Browsing by Author "Ginchev, Todor"

Now showing 1 - 4 of 4

Biofeedback and Digitalized Motivational Interviewing to Increase Daily Physical Activity: Series of Factorial N-of-1 Randomized Controlled Trials Piloting the Precious App
(2023-01) Nurmi, Johanna; Knittle, Keegan; Naughton, Felix; Sutton, Stephen; Ginchev, Todor; Khattak, Fidaullah; Castellano-Tejedor, Carmina; Lusilla-Palacios, Pilar; Ravaja, Niklas; Haukkala, Ari
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
Background: Insufficient physical activity is a public health concern. New technologies may improve physical activity levels and enable the identification of its predictors with high accuracy. The Precious smartphone app was developed to investigate the effect of specific modular intervention elements on physical activity and examine theory-based predictors within individuals. Objective: This study pilot-tested a fully automated factorial N-of-1 randomized controlled trial (RCT) with the Precious app and examined whether digitalized motivational interviewing (dMI) and heart rate variability–based biofeedback features increased objectively recorded steps. The secondary aim was to assess whether daily self-efficacy and motivation predicted within-person variability in daily steps. Methods: In total, 15 adults recruited from newspaper advertisements participated in a 40-day factorial N-of-1 RCT. They installed 2 study apps on their phones: one to receive intervention elements and one to collect ecological momentary assessment (EMA) data on self-efficacy, motivation, perceived barriers, pain, and illness. Steps were tracked using Xiaomi Mi Band activity bracelets. The factorial design included seven 2-day biofeedback interventions with a Firstbeat Bodyguard 2 (Firstbeat Technologies Ltd) heart rate variability sensor, seven 2-day dMI interventions, a wash-out day after each intervention, and 11 control days. EMA questions were sent twice per day. The effects of self-efficacy, motivation, and the interventions on subsequent steps were analyzed using within-person dynamic regression models and aggregated data using longitudinal multilevel modeling (level 1: daily observations; level 2: participants). The analyses were adjusted for covariates (ie, within- and between-person perceived barriers, pain or illness, time trends, and recurring events). Results: All participants completed the study, and adherence to activity bracelets and EMA measurements was high. The implementation of the factorial design was successful, with the dMI features used, on average, 5.1 (SD 1.0) times of the 7 available interventions. Biofeedback interventions were used, on average, 5.7 (SD 1.4) times out of 7, although 3 participants used this feature a day later than suggested and 1 did not use it at all. Neither within- nor between-person analyses revealed significant intervention effects on step counts. Self-efficacy predicted steps in 27% (4/15) of the participants. Motivation predicted steps in 20% (3/15) of the participants. Aggregated data showed significant group-level effects of day-level self-efficacy (B=0.462; P<.001), motivation (B=0.390; P<.001), and pain or illness (B=−1524; P<.001) on daily steps. Conclusions: The automated factorial N-of-1 trial with the Precious app was mostly feasible and acceptable, especially the automated delivery of the dMI components, whereas self-conducted biofeedback measurements were more difficult to time correctly. The findings suggest that changes in self-efficacy and motivation may have same-day effects on physical activity, but the effects vary across individuals. This study provides recommendations based on the lessons learned on the implementation of factorial N-of-1 RCTs.
