EClinicalMedicine最新文献

{"title":"Inter-pregnancy interval and uterine rupture during a trial of labour after one previous caesarean delivery and no previous vaginal births: a retrospective population-based cohort study.","authors":"Pejman Adily, Travis Bettison, Mark Lauer, Rajit Narayan, Adam Mackie, Hala Phipps, Vincenzo Berghella, Marjan M Haghighi, Katelyn Perren, George Johnson, Bradley de Vries","doi":"10.1016/j.eclinm.2025.103071","DOIUrl":"10.1016/j.eclinm.2025.103071","url":null,"abstract":"<p><strong>Background: </strong>Short interpregnancy interval (IPI) following caesarean delivery is associated with uterine rupture in subsequent pregnancies. However, the interval required to minimise this risk is unknown. We investigated how the interval between pregnancies and induction or augmentation of labour affect the likelihood of uterine rupture among parturients with one previous livebirth by caesarean delivery who had a subsequent trial of labour.</p><p><strong>Methods: </strong>In this population-based cohort study, we used data from U.S National Vital Statistics System from 2011 to 2021. Multiple pregnancies and births of infants with congenital abnormalities were excluded. A linear spline logistic regression with one knot was used to assess the relationship between uterine rupture and interpregnancy interval for spontaneous and for induced/augmented labours. Multivariable logistic regression was performed with multiple imputation and stepwise backward elimination to adjust for maternal demographic and clinical factors including maternal age, height, and BMI and gestational age. The predicted risk of uterine rupture was tabulated for interpregnancy intervals between zero and 21 months. Adverse outcomes were compared between labours with and without uterine rupture.</p><p><strong>Findings: </strong>We examined 491,998 trials of labour among parturients with one previous livebirth by caesarean delivery and no previous vaginal births. The odds ratio (OR) of uterine rupture per three months interpregnancy interval was 0.91 (95% CI 0.88-0.94) between zero and 21 months after adjusting for confounders, with no further change in risk detected beyond 21 months. The OR was 2.51 (95% CI 2.27-2.78) for induced or augmented labours compared with spontaneous labours. Other factors associated with uterine rupture included older maternal age, shorter maternal height, more advanced gestational age (from 35 to 43 weeks), and heavier birthweight. Predicted rates of uterine rupture ranged from 0.36% at zero to 0.19% at 21 months' interpregnancy interval for spontaneous labours and from 0.91% to 0.47% for induced/augmented labours for parturients with a typical clinical and demographic background. When uterine rupture occurred, the rates of unplanned hysterectomy, intrapartum or neonatal death, and neonatal seizures were 4.0% (95% CI 3.2-5.1%), 3.7% (95% CI 2.7-5.1%), and 2.6% (95% CI 1.8-3.3%) respectively.</p><p><strong>Interpretation: </strong>The risk of uterine rupture progressively decreases as IPI increases until about 21 months and then stabilises. Counselling should advise that for women choosing between a planned TOLAC or a planned caesarean delivery after one previous caesarean delivery and no previous vaginal births waiting until 21 months or longer after a prior low transverse caesarean delivery might minimise the risk of uterine rupture. The absolute risk of certain serious maternal and fetal/neonatal complications such as unplanned hyste","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103071"},"PeriodicalIF":9.6,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11788787/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143122450","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":"An interpretable machine learning tool for in-home monitoring of agitation episodes in people living with dementia: a proof-of-concept study.","authors":"Marirena Bafaloukou, Ann-Kathrin Schalkamp, Nan Fletcher-Lloyd, Alex Capstick, Chloe Walsh, Cynthia Sandor, Samaneh Kouchaki, Ramin Nilforooshan, Payam Barnaghi","doi":"10.1016/j.eclinm.2024.103032","DOIUrl":"10.1016/j.eclinm.2024.103032","url":null,"abstract":"<p><strong>Background: </strong>Agitation affects around 30% of people living with dementia (PLwD), increasing carer burden and straining care services. Agitation identification typically relies on subjective clinical scales and direct patient observation, which are resource-intensive and challenging to incorporate into routine care. Clinical applicability of data-driven methods for agitation monitoring is limited by constraints such as short observational periods, data granularity, and lack of interpretability and generalisation. Current interventions for agitation are primarily medication-based, which may lead to severe side effects and lack personalisation. Understanding how real-world factors interact with agitation within home settings offers a promising avenue towards identifying potential personalised non-pharmacological interventions.