@theregister.com 12 months ago
ChatGPT can't pass these medical exams – yet
@Rejuve_AI 1 year ago
(5/6): The GCN is great at modeling biological signal coordination, explaining "omics" data, and differentiating user-contributed models into useful biological systems. #datascience #medicalresearch
@nelsonSpinto 2 years ago
My surprised face reading this article: Great work by @kdpsinghlab et al. Lesson learned: #DataScience models in medicine are going nowhere without thorough evaluation and post-implementation monitoring. https://twitter.com/jamainternalmed/status/1407005406514319361
@FJCarmonas 3 years ago
Great discussion at the #sail20 Symposium with @zakkohane @MarzyehGhassemi & colleagues on the obstacles that #ArtificialIntelligence models face as these approach deployment in #healthcare, how these are being tackled, and what the future holds! #medicine #MachineLearning https://t.co/evn5jDbrVh
@ewenharrison 4 years ago
Black box models are not acceptable for high stakes decisions in medicine. Models must be interpretable, not just explainable (explanations are wrong by definition). Here’s your great long-read for today by @CynthiaRudin https://arxiv.org/abs/1811.10154 #rstats #DataScience