Leading a sedentary lifestyle may cause numerous health problems. Therefore, passive lifestyle changes should be given priority to avoid severe long-term damage. Automatic health coaching system may ...help people manage a healthy lifestyle with continuous health state monitoring and personalized recommendation generation with machine learning (ML). This study proposes a semantic ontology model to annotate the ML-prediction outcomes and personal preferences to conceptualize personalized recommendation generation with a hybrid approach. We use a transfer learning approach to improve ML model training and its performance, and an incremental learning approach to handle daily growing data and fit them into the ML models. Furthermore, we propose a personalized activity recommendation algorithm for a healthy lifestyle by combining transfer learning, incremental learning, the proposed semantic ontology model, and personal preference data. For the overall experiment, we use public and private activity datasets collected from healthy adults (n = 33 for public datasets; n = 16 for private datasets). The standard ML algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity, medium physical activity, and vigorous physical activity serve as input for the classification models. We first use publicly available Fitbit datasets to build the initial classification models. Subsequently, we re-use the pre-trained ML classifiers on the real-time MOX2-5 dataset using transfer learning. We test several standard algorithms and select the best-performing model with optimized configuration for our use case by empirical testing. We find that DecisionTreeClassifier with a criterion "entropy" outperforms other ML classifiers with a mean accuracy score of 97.50% (F1 = 97.00, precision = 97.00, recall = 98.00, MCC = 96.78) and 96.10% (F1 = 96.00, precision = 96.00, recall = 96.00, MCC = 96.10) in Fitbit and MOX2-5 datasets, respectively. Using transfer learning, the DecisionTreeClassifier with a criterion "entropy" outperforms other classifiers with a mean accuracy score of 97.99% (F1 = 98.00, precision = 98.00, recall = 98.00, MCC = 96.79). Therefore, the transfer learning approach improves the machine learning model performance by ≈ 1.98% for defined datasets and settings on MOX2-5 datasets. The Hermit reasoner outperforms other reasoners with an average reasoning time of 1.1-2.1 s, under defined settings in our proposed ontology model. Our proposed algorithm for personalized recommendations conceptualizes a direction to combine the classification results and personal preferences in an ontology for activity eCoaching. The proposed method of combining machine learning technology with semantic rules is an invaluable asset in personalized recommendation generation. Moreover, the semantic rules in the knowledge base and SPARQL (SPARQL Protocol and RDF Query Language) query processing in the query engine helps to understand the logic behind the personalized recommendation generation.
Heterogeneity is a problem in storing and exchanging data in a digital health information system (HIS) following semantic and structural integrity. The existing literature shows different methods to ...overcome this problem. Fast healthcare interoperable resources (FHIR) as a structural standard may explain other information models, (e.g., personal, physiological, and behavioral data from heterogeneous sources, such as activity sensors, questionnaires, and interviews) with semantic vocabularies, (e.g., Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT)) to connect personal health data to an electronic health record (EHR). We design and develop an intuitive health coaching (eCoach) smartphone application to prove the concept. We combine HL7 FHIR and SNOMED-CT vocabularies to exchange personal health data in JavaScript object notion (JSON). This study explores and analyzes our attempt to design and implement a structurally and logically compatible tethered personal health record (PHR) that allows bidirectional communication with an EHR. Our eCoach prototype implements most PHR-S FM functions as an interoperability quality standard. Its end-to-end (E2E) data are protected with a TSD (Services for Sensitive Data) security mechanism. We achieve 0% data loss and 0% unreliable performances during data transfer between PHR and EHR. Furthermore, this experimental study shows the effectiveness of FHIR modular resources toward flexible management of data components in the PHR (eCoach) prototype.
Automated coaches (eCoach) can help people lead a healthy lifestyle (e.g., reduction of sedentary bouts) with continuous health status monitoring and personalized recommendation generation with ...artificial intelligence (AI). Semantic ontology can play a crucial role in knowledge representation, data integration, and information retrieval.
This study proposes a semantic ontology model to annotate the AI predictions, forecasting outcomes, and personal preferences to conceptualize a personalized recommendation generation model with a hybrid approach. This study considers a mixed activity projection method that takes individual activity insights from the univariate time-series prediction and ensemble multi-class classification approaches. We have introduced a way to improve the prediction result with a residual error minimization (REM) technique and make it meaningful in recommendation presentation with a Naïve-based interval prediction approach. We have integrated the activity prediction results in an ontology for semantic interpretation. A SPARQL query protocol and RDF Query Language (SPARQL) have generated personalized recommendations in an understandable format. Moreover, we have evaluated the performance of the time-series prediction and classification models against standard metrics on both imbalanced and balanced public PMData and private MOX2-5 activity datasets. We have used Adaptive Synthetic (ADASYN) to generate synthetic data from the minority classes to avoid bias. The activity datasets were collected from healthy adults (n = 16 for public datasets; n = 15 for private datasets). The standard ensemble algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) serve as input for the classification models. Subsequently, we re-verify the classifiers on the private MOX2-5 dataset. The performance of the ontology has been assessed with reasoning and SPARQL query execution time. Additionally, we have verified our ontology for effective recommendation generation.
We have tested several standard AI algorithms and selected the best-performing model with optimized configuration for our use case by empirical testing. We have found that the autoregression model with the REM method outperforms the autoregression model without the REM method for both datasets. Gradient Boost (GB) classifier outperforms other classifiers with a mean accuracy score of 98.00%, and 99.00% for imbalanced PMData and MOX2-5 datasets, respectively, and 98.30%, and 99.80% for balanced PMData and MOX2-5 datasets, respectively. Hermit reasoner performs better than other ontology reasoners under defined settings. Our proposed algorithm shows a direction to combine the AI prediction forecasting results in an ontology to generate personalized activity recommendations in eCoaching.
