Reporting guidelines for clinical prediction (including for AI/ML) TRIPOD+AI (https://xitter.cf/t.co/Z1UKuwdaSS) TRIPOD-LLM (https://xitter.cf/t.co/09Pdjb0uS0)
Joined September 2013
- Tweets526
- Following21
- Followers1.4K
- Likes486
Pinned Tweet
A periodic reminder that if you are writing up your study developing/validating a #machinelearning clinical prediction model then make sure you are reporting all the necessary information by following the TRIPOD+AI standards ๐
tinyurl.com/4kv7pb3m
#transparency #AI
TRIPODStatement retweeted
We are setting out to develop some new recommendations (TRIPOD-CODE) to provide guidance on reporting the availability & structure of code for predictive AI healthcare tools
Watch this space & read the protocol here
link.springer.com/article/10โฆ
#transparency #code #reproducibility
We are setting out to develop some new recommendations (TRIPOD-CODE) to provide guidance on reporting the availability & structure of code for predictive AI healthcare tools
Watch this space & read the protocol here
link.springer.com/article/10โฆ
#transparency #code #reproducibility
In TRIPOD+AI (tinyurl.com/4s6pmz5d) we ask authors to report the performance of their #AI model. This new authoritative position paper provides clarity on what measures should be reported and why
--> tinyurl.com/bdehp3ht
#predictiveAI #machinelearning #digitalhealth
TRIPODStatement retweeted
Thank you @Anaes_Journal for the incredible opportunity to share our work! Grateful to the GRAITE-USRA steering group, all Delphi experts & endorsing societies for their invaluable contributions, insights & support. A true multidisciplinary effort to improve AI reporting in RA ๐๐ผ
Guidance for reporting AI technology evaluations for ultrasound scanning in regional anaesthesia
@xiaoxi_6 @Jennythatcanbl1 @davidwhewson @STHJournalClub @bowness_james
#anaesthesia #regionalanaesthesia #regionalanesthesia #AI #MedTwitter
doi.org/10.1111/anae.16733
TRIPODStatement retweeted
Attention #AI researchers, clinicians, patients, editors, publishers, & beyond๐
Just in ๐จ๏ธ - the #CHART reporting guideline โ
for studies evaluating #genAI models like #ChatGPT & other #LLMs for health advice
Statement:
๐bit.ly/CHARTbmjmed
๐bit.ly/CHARTbjs
๐bit.ly/CHARTbmc
๐bit.ly/CHARTjamao
๐bit.ly/CHARTannfam
๐bit.ly/CHARTartmed
E&E:
๐bit.ly/CHARTbmj
Published in @BMJMedicine @BJSurgery @JAMANetworkOpen @BMCMedicine @AnnFamMed & Art Med
@GuyattGH | @GSCollins | @Cacciamani_MD | @CLaineMD | @AFlanagin | @thirumasu | @AlfonsoIorio | @juliomayol | @nliulab | @riazagha | @DrXiaoLiu | @SunjayaMD | @drnipunverma | @YJeremyNg | @mike_mitt | @meerpohl | @Tfeend | @eloder | @HelenFrankish | @LoebStacy | @tylermckechnie | @YungLeeMDMPH
@EQUATORNetwork
TRIPODStatement retweeted
NEW PAPER in @bmj_latest "Dealing with continuous variables and modelling non-linear associations in healthcare data: practical guide"
--> bmj.com/content/390/bmj-2024โฆ
#methodologymatters
TRIPODStatement retweeted
๐ Advancing international partnership for governing generative #AI (#GenAI) models in #medicine and #healthcare. We introduce POLARIS-GM initiative: a scenario-based, consensus-driven framework for GenAI #governance and #regulation. @NatureMedicine
nature.com/articles/s41591-0โฆ
TRIPODStatement retweeted
NEW PREPRINT "Critical Appraisal of Fairness Metrics in Clinical Predictive AI"
-> arxiv.org/abs/2506.17035
We identified 62 fairness metrics (& growing) - unsurprisingly it's all a bit of a mess...with most metrics not fit for purpose
#predictiveAI #fairness #machinelearning
Item 10 of the TRIPOD+AI asks
(bmj.com/content/385/bmj-2023โฆ)
"Explain how the study size was arrived at, and justify that the study size was sufficient to answer the research question. Include details of any sample size calculation"
Here's why it's important ๐
**New Lancet DH paper
"Importance of sample size on the quality & utility of AI-based prediction models for healthcare"
- for broad audience
- why inadequate SS harms model training, evaluation & performance
- pushback to claims SS irrelevant to #AI
๐
tinyurl.com/yrje52fn
A guideline to boost transparency in AI-driven medical prediction models! Evolved from TRIPOD, it ensures studies are reproducible, ethical, and clinically meaningful. Crucial for trustworthy #AI in healthcare.
Read the paper: bmj.com/content/385/bmj-2023โฆ
#HealthTech
Who uses TRIPOD-AI?
๐ฉ๐ฌ Researchers designing models
๐จโ๏ธ Clinicians evaluating tools
๐ฉ๐ป Developers building algorithms
๐ Journals & peer reviewers
A shared framework for responsible innovation. ๐ค #DigitalHealth #HealthcareAI
Letโs raise the standard!
Adopting TRIPOD+AI means advancing equitable, accountable AI ready for clinics. Check guidelines: tripod-statement.org ๐
Together, we can ensure AI serves patients first. #OpenScience #AIforGood
TRIPODStatement retweeted
Reporting guidelines have become an essential instrument of scientific integrity. We need to make the leap from just producing reporting guidelines to helping researchers put them into practice, writes @GSCollins
bmj.com/content/389/bmj.r718โฆ
TRIPODStatement retweeted
A periodic reminder that if you are writing up your study developing/validating a #machinelearning clinical prediction model then make sure you are reporting all the necessary information by following the TRIPOD+AI standards ๐
tinyurl.com/4kv7pb3m
#transparency #AI
TRIPODStatement retweeted
Underpinning the FUTURE-AI recommendations ๐ is transparency
TRIPOD+AI recommendations are essential to ensure all key details are completely & transparently reported
bmj.com/content/385/bmj-2023โฆ
#predictiveAI #machinelearning #trustworthyAI #healthcareAI #digitalhealth
This paper describes the FUTURE-AI framework, which provides guidance for the development and deployment of trustworthy AI tools in healthcare, @KarimLekadir and colleagues
bmj.com/content/388/bmj-2024โฆ
Underpinning the FUTURE-AI recommendations ๐ is transparency
TRIPOD+AI recommendations are essential to ensure all key details are completely & transparently reported
bmj.com/content/385/bmj-2023โฆ
#predictiveAI #machinelearning #trustworthyAI #healthcareAI #digitalhealth
This paper describes the FUTURE-AI framework, which provides guidance for the development and deployment of trustworthy AI tools in healthcare, @KarimLekadir and colleagues
bmj.com/content/388/bmj-2024โฆ
TRIPODStatement retweeted
This paper describes the FUTURE-AI framework, which provides guidance for the development and deployment of trustworthy AI tools in healthcare, @KarimLekadir and colleagues
bmj.com/content/388/bmj-2024โฆ