Article
Multidisciplinary Sciences
Jane Whelan, Helen Marshall, Thomas R. Sullivan
Summary: Cluster randomized trials (cRCT) play a crucial role in assessing vaccine effectiveness by considering indirect effects of vaccination. This study investigated the impact of shared behaviors and characteristics on the ICC in a school-based cRCT evaluating the effectiveness of a meningococcal B vaccine. The findings suggest that adjusting for social behaviors and personal characteristics can significantly reduce the ICC for disease carriage.
Article
Public, Environmental & Occupational Health
Yongdong Ouyang, Karla Hemming, Fan Li, Monica Taljaard
Summary: It is crucial to estimate the intra-cluster correlation coefficient (ICC) in designing a cluster randomized trial (CRT). For longitudinal CRTs, more complex correlation structures, such as exchangeable, nested/block exchangeable, and exponential decay correlations, are required. Estimating these correlation parameters is a common challenge for researchers. This tutorial provides guidance on estimating correlation parameters for continuous and binary outcomes using different correlation structures and programming code in R, SAS, and Stata.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2023)
Article
Biochemical Research Methods
Jun Chen, Xianyang Zhang
Summary: Due to the sparsity and high dimensionality, microbiome data are often summarized into pairwise distances to capture compositional differences and gain biological insights through analyzing the distance matrix in relation to covariates. This study extends the traditional intraclass correlation coefficient (ICC) to distance measures, proposing a distance-based ICC (dICC) and demonstrating its effectiveness through the application of experimental data.
Article
Health Care Sciences & Services
Ariane M. Mbekwe Yepnang, Agnes Caille, Sandra M. Eldridge, Bruno Giraudeau
Summary: In cluster randomised trials, reporting the measure of intracluster correlation for each primary outcome is important for calculating sample size and interpreting trial results in future studies. The intracluster correlation, especially for binary outcomes, is affected by the prevalence of the outcome, which raises concerns about its use in different prevalence settings. Various measures like variance partition coefficient and tetrachoric correlation coefficient have been proposed for clustered binary data settings to address this issue.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Mathematical & Computational Biology
Fan Li, Xinyuan Chen, Zizhong Tian, Rui Wang, Patrick J. Heagerty
Summary: This article proposes novel variance formulas for analyzing heterogeneity of treatment effects in stepped wedge designs, applicable to both average treatment effect and subgroup treatment effects. The study also investigates optimal design allocations of clusters to maximize precision for evaluating both average and heterogeneous treatment effects.
STATISTICS IN MEDICINE
(2023)
Review
Orthopedics
Lauren K. King, Nicolas S. Bodmer, Pakeezah Saadat, Pavlos Bobos, Gillian A. Hawker, Bruno R. da Costa
Summary: This study reviewed 20 cluster randomized controlled trials (RCTs) in osteoarthritis (OA) and found that only 25% of trials reported the observed intracluster correlation coefficient (ICC), with one trial being underpowered due to a larger ICC value than used for sample size calculation. This highlights the need for more attention and reporting on the importance of ICCs in cluster RCTs.
OSTEOARTHRITIS AND CARTILAGE
(2023)
Article
Health Care Sciences & Services
Kristin J. Konnyu, Monica Taljaard, Noah M. Ivers, David Moher, Jeremy M. Grimshaw
Summary: This study investigated the use of posterior predictive distributions to impute missing ICCs in cluster randomized trials for meta-analysis, demonstrating the importance of accounting for ICC variation and uncertainty. The results of the study showed that this approach can facilitate principled meta-analyses and may improve review inferences for different reviews based on various factors.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2021)
Review
Radiology, Nuclear Medicine & Medical Imaging
Cindy Xue, Jing Yuan, Gladys G. Lo, Amy T. Y. Chang, Darren M. C. Poon, Oi Lei Wong, Yihang Zhou, Winnie C. W. Chu
Summary: Radiomics research has been rapidly growing in recent years, with concerns on reliability raised. This systematic review focused on the use of the intraclass correlation coefficient (ICC) as a reliability metric in radiomics studies. The review found that while feature reliability to image segmentation is extensively studied, image acquisition introduces more variability than image segmentation, particularly in MRI studies.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2021)
Article
Ecology
Josep L. Carrasco
Summary: Repeatability is a concept widely used in different scientific fields to assess the agreement among repeated measurements from the same cluster of subjects. In this work, a novel approach based on spatial distances is proposed to estimate the repeatability of spatial trajectories. The methodology is illustrated with a real case example and simulations.