The proposed method combining step-prediction, activity-level classification techniques, and personal preference information with semantic rules is an asset for generating personalized recommendations.
Abstract
Background
Regular physical activity (PA), healthy habits, and an appropriate diet are recommended guidelines to maintain a healthy lifestyle. A healthy lifestyle can help to avoid chronic ...diseases and long-term illnesses. A monitoring and automatic personalized lifestyle recommendation system (i.e., automatic electronic coach or eCoach) with considering clinical and ethical guidelines, individual health status, condition, and preferences may successfully help participants to follow recommendations to maintain a healthy lifestyle. As a prerequisite for the prototype design of such a helpful eCoach system, it is essential to involve the end-users and subject-matter experts throughout the iterative design process.
Methods
We used an iterative user-centered design (UCD) approach to understend context of use and to collect qualitative data to develop a roadmap for self-management with eCoaching. We involved researchers, non-technical and technical, health professionals, subject-matter experts, and potential end-users in design process. We designed and developed the eCoach prototype in two stages, adopting different phases of the iterative design process. In design workshop 1, we focused on identifying end-users, understanding the user’s context, specifying user requirements, designing and developing an initial low-fidelity eCoach prototype. In design workshop 2, we focused on maturing the low-fidelity solution design and development for the visualization of continuous and discrete data, artificial intelligence (AI)-based interval forecasting, personalized recommendations, and activity goals.
Results
The iterative design process helped to develop a working prototype of eCoach system that meets end-user’s requirements and expectations towards an effective recommendation visualization, considering diversity in culture, quality of life, and human values. The design provides an early version of the solution, consisting of wearable technology, a mobile app following the “Google Material Design” guidelines, and web content for self-monitoring, goal setting, and lifestyle recommendations in an engaging manner between the eCoach app and end-users.
Conclusions
The adopted iterative design process brings in a design focus on the user and their needs at each phase. Throughout the design process, users have been involved at the heart of the design to create a working research prototype to improve the fit between technology, end-user, and researchers. Furthermore, we performed a technological readiness study of ProHealth eCoach against standard levels set by European Union (EU).
An eCoach system may allow people to manage a healthy lifestyle with health state monitoring (e.g., physical activity) and personalized recommendation generation. Daily step count is an important ...feature to provide a direct and indirect reflection on individual activity levels. Therefore, a personalized, predictive model may be beneficial to forecast future "steps" to motivate participants based on the temporal "step" pattern. Here, we have conceptualized the idea with a Bidirectional Long-ShortTerm-Memory (LSTM) model for weekly activity forecasting and a rule-base for personalized recommendation generation with Ontology reasoning and querying in activity eCoaching. First, we have used the publicly available "PMData" dataset of 16 adults (M: 13; F: 3) to train and test the models and explore the possibility of accurate univariate time-series forecasting of "step counts". Second, we have created an Ontology and a rule-base to generate personalized activity recommendations to motivate participants to accomplish their activity goals (e.g., complete "X" steps daily and stay active for the entire week).
The gradual increase of negative behavior in humans because of physical inactivity, unhealthy habit, and improper nutrition expedites the growth of lifestyle diseases. Proper lifestyle management may ...help to reach personal weight goals or maintain a normal weight range with optimization of health behaviors (physical activity, diet, and habits). This study conceptualizes a method to integrate the proposed mathematical model in a digital intervention strategy targeting obesity as a study case. We verify our proposed model with simulated data and compare it with related models based on the defined constraints. We express the mathematical model as a function of activity, habit, and nutrition with the first order law of thermodynamics, basal metabolic rate (BMR), total daily energy expenditure (TDEE), and body-mass-index (BMI) to establish a link between health behavior and weight change. We have used revised Harris-Benedict formulas (HB) for BMR and TDEE calculations. The proposed model showed a strong relationship between health behavior and weight change. The adoption of BMR and TDEE measures following the revised HB formula has outperformed the classical Wishnofsky's rule (3500 kcal. ≈ 1 lb. or 7700 kcal ≈ 1 Kg.), and the models proposed by Toumasis et al., Azzeh et al., and Mickens et al. with an average standard deviation (σ) of ±2.26, ±2.67, ±2.432, and ±2.29 respectively. This study helped us to understand the impact of healthy behavior on weight change with a mathematical model and its importance in maintaining a healthy lifestyle.
With the ongoing heart problems of the population worldwide, the medical requirements of the people are expected to increase. Electrocardiogram (ECG) is one of the proven to capture the heart ...response signal to assess the electrical and muscular functions of the heart. The ECG setup is expensive and needs proper training, and of course, it is not instant. For fast, accurate heart parameter monitoring, scientists pay attention to the photoplethysmogram signal (PPG), based on the light intensity of a particular wavelength. Android smartphone with a good quality camera has come to ordinary people's reach and has become one of the most necessary and rugged devices for today and future generations. We can use its powerful features to solve or assess heart state monitoring by capturing the image's necessary data. The mobile camera has a photo emitting diode and a photodetector. The light source illuminates the tissue. The photodetector calculates the small variation in light intensity associated with blood volume change in the vessels (mainly fingertips, toes, and ears). We have captured unfocused contact video to capture PPG using an Android Smartphone. Then, we removed a certain percent of camera touch errors based on average pixel intensity count in the red plane, and it is a new approach that has been introduced in this research. We used a 2nd order Butterworth (IIR) band pass filter for noise removal, FFT Hann Window for frequency analysis and leakage reduction. We have developed an algorithm using MATLAB as a development platform, for accurate pulse (BPM) measurement. Moreover, we have done a comparative analysis of developed algorithm with other available algorithms for PPG-based pulse calculation. In this study, the fingertip video was captured when the body was at rest