In This Episode
In this episode, the Sigma team discuss the claim that machine learning and data science may overtake traditional research methods in nutrition.
They discuss how machine learning could solve some current limitations of traditional methods, studies on its use so far, potential applications in future trials, and potential limitations or problems with the increased use of data science (including ethical and societal concerns).
They also ponder on how tech is currently being used (and abused) in relation to personalised nutrition, tech products, continuous glucose monitoring use, among other things.
Relevant Links
- Sak & Suchodolska, 2021 - Artificial Intelligence in Nutrients Science Research: A Review
- Kaput, 2020 - Lessons from application of data science strategies in nutritional research
- Zeevi et al., 2015 - Personalized Nutrition by Prediction of Glycemic Responses
- Leshem et al., 2020 - The Gut Microbiome and Individual-Specific Responses to Diet
- Celis-Morales, 2017 - Effect of personalized nutrition on health-related behaviour change: evidence from the Food4Me European randomized controlled trial
- Liu et al. - DeepFood: Deep Learning-based Food Image Recognition for Computer-aided Dietary Assessment
- Salim et al., 2021 - Study for Food Recognition System Using Deep Learning
- Ebers, 2021 - Regulating Explainable AI in the European Union. An Overview of the Current Legal Framework(s)
- Holland et al., 2018 - The Dataset Nutrition Label: A Framework To Drive Higher Data Quality Standards
Related Podcasts:
- #298: David Zeevi, PhD – Genes of Gut Microbes & Inter-Individual Variation in Glucose Response
- #361: Sarah Berry, PhD – The PREDICT Study, Postprandial Metabolism & Personalised Nutrition
- #386: Deirdre Tobias, ScD – Study Design, Diet Collection Methods and Nutrition Epidemiology
- #378: Nutritional Epidemiology
- #263: Brenda Davy, PhD – Dietary Assessment Methods in Nutrition Research
