Gary Collins
@gscollins.bsky.social
Statistician • Professor • University of Birmingham • NIHR Senior Investigator • 🚴♂️
TRIPOD+AI: tinyurl.com/2dsb9e75
EQUATOR Network: tinyurl.com/5dw4rcy5
Google scholar: tinyurl.com/ysv3zwek
EQUATOR Network (https://www.equator-network.org)
TRIPOD+AI: tinyurl.com/2dsb9e75
EQUATOR Network: tinyurl.com/5dw4rcy5
Google scholar: tinyurl.com/ysv3zwek
EQUATOR Network (https://www.equator-network.org)
NEW PAPER: "Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when?"
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
November 7, 2025 at 12:44 PM
NEW PAPER: "Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when?"
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
NEW paper "Clinical prediction models using machine learning in oncology: challenges and recommendations"
--> tinyurl.com/2h2mcy5h
#machinelearning #prediction #statssky #MLsky #methodsmatter
--> tinyurl.com/2h2mcy5h
#machinelearning #prediction #statssky #MLsky #methodsmatter
October 30, 2025 at 8:38 AM
NEW paper "Clinical prediction models using machine learning in oncology: challenges and recommendations"
--> tinyurl.com/2h2mcy5h
#machinelearning #prediction #statssky #MLsky #methodsmatter
--> tinyurl.com/2h2mcy5h
#machinelearning #prediction #statssky #MLsky #methodsmatter
NEW PAPER "The STARD-AI reporting guideline for diagnostic accuracy studies using #artificialintelligence"
--> www.nature.com/articles/s41...
#machinelearning #MLsky #statssky #digitalhealth #transparency
--> www.nature.com/articles/s41...
#machinelearning #MLsky #statssky #digitalhealth #transparency
September 15, 2025 at 5:30 PM
NEW PAPER "The STARD-AI reporting guideline for diagnostic accuracy studies using #artificialintelligence"
--> www.nature.com/articles/s41...
#machinelearning #MLsky #statssky #digitalhealth #transparency
--> www.nature.com/articles/s41...
#machinelearning #MLsky #statssky #digitalhealth #transparency
NEW PAPER: the CHART reporting guideline for studies evaluating generative AI models like #ChatGPT & other #LLMs for providing health advice
--> bmjmedicine.bmj.com/content/4/1/...
The explanation & elaboration paper
--> www.bmj.com/content/390/...
#genAI #chatbots #healthadvice #reporting
--> bmjmedicine.bmj.com/content/4/1/...
The explanation & elaboration paper
--> www.bmj.com/content/390/...
#genAI #chatbots #healthadvice #reporting
August 3, 2025 at 2:36 PM
NEW PAPER: the CHART reporting guideline for studies evaluating generative AI models like #ChatGPT & other #LLMs for providing health advice
--> bmjmedicine.bmj.com/content/4/1/...
The explanation & elaboration paper
--> www.bmj.com/content/390/...
#genAI #chatbots #healthadvice #reporting
--> bmjmedicine.bmj.com/content/4/1/...
The explanation & elaboration paper
--> www.bmj.com/content/390/...
#genAI #chatbots #healthadvice #reporting
NEW PAPER in @bmj.com "Dealing with continuous variables and modelling non-linear associations in healthcare data: practical guide"
--> www.bmj.com/content/390/...
#methodologymatters #StatsSky #EpiSky
--> www.bmj.com/content/390/...
#methodologymatters #StatsSky #EpiSky
July 16, 2025 at 11:59 AM
NEW PAPER in @bmj.com "Dealing with continuous variables and modelling non-linear associations in healthcare data: practical guide"
--> www.bmj.com/content/390/...
#methodologymatters #StatsSky #EpiSky
--> www.bmj.com/content/390/...
#methodologymatters #StatsSky #EpiSky
NEW PAPER in @jclinepi.bsky.social looking at the content of open peer-review reports of RCTs in the field of oncology
www.jclinepi.com/article/S089...
Peer review reports [...] were short (median 276 words), superficial, and rarely constructive
#metascience #peerreview #RCTs
www.jclinepi.com/article/S089...
Peer review reports [...] were short (median 276 words), superficial, and rarely constructive
#metascience #peerreview #RCTs
July 1, 2025 at 8:52 AM
NEW PAPER in @jclinepi.bsky.social looking at the content of open peer-review reports of RCTs in the field of oncology
www.jclinepi.com/article/S089...
Peer review reports [...] were short (median 276 words), superficial, and rarely constructive
#metascience #peerreview #RCTs
www.jclinepi.com/article/S089...