</p><p><strong>Methods: </strong>We used longitudinal data (32,896 person-days from n = 63 PLwD) collected using in-home monitoring devices between December 2020 and March 2023. Employing machine learning techniques, we developed a monitoring tool to identify the presence of agitation during the week. We incorporated a traffic-light system to stratify agitation probability estimates supporting clinical decision-making, and employed the SHapley Additive exPlanations (SHAP) framework to enhance interpretability. We designed an interactive tool that enables the exploration of personalised non-pharmacological interventions, such as modifying ambient light and temperature.</p><p><strong>Findings: </strong>Light Gradient-boosting Machine (LightGBM) achieved the highest performance in identifying agitation over an 8-day period with a sensitivity of 71.32% ± 7.38 and specificity of 75.28% ± 7.38. Implementing the traffic-light system for stratification increased specificity to 90.3% ± 7.55 and improved all metrics. Key features for identifying agitation included low nocturnal respiratory rate, heightened alertness during sleep, and increased indoor illuminance, as revealed by statistical and feature importance analysis. Using our interactive tool, we identified indoor lighting and temperature adjustments as the most promising and feasible intervention options within our cohort.</p><p><strong>Interpretation: </strong>Our interpretable framework for agitation monitoring, developed using data from a dementia care study, showcases significant clinical value. The accompanying interactive interface allows for the <i>in-silico</i> simulation of non-pharmacological interventions, facilitating the design of personalised interventions that can improve in-home dementia care.</p><p><strong>Funding: </strong>This study is funded by the UK Dementia Research Institute [award number UK DRI-7002] through UK DRI Ltd, principally funded by the Medical Research Council (MRC), and the UKRI Engineering and Physical Sciences Research Council (EPSRC) PROTECT Project (grant number: EP/W031892/1). Infrastructure support for this research was ","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103032"},"PeriodicalIF":9.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787694/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143078975","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":"Discrepancies in reported results between trial registries and journal articles for AI clinical research.","authors":"Zixuan He, Lan Yang, Xiaofan Li, Jian Du","doi":"10.1016/j.eclinm.2024.103066","DOIUrl":"10.1016/j.eclinm.2024.103066","url":null,"abstract":"<p><strong>Background: </strong>Complete and unbiased reporting of clinical trial results is essential for evaluating medical advances, yet publication bias and reporting discrepancies in research on the clinical application of artificial intelligence (AI) remain unknown.</p><p><strong>Methods: </strong>We conducted a comprehensive search of research publications and clinical trial registries focused on the application of AI in healthcare. Our search included publications in Dimensions.ai and pre-registered records from ClinicalTrials.gov and the EU Clinical Trials Registry before 31 December 2023. We linked registered trials to their corresponding publications, analysed the registration, reporting and different dissemination patterns of results, identified discrepancies between clinical trial registries and published literature, and assessed the use of these results in secondary research.