Editorial Material
Oncology
Mary E. Putt
Summary: The statistical significance of a risk factor is influenced by sample size and the distributions of outcome and predictor variables. Paying closer attention to confidence intervals and visual displays can lead to a more comprehensive understanding of data analysis results.
Article
Gastroenterology & Hepatology
David W. Nelms, H. David Vargas, Ryan S. Bedi, Jennifer L. Paruch
Summary: This study reviewed the fragility indices of randomized controlled trials in colorectal surgery and found that most trials have a low fragility index. In 57% of trials, the number of patients lost to follow-up exceeded the threshold required to change the significance of the trial. This highlights the importance of assessing the robustness of clinical trials and not solely relying on p values when considering their clinical application.
DISEASES OF THE COLON & RECTUM
(2022)
Review
Orthopedics
Michael Constant, David P. Trofa, Bryan M. Saltzman, Christopher S. Ahmad, Xinning Li, Robert L. Parisien
Summary: The fragility analysis of patellofemoral instability (PFI) literature revealed a lack of robustness in the reported results, with only a few outcome events required to reverse statistical significance. It is recommended to triple report the P value, FI, and FQ in future comparative trials in the PFI literature to aid in the interpretation of statistical integrity.
AMERICAN JOURNAL OF SPORTS MEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Gary F. Templeton, Martin Kang, Nargess Tahmasbi
Summary: This study introduces a single imputation method to address missing input values in data, improving statistical power and emulation compared to other popular multiple imputation methods. It also presents new imputation performance metrics and visualizations, as well as specified imputation models for commonly used inputs to firm performance calculations.
DECISION SUPPORT SYSTEMS
(2021)
Review
Critical Care Medicine
Michael Megafu, Emmanuel Megafu
Summary: The study aimed to evaluate the reliability of randomized controlled trials (RCTs) on distal radius fractures and concluded that orthopedic literature should report the fragility index (FI) and fragility quotient (FQ) in addition to P values to aid the reader in interpreting the results reliably.
INJURY-INTERNATIONAL JOURNAL OF THE CARE OF THE INJURED
(2022)
Article
Multidisciplinary Sciences
Benjamin R. Baer, Mario Gaudino, Mary Charlson, Stephen E. Fremes, Martin T. Wells
Summary: This article proposes a generalization of the fragility index to a family of fragility indices called the incidence fragility indices, which allow for outcome modifications that are sufficiently likely. An exact algorithm for calculating the incidence fragility indices is provided. This far-reaching generalization also explains how to permit sufficiently likely modifications for nondichotomous outcomes, while following the concept of the fragility index.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Review
Orthopedics
Robert L. Parisien, Michael Constant, Bryan M. Saltzman, Charles A. Popkin, Christopher S. Ahmad, Xinning Li, David P. Trofa
Summary: The study analyzed 19 RCTs from 11 orthopedic journals and found that the literature evaluating articular cartilage defects of the knee is fragile, with relatively few outcome events potentially altering the significance of statistical findings. The recommendation is to conduct comprehensive fragility analysis and report the P value, FI, and FQ to aid in the interpretation and contextualization of clinical findings in cartilage restoration literature.
Article
Chemistry, Analytical
Jeremy D. Inglis, Kyle M. Samperton, Andrew A. Reinhard, Travis Tenner, Robert E. Steiner, Stephen P. Lamont
Summary: Particulate isotopic analysis in nuclear forensics has seen rapid development in the past two decades, thanks to advancements in determining the isotopic composition of individual particles. This paper introduces basic statistical concepts to help analysts understand the importance of statistical adequacy when interpreting particle data. While these methods are useful for analyzing particle data, more sophisticated statistical and modeling approaches will be needed in the future to extract maximal information from such datasets.
JOURNAL OF RADIOANALYTICAL AND NUCLEAR CHEMISTRY
(2023)
Review
Critical Care Medicine
Hassan Mian, Michael Megafu, Emmanuel Megafu, Sulabh Singhal, Nicholas. G. Richardson, Paul Tornetta III, Robert. L. Parisien
Summary: The purpose of this study was to evaluate the statistical fragility in the distal fibular fracture literature using the fragility index (FI) and fragility quotient (FQ). Six randomized controlled trials were analyzed and it was found that the overall FI and FQ were 5 and 0.089, respectively. The study suggests that relying solely on a P value threshold for statistical analysis in the literature may be misleading, and standardized reporting of P value, FI, and FQ can help draw reliable conclusions based on outcome fragility.
INJURY-INTERNATIONAL JOURNAL OF THE CARE OF THE INJURED
(2023)
Article
Clinical Neurology
Najib E. El Tecle, Jorge F. Urquiaga, Samuel T. Griffin, Georgios Alexopoulos, Tarek Y. El Ahmadieh, Salah G. Aoun, Tobias A. Mattei
Summary: The study revealed that misinterpretations of null hypothesis significance testing results near the P-value threshold are present in at least 1% of neurosurgical literature. While most statistical errors may be unintentional, additional measures should be implemented to prevent the future adoption of such undesirable methodological practices among researchers.
