This is madness. 60% accuracy at best on your training dataset (2019 data)! So it will be in all likelihood worse on the 2020 data. How did anyone approve this to be used. And it's not like it's important to a whole heap of people's future. Awful. https://t.co/6dbvtg1qwR


from Twitter https://twitter.com/danbrewer

Comments

Popular posts from this blog

RT @CancerInNorwich: 📢 Join us on Monday at 1pm for the next talk in our virtual seminar series. We will be hearing from Dr Wafa Al-Jamal from @QUBelfast, who will be talking about "Smart Nanomedicimes for Pancreatic Cancer". All are welcome to join via the MS Teams link: https://t.co/4xCYpjGuBZ https://t.co/EGyD4NAgeP

RT @CancerInNorwich: We're at The Forum until 4pm! Come and learn about how we can test for prostate cancer, play our puzzle game and make tissue slides! #CancerInNorwich https://t.co/zEapurramu

An excellent opportunity to join the cancer genetics team as a diagnostic lab bioinformatician in Norwich. Lots of exciting projects to get involved in. Deadline: 30/05/2023. Happy to chat about this role. https://t.co/SltGsxYF6Y https://t.co/zh08bqZFDb