An AI assisted platform that will take your systematic review idea from protocol to publication. Visit us: coresr.ai
Toronto, Ontario
- Tweets 416
- Following 58
- Followers 10
- Likes 141
Risk-of-bias tools only help if judgments are inspectable. In CoreSR, GLASS grounds each appraisal in quoted study text — the human still decides. No black-box score. #SystematicReview #RiskOfBias #EvidenceSynthesis
1
4
coresr.ai — quote-grounded appraisals; human decides. Trial from $39 CAD/mo.
4
“Living” isn’t a methods free pass.
Syst Rev: 23 Cochrane + 23 non-Cochrane LSRs—43% of Cochrane met all 3 need criteria for living mode; 0% of non-Cochrane did. Guideline citations stayed scarce.
#LivingReview #SystematicReview #EvidenceSynthesis
1
5
coreSR now runs inside Claude and ChatGPT
I connected the coreSR MCP server and gave Claude one sentence: build a search on sildenafil for pulmonary arterial hypertension, run it, and screen it with TITAN at the strictest setting, randomized trials only.
Twelve minutes later, Claude had searched PubMed and Europe PMC, run TITAN across 1,022 unique records, and written a report that reads like a methods section. It also checked the screen against landmark trials. Two were missing. Claude traced the gap to the search strategy, ran a corrected supplement, and recovered both.
That division of labour is the point. Validated engines do the science. Claude does the legwork. You make the final calls.
The full demo runs under three minutes. Connect at coresr.ai/mcp.
#SystematicReview #EvidenceSynthesis #MetaAnalysis #ClaudeAI
2
2
47
CoreSR retweeted
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/
6
14
1,872
RoB without a quote trail is hard to audit later. GLASS surfaces the supporting text for each domain; a human still makes the call. Faster appraisal, same accountability. #RiskOfBias #SystematicReview #EvidenceSynthesis
1
18
coresr.ai — quote-grounded appraisals in the same project as screening and stats. 7-day trial.
2
In 17 trauma-mortality studies (n=243,324), ML beat logistic regression by ΔAUC 0.026—and the 95% prediction interval crossed zero (I²=97.9%). Best-of-tournament ML vs one LR is a biased estimand. Only 4/17 low PROBAST RoB.
#PredictionModels #Metaresearch #PROBAST
1
16
Most evidence stacks die at the handoff: screening in one tool, RoB in another, NMA in R, GRADE elsewhere. One workspace keeps the audit trail intact from question to published review.
#EvidenceSynthesis #SystematicReview #GRADE
1
16
Try it: coresr.ai — pairwise, frequentist/Bayesian NMA, CNMA, dose-response, plus native GRADE including NMA GRADE. 7-day trial.
7
A JCE scoping review found 90 beginner-facing NMA methods resources (2011–2025)—still no single path from nodes to certainty. First-timers stitch Cochrane, GRADE, and PRISMA-NMA alone. Consolidation would cut the black box.
#NetworkMetaAnalysis #SystematicReview
2
13