Some recent studies we've carried out looking at the medical literature that have applied #MachineLearning for prediction Conduct -> https://tinyurl.com/44444rx9 Reporting -> https://tinyurl.com/bdcs9rma Risk of bias -> https://tinyurl.com/ynbxh2pz #statstwitter #medtwitter #openscience https://t.co/XnYkAuIp5f
Great to see @US_FDA Guiding Principles for #AI #MachineLearning device development in medicine released. We wrote about many of these in @ScienceMagazine 2 yrs ago: https://www.science.org/doi/abs/10.1126/science.aaw0029. Reporting Human-AI partnerships is gr8 idea in particular. https://www.fda.gov/medical-devices/software-medical-device-samd/good-machine-learning-practice-medical-device-development-guiding-principles https://t.co/jcX6YQl157
Reporting quality of studies using #MachineLearning models for medical diagnosis by @epi_afro "All studies in this review failed to use reporting guidelines, and a large proportion of them lacked adequate detail..." https://tinyurl.com/s37a59w
Deep / machine learning is rapidly becoming the default approach applied in all areas of the medical imaging workflow, from image acquisition to analysis to reporting. #MachineLearning #ONTAPAI
Great paper published a few weeks ago showing progress on heart attack care; but also deficiencies in our data systems…it is only reporting up to 2012! We need more timely data in medicine. https://www.ahajournals.org/doi/10.1161/JAHA.118.008096 #bigdata https://t.co/l1ygp9yl2a