Page 359 - Special Topic Session (STS) - Volume 4
P. 359

STS1080 Karina G. et al.




                           Diet4You: A personal intelligent assistant for
                                   diets integrating data science
               Karina Gibert 1,2,4 , Beatriz Sevilla-Villanueva 1,2,4 , Miquel Sànchez-Marrè 1,3,4
                1  Knowledge Engineering and Machine Learning Group at Intelligent Data Science and
                            Artificial Intelligence Research Center (KEMLG-at-IDEAI)
                               2  Statistics and Operations Research Department
                                     3  Computer Science department
                    4  Universitat Politècnica de Catalunya-BarcelonaTech, Barcelona (Catalonia)

            Abstract
            Prevention and nutrition are key issues to guarantee a healthy lifestyle and are
            in the kernel of the new paradigm of patient-centered medicine. More and
            more, making right diets is becoming essential from the health point of view.
            However, nutritionists design diets on the specific needs of each patient, using
            their  accumulated  experience  and  there  are  no  well-formalized  support
            mechanisms for such activity.
            The project Diet4You (financed by Spanish government) proposes the creation
            of  an  intelligent  decision  support  System  oriented  to  the  adaptive  and
            dynamic  preparation  of  personalized  diets  for  the  specific  individuals  in
            general population, having, or not, one or more diseases. The diets are built
            by taking into account all the information available on the person, including
            the characteristics of the person itself, their health conditions, their habits and
            eventual drugs intake and their genòmic information. Authors are not aware
            of  other  Systems  considering  all  these  factors  together  for  the  menus
            recommendations. The Diet4You tool is a hybrid system interacting several
            components in a complex way. The paper shows how a data science approach
            helps to establish a reference set of prototypical dietary paterns as a starting
            point to establish the behaviour of the complete Diet4you System. Also, a CBR
            component,  based  on  Knn  with  some  especial  distances  helps  to  provide
            adaptive behaviour to the System, which includes as well, some knowledge
            based modules.

            Keywords
            Personalized  Recommendation;  Nutritional  Plan  Prescription;  Case-based
            reasoning;  Knowledge  management;  Contextual  information;  Healthy
            lifestyles; Personalized Medicine; Data science.







                                                               348 | I S I   W S C   2 0 1 9
   354   355   356   357   358   359   360   361   362   363   364