Evaluation of a Novel Artificial Intelligence System to Monitor and Assess Energy and Macronutrient Intake in Hospitalised Older Patients

Nutrients. 2021 Dec 17; 13(12):4539. doi: 10.3390/nu13124539.
Papathanail, I., Brühlmann, J., Vasiloglou, M. F., Stathopoulou, T., Exadaktylos, A. K., Stanga, Z., Münzer, T., & Mougiakakou, S.


Malnutrition is common, especially among older, hospitalised patients, and is associated with higher mortality, longer hospitalisation stays, infections, and loss of muscle mass. It is therefore of utmost importance to employ a proper method for dietary assessment that can be used for the identification and management of malnourished hospitalised patients. In this study, we propose an automated Artificial Intelligence (AI)-based system that receives input images of the meals before and after their consumption and is able to estimate the patient's energy, carbohydrate, protein, fat, and fatty acids intake. The system jointly segments the images into the different food components and plate types, estimates the volume of each component before and after consumption, and calculates the energy and macronutrient intake for every meal, based on the kitchen's menu database. Data acquired from an acute geriatric hospital as well as from our previous study were used for the fine-tuning and evaluation of the system. The results from both our system and the hospital's standard procedure were compared to the estimations of experts. Agreement was better with the system, suggesting that it has the potential to replace standard clinical procedures with a positive impact on time spent directly with the patients.

Information NutriBib

Reference work for leading, current and selected literature in the field of clinical nutrition

Publications on clinical nutrition have grown steadily in recent years and the scientific evidence has been improved by numerous observational as well as intervention studies. Various umbrella organisations, such as the Swiss Society for Clinical Nutrition (GESKES), the German Society for Nutritional Medicine (DGEM) or the European Society for Clinical Nutrition and Metabolism (ESPEN) publish guidelines on nutrition in various clinical situations at regular intervals. Thus, a large amount of literature is available for evidence-based nutritional medicine.

The NutriBib aims to filter out authoritative publications in the various fields of nutritional medicine and thus to provide an overview of the abundance of literature. A large number of experienced nutrition experts contributed to the selection of relevant sources and allow a broadly based selection. Nevertheless, the literature selection cannot be considered exhaustive. Specific literature can be found by entering search words (using the magnifying glass at the top right) or by searching the table of contents.

Is important literature still missing? We would be very pleased to hear from you:

List of abbreviations

DGEM German Society for Nutritional Medicine (German Deutsche Gesellschaft für Ernährungsmedizin)
GESKES  Swiss Society for Clinical Nutrition (German Gesellschaft für klinische Ernährung der Schweiz) 
ESPEN European Society of Clinicl Nutrition and Metabolism