Episode 4: Can We Predict Who Gets Sick? The Hidden Catch in Medical Data| S1: Coding The Cure |
Det gick inte att lägga till artiklar
Titeln kunde inte läggas till i kundvagnen.
Titeln kunde inte läggas till i Önskelistan.
„Ta bort från Önskelista“ misslyckades.
„Följ podcast“ misslyckades
„Sluta följa podcast“ misslyckades
Episode 4: Can We Predict Who Gets Sick? The Hidden Catch in Medical Data| S1: Coding The Cure |
-
Berättare:
-
Av:
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.