METHODS IN ECOLOGY AND EVOLUTION
(2023)
Article
Health Care Sciences & Services
Kitty Parker, Michael Nunns, ZhiMin Xiao, Tamsin Ford, Obioha C. Ukoumunne
Summary: This study aims to summarize intracluster correlation coefficient (ICC) estimates for pupil health outcomes from school-based cluster randomized trials (CRTs) across world regions. The findings showed that the distribution of school-level ICCs worldwide was similar to previous summaries from studies in the United States.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Public, Environmental & Occupational Health
Karla Hemming, Monica Taljaard
Summary: Cluster randomized trials require larger sample size and face additional complexities. The potential for contamination justifies the use of cluster randomization, but the risk of contamination should be weighed against the problem of questionable scientific validity in settings with post-randomization identification or recruitment of unblinded participants. Guidelines are provided to minimize bias and maximize statistical efficiency in conducting cluster trials, emphasizing that methods for individually randomized trials rarely apply. Cluster randomization should be used when necessary, balancing its benefits, risks, and sample size. Clustering, restricted randomization, and adjustment for covariates should be considered, and recruitment should preferably be done before randomizing clusters.
INTERNATIONAL JOURNAL OF EPIDEMIOLOGY
(2023)
Article
Biotechnology & Applied Microbiology
Yuxin Li, Lei Tian, Li-Li Guo, Yiran Hao, Ying Jie
Summary: This study evaluated the repeatability and reproducibility of 36 DCR parameters and bIOP parameters derived from Corvis ST in healthy eyes, and investigated their relationship with demographic and ocular characteristics.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Health Care Sciences & Services
Fan Li, James P. Hughes, Karla Hemming, Monica Taljaard, Edward R. Melnick, Patrick J. Heagerty
Summary: The stepped wedge cluster randomized design is gaining attention in pragmatic clinical trials and implementation science research. The design features clusters crossing over from control to intervention conditions in a unidirectional manner on a staggered schedule, which may confound intervention effects over time. This design first appeared in the Gambia hepatitis study in the 1980s, but the statistical model for its design and analysis was formally introduced in 2007. Various mixed-effects model extensions have since been proposed for the design and analysis of these trials.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2021)
Article
Clinical Neurology
Fan Li, Rui Wang
Summary: This study provides an update on the design of stepped wedge randomized trials, including new methodological tools, for neurosurgeon scientists. The study highlights the indications for this design and discusses key considerations such as analysis methods and sample size determination.
WORLD NEUROSURGERY
(2022)
Article
Mathematical & Computational Biology
Fan Li, Xinyuan Chen, Zizhong Tian, Denise Esserman, Patrick J. Heagerty, Rui Wang
Summary: This article explores the heterogeneity of treatment effects in different patient subpopulations in cluster randomized trials and presents a novel analytical design formula that can be widely applied to evaluate effect modifiers at different levels. The effectiveness of this new method is validated through simulation studies and real-world trial examples.
Article
Dermatology
Ketaki Bhate, Kathryn E. Mansfield, Sarah-Jo Sinnott, David J. Margolis, Elizabeth Adesanya, Nick Francis, Clemence Leyrat, Susan Hopkins, Richard Stabler, Laura Shallcross, Sinead M. Langan, Rohini Mathur
Summary: This study investigated the use of oral antibiotics for moderate-to-severe acne vulgaris using primary care data. It was found that 44.5% of individuals received long-term oral antibiotic treatment, with a median of four continuous courses per person. Further research is needed to understand the consequences of using antibiotics for shorter periods.
BRITISH JOURNAL OF DERMATOLOGY
(2023)
Article
Cardiac & Cardiovascular Systems
Jennifer A. Davidson, Amitava Banerjee, Ian Douglas, Clemence Leyrat, Richard Pebody, Helen McDonald, Emily Herrett, Harriet Forbes, Liam Smeeth, Charlotte Warren-Gash
Summary: This study reveals that the incidence of first myocardial infarction and stroke is reduced 1-3 months after influenza vaccination. However, it is still unclear how underlying cardiovascular risk affects this association.