</p><p><strong>Findings: </strong>We identified 28,248 publications related to the use of AI in clinical settings and found 1863 publications that included a clinical trial registration ID. The clinical trial registry search identified 3710 trials evaluating the use of AI in clinical settings, of which 1106 trials are completed, yet only 101 trials have published results. By linking the trials to their corresponding publications, we found that 26 trials had results available from both registries and publications. There were more results in trial registries than in articles, but researchers showed a clear preference for rapid dissemination of results through peer-reviewed articles (37.6% published within one year) over trial registries (15.8%). Discrepancies and omissions of results were common, and no complete agreement was observed between the two sources. Selective reporting of publications occurred in 53.6% of cases, and the underestimation of the incidence of adverse events is alarming.</p><p><strong>Interpretation: </strong>This research uncovers concerns with the registration and reporting of AI clinical trial results. While trial registries and publications serve distinct yet complementary roles in disseminating research findings, discrepancies between them may undermine the reliability of the evidence. We emphasise adherence to guidelines that promote transparency and standardisation of reporting, especially for investigator-initiated trials (IITs).</p><p><strong>Funding: </strong>The authors declare no source of funding.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103066"},"PeriodicalIF":9.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11831125/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143440283","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":"Hybrid versus vaccine immunity of mRNA-1273 among people living with HIV in East and Southern Africa: a prospective cohort analysis from the multicentre CoVPN 3008 (Ubuntu) study.","authors":"Nigel Garrett, Asa Tapley, Aaron Hudson, Sufia Dadabhai, Bo Zhang, Nyaradzo M Mgodi, Jessica Andriesen, Azwidihwi Takalani, Leigh H Fisher, Jia Jin Kee, Craig A Magaret, Manuel Villaran, John Hural, Erica Andersen-Nissen, Guido Ferarri, Maurine D Miner, Bert Le Roux, Eduan Wilkinson, Richard Lessells, Tulio de Oliveira, Jackline Odhiambo, Parth Shah, Laura Polakowski, Margaret Yacovone, Taraz Samandari, Zvavahera Chirenje, Peter James Elyanu, Joseph Makhema, Ethel Kamuti, Harriet Nuwagaba-Biribonwoha, Sharlaa Badal-Faesen, William Brumskine, Soritha Coetzer, Rodney Dawson, Sinead Delany-Moretlwe, Andreas Henri Diacon, Samantha Fry, Katherine Margaret Gill, Zaheer Ahmed Ebrahim Hoosain, Mina C Hosseinipour, Mubiana Inambao, Craig Innes, Steve Innes, Dishiki Kalonji, Margaret Kasaro, Priya Kassim, Noel Kayange, William Kilembe, Fatima Laher, Moelo Malahleha, Vongane Louisa Maluleke, Grace Mboya, Kirsten McHarry, Essack Mitha, Kathryn Mngadi, Pamela Mda, Tumelo Moloantoa, Cissy Kityo Mutuluuza, Nivashnee Naicker, Vimla Naicker, Anusha Nana, Annet Nanvubya, Maphoshane Nchabeleng, Walter Otieno, Elsje Louise Potgieter, Disebo Potloane, Zelda Punt, Jamil Said, Yashna Singh, Mohammed Siddique Tayob, Yacoob Vahed, Deo Ogema Wabwire, M Juliana McElrath, James G Kublin, Linda-Gail Bekker, Peter B Gilbert, Lawrence Corey, Glenda E Gray, Yunda Huang, Philip Kotze","doi":"10.1016/j.eclinm.2024.103054","DOIUrl":"10.1016/j.eclinm.2024.103054","url":null,"abstract":"<p><strong>Background: </strong>With limited access to mRNA COVID-19 vaccines in lower income countries, and people living with HIV (PLWH) largely excluded from clinical trials, Part A of the multicentre CoVPN 3008 (Ubuntu) study aimed to assess the safety of mRNA-1273, the relative effectiveness of hybrid versus vaccine immunity, and SARS-CoV-2 viral persistence among PLWH in East and Southern Africa during the omicron outbreak.</p><p><strong>Methods: </strong>Previously unvaccinated adults with HIV and/or other comorbidities associated with severe COVID-19 received either one (hybrid immunity) or two (vaccine immunity) 100-mcg doses of ancestral strain mRNA-1273 in the first month, depending on baseline evidence of prior SARS-CoV-2 infection. In a prospective cohort study design, we used covariate-adjusted Cox regression and counterfactual cumulative incidence methods to determine the hazard ratio and relative risk of COVID-19 and severe COVID-19 with hybrid versus vaccine immunity within six months. The ongoing Ubuntu study is registered on ClinicalTrials.gov (NCT05168813) and this work was conducted from December 2021 to March 2023.