My PhD research is in micro/ecotoxicology and I do modeling/data analysis for work and I can tell you with absolute certainty that there is not enough data to make AI for toxicity testing robust enough to replace animal models.
Reposted from
Bita Moghaddam
FDA plans to phase out animal testing requirement for drug testing and replace it with “AI-based computational models of toxicity” and organoid toxicity testing www.fda.gov/news-events/...
Comments
We have decades of raw data from pharmaceutical research to train the AI.
Is it our ability to model the physiology of the body or the raw data itself you find flawed?
Do you think the data is bad? Like smoking research was rigged? Or how oxy was rigged?