Episode 4: Can We Predict Who Gets Sick? The Hidden Catch in Medical Data| S1: Coding The Cure |
Nie udało się dodać produktów
Nie udało się dodać tytułu do koszyka.
Nie udało się dodać tytułu do schowka.
„Usuń ze schowka“ nie powiodło się.
„Obserwuj podcast“ nie powiodło się
„Przestań obserwować podcast“ nie powiodło się
Episode 4: Can We Predict Who Gets Sick? The Hidden Catch in Medical Data| S1: Coding The Cure |
-
Czyta:
-
Autor:
What if your medical history contains clues about your medical future?In this episode, we look at three ways scientists forecast who might get sick: from genes, from routine blood and urine measurements, and from medical history itself. One of them, an AI model called Delphi-2M, was trained on the health records of about 400,000 people and tested on about 1.9 million more in Denmark.Then we look at what the researchers found inside the model: some of the patterns it learned reflected how records are collected, not just biology. And we ask a second question hidden in the title: who is actually in the data?Three ideas to take away: a prediction is not a diagnosis, a pattern is not an explanation, and accuracy for a group is not proof of accuracy for every person.The Computational Cure, Season 1: Coding the Cure. Hosted by Diya Karthik.This podcast is for education and is not medical advice.