AIM in Eating Disorders

Kopyto D, Uhlenberg L, Zhang R, Stonawski V, Horndasch S, Amft O (2022)

Publication Type: Book chapter / Article in edited volumes

Publication year: 2022

Publisher: Springer International Publishing

Edited Volumes: Artificial Intelligence in Medicine

ISBN: 9783030645731

DOI: 10.1007/978-3-030-64573-1_213

Abstract

Over the past decades, the burden of eating disorders (ED) and comorbidities increased worldwide. Assisting diet monitoring with AI methods and Automated Dietary Monitoring (ADM) can support ED risk prediction, diagnosis, tracking associated symptoms, and medical guidance during a long-term behavior change process. This chapter gives an overview of important directions in AI in the field of EDs and obesity. State-of-the-art methods and technologies for ADM are summarized in connection to digital biomarkers that reflect diet-related behavior in general. Two sensorbased ADM examples are detailed: food type classification and eating timing estimation. On the example of anorexia nervosa (AN), dietrelated psychological parameters are detailed and AI-based approaches to support AN diagnosis and treatment are described.

Authors with CRIS profile

David Kopyto Lehrstuhl für Digital Health Lena Uhlenberg Lehrstuhl für Digital Health Rui Zhang Lehrstuhl für Digital Health Valeska Stonawski Department of Child and Adolescent Mental Health Stefanie Horndasch Department of Child and Adolescent Mental Health Oliver Amft Lehrstuhl für Digital Health

How to cite

APA:

Kopyto, D., Uhlenberg, L., Zhang, R., Stonawski, V., Horndasch, S., & Amft, O. (2022). AIM in Eating Disorders. In Niklas Lidströmer, Hutan Ashrafian (Eds.), Artificial Intelligence in Medicine. Springer International Publishing.

MLA:

Kopyto, David, et al. "AIM in Eating Disorders." Artificial Intelligence in Medicine. Ed. Niklas Lidströmer, Hutan Ashrafian, Springer International Publishing, 2022.

BibTeX: Download