Engaging Users in the Behavior Change Process With Digitalized Motivational Interviewing and Gamification: Development and Feasibility Testing of the Precious App
(2020-01-30) Nurmi, Johanna; Knittle, Keegan; Ginchev, Todor; Khattak, Fida; Helf, Christopher; Zwickl, Patrick; Castellano-Tejedor, Carmina; Lusilla-Palacios, Pilar; Costa-Requena, Jose; Ravaja, Niklas; Haukkala, Ari
A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
BACKGROUND: Most adults do not engage in sufficient physical activity to maintain good health. Smartphone apps are increasingly used to support physical activity but typically focus on tracking behaviors with no support for the complex process of behavior change. Tracking features do not engage all users, and apps could better reach their targets by engaging users in reflecting their reasons, capabilities, and opportunities to change. Motivational interviewing supports this active engagement in self-reflection and self-regulation by fostering psychological needs proposed by the self-determination theory (ie, autonomy, competence, and relatedness). However, it is unknown whether digitalized motivational interviewing in a smartphone app engages users in this process. OBJECTIVE: This study aimed to describe the theory- and evidence-based development of the Precious app and to examine how digitalized motivational interviewing using a smartphone app engages users in the behavior change process. Specifically, we aimed to determine if use of the Precious app elicits change talk in participants and how they perceive autonomy support in the app. METHODS: A multidisciplinary team built the Precious app to support engagement in the behavior change process. The Precious app targets reflective processes with motivational interviewing and spontaneous processes with gamified tools, and builds on the principles of self-determination theory and control theory by using 7 relational techniques and 12 behavior change techniques. The feasibility of the app was tested among 12 adults, who were asked to interact with the prototype and think aloud. Semistructured interviews allowed participants to extend their statements. Participants' interactions with the app were video recorded, transcribed, and analyzed with deductive thematic analysis to identify the theoretical themes related to autonomy support and change talk. RESULTS: Participants valued the autonomy supportive features in the Precious app (eg, freedom to pursue personally relevant goals and receive tailored feedback). We identified the following five themes based on the theory-based theme autonomy support: valuing the chance to choose, concern about lack of autonomy, expecting controlling features, autonomous goals, and autonomy supportive feedback. The motivational interviewing features actively engaged participants in reflecting their outcome goals and reasons for activity, producing several types of change talk and very little sustain talk. The types of change talk identified were desire, need, reasons, ability, commitment, and taking steps toward change. CONCLUSIONS: The Precious app takes a unique approach to engage users in the behavior change process by targeting both reflective and spontaneous processes. It allows motivational interviewing in a mobile form, supports psychological needs with relational techniques, and targets intrinsic motivation with gamified elements. The motivational interviewing approach shows promise, but the impact of its interactive features and tailored feedback needs to be studied over time. The Precious app is undergoing testing in a series of n-of-1 randomized controlled trials.
Food Object Recognition: An Application of Deep Learning
(2018-06-18) Koirala, Janaki
Perustieteiden korkeakoulu | Master's thesis
Identifying a food from its image can save people’s life. It can be used to know the presence of potential allergens in food or by estimating the nutritional content of food, it may also be used to combat the obesity epidemic. With such applications in mind, we seek to exploit the advances in machine learning and deep learning to train models that identify European food from digital photos. From the literature it was discovered that the Faster RCNN was the current state-of-art CNN based framework which could get local information of object in image and recognize it. Furthermore, we also develop an Android application for recognition of food objects. Faster RCNN requires a large volume of data with labels and localization infor- mation of the objects present in them. It is very challenging to find such datasets to train our network. We made up a food dataset of 69k images with 445 labels and trained our model using those images. But the dataset was skewed in terms of numbers of images per category that negatively affected the performance of the model. To improve the performance, we tried several approaches like taking only a subset of labels and equalizing the number of training samples for each label. We also used transfer learning to get around the problem of overfitting the network when our training sample size is limited. Finally, by using publicly available data set and adapting it to our needs, our model was able to identify images with 0.37 mean Average Precision. The Android application uses this model to recognize food objects from images.
Wearable Electronic Device Design for Preventive Health Care-Related Purposes
(2015-12-14) Ginchev, Todor
Sähkötekniikan korkeakoulu | Master's thesis
Medical diagnosis and healthcare recommendations are often challenging and require the correlation between different health-related inputs from the subject. On the one hand, some of the biometric data inputs are only possible to be determined by 24/7 monitoring, such as physical activity tracking, sleep quality or food intake nutritional information and quantity estimation. On the other hand, it is a big data problem as the correlation between all the inputs is rather challenging and time-consuming to be done by a human being. This work presents the design of wearable wristband electronic device, capable of continuous monitoring of several biometric inputs. The device connects to the Internet via smartphone and sends the data to a server in a secure way, using proper authentication and personal data protection. The biometric data will be available for physicians and at the same time a machine learning algorithm will elaborate and send healthcare related recommendations to the user. The wristband device is capable of tracking the physical activity, sleep quality and food intake of the subject. This is be done by several built-in sensors such as accelerometer, gyroscope, heart-rate sensor and digital camera. The accelerometer is be used to track the physical activity and the gyroscope detects wrist motion in order to recognize when the subject is eating and count the taken bites. Furthermore, the heart-rate sensor detects stress situations and the built-in camera takes a picture of the food. Thus, the picture is send to the smartphone via Bluetooth and then a computer vision algorithm is used to recognize the food. The designed smart wristband circuit is first tested on a protoboard and then on an Arduino nano board. After that, the circuit is fabricated on a RF4 substrate PCB in order to test the final design. After verification, the circuit is finally fabricated on a flexible circuit, which concludes with the wristband prototype design, fabrication and verification.