RESUMEN
Aims: A key treatment for patients with varying stages of heart failure with preserved ejection fraction (HFpEF) is exercise. Yet, despite a Class 1A recommendation, only one-third of patients exercise sufficiently. A huge treatment gap exists between guidelines and clinical practice. PRIORITY aims to establish the feasibility, clinical effectiveness and cost-effectiveness of a hybrid centre and home-based personalized exercise and physical activity intervention for patients along the HFpEF continuum. Methods: An assessor-blinded, multicenter randomized controlled trial will be conducted among 312 patients along the HFpEF continuum. Participants will be randomized (1:1) to the PRIORITY intervention or a comparator group receiving only a written exercise prescription. Participants in the PRIORITY group will receive 18 supervised centre-based exercise sessions during one year, supplemented with a remotely guided home-based physical activity program. Outcomes will be assessed at baseline, 4 months, one and two years. The primary outcome is the peak oxygen uptake (pVO2) at 1-year. Secondary outcomes include physical activity, other physical fitness parameters, cardiovascular health, echocardiographic parameters, health-related quality of life and costs at 1-year FU. Machine learning algorithms will analyse big data on physical activity collected during the 1-year intervention to develop models that can predict physical activity uptake and adherence as well as changes in fitness and health. A cost-utility analysis will be performed to evaluate the cost-effectiveness of the PRIORITY intervention compared to the control condition. Discussion: We anticipate that participants in the supervised home-based exercise intervention group will have a greater increase in pVO2 compared to those receiving a written exercise prescription. Trial registration number: This trial is registered at ClinicalTrials.gov (NCT04745013) and is currently in the recruitment stage.
RESUMEN
AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system's effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.