</p><p><strong>Findings: </strong>Between December 2021 and September 2022, 14,237 participants enrolled, and 14,002 (83% PLWH, 69% SARS-CoV-2 seropositive) were included in the analyses. Vaccinations were safe and well tolerated. Common adverse events were pain or tenderness at the injection site (26.7%), headache (20.4%), and malaise (20.3%). Severe adverse events were rare (0.8% of participants after the first and 1.1% after the second vaccination), and none were life-threatening or fatal. Among PLWH, the median CD4 count was 635 cells/μl and 18.5% had HIV viraemia. The six-month cumulative incidences in the hybrid immunity and vaccine immunity groups were 2.02% (95% confidence interval [CI] 1.61-2.44) and 3.40% (95% CI 2.30-4.49) for COVID-19, and 0.048% (95% CI 0.00-0.10) and 0.32% (95% CI 0.59-0.63) for severe COVID-19. Among all PLWH the hybrid immunity group had a 42% lower hazard rate of COVID-19 (hazard ratio [HR] 0.58; 95% CI 0.44-0.77; p < 0.001) and a 73% lower hazard rate of severe COVID-19 (HR 0.27; 95% CI 0.07-1.04; p = 0.056) than the vaccine immunity group, but this effect was not seen among PLWH with CD4 counts <350 cells/μl or HIV viraemia. Twenty PLWH had persistent SARS-CoV-2 virus at least 50 days.</p><p><strong>Interpretation: </strong>Hybrid immunity was associated with superior protection from COVID-19 compared to vaccine immunity with the ancestral mRNA-1273 vaccine. Persistent infections among immunocompromised PLWH may provide reservoirs for emerging variants.</p><p><strong>Funding: </strong>National Institute of Allergy and Infectious Diseases.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103054"},"PeriodicalIF":9.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11788791/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143122529","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-based prediction of second stage duration in labor: a multicenter retrospective cohort analysis.","authors":"Xiaoqing Huang, Xiaodan Di, Suiwen Lin, Minrong Yao, Suijin Zheng, Shuyi Liu, Wayan Lau, Zhixin Ye, Zilian Wang, Bin Liu","doi":"10.1016/j.eclinm.2025.103072","DOIUrl":"10.1016/j.eclinm.2025.103072","url":null,"abstract":"<p><strong>Background: </strong>Duration of second stage of labor is crucial for fetal delivery, but the optimal length of this stage remains controversial. While extending the duration of second stage can reduce primary cesarean delivery rates, it may increase maternal and neonatal morbidities as the duration progresses. We aimed to develop a personalized machine learning (ML) model to predict the possible second-stage duration.</p><p><strong>Methods: </strong>This multicenter, retrospective study was conducted at four tertiary hospitals in China from September 2013 to October 2022. Data from three hospitals in Guangdong Province was selected as derivation set, and a geographically independent dataset from Fujian Province as the external validation set. Singleton vaginal deliveries with term live birth in a cephalic position were included. The primary outcome was the duration of the second stage of labor. Since durations beyond 3 h were rare, we developed binary classification models with thresholds at 1 h and 2 h. After the optimal features selected by recursive feature elimination (RFE) method, four ML algorithms were employed to build the models. The best model would be selected with the predictive performance and interpreted with Shapley Additive exPlanations method. The study is registered in Clinical Trial (ChiCTR2400085338).</p><p><strong>Findings: </strong>Electronic medical records of 79,381 vaginal deliveries were obtained, and 63,401 deliveries meeting the inclusion criteria were included in the final analysis. Eight risk features were selected through the RFE process. Gradient boosting machine implemented by decision tree models achieved the best performance, yielding areas under the curve for 1-h and 2-h models of 0.808 (95% confidence interval [CI] 0.797-0.819) and 0.824 (95% CI 0.804-0.843) in the testing set, and 0.862 (95% CI 0.854-0.870) and 0.859 (95% CI 0.843-0.875) in the external validation set, respectively.</p><p><strong>Interpretation: </strong>An explainable and reliable ML model was developed to predict the probable second-stage duration, which could assist in individualized labor management. Factors such as first-stage duration and maternal age are potential predictors for the second stage.</p><p><strong>Funding: </strong>National Natural Science Foundation of China (No.82371689, N0.81771602), and National Key Research and Development Program of China (No.2021YFC2700703).