Dataset Information

Personalized Recommendations for Physical Activity e-Coaching (OntoRecoModel): Ontological Modeling.

ABSTRACT:

Background

Automatic e-coaching may motivate individuals to lead a healthy lifestyle with early health risk prediction, personalized recommendation generation, and goal evaluation. Multiple studies have reported on uninterrupted and automatic monitoring of behavioral aspects (such as sedentary time, amount, and type of physical activity); however, e-coaching and personalized feedback techniques are still in a nascent stage. Current intelligent coaching strategies are mostly based on the handcrafted string messages that rarely individualize to each user's needs, context, and preferences. Therefore, more realistic, flexible, practical, sophisticated, and engaging strategies are needed to model personalized recommendations.

Objective

This study aims to design and develop an ontology to model personalized recommendation message intent, components (such as suggestion, feedback, argument, and follow-ups), and contents (such as spatial and temporal content and objects relevant to perform the recommended activities). A reasoning technique will help to discover implied knowledge from the proposed ontology. Furthermore, recommendation messages can be classified into different categories in the proposed ontology.

Methods

The ontology was created using Protégé (version 5.5.0) open-source software. We used the Java-based Jena Framework (version 3.16) to build a semantic web application as a proof of concept, which included Resource Description Framework application programming interface, World Wide Web Consortium Web Ontology Language application programming interface, native tuple database, and SPARQL Protocol and Resource Description Framework Query Language query engine. The HermiT (version 1.4.3.x) ontology reasoner available in Protégé 5.x implemented the logical and structural consistency of the proposed ontology. To verify the proposed ontology model, we simulated data for 8 test cases. The personalized recommendation messages were generated based on the processing of personal activity data in combination with contextual weather data and personal preference data. The developed ontology was processed using a query engine against a rule base to generate personalized recommendations.

Results

The proposed ontology was implemented in automatic activity coaching to generate and deliver meaningful, personalized lifestyle recommendations. The ontology can be visualized using OWLViz and OntoGraf. In addition, we developed an ontology verification module that behaves similar to a rule-based decision support system to analyze the generation and delivery of personalized recommendation messages following a logical structure.

Conclusions

This study led to the creation of a meaningful ontology to generate and model personalized recommendation messages for physical activity coaching.

SUBMITTER: Chatterjee A

PROVIDER: S-EPMC9282669 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundExisting evidence supports the many benefits of physical activity (PA) in breast cancer survival. However, few breast cancer survivors adhere to the recommended levels of activity. A PA coaching app that provides personalized feedback, guidance, and motivation to the user might have the potential to engage these individuals in a more active lifestyle, in line with the general recommendations. To develop a successful tool, it is important to involve the end users in the design process and to make theoretically grounded design decisions.ObjectiveThis study aimed to execute the design process and early prototype evaluation of a personalized PA coaching app for posttreatment breast cancer survivors. In particular, the study explored a design combining behavioral theory and tailored coaching strategies.MethodsThe design process was led by a multidisciplinary team, including technical and health professionals, and involved input from a total of 22 survivors. The process comprised 3 stages. In stage 1, the literature was reviewed and 14 patients were interviewed to understand the needs and considerations of the target population toward PA apps. In stage 2, the global use case for the tool was defined, the features were ideated and refined based on theory, and a digital interactive prototype was created. In stage 3, the prototype went through usability testing with 8 patients and was subjected to quality and behavior change potential evaluations by 2 human-computer interaction experts.ResultsThe design process has led to the conceptualization of a personalized coaching app for walking activities that addresses the needs of breast cancer survivors. The main features of the tool include a training plan and schedule, adaptive goal setting, real-time feedback and motivation during walking sessions, activity status through the day, activity history, weekly summary reports, and activity challenges. The system was designed to measure users' cadence during walking, use this measure to infer their training zone, and provide real-time coaching to control the intensity of the walking sessions. The outcomes from user testing and expert evaluation of the digital prototype were very positive, with scores from the system usability scale, mobile app rating scale, and app behavior change scale of 95 out of 100, 4.6 out of 5, and 15 out of 21, respectively.ConclusionsImplementing a user-centered design approach for the development and early evaluation of an app brings essential considerations to tailor the solution to the user's needs and context. In addition, informing the design on behavioral and tailored coaching theories supports the conceptualization of the PA coaching system. This is critical for optimizing the usability, acceptability, and long-term effectiveness of the tool. After successful early in-laboratory testing, the app will be developed and evaluated in a pilot study in a real-world setting.