EUROPEAN HEART JOURNAL
(2023)
Article
Mathematical & Computational Biology
Corentin Segalas, Clemence Leyrat, James R. Carpenter, Elizabeth Williamson
Summary: One popular method for addressing confounding in causal inference is propensity score matching, which matches treated patients with untreated patients based on similar propensity scores. Multiple imputation is often used for handling missing data. However, combining propensity score matching and multiple imputation can result in over-coverage of the confidence interval for the treatment effect estimate. In this article, the authors investigate the cause of this over-coverage and propose a correction to remove it.
STATISTICS IN MEDICINE
(2023)
Article
Medicine, Research & Experimental
Mia S. Tackney, Tim Morris, Ian White, Clemence Leyrat, Karla Diaz-Ordaz, Elizabeth Williamson
Summary: Adjusting for baseline covariates in randomized trials can lead to power gains and protect against chance imbalances. However, for continuous covariates, adjusted methods may misspecify the relationship between the covariate and outcome. Through simulation studies, we find that G-computation, IPTW, AIPTW, and TMLE offer improvement over ANCOVA when there is a non-linear interaction between treatment and a skewed covariate in small sample sizes.
Article
Oncology
Sophie Pilleron, Camille Maringe, Eva J. A. Morris, Clemence Leyrat
Summary: In this study conducted in England, it was found that the risk of immortal-time bias (ITB) increases with age when estimating the effect of surgery on 1-year overall survival (OS) in patients with Stage IV colon cancer. Simulation results showed that the magnitude of ITB was larger among older patients when their probability of early death increased or treatment was delayed. The methods addressing ITB corrected the bias, yielding a smaller effect of surgery compared to the time-fixed exposure approach.
BRITISH JOURNAL OF CANCER
(2023)
Article
Health Care Sciences & Services
Mathilde Husson, Agnes Dechartres, Bruno Ramdjee, Maelle Diverres, Tarik Zejli, Marianne L'Henaff, Eric Jehanno, Florence Tubach, Agnes Caille
Summary: This study aims to describe patient and public involvement (PPI) in randomized controlled trials (RCTs) addressing chronic conditions and analyze whether PPI is associated with trial characteristics. The results showed that 40% of the RCTs reported PPI at any stage of the research process, with the majority occurring at the design stage and the conduct stage. PPI RCTs were more likely to be published in The BMJ, have authors from the United Kingdom, report public funding, have a higher inclusion rate, use usual care as a control, and evaluate a digital intervention.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Medicine, General & Internal
Petra C. Vinke, Marc Combalia, Geertruida H. de Bock, Clemence Leyrat, Anne Mea Spanjaart, Stephane Dalle, Maria Gomes da Silva, Aurore Fouda Essongue, Aurelie Rabier, Myriam Pannard, Mohammad S. Jalali, Amal Elgammal, Mike Papazoglou, Mohand-Said Hacid, Catherine Rioufol, Marie-Jose Kersten, Martijn G. H. van Oijen, Erick Suazo-Zepeda, Ananya Malhotra, Emmanuel Coquery, Amelie Anota, Marie Preau, Mathieu Fauvernier, Elsa Coz, Susana Puig, Delphine Maucort-Boulch
Summary: This study aims to investigate the impact of immunotherapy on patients' quality of life, especially immune-related adverse events (irAEs) and its determinants in real-world settings. Through longitudinal observation and data analysis, researchers will collect data from clinical questionnaires and electronic patient files, and analyze them using advanced statistical methods. This study not only contributes to the understanding of the effects of immunotherapy but also facilitates better communication among patients, clinicians, and the general population, and contributes to personalized medicine.
Article
Public, Environmental & Occupational Health
Caroline Whidden, Kassoum Kayentao, Naimatou Kone, Jenny Liu, Mohamed Bana Traore, Djoume Diakite, Mama Coumare, Mohamed Berthe, Mahamadou Guindo, Brian Greenwood, Daniel Chandramohan, Clemence Leyrat, Emily Treleaven, Ari Johnson
Summary: This study conducted a trial in rural Mali to examine the effects of proactive community health worker (CHW) delivery on child mortality and access to healthcare. The results showed that children in the intervention group, where CHWs conducted door-to-door visits, had a 22% higher chance of receiving prompt healthcare compared to the control group. However, this effect diminished after 12 months.
