The Effect of a Machine Learning-Based Mobile Application on Physical Activity in Overweight and Obese Women

The goal of this clinical trial is to evaluate the effect of an algorithm-driven mobile application that provides personalized recommendations for increasing physical activity, which is an important health behavior, in the prevention of obesity and many other related non-communicable diseases in overweight and obese women. Hypotheses of this study are:

• The physical activity level of overweight and obese adult women in the intervention group increases.
• Body Mass Index decreases in overweight and obese adult women in the intervention group.
• The daily step count of overweight and obese adult women in the intervention group increases.

Participants will be asked to use the mobile application they received daily and follow their personalized physical activity program.

Researchers will compare the experimental and control groups to see if the mobile application affected the physical activity level.

Study Overview

• Status: Completed
• Conditions: Physical Inactivity
• Intervention / Treatment: Behavioral: Individualized physical activity management system

Detailed Description

According to the World Health Organization (WHO), physical inactivity is one of the significant public health issues of our time. Health problems associated with this issue lead to an overload of healthcare services. According to the report published by WHO in 2022, the prevalence of overweight and obesity in the world constitutes 60% of the total population and causes 1.2 million deaths in the European region. In Turkey, the prevalence of obesity is 66.8 in all genders and 69.3 in women. The increasing epidemic of excessive weight and obesity, which leads to chronic diseases in the long term, poses a significant public health threat both globally and in our country.

Physical activity is an essential lifestyle measure for maintaining a healthy weight and preventing obesity. In women, physical activity levels decrease during pregnancy, and inactivity continues after childbirth. Therefore, determining the physical activity levels of women at risk for obesity and planning public health initiatives to increase their physical activity levels are also important.

Cognitive Behavioral Theory (CBT) is a theory that suggests thoughts, feelings, and behaviors are interconnected and influence each other. CBT is used in many health improvement interventions, such as improving physical activity levels. On the other hand, Social Cognitive Theory (SCT) is an important theory in planning behavior change interventions related to individuals' changing and sustaining health behaviors. SCT provides a strong perspective in understanding health behaviors related to physical activity by identifying the interaction between individuals, the environment, and behavior. Associating the components of CBT and SCT with the level of physical activity will provide a comprehensive approach by simultaneously addressing cognitive, behavioral, environmental, and social factors that affect the physical activity levels of middle-aged women.

Increasing physical activity is an effective intervention in reducing the prevalence of obesity and overweight, which are significant public health problems worldwide and in our country. There is an urgent need for behavior change interventions to determine and increase physical activity levels in the entire society and especially in risk groups to promote healthy lifestyles. This research is designed to evaluate the impact of a machine learning-based mobile application that provides personalized recommendations to increase physical activity, which is an essential health behavior in preventing obesity and many other non-communicable diseases in overweight and obese women.

After obtaining institutional and ethical approvals, data will be collected through face-to-face interviews with women aged 35-60 who apply to Family Health Centers in Istanbul. The height and weight of the women will be measured, and their Body Mass Index (BMI) will be calculated. Women with a BMI value of 25 or higher and no medical condition or health issue that would impede their physical activity status will be included in the study.

The data for the study will be collected using the following tools and measures: Identifying Characteristics Form, Visual Analog Scale (VAS), Anthropometric Measurements, International Physical Activity Questionnaire (Short Form), Women's Physical Activity Self-Efficacy Scale, Physical Activity Barriers Scale, Cognitive Behavioral Physical Activity Scale, Exercise Self-Efficacy Scale, and a smart wristband.

After data collection, the data will be transferred to the Statistical Package for the Social Sciences (SPSS) 25.0 software package for analysis. The data analysis will include percentages, mean values, standard deviations and chi-square test, independent sample t-test, repeated measures ANOVA test, and the corrected Bonferroni test for advanced analyses.

• Study Type: Interventional
• Enrollment (Actual): 80
• Phase: Not Applicable

Contacts and Locations

Study Locations

• Turkey
  • Istanbul, Turkey
    • Istanbul University - Cerrahpasa (IUC)

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• BMI>25
• Who do not have any obstacle to participating in physical activities

Exclusion Criteria:

• Who have previously used a smart band to increase their physical activity levels

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Prevention
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Triple

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Individualized physical activity management system; The mobile application will be downloaded to the smartphones of the participants in the experimental group and the application will be introduced by the nurse at the family health center. Participants will receive daily and weekly goals with personalized physical activity recommendations, using the exercise recommendations determined by the decision system by public health nursing and physiotherapy and rehabilitation experts in the mobile application. With the initial data collected, a personalized physical activity program will be created according to each participant's lifestyle, physical activity level and physical activity barriers. The physical activity program will include a daily step count goals, exercises and stretching movements for each participant, and this program will be offered to the participants via the mobile application. The exercises that the participants are expected to complete will be shown in the application as videos with animated characters.	Behavioral: Individualized physical activity management system; Participants will be provided with personalized exercise recommendations determined by a decision system by public health nursing and physiotherapy and rehabilitation experts via the mobile application. Targets will be determined for participants based on their completion of physical activity recommendations every day and every week in the mobile application. The initial program will be individually created based on the initial data collected and each participant's lifestyle, physical activity level and barriers to physical activity. Then, depending on the participants' ability to achieve their goals, the duration and intensity of the suggestions given will be individualized to a level that the person can complete.
No Intervention: Control; The mobile application will be downloaded to the smartphones of the participants in the experimental and control groups and the application will be introduced by the nurse at the family health center to which the participants are affiliated. Participants in the control group will use the mobile application only to enter and track daily step counts and other data.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
International Physical Activity Questionnaire (IPAQ) score	Participants' International Physical Activity Questionnaire (IPAQ) score.	3 months
Daily step count	Participants' daily step counts measured with their smart bands	3 months
BMI	Weight and height will be combined to report BMI in kg/m^2	3 months

Collaborators and Investigators

• Sponsor: Istanbul University - Cerrahpasa (IUC)

Publications and helpful links

General Publications

• Bandura A. Social cognitive theory: an agentic perspective. Annu Rev Psychol. 2001;52:1-26. doi: 10.1146/annurev.psych.52.1.1.
• Bandura A. Health promotion by social cognitive means. Health Educ Behav. 2004 Apr;31(2):143-64. doi: 10.1177/1090198104263660.
• Evenson KR, Aytur SA, Borodulin K. Physical activity beliefs, barriers, and enablers among postpartum women. J Womens Health (Larchmt). 2009 Dec;18(12):1925-34. doi: 10.1089/jwh.2008.1309.
• World Health Organization. Burden: mortality, morbidity and risk factors. Global status report on non communicable diseases. 2010.
• WHO European Regional Obesity Report. Copenhagen: WHO Regional Office for Europe. 2022. Licence: https://creativecommons.org/licenses/by-nc-sa/3.0/igo
• Fadhil, A. Towards Automatic and Personalised Mobile Health Interventions: An Interactive Machine Learning Perspective. arXiv preprint arXiv:1803.01842. 2018