WORLD NEUROSURGERY
(2022)
Review
Orthopedics
Cooper B. Ehlers, Andrew J. Curley, Nathan P. Fackler, Arjun Minhas, Edward S. Chang
Summary: This study examined the statistical stability of studies comparing hamstring tendon and bone-patellar tendon-bone autografts in primary single-bundle anterior cruciate ligament reconstruction. It found that these studies are vulnerable to a small number of outcome event reversals, often fewer than the number of patients lost to follow-up.
AMERICAN JOURNAL OF SPORTS MEDICINE
(2021)
Review
Orthopedics
Cooper B. Ehlers, Andrew J. Curley, Nathan P. Fackler, Arjun Minhas, Edward S. Chang
Summary: The study examined the statistical stability of studies comparing hamstring tendon and bonepatellar tendon-bone autografts in primary single-bundle anterior cruciate ligament reconstruction. The findings suggest that these studies are vulnerable to a small number of outcome event reversals, often fewer than the number of patients lost to follow-up. More caution and consideration may be needed in interpreting the statistical significance of similar comparative studies and RCTs.
AMERICAN JOURNAL OF SPORTS MEDICINE
(2021)
Article
Clinical Neurology
Iris S. C. Verploegh, Nicole A. Lazar, Ronald H. M. A. Bartels, Victor Volovici
Summary: The application and interpretation of P values have been a topic of debate for several decades and have gained increasing importance in recent years. While P values can indicate the presence of an effect, they are often misused to exaggerate the significance of findings, without considering the effect size and clinical relevance.
WORLD NEUROSURGERY
(2022)
Article
Critical Care Medicine
Jian Zhang, Haotian Wei, Xiaohu Chang, Jiahui Liang, Zhiyuan Lou, Xin Tang
Summary: This study assessed the statistical robustness of randomized controlled trials (RCTs) for femoral neck fractures using the fragility index (FI) and found that they were not as statistically robust as previously thought.
INJURY-INTERNATIONAL JOURNAL OF THE CARE OF THE INJURED
(2023)
Article
Business, Finance
Michael Michaelides
Summary: The majority of empirical studies in finance use large sample sizes and conventional thresholds for statistical significance, potentially leading to spurious results. This paper introduces a rule of thumb for determining appropriate thresholds for statistical significance and suggests that the list of statistically significant findings in finance literature may shrink significantly after accounting for large sample size bias.
FINANCE RESEARCH LETTERS
(2021)
Article
Cardiac & Cardiovascular Systems
N. Bryce Robinson, Hillary Lia, Mohamed Rahouma, Katia Audisio, Giovanni Soletti, Michelle Demetres, Jeremy R. Leonard, Stephen E. Fremes, Leonard N. Girardi, Mario Gaudino
Summary: The study aimed to investigate the impact of multiple arterial grafting on long-term all-cause mortality in women undergoing isolated coronary artery bypass grafting. The findings showed that women who received multiple arterial grafting had lower long-term mortality and spontaneous myocardial infarction compared to those who received single arterial grafting.
JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Derrick Y. Tam, Marc Ruel, Stephen E. Fremes
JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Dominique Vervoort, Derrick Y. Tam, Stephen E. Fremes
CANADIAN JOURNAL OF CARDIOLOGY
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Kevin R. An, Veronica F. Chan, Stephen E. Fremes
ANNALS OF THORACIC SURGERY
(2023)
Review
Cardiac & Cardiovascular Systems
Grace Lee, Joanna Chikwe, Milan Milojevic, Harindra C. Wijeysundera, Giuseppe Biondi-Zoccai, Marcus Flather, Mario F. L. Gaudino, Stephen E. Fremes, Derrick Y. Tam
Summary: This review compares the latest European and American guidelines on the management of aortic stenosis (AS) and identifies three areas of divergence: timing of intervention, valve selection, and surgical vs. transcatheter aortic valve replacement criteria. Gaps in the literature for specific aspects of AS treatment are also highlighted.
EUROPEAN HEART JOURNAL
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Mario Gaudino, John Alexander, Umberto Benedetto, Andreas Boening, Arnaldo Dimagli, Stephen Fremes, Joanna Chikwe, Leonard Girardi, David Hare, Paul Kurlansky, Andre Lamy, Katia Audisio, Antonino Di Franco, P. J. Devereaux, Anno Diegeler, Marcus Flather, Jennifer S. Lawton, Derrick Y. Tam, Wilko Reents, Mohamed Rahouma
EUROPEAN JOURNAL OF CARDIO-THORACIC SURGERY
(2023)
Article
Engineering, Biomedical
Nhien Tran-Nguyen, Andrew T. T. Yan, Stephen Fremes, Piero Triverio, Laura Jimenez-Juan
Summary: Coronary artery bypass graft surgery, a common treatment for coronary artery disease, can suffer from graft failure, and the underlying mechanisms are not fully understood. In this study, computational fluid dynamics simulations were used to investigate the relationship between graft hemodynamics and surgical outcomes. Results showed that abnormal wall shear stress (WSS) area one month after surgery correlated with graft lumen remodeling one year after surgery, suggesting that shear-related mechanisms may play a role in post-operative graft remodeling and explain differences in failure rates between arterial and venous grafts.