JOURNAL OF GLOBAL HEALTH
(2023)
Article
Endocrinology & Metabolism
M. Katsoulis, A. G. Lai, D. K. Kipourou, M. Gomes, A. Banerjee, S. Denaxas, R. T. Lumbers, K. Tsilidis, Maria Kostara, A. Belot, C. Dale, R. Sofat, C. Leyrat, H. Hemingway, K. Diaz-Ordaz
Summary: When studying the effect of weight change on health outcomes using observational data, the timing and confounding factors are important considerations. This study utilized a target trial emulation framework and proposed a strategy to address these issues by treating weight change as a hypothetical intervention.
INTERNATIONAL JOURNAL OF OBESITY
(2023)
Article
Health Care Sciences & Services
Pierre Poupin, Agnes Caille, Wassim Gana, Bertrand Fougere, Bruno Giraudeau
Summary: This study aimed to assess the feasibility of using an open-cohort design in cluster randomized trials with closed-cohort design. The results showed that an open-cohort design could be a relevant alternative for most of the interventions assessed in nursing homes and should be considered more often.
JOURNAL OF CLINICAL EPIDEMIOLOGY
(2023)
Article
Health Care Sciences & Services
Ananya Malhotra, Heidi P. P. Fransen, Manuela Quaresma, Natasja Raijmakers, Moyke A. J. Versluis, Bernard Rachet, Marissa C. C. van Maaren, Clemence Leyrat
Summary: This study examined the associations between quality of life (QoL) and different cancer treatments and comorbidities in patients with advanced cancer. The results showed that immunotherapy was not associated with overall QoL but was related to reduced appetite loss. Chemotherapy was associated with lower QoL, back pain, depression, thyroid diseases, and diabetes, as well as decreased physical and role functioning, and increased pain and fatigue.
QUALITY OF LIFE RESEARCH
(2023)
Article
Mathematical & Computational Biology
Juan Segura-Buisan, Clemence Leyrat, Manuel Gomes
Summary: This article assesses the relative advantages of multiple imputation (MI) and inverse probability weighting (IPW) to address missing data in both outcomes and confounders measured over time. Through a comprehensive simulation study, MI consistently provided low bias and more precise estimates compared to IPW across a wide range of scenarios.
STATISTICS IN MEDICINE
(2023)
Article
Cardiac & Cardiovascular Systems
Jeremy P. Brown, Kevin Wing, Clemence Leyrat, Stephen J. Evans, Kathryn E. Mansfield, Angel Y. S. Wong, Liam Smeeth, Nicholas W. Galwey, Ian J. Douglas
Summary: By using multiple study designs and databases, this study found that the association between fluoroquinolone use and aortic aneurysm or dissection may be influenced by confounding factors. After adjusting for these confounding factors, no association was found between fluoroquinolone use and aortic aneurysm or dissection. These results provide reassurance regarding the safety of fluoroquinolones in relation to aortic aneurysm or dissection.
Article
Psychology, Clinical
Agnes Caille, Aude Allemang-Trivalle, Myriam Blanchin, Anne Rebion, Anne Sauvaget, Benedicte Gohier, Philippe Birmes, Eric Bui, Eric Fakra, Marie-Odile Krebs, Cedric Lemogne, Nathalie Prieto, Isabelle Jalenques, Pierre Vidailhet, Bruno Aouizerate, Coraline Hingray, Wissam El-Hage
Summary: This study aims to assess the mental health status of healthcare workers during the COVID-19 pandemic and evaluate the effectiveness of "EMDR + usual care" for healthcare workers with significant psychological symptoms. Through a prospective cohort study and a randomized controlled trial, participants will receive 12 separate EMDR sessions. The primary outcomes are changes in depression, burnout, and PTSD scores.
EUROPEAN JOURNAL OF PSYCHOTRAUMATOLOGY
(2023)
Article
Cardiac & Cardiovascular Systems
Jeremy P. Brown, Kevin Wing, Clemence Leyrat, Stephen J. Evans, Kathryn E. Mansfield, Angel Y. S. Wong, Liam Smeeth, Nicholas W. Galwey, Ian J. Douglas
Summary: The association between fluoroquinolone use and aortic aneurysm or dissection may be affected by confounding factors. When confounding is taken into account, there is no significant association, providing reassurance about the safety of fluoroquinolones with respect to aortic aneurysm or dissection. Fluoroquinolone use does not increase the risk of developing aortic aneurysm or dissection.
