1016/j.eclinm.2025.103123","DOIUrl":"10.1016/j.eclinm.2025.103123","url":null,"abstract":"<p><strong>Background: </strong>Bronchodilator responsiveness testing is mainly used for diagnosing asthma. We aimed to investigate whether it is associated with progression to chronic airflow obstruction over time.</p><p><strong>Methods: </strong>The multinational Burden of Obstructive Lung Disease cohort study surveyed adults, aged 40 years and above, at baseline and followed them up after a mean of 9.1 years. Recruitment took place between January 2, 2003 and December 26, 2016. Follow-up measurements were collected between January 29, 2019 and October 24, 2021. On both occasions, study participants provided information on respiratory symptoms, health status and several environmental and lifestyle exposures. They also underwent pre- and post-bronchodilator spirometry. We defined bronchodilator responsiveness at baseline using the American Thoracic Society and European Respiratory Society (ATS/ERS) 2022 definition, and the presence of chronic airflow obstruction at follow-up as a post-bronchodilator forced expiratory volume in 1 s to forced vital capacity ratio (FEV₁/FVC) less than the lower limit of normal. We used multi-level regression models to estimate the association between baseline bronchodilator responsiveness and incident chronic airflow obstruction. We stratified analyses by gender and performed a sensitivity analysis in never smokers.</p><p><strong>Findings: </strong>We analysed data from 3701 adults with 56% being women. Compared to those without bronchodilator responsiveness at baseline, those with bronchodilator responsiveness had 36% increased risk of developing chronic airflow obstruction (RR: 1.36, 95%CI 1.04, 1.80). This effect was stronger in women (RR: 1.45, 95%CI 1.09, 1.91) than men (RR: 1.07, 95%CI 0.51, 2.24). Never smokers with bronchodilator responsiveness also were at greater risk of incident chronic airflow obstruction (RR: 1.48, 95%CI 1.01, 2.20).</p><p><strong>Interpretation: </strong>Bronchodilator responsiveness appears to be a risk factor for incident chronic airflow obstruction. It is important that future studies in other large population-based cohorts replicate these findings.</p><p><strong>Funding: </strong>National Heart and Lung Institute, UK Medical Research Council, and Wellcome Trust.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103123"},"PeriodicalIF":9.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11905823/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143623949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Leveraging near-real-time patient and population data to incorporate fluctuating risk of severe COVID-19: development and prospective validation of a personalised risk prediction tool.","authors":"Kaitlin Swinnerton, Nathanael R Fillmore, Austin Vo, Jennifer La, Danne Elbers, Mary Brophy, Nhan V Do, Paul A Monach, Westyn Branch-Elliman","doi":"10.1016/j.eclinm.2025.103114","DOIUrl":"10.1016/j.eclinm.2025.103114","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;Novel strategies that account for population-level changes in dominant variants, immunity, testing practices and changes in individual risk profiles are needed to identify patients who remain at high risk of severe COVID-19. The aim of this study was to develop and prospectively validate a tool to predict absolute risk of severe COVID-19 incorporating dynamic parameters at the patient and population levels that could be used to inform clinical care.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;A retrospective cohort of vaccinated US Veterans with SARS-CoV-2 from July 1, 2021, through August 25, 2023 was created. Models were estimated using logistic-regression-based machine learning with backward selection and included a variable with fluctuating absolute risk of severe COVID-19 to account for temporal changes. Age, sex, vaccine type, fully boosted status, and prior infection before vaccination were included &lt;i&gt;a priori&lt;/i&gt;. Variations in individual risk over time, e.g., due to receipt of immune suppressive medications, were also potentially included. The model was developed using data from July 1, 2021, through August 31, 2022 and prospectively validated on a subsequent second cohort (September 1, 2022, through August 25, 2023). Model performance was quantified by the area under the receiver operating characteristic curve (AUC) and calibration by Brier score. The final model was used to compare observed rates of severe disease to predicted rates among patients who received oral antivirals.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;216,890 SARS-CoV-2 infections in Veterans not treated with oral antivirals were included (median age, 65; 88% male). The development cohort included 165,303 patients (66,121 in the training set, 49,591 in the tuning set, and 49,591 in the testing set) and the prospective validation cohort included 51,587 patients. The percentage of severe infections ranged from 5% to 25%. Model performance improved until 24 clinical predictor variables including age, co-morbidities, and immune-suppressive medications plus a 30-day rolling risk window were included (AUC in development cohort, 0.88 (95% CI, 0.87-0.88), AUC in prospective validation, 0.85 (95% CI, 0.84-0.85), Brier Score, 0.13). The most important variables for predicting severe disease included age, chronic kidney disease, chronic obstructive pulmonary disease, Alzheimer's disease, heart failure, and anaemia. Glucocorticoid use during the one-month prior to COVID-19 diagnosis was the next most important predictor. Models that included a near-real time fluctuating population risk variable performed better than models stratified by circulating variant and models with dominant variant included as a predictor. Patients with predicted severe disease risk &gt;3% who received oral antivirals had approximately 4-fold lower rates of severe COVID-19 untreated patients at a similar risk level.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;Our novel risk prediction tool uses a simple","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"81 ","pages":"103114"},"PeriodicalIF":9.6,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11893359/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143604366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}