Jesús D. Cerón

A mobile system for sedentary behaviors classification based on accelerometer and location data

Abstract Background Sedentary behaviors are associated to the development of noncommunicable diseases (NCD) such as cardiovascular diseases (CVD), type 2 diabetes, and cancer. Accelerometers and inclinometers have been used to estimate sedentary behaviors, however a major limitation is that these devices do not provide enough contextual information in order to recognize the specific sedentary behavior performed, e.g., sitting or lying watching TV, using the PC, sitting at work, driving, etc. Objective Propose and evaluate the precision of a mobile system for objectively measuring six sedentary behaviors using accelerometer and location data. Results The system is implemented as an Android Mobile App, which identifies individual’s sedentary behaviors based on accelerometer data taken from the smartphone or a smartwatch, and symbolic location data obtained from Bluetooth Low Energy (BLE) beacons. The system infers sedentary behaviors by means of a supervised Machine Learning Classifier. The precision of the classification of five of the six studied sedentary behaviors exceeded 95% using accelerometer data from a smartwatch attached to the wrist and 98% using accelerometer data from a smartphone put into the pocket. Statistically significant improvement in the average precision of the classification due to the use of BLE beacons was found by comparing the precision of the classification using accelerometer data only, and BLE beacons localization technology. Conclusions The proposed system provides contextual information of specific sedentary behaviors by inferring with very high precision the physical location where the sedentary event occurs. Moreover, it was found that, when accelerometers are put in the user’s pocket, instead of the wrist and, when symbolic location is inferred using BLE beacons; the precision in the classification is improved. In practice, the proposed system has the potential to contribute to the understanding of the context and determinants of sedentary behaviors, necessary for the implementation and monitoring of personalized noncommunicable diseases prevention programs, for instance, sending sedentary behavior alerts, or providing personalized recommendations on physical activity. The system could be used at work to promote active breaks and healthy habits.

Human-centered design of a personal health record system for metabolic syndrome management based on the ISO 9241-210:2010 standard

Background Previous studies have demonstrated the effectiveness of information and communication technologies to support healthy lifestyle interventions. In particular, personal health record systems (PHR-Ss) empower self-care, essential to support lifestyle changes. Approaches such as the user-centered design (UCD), which is already a standard within the software industry (ISO 9241-210:2010), provide specifications and guidelines to guarantee user acceptance and quality of eHealth systems. However, no single PHR-S for metabolic syndrome (MS) developed following the recommendations of the ISO 9241-210:2010 specification has been found in the literature. Objective The aim of this study was to describe the development of a PHR-S for the management of MS according to the principles and recommendations of the ISO 9241-210 standard. Methods The proposed PHR-S was developed using a formal software development process which, in addition to the traditional activities of any software process, included the principles and recommendations of the ISO 9241-210 standard. To gather user information, a survey sample of 1,187 individuals, eight interviews, and a focus group with seven people were performed. Throughout five iterations, three prototypes were built. Potential users of each system evaluated each prototype. The quality attributes of efficiency, effectiveness, and user satisfaction were assessed using metrics defined in the ISO/IEC 25022 standard. Results The following results were obtained: 1) a technology profile from 1,187 individuals at risk for MS from the city of Popayan, Colombia, identifying that 75.2% of the people use the Internet and 51% had a smartphone; 2) a PHR-S to manage MS developed (the PHR-S has the following five main functionalities: record the five MS risk factors, share these measures with health care professionals, and three educational modules on nutrition, stress management, and a physical activity); and 3) usability tests on each prototype obtaining the following results: 100% effectiveness, 100% efficiency, and 84.2 points in the system usability scale. Conclusion The software development methodology used was based on the ISO 9241-210 standard, which allowed the development team to maintain a focus on user’s needs and requirements throughout the project, which resulted in an increased satisfaction and acceptance of the system. Additionally, the establishment of a multidisciplinary team allowed the application of considerations not only from the disciplines of software engineering and health sciences but also from other disciplines such as graphical design and media communication. Finally, usability testing allowed the observation of flaws in the designs, which helped to improve the solution.