ANNALS OF BIOMEDICAL ENGINEERING
(2023)
Editorial Material
Cardiac & Cardiovascular Systems
Mario Gaudino, Stephen E. Fremes, Roxana Mehran, C. Noel Bairey Merz
Review
Medicine, General & Internal
Dominique Vervoort, Malak Elbatarny, Rodolfo Rocha, Stephen E. E. Fremes
Summary: Ischemic heart disease leads to high morbidity and mortality worldwide, often requiring coronary revascularization. Coronary artery bypass grafting (CABG) is a common surgical procedure using different bypass conduits. Saphenous vein grafts and left internal thoracic artery are commonly used for CABG. Multiple arterial grafting (MAG) is believed to be superior, but its adoption is limited due to technical complexity and lack of conclusive evidence from randomized controlled trials.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Statistics & Probability
Dominique Fourdrinier, William E. Strawderman, Martin T. Wells
Summary: This paper investigates the construction of prior distributions that result in Bayes minimax estimators for a normal mean vector. The focus is on priors that are not scale mixtures of normal distributions.
JAPANESE JOURNAL OF STATISTICS AND DATA SCIENCE
(2023)
Article
Cardiac & Cardiovascular Systems
Mario Gaudino, Sigrid Sandner, Kevin R. An, Arnaldo Dimagli, Antonino Di Franco, Katia Audisio, Lamia Harik, Roberto Perezgrovas-Olaria, Giovanni Soletti, Stephen E. Fremes, David L. Hare, Alexander Kulik, Andre Lamy, Joyce Peper, Marc Ruel, Jurrien M. ten Berg, Laura M. Willemsen, Qiang Zhao, Daniel M. Wojdyla, Deepak L. Bhatt, John H. Alexander, Bjorn Redfors
Summary: Graft failure after CABG is common and strongly associated with adverse cardiac events. Age, female sex, and smoking are independent risk factors for graft failure, while statins have a protective effect. Graft failure is associated with an increased risk of myocardial infarction, repeat revascularization, and death.
Article
Cardiac & Cardiovascular Systems
Stephen Fremes, Guillaume Marquis-Gravel, Mario F. L. Gaudino, E. Marc Jolicoeur, Sylvain Bedard, Ruth Masterson Creber, Marc Ruel, Dominique C. Vervoort, Harindra E. Wijeysundera, Michael Farkouh, Jean-Lucien Rouleau
Summary: The STICH3C trial aims to compare the efficacy and safety of CABG and PCI in patients with iLVSD and multivessel disease. This trial will provide important evidence to guide clinical practice.
CIRCULATION-CARDIOVASCULAR INTERVENTIONS
(2023)
Review
Cardiac & Cardiovascular Systems
Robert A. Byrne, Stephen Fremes, Davide Capodanno, Martin Czerny, Torsten Doenst, Jonathan R. Emberson, Volkmar Falk, Mario Gaudino, John J. Mcmurray, Roxana Mehran, Milan Milojevic, Miguel Sousa Uva
Summary: In October 2021, the ESC and EACTS established a task force to review the 2018 guidelines on myocardial revascularization for patients with LM disease. The task force suggested updated recommendations for revascularization modality, stating that both CABG and PCI are clinically reasonable options for stable patients with LM disease. The task force also acknowledged knowledge gaps and emphasized the need for more data.
EUROPEAN HEART JOURNAL
(2023)
Article
Pharmacology & Pharmacy
Yi-Cheng Tai, Weijing Wang, Martin T. Wells
Summary: We introduce a new two-sample inference procedure that assesses the performance of two groups over time without assuming proportional hazards. Our method includes a diagnostic plot to identify changes in hazard timing and a formal inference procedure. The measures we develop provide clinically meaningful estimands to summarize the treatment effect over time. Our proposed statistic is a martingale U-statistic that allows for construction of confidence intervals and hypothesis testing. We demonstrate the robustness of our approach and its application in scenarios with missing tail information due to insufficient follow-up.
PHARMACEUTICAL STATISTICS
(2023)
Article
Cardiac & Cardiovascular Systems
Salil V. Deo, Andrew Althouse, Sadeer Al-Kindi, David A. Mcallister, Ariela Orkaby, Yakov E. Elgudin, Stephen Fremes, Danny Chu, Frank L. J. Visseren, Jill P. Pell, Naveed Sattar
Summary: The SMART2 risk score performs well in coronary artery bypass grafting patients, with better predictive capabilities in patients with chronic kidney disease. However, it underestimates the incidence of major adverse cardiovascular events and shows differences in predictive ability between White and Black patients.
JOURNAL OF THE AMERICAN HEART ASSOCIATION
(2023)