Peer review reports [...] were short (median 276 words), superficial, and rarely constructive
#metascience #peerreview #RCTs
NEW PREPRINT "Critical Appraisal of Fairness Metrics in Clinical Predictive AI"
-> arxiv.org/abs/2506.17035
We identified 62 fairness metrics (and growing) - unsurprisingly it's all a bit of a mess...with most metrics not fit for purpose
#predictiveAI #fairness #machinelearning #StatsSky #MLSky
-> arxiv.org/abs/2506.17035
We identified 62 fairness metrics (and growing) - unsurprisingly it's all a bit of a mess...with most metrics not fit for purpose
#predictiveAI #fairness #machinelearning #StatsSky #MLSky
June 26, 2025 at 7:33 PM
NEW PREPRINT "Critical Appraisal of Fairness Metrics in Clinical Predictive AI"
-> arxiv.org/abs/2506.17035
We identified 62 fairness metrics (and growing) - unsurprisingly it's all a bit of a mess...with most metrics not fit for purpose
#predictiveAI #fairness #machinelearning #StatsSky #MLSky
-> arxiv.org/abs/2506.17035
We identified 62 fairness metrics (and growing) - unsurprisingly it's all a bit of a mess...with most metrics not fit for purpose
#predictiveAI #fairness #machinelearning #StatsSky #MLSky
NEW PAPER "Importance of sample size on the quality and utility of AI-based prediction models for healthcare"
www.thelancet.com/journals/lan...
We discuss seven reasons why inadequate sample size negatively affects model training, evaluation, and performance.
#StatsSky #machinelearning #AI
www.thelancet.com/journals/lan...
We discuss seven reasons why inadequate sample size negatively affects model training, evaluation, and performance.
#StatsSky #machinelearning #AI
June 2, 2025 at 4:29 PM
NEW PAPER "Importance of sample size on the quality and utility of AI-based prediction models for healthcare"
www.thelancet.com/journals/lan...
We discuss seven reasons why inadequate sample size negatively affects model training, evaluation, and performance.
#StatsSky #machinelearning #AI
www.thelancet.com/journals/lan...
We discuss seven reasons why inadequate sample size negatively affects model training, evaluation, and performance.
#StatsSky #machinelearning #AI
Anneke Damen talking about the updated PROBAST+AI tool for assessing risk of bias and quality of predictive AI tools #memtab
www.bmj.com/content/388/...
www.bmj.com/content/388/...
May 1, 2025 at 10:01 AM
Anneke Damen talking about the updated PROBAST+AI tool for assessing risk of bias and quality of predictive AI tools #memtab
www.bmj.com/content/388/...
www.bmj.com/content/388/...
great talk by @msafavi.bsky.social on ‘Value of information analysis: towards a value-based approach in biomarker and prediction model research’ #memtab
April 30, 2025 at 12:53 PM
great talk by @msafavi.bsky.social on ‘Value of information analysis: towards a value-based approach in biomarker and prediction model research’ #memtab
last talk before lunch - @glenmartin.bsky.social talking about how to handle missing data across model development, validation and implementation #memtab
April 30, 2025 at 11:08 AM
last talk before lunch - @glenmartin.bsky.social talking about how to handle missing data across model development, validation and implementation #memtab
sample size is a hot topic…Menelaos Pavlov talking about his work on adapting sample size calculations for the development of predictions models to control for model stability #memtab
April 30, 2025 at 10:54 AM
sample size is a hot topic…Menelaos Pavlov talking about his work on adapting sample size calculations for the development of predictions models to control for model stability #memtab
next up is @joieensor.bsky.social talking about his work on software implementation for sample size calculations for targeting precise risk predictions - code available to do this available here
github.com/JoieEnsor/pm...
#memtab
github.com/JoieEnsor/pm...
#memtab
April 30, 2025 at 10:31 AM
next up is @joieensor.bsky.social talking about his work on software implementation for sample size calculations for targeting precise risk predictions - code available to do this available here
github.com/JoieEnsor/pm...
#memtab
github.com/JoieEnsor/pm...
#memtab
recommendations on which prediction model performance measures to report and which not too by @benvancalster.bsky.social
more discussion here…
arxiv.org/abs/2412.10288
#memtab
more discussion here…
arxiv.org/abs/2412.10288
#memtab
April 30, 2025 at 10:21 AM
recommendations on which prediction model performance measures to report and which not too by @benvancalster.bsky.social
more discussion here…
arxiv.org/abs/2412.10288
#memtab
more discussion here…
arxiv.org/abs/2412.10288
#memtab
We have also published a new Explanation and Elaboration paper in @BMJ.com providing updated guidance and examples for reporting protocols of randomised trials.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
April 29, 2025 at 5:59 AM
We have also published a new Explanation and Elaboration paper in @BMJ.com providing updated guidance and examples for reporting protocols of randomised trials.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
Also published in
-> www.thelancet.com/journals/lan... (Lancet)
-> jamanetwork.com/journals/jam... (JAMA)
-> www.nature.com/articles/s41... (Nature Medicine)
-> journals.plos.org/plosmedicine... (PLoS Medicine)
-> www.thelancet.com/journals/lan... (Lancet)
-> jamanetwork.com/journals/jam... (JAMA)
-> www.nature.com/articles/s41... (Nature Medicine)
-> journals.plos.org/plosmedicine... (PLoS Medicine)
April 29, 2025 at 5:59 AM
Also published in
-> www.thelancet.com/journals/lan... (Lancet)
-> jamanetwork.com/journals/jam... (JAMA)
-> www.nature.com/articles/s41... (Nature Medicine)
-> journals.plos.org/plosmedicine... (PLoS Medicine)
-> www.thelancet.com/journals/lan... (Lancet)
-> jamanetwork.com/journals/jam... (JAMA)
-> www.nature.com/articles/s41... (Nature Medicine)
-> journals.plos.org/plosmedicine... (PLoS Medicine)
NEW PAPER: Updated SPIRIT-2025 for reporting protocols of randomised trials is now available in the @BMJ.com, @JAMA.com, @thelancet.bsky.social, @PLoS.org, and @natmedicine.bsky.social.
