Health Recommender Systems: Systematic Review

Abstract

Background Health recommender systems (HRSs) offer the potential to motivate and engage users to change their behavior by sharing better choices and actionable knowledge based on observed user behavior. Objective We aim to review HRSs targeting nonmedical professionals (laypersons) to better understand the current state of the art and identify both the main trends and the gaps with respect to current implementations. Methods We conducted a systematic literature review according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and synthesized the results. A total of 73 published studies that reported both an implementation and evaluation of an HRS targeted to laypersons were included and analyzed in this review. Results Recommended items were classified into four major categories: lifestyle, nutrition, general health care information, and specific health conditions. The majority of HRSs use hybrid recommendation algorithms. Evaluations of HRSs vary greatly; half of the studies only evaluated the algorithm with various metrics, whereas others performed full-scale randomized controlled trials or conducted in-the-wild studies to evaluate the impact of HRSs, thereby showing that the field is slowly maturing. On the basis of our review, we derived five reporting guidelines that can serve as a reference frame for future HRS studies. HRS studies should clarify who the target user is and to whom the recommendations apply, what is recommended and how the recommendations are presented to the user, where the data set can be found, what algorithms were used to calculate the recommendations, and what evaluation protocol was used. Conclusions There is significant opportunity for an HRS to inform and guide health actions. Through this review, we promote the discussion of ways to augment HRS research by recommending a reference frame with five design guidelines.

Applications of Machine Learning Models to Predict and Prevent Obesity: A Mini-Review

“…Deep learning approaches based on the embedding models are now popularly used in modern recommendation systems ( 15 ). The core utility of the food recommendation system is to provide recipe retrieval ( 16 ). PFoodReq is a novel question-answering food recommendation system based on a large-scale food knowledge base/graph ( 17 ).…”

The role of recommender systems in fostering consumers' long-term platform engagement

“…Health RS are used as complementary resources to increase usability of technologies and reduce information overload in healthcare service decision-making (Sezgin and € Ozkan, 2013) but can also help consumers find personalized medical interventions or support them with preventive healthcare measures (e.g. De Croon et al, 2021;Sch€ afer et al, 2017). RS can also improve decision making by providing relevant (personalized and localized) information about current affairs, including political, social and health information (e.g.…”

“…Health RS are used as complementary resources to increase usability of technologies and reduce information overload in healthcare service decision-making (Sezgin and Özkan, 2013) but can also help consumers find personalized medical interventions or support them with preventive healthcare measures (e.g. De Croon et al. , 2021; Schäfer et al.…”

PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets

“…Generally, recommender systems are the ones producing individualized recommendations or guiding users in a personalized way towards interesting or useful choices from a large pool of possible options [ 9 ]. The interested reader may find comparative evaluations and reviews of health recommendation systems and food recommendation systems in the works of De Croon et al, Theodoridis et al, and Trattner and Elsweiler [ 10 , 11 , 12 ]. Food recommender systems are often categorized based on the method used to recommend healthy diets, namely content-based (CB), collaborative filtering-based (CF) and hybrid approaches.…”