@Carsonlam 1 year ago
https://pubmed.ncbi.nlm.nih.gov/35704370/ When you train your neural network on many related tasks (#EHR time-series prediction tasks) simultaneously, it trains faster and improves the AUROC #medicalinformatics #multitasklearning #deeplearning #machinelearning #healthcare #datascience
@moorejh 2 years ago
The labels attached to images used to train machine-vision systems are often wrong. That could mean bad decisions by self-driving cars and medical algorithms. https://www.wired.com/story/foundations-ai-riddled-errors/ #machinelearning #datascience #deeplearning
@FelipeKitamura 3 years ago
1/20ish Do you train #MachineLearning models on #medicalimaging #data? These are a few tips to help prepare your data. A #tweetorial for #radres, #rads and #DataScientists. Inspired by a recent paper in @radiology_rsna https://pubs.rsna.org/doi/pdf/10.1148/radiol.2020192224
@curtlanglotz 6 years ago
Such a pleasure to speak this morning to #RadISummit18 on intersection of #AI, medical imaging, and performance improvement. Bottom line: Data generated by performance improvement projects can train #machinelearning systems to support high-reliability processes. https://twitter.com/AKrishnarajMD/status/962366493764632576