—> www.bmj.com/content/389/...
#openscience #transparency #medsky #statssky #episky
—> www.bmj.com/content/389/...
#openscience #transparency #medsky #statssky #episky
April 29, 2025 at 5:59 AM
NEW PAPER: Updated SPIRIT-2025 for reporting protocols of randomised trials is now available in the @BMJ.com, @JAMA.com, @thelancet.bsky.social, @PLoS.org, and @natmedicine.bsky.social.
—> www.bmj.com/content/389/...
#openscience #transparency #medsky #statssky #episky
—> www.bmj.com/content/389/...
#openscience #transparency #medsky #statssky #episky
Shouldn't need saying, but clearly it does "Reporting guideline checklists are not quality evaluation forms: they are guidance for writing"
--> onlinelibrary.wiley.com/doi/10.1002/...
...quality/risk of bias assessment is aided by transparent reporting though.
--> onlinelibrary.wiley.com/doi/10.1002/...
...quality/risk of bias assessment is aided by transparent reporting though.
April 24, 2025 at 7:29 AM
Shouldn't need saying, but clearly it does "Reporting guideline checklists are not quality evaluation forms: they are guidance for writing"
--> onlinelibrary.wiley.com/doi/10.1002/...
...quality/risk of bias assessment is aided by transparent reporting though.
--> onlinelibrary.wiley.com/doi/10.1002/...
...quality/risk of bias assessment is aided by transparent reporting though.
April 15, 2025 at 5:55 AM
See also this opinion piece by me published alongside CONSORT-2025 on the challenges of adhering to reporting guidelines, and making a plea for innovative solutions to improve the completeness of reporting in healthcare research.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
April 15, 2025 at 5:55 AM
See also this opinion piece by me published alongside CONSORT-2025 on the challenges of adhering to reporting guidelines, and making a plea for innovative solutions to improve the completeness of reporting in healthcare research.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
David Moher and Ken Schulz have also published this opinion piece on the evolution of CONSORT, and legacy of the late Doug Altman and his role in CONSORT.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
April 15, 2025 at 5:55 AM
David Moher and Ken Schulz have also published this opinion piece on the evolution of CONSORT, and legacy of the late Doug Altman and his role in CONSORT.
—> www.bmj.com/content/389/...
—> www.bmj.com/content/389/...
We have also published a new Explanation and Elaboration paper in @bmj.com providing updated guidance and examples for reporting randomised trials.
--> www.bmj.com/content/389/...
The CONSORT-SPIRIT website has also been updated —> www.consort-spirit.org
--> www.bmj.com/content/389/...
The CONSORT-SPIRIT website has also been updated —> www.consort-spirit.org
April 15, 2025 at 5:55 AM
We have also published a new Explanation and Elaboration paper in @bmj.com providing updated guidance and examples for reporting randomised trials.
--> www.bmj.com/content/389/...
The CONSORT-SPIRIT website has also been updated —> www.consort-spirit.org
--> www.bmj.com/content/389/...
The CONSORT-SPIRIT website has also been updated —> www.consort-spirit.org
—> tinyurl.com/28j8r366 (Lancet)
—> tinyurl.com/kkj9evzp (JAMA)
—> tinyurl.com/yck9jt88 (Nature Medicine)
—> tinyurl.com/48du7ccc (PLoS Medicine)
—> tinyurl.com/kkj9evzp (JAMA)
—> tinyurl.com/yck9jt88 (Nature Medicine)
—> tinyurl.com/48du7ccc (PLoS Medicine)
April 15, 2025 at 5:55 AM
—> tinyurl.com/28j8r366 (Lancet)
—> tinyurl.com/kkj9evzp (JAMA)
—> tinyurl.com/yck9jt88 (Nature Medicine)
—> tinyurl.com/48du7ccc (PLoS Medicine)
—> tinyurl.com/kkj9evzp (JAMA)
—> tinyurl.com/yck9jt88 (Nature Medicine)
—> tinyurl.com/48du7ccc (PLoS Medicine)