Just published big news: ROBUST-RCT first instrument designed for RCTs to show, in the words of the authors: “a reliable and straightforward tool for assessing the risk of bias in systematic reviews”. Contrast with Cochrane Rob 2 which is not straightforward or reliable. sciencedirect.com/science/ar…

Demonstration of impact of research on policy. This review showed no clear benefits of activity-based funding that pays hospitals a fixed fee per patient and risks of increased post-acute care readmissions helped stop spread of ABF in Canada. pubmed.ncbi.nlm.nih.gov/2534…

Recent Guideline International meeting Prashanti Eachemapati remarkable presentation: guideline dissemination throughout development process; methods innovation (SPICE #GRADE causal chain biology; JUDGE implementing Core GRADE); startlingly original guideline education strategy. #GIN youtube.com/watch?v=PVXLkEI3…

Studies of minimally important differences (#MID) in patient reported outcomes can use receiver operating characteristic (#ROC) analysis. This study demonstrates that precision, validity optimal when using the entire cohort rather than just adjacent response categories pubmed.ncbi.nlm.nih.gov/1901…

With my heroes Inday and Tony Dans who have made enormous contributions to health care in the Philippines including key role in fourfold increase in tabaco taxes, proceeds to health care; at their home in Manilla with three children, spouses, grandkids. See what children are spelling?

#SystematicReview provides moderate certainty evidence of benefit of #midodrine in recurrent reflex #syncope but also demonstrates approaches to pooling results from studies using different instruments to measure same symptoms – a methods challenge that continues to evolve. pubmed.ncbi.nlm.nih.gov/2515…

Just published @JAMAInternalMed: Brilliant essay describes how clinician-facing #AI medical knowledge platforms risk severe quality degradation over time as private capital and corporate profit motives drive a process of platform decay and what we can do about it. pubmed.ncbi.nlm.nih.gov/4250…

#GRADE summary of findings tables require footnotes explaining reasons for rating down certainty of evidence for the outcomes included. There’s an art to doing it well: this paper tells you how pubmed.ncbi.nlm.nih.gov/2679…

Published in @JAMA_current , brilliant demonstration of selective reporting. #Cochrane #MetaAnalyses: for each outcome, on average less than half the eligible trials contributed to estimates. The fewer included, the larger the effect size! Studies with null effect weren’t reporting! pubmed.ncbi.nlm.nih.gov/1728…

This just published paper documents the excellent and, compared to alternatives, superior performance of the title and abstract screening tool of our CoreSR package. pubmed.ncbi.nlm.nih.gov/4276… coresr.ai/

Sample size estimation often a hoax, driven by feasibility and available funding. #SystematicReviews generate precise estimates of effect to guide clinical decisions. Grant submissions should justify #RCTs on contribution to international efforts to answer important questions. pubmed.ncbi.nlm.nih.gov/1817…

Just published study of #GRADE practice in #SystematicReviews. How often do reviews assess whether results show any effect (threshold the null) and how often whether they show important effect (threshold minimal important difference). Answer, about equal. Both useful approaches. pubmed.ncbi.nlm.nih.gov/4258…

In Canada in general, and in academic medicine in particular, we’ve come a long way to address gender bias against women. Nevertheless, this study demonstrates underfunding of women applicants to Canada’s most prestigious funding body. Stil a way to go. pubmed.ncbi.nlm.nih.gov/3161…

Just published brilliant, deeply insightful paper from ethicist and academic pediatrician specializing in adolescent medicine coauthors vividly demonstrates how #EBM has been unconscionably misused by #AntiTrans forces wishing to deny #GenderAffirming care. pubmed.ncbi.nlm.nih.gov/4254…

#MAGIC-led #BMJ Rapid Recommendations have provided a transformative model for living #guidelines, offering updated trustworthy recommendations for widely applicable indications based on new practice-changing evidence. pubmed.ncbi.nlm.nih.gov/2768…

Just published @JAMAPediatrics brilliant, deeply insightful paper from ethicist and academic pediatrician specializing in adolescent medicine. Authors vividly demonstrates how #EBM has been unconscionably misused by #antitrans forces wishing to deny #GenderAffirmingCare. pubmed.ncbi.nlm.nih.gov/4254…

Just published #BMJ Neurology fascinating international survey how clinicians manage severely demented patients with #pneumonia. No antibiotics: Norway 90%, Switzerland 65%, Canada 49%, India 24%, Saudi Arabia 14%. Enormous variability between, within countries. pubmed.ncbi.nlm.nih.gov/4255…

Statistical heterogeneity in #MetaAnalysis refers to the variability in treatment effects across different studies often measured with I2. High statistical #heterogeneity occurs more frequently in continuous outcomes than in binary outcomes, requires different interpretation pubmed.ncbi.nlm.nih.gov/2638…

Intransitivity and incoherence are the two GRADE domains most NMA software ignores. Both demand structured judgment. Neither reduces to a p-value. CoreSR implements both, and guards against the common error: a double downgrade for one problem. youtube.com/@CoreSR coresr.ai/

NMA has meant handing the analysis to whoever on the team writes R. Methodological review stays shallow. Few co-authors can check work they cannot reproduce. CoreSR puts frequentist and Bayesian engines behind an interface a methodologist can drive. Disclosure: co-founder, I hold equity. youtu.be/wBh_GNqxoLE?si=Bjks… coresr.ai/