The most surprising bit of the interview was the discussion about prediction in the healthcare system, specifically regarding neurological disorders. It was interesting to hear about how data is collected and how people get participants for these data points. One important part was how participants don't have well-structured lives and how that impacts data/prediction models. In that particular study, researchers tried to help people be more self-aware. It was interesting to consider how researchers want to help participants to overcome their difficulties and help advance prediction models to help other people in the future. Lastly, I think the idea of hypothesis-free science is very important so that we can learn more and not have significant bias.
Further reading on Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: de Hond, A.A.H., Leeuwenberg, A.M., Hooft, L. et al. Guidelines and quality criteria for artificial intelligence-based prediction models in healthcare: a scoping review. npj Digit. Med. 5, 2 (2022). https://doi.org/10.1038/s41746-021-00549-7
Image courtesy of https://www.revealbi.io/blog/predictive-analytics-in-healthcare -->