</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103072"},"PeriodicalIF":9.6,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11831126/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143440279","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":"Antiviral efficacy of fluoxetine in early symptomatic COVID-19: an open-label, randomised, controlled, adaptive platform trial (PLATCOV).","authors":"Podjanee Jittamala, Simon Boyd, William H K Schilling, James A Watson, Thundon Ngamprasertchai, Tanaya Siripoon, Viravarn Luvira, Elizabeth M Batty, Phrutsamon Wongnak, Lisia M Esper, Pedro J Almeida, Cintia Cruz, Fernando R Ascencao, Renato S Aguiar, Najia K Ghanchi, James J Callery, Shivani Singh, Varaporn Kruabkontho, Thatsanun Ngernseng, Jaruwan Tubprasert, Wanassanan Madmanee, Kanokon Suwannasin, Amornrat Promsongsil, Borimas Hanboonkunupakarn, Kittiyod Poovorawan, Manus Potaporn, Attasit Srisubat, Bootsakorn Loharjun, Walter R J Taylor, Farah Qamar, Abdul Momin Kazi, M Asim Beg, Danoy Chommanam, Sisouphanh Vidhamaly, Kesinee Chotivanich, Mallika Imwong, Sasithon Pukrittayakamee, Arjen M Dondorp, Nicholas P J Day, Mauro M Teixeira, Watcharapong Piyaphanee, Weerapong Phumratanaprapin, Nicholas J White","doi":"10.1016/j.eclinm.2024.103036","DOIUrl":"10.1016/j.eclinm.2024.103036","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background: &lt;/strong&gt;The selective serotonin reuptake inhibitors (SSRIs) fluoxetine and fluvoxamine were repurposed for the treatment of early COVID-19 based on their antiviral activity &lt;i&gt;in vitro&lt;/i&gt;, and observational and clinical trial evidence suggesting they prevented progression to severe disease. However, these SSRIs have not been recommended in therapeutic guidelines and their antiviral activity &lt;i&gt;in vivo&lt;/i&gt; has not been characterised.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;PLATCOV is an open-label, multicentre, phase 2, randomised, controlled, adaptive pharmacometric platform trial running in Thailand, Brazil, Pakistan, and Laos. We recruited low-risk adult outpatients aged 18-50 with early symptomatic COVID-19 (symptoms &lt;4 days) between 5 April 2022 and 8 May 2023. Patients were assigned using block randomisation to one of eleven treatment arms including oral fluoxetine (40 mg/day for 7 days), or no study drug. Uniform randomisation ratios were applied across the active treatment groups while the no study drug group comprised ≥20% of patients at all times. The primary endpoint was the rate of oropharyngeal viral clearance assessed until day 7. Measurements were taken daily between days 0 and 7 and analysed in a modified intention-to-treat population (&gt;2 days follow-up).The viral clearance rate was estimated under a Bayesian hierarchical linear model fitted to the log&lt;sub&gt;10&lt;/sub&gt; viral densities measured in standardised duplicate oropharyngeal swab eluates taken daily over one week (18 measurements per patient). Secondary endpoints were all-cause hospital admission at 28 days, and time to resolution of fever and symptoms. This ongoing trial is registered at ClinicalTrials.gov (NCT05041907).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Findings: &lt;/strong&gt;271 patients were concurrently randomised to either fluoxetine (n = 120) or no study drug (n = 151). All patients had received at least one COVID-19 vaccine dose and 67% were female (182/271). In the primary analysis, viral clearance rates following fluoxetine were compatible with a small or no increase relative to the no study drug arm (15% increase; 95% credible interval (CrI): -2 to 34%). There were no deaths or hospitalisations in either arm. There were no significant differences in times to symptom resolution or fever clearance between the fluoxetine and the no study drug arms (although only a quarter of patients were febrile at baseline). Fluoxetine was well tolerated, there were no serious adverse events and only one grade 3 adverse event in the intervention arm.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Interpretation: &lt;/strong&gt;Overall, the evidence from this study is compatible with fluoxetine having a weak &lt;i&gt;in vivo&lt;/i&gt; antiviral activity against SARS-CoV-2, although the primary endpoint is also compatible with no effect. This level of antiviral efficacy is substantially less than with other currently available antiviral drugs.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Funding: &lt;/strong&gt;Wellcome Trust Grant ref: 223195/Z/21/Z through the COVID-19 Therapeu","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103036"},"PeriodicalIF":9.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787712/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143078980","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":"Albumin and mortality: addressing critiques and reaffirming findings.","authors":"Augusto Di Castelnuovo, Licia Iacoviello, Francesco Violi","doi":"10.1016/j.eclinm.2024.102948","DOIUrl":"10.1016/j.eclinm.2024.102948","url":null,"abstract":"","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"102948"},"PeriodicalIF":9.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787648/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143078971","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":"Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation study.","authors":"Hayeon Lee, Seung Ha Hwang, Seoyoung Park, Yunjeong Choi, Sooji Lee, Jaeyu Park, Yejun Son, Hyeon Jin Kim, Soeun Kim, Jiyeon Oh, Lee Smith, Damiano Pizzol, Sang Youl Rhee, Hyunji Sang, Jinseok Lee, Dong Keon Yon","doi":"10.1016/j.eclinm.2025.103069","DOIUrl":"10.1016/j.eclinm.2025.103069","url":null,"abstract":"<p><strong>Background: </strong>Type 2 diabetes mellitus (T2DM) is a significant global public health concern that has steadily increased over the past few decades. Thus, this study aimed to predict the incidence of T2DM within 5 years and the risk of mortality following the onset of T2DM. Data from three independent cohorts worldwide were used.</p><p><strong>Methods: </strong>We utilized data from three independent, large-scale, general population-based, and worldwide cohort studies. The Korean cohort (NHIS-NSC cohort; discovery cohort; n = 973,303), conducted between 1 January, 2002 and 31 December, 2013, was used for training and internal validation, whereas the Japanese cohort (JMDC cohort; validation cohort A; n = 12,143,715) and UK cohort (UK Biobank; validation cohort B; n = 416,656) were used for external validation. We employed various machine learning (ML)-based models, using 18 features, to predict the incidence of T2DM within five years of regular health checkups and calculated the Shapley Additive Explanation (SHAP) values. To ensure the robustness of our ML-based prediction model, we investigated the potential association between the model probability divided into tertiles and the risk of mortality following the onset of T2DM.</p><p><strong>Findings: </strong>In the discovery cohort, the ensemble model using voting with logistic regression and adaptive boosting achieved a balanced accuracy of 72.6% and an area under the receiver operating characteristics curve (AUROC) of 0.792. The SHAP value analysis of our proposed model revealed that age was the most important predictor of incident T2DM, followed by fasting blood glucose, hemoglobin, γ-glutamyl transferase level, and body mass index. The model probability is associated with an increased risk of mortality (T1: adjusted hazard ratio, 2.82 [95% CI, 2.01-3.94]; T2: 3.89 [2.74-5.53]; and T3: 7.73 [5.37-11.12]). Similar patterns and trends were observed in the validation cohorts (T1: 1.74 [1.49-2.03], T2: 1.97 [1.69-2.30], and T3: 3.31 [2.82-3.38] in validation cohort A; T1: 1.33 [1.03-1.71], T2: 1.54 [1.21-1.96], and T3: 1.73 [1.36-2.20] in validation cohort B).</p><p><strong>Interpretation: </strong>This study derived and validated an ML-based model to predict the incidence of T2DM within 5 years across three countries (South Korea, Japan, and the UK), showing that the model probability is associated with an increased risk of mortality.</p><p><strong>Funding: </strong>Institute of Information & Communications Technology Planning & Evaluation, South Korea.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103069"},"PeriodicalIF":9.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787438/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143079051","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":"Association of clinical signs of possible serious bacterial infections identified by community health workers with mortality of young infants in South Asia: a prospective, observational cohort study.","authors":"Gary L Darmstadt, Saifuddin Ahmed, Mohammad Shahidul Islam, Safa Abdalla, Shams El Arifeen, Melissa L Arvay, Abdullah H Baqui, Zulfiqar A Bhutta, Anuradha Bose, Nicholas E Connor, Belal Hossain, Rita Isaac, Arif Mahmud, Dipak K Mitra, Luke C Mullany, Imran Nisar, Kalpana Panigrahi, Pinaki Panigrahi, Qazi Sadeq-Ur Rahman, Senjuti Saha, Sajid B Soofi, Nardos Solomon, Mathuram Santosham, Stephanie J Schrag, Shamim A Qazi, Samir K Saha","doi":"10.1016/j.eclinm.2025.103070","DOIUrl":"10.1016/j.eclinm.2025.103070","url":null,"abstract":"<p><strong>Background: </strong>The World Health Organization (WHO) has developed guidance for community health workers (CHWs) in identifying sick young infants based on clinical signs. We conducted a prospective, observational cohort study to characterise mortality risk of young infants based on their clinical signs.</p><p><strong>Methods: </strong>We conducted a population-based, prospective observational cohort study at five sites in Bangladesh (Sylhet, November 01, 2011-December 31, 2013), India (Vellore and Odisha, September 01, 2013-February 28, 2015), and Pakistan (Karachi, January 01, 2012-December 31, 2013; Matiari, March 01, 2012-December 31, 2013) to identify newborn infants who were followed-up by CHWs through 10 scheduled home visits over the first 60 completed days after birth to identify signs of possible serious bacterial infection (PSBI). We determined the frequency of signs and conducted Cox regression to investigate the association of signs with mortality risk within 7 days of identification of the signs.</p><p><strong>Findings: </strong>CHWs made 522,309 visits to assess 63,017 young infants and found ≥1 sign(s) of PSBI at 14,245 visits (2.7%), including 5.8% (5568 of 96,390) and 1.8% (6635 of 365,769) of visits of infants 0-<3 and 7-<60 days of age, respectively. Each of the seven signs of PSBI when found alone was associated with significantly (p < 0.0001) increased risk for mortality, which increased further if any other additional sign of PSBI was found concurrently. Over the young infant period (days 0-<60) CHW identification of no movement or movement only on stimulation was associated with the highest risk for mortality [adjusted hazard ratio (aHR) 73.0, 95% confidence interval (CI) 44.4-119.9] followed by poor feeding (aHR 31.9, 95% CI 24.1-42.3) and hypothermia (<35.5 °C) (aHR 31.4, 95% CI 23.5-41.9). Hypothermia had particularly high risk for mortality during days 7-<60 (HR 45.1, 95% CI 27.6-73.4).</p><p><strong>Interpretation: </strong>WHO reconsideration of hypothermia as a sign of critical illness is warranted. Implementation research is urgently needed to reduce infant mortality by ensuring immediate referrals and interventions for children identified early by CHWs with no movement or movement only on stimulation, hypothermia, or poor feeding, especially in resource-poor settings.</p><p><strong>Funding: </strong>Bill and Melinda Gates Foundation, New Venture Fund for Global Policy and Advocacy.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103070"},"PeriodicalIF":9.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143079002","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":"Time to invest in cholera.","authors":"Rebecca C Stout, Nicholas Feasey, Marion Péchayre, Nicholas Thomson, Benson Z Chilima","doi":"10.1016/j.eclinm.2024.103044","DOIUrl":"10.1016/j.eclinm.2024.103044","url":null,"abstract":"<p><p>The recent surge in cholera cases globally calls for urgent evaluation of current approaches to prevention and control of the disease. Malawi was one of the worst affected countries in 2022-2023 with the highest number of deaths due to cholera in the world. In this personal view, we look at Malawi as a case example to illustrate how current approaches lack sufficient investment. We review the history of cholera in Malawi and compare previous outbreaks to the 2022/23 outbreak. We discuss contributing factors to the outbreak including a lack of investment in water, sanitation and hygiene (both historically and currently), human resource constraints, and the market structures which make accessing oral cholera vaccine challenging both in the midst of an ongoing outbreak and as a preventative approach. We call for international action to address the economic and structural challenges underlying cholera persistence and propose solutions to prevent future epidemics and to eliminate cholera as a public health threat.</p>","PeriodicalId":11393,"journal":{"name":"EClinicalMedicine","volume":"80 ","pages":"103044"},"PeriodicalIF":9.6,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787441/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143079055","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}