Project description:BackgroundExisting physical activity guidelines predominantly focus on healthy age-stratified target groups. The objective of this study was to develop evidence-based recommendations for physical activity (PA) and PA promotion for German adults (18-65?years) with noncommunicable diseases (NCDs).MethodsThe PA recommendations were developed based on existing PA recommendations. In phase 1, systematic literature searches were conducted for current PA recommendations for seven chronic conditions (osteoarthrosis of the hip and knee, chronic obstructive pulmonary disease, stable ischemic heart disease, stroke, clinical depression, and chronic non-specific back pain). In phase 2, the PA recommendations were evaluated on the basis of 28 quality criteria, and high-quality recommendations were analysed. In phase 3, PA recommendations for seven chronic conditions were deducted and then synthesised to generate generic German PA recommendations for adults with NCDs. In relation to the recommendations for PA promotion, a systematic literature review was conducted on papers that reviewed the efficacy/effectiveness of interventions for PA promotion in adults with NCDs.ResultsThe German recommendations for physical activity state that adults with NCDs should, over the course of a week, do at least 150?min of moderate-intensity aerobic PA, or 75?min of vigorous-intensity aerobic PA, or a combination of both. Furthermore, muscle-strengthening activities should be performed at least twice a week. The promotion of PA among adults with NCDs should be theory-based, specifically target PA behaviour, and be tailored to the respective target group. In this context, and as an intervention method, exercise referral schemes are one of the more promising methods of promoting PA in adults with NCDs.ConclusionThe development of evidence-based recommendations for PA and PA promotion is an important step in terms of the initiation and implementation of actions for PA-related health promotion in Germany. The German recommendations for PA and PA promotion inform adults affected by NCDs and health professionals on how much PA would be optimal for adults with NCDs. Additionally, the recommendations provide professionals entrusted in PA promotion the best strategies and interventions to raise low PA levels in adults with NCDs. The formulation of specific PA recommendations for adults with NCDs and their combination with recommendations on PA promotion is a unique characteristic of the German recommendations.

Project description:BackgroundAdequate intake of macro- and micronutrients and adoption of an active lifestyle during pregnancy are essential for optimum maternal and fetal health and offspring development. Dietary counseling and advice regarding adequate physical activity are integral components of antenatal care. Personalized coaching through the use of mobile health (mHealth) that supports behavior modification is an innovative approach that needs exploration.ObjectiveOur primary aim is to assess the efficacy of an mHealth program in improving diet, supplement use, and physical activity during pregnancy. Secondary objectives include evaluation of the program's effect on maternal and offspring health outcomes and assessment of its compliance and usability.MethodsA randomized controlled trial was initiated at the Aga Khan University Hospital in Karachi, Pakistan, in January 2020. We aim to recruit 300 pregnant women in their first trimester who have smartphones, do not have comorbidities, and are not taking medications. The intervention group will be trained to use an mHealth app called PurUmeed Aaghaz. Through this app, the subjects will report information about their diet, supplement use, and physical activity and will receive personalized advice and three push messages as weekly reminders. The research assistant will obtain similar information from the control group via a paperless questionnaire; this group will receive standard face-to-face counseling regarding diet, supplement use, and physical activity. Data will be collected at enrollment and during four follow-up sessions scheduled 6 weeks apart. Primary study outcomes include improvements in diet (ie, change in mean dietary risk score from baseline to each follow-up), supplement use (ie, changes in mean supplement use score and biochemical levels of folic acid, iron, calcium, and vitamin D on a study subset), and mean duration of reported physical activity (minutes). Secondary study outcomes relate to maternal health (ie, gestational diabetes mellitus, gestational hypertension, pre-eclampsia, and gestational weight gain), newborn health (ie, birth weight and length and gestational age at delivery), and infant health (ie, BMI and blood pressure at 1 year of age). Compliance will be determined by the proportion of participants who complete the 6-month coaching program. Usability will be assessed based on features related to design, interface, content, coaching, perception, and personal benefit.ResultsThe study was approved by the Ethics Review Committee of the Aga Khan University in 2017. The recruitment of study participants was completed in September 2021. All follow-ups and outcome assessments are expected to be completed by March 2023 and analysis is expected to be completed by June 2023. We expect the results to be published by the end of 2023.ConclusionsThis study will be an important step toward evaluating the role of mHealth in improving behaviors related to a healthy diet, supplement use, and promotion of physical activity during pregnancy, as well as in influencing maternal and offspring outcomes. If proven effective, mHealth interventions can be scaled up and included in antenatal care packages at tertiary care hospitals of low- and middle-income countries.Trial registrationClinicalTrials.gov NCT04216446; https://clinicaltrials.gov/ct2/show/NCT04216446.International registered report identifier (irrid)DERR1-10.2196/31611.

Project description:BackgroundFitness devices have spurred the development of apps that aim to motivate users, through interventions, to increase their physical activity (PA). Personalization in the interventions is essential as the target users are diverse with respect to their activity levels, requirements, preferences, and behavior.ObjectiveThis review aimed to (1) identify different kinds of personalization in interventions for promoting PA among any type of user group, (2) identify user models used for providing personalization, and (3) identify gaps in the current literature and suggest future research directions.MethodsA scoping review was undertaken by searching the databases PsycINFO, PubMed, Scopus, and Web of Science. The main inclusion criteria were (1) studies that aimed to promote PA; (2) studies that had personalization, with the intention of promoting PA through technology-based interventions; and (3) studies that described user models for personalization.ResultsThe literature search resulted in 49 eligible studies. Of these, 67% (33/49) studies focused solely on increasing PA, whereas the remaining studies had other objectives, such as maintaining healthy lifestyle (8 studies), weight loss management (6 studies), and rehabilitation (2 studies). The reviewed studies provide personalization in 6 categories: goal recommendation, activity recommendation, fitness partner recommendation, educational content, motivational content, and intervention timing. With respect to the mode of generation, interventions were found to be semiautomated or automatic. Of these, the automatic interventions were either knowledge-based or data-driven or both. User models in the studies were constructed with parameters from 5 categories: PA profile, demographics, medical data, behavior change technique (BCT) parameters, and contextual information. Only 27 of the eligible studies evaluated the interventions for improvement in PA, and 16 of these concluded that the interventions to increase PA are more effective when they are personalized.ConclusionsThis review investigates personalization in the form of recommendations or feedback for increasing PA. On the basis of the review and gaps identified, research directions for improving the efficacy of personalized interventions are proposed. First, data-driven prediction techniques can facilitate effective personalization. Second, use of BCTs in automated interventions, and in combination with PA guidelines, are yet to be explored, and preliminary studies in this direction are promising. Third, systems with automated interventions also need to be suitably adapted to serve specific needs of patients with clinical conditions. Fourth, previous user models focus on single metric evaluations of PA instead of a potentially more effective, holistic, and multidimensional view. Fifth, with the widespread adoption of activity monitoring devices and mobile phones, personalized and dynamic user models can be created using available user data, including users' social profile. Finally, the long-term effects of such interventions as well as the technology medium used for the interventions need to be evaluated rigorously.