DIETOS: A dietary recommender system for chronic diseases monitoring and management. (January 2018)

• Record Type: Journal Article
• Authors: Agapito, Giuseppe; Simeoni, Mariadelina; Calabrese, Barbara; Caré, Ilaria; Lamprinoudi, Theodora; Guzzi, Pietro H.; Pujia, Arturo; Fuiano, Giorgio; Cannataro, Mario
• Is Part Of: Computer methods and programs in biomedicine. Volume 153(2018)
• Page Start: 93
• Page End: 104
• Publication Date: 2018-01
• Subjects: Food recommender system -- Health profile -- Foods database -- Chronic diseases -- Chronic kidney diseases; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.10.014
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: A new methodology to create the user's health profile has been defined through dynamic adaptive questionnaires. Adaptive questionnaires have been prepared and validated by medical doctors. The resulting health profile extends the typical user profile of adaptive web system, including health information. A database of typical Calabrian foods annotated by nutritional facts and indication with respect to main diseases. A recommendation methodology suggests foods to the user according to his/her health conditions and eventual chronic diseases. Abstract: Background and objective: Use of mobile and web-based applications for diet and weight management is currently increasing. However, the impact of known apps on clinical outcomes is not well-characterized so far. Moreover, availability of food recommender systems providing high quality nutritional advices to both healthy and diet-related chronic diseases users is very limited. In addition, the potentiality of nutraceutical properties of typical regional foods for improving app utility has not been exerted to this end. We present DIETOS, a recommender system for the adaptive delivery of nutrition contents to improve the quality of life of both healthy subjects and patients with diet-related chronic diseases. DIETOS provides highly specialized nutritional advices in different health conditions. Methods: DIETOS was projected to provide users with health profile and individual nutritional recommendation. Health profiling was based on user answers to dynamic real-time medical questionnaires. Furthermore, DIETOS contains catalogs of typical foods from Calabria, a southern Italian region. Several Calabrian foods have been inserted because of their nutraceutical properties widely reported in several quality studies. DIETOS includes some well known methods for user profiling (overlay profiling) and content adaptation (content selection) coming from general purpose adaptive web systems. Results: DIETOS has been validated for usability for both patients and specialists and for assessing the correctness of the profiling and recommendation, by enrolling 20 chronic kidney disease (CKD) patients at the Department of Nephrology and Dialysis, University Hospital, Catanzaro (Italy) and 20 age-matched healthy controls. Recruited subjects were invited to register to DIETOS and answer to medical questions to determine their health status. Based on our results, DIETOS has high specificity and sensitivity, allowing to determine a medical-controlled user's health profile and to perform a fine-grained recommendation that is better adapted to each user health status. The current version of DIETOS, available online athttp://www.easyanalysis.it/dietos is not intended to be used by general users, but only for review purpose. Conclusions: DIETOS is a novel food recommender system for healthy people and individuals affected by diet-related chronic diseases. The proposed system builds a users health profile and, accordingly, provides individualized nutritional recommendations, also with attention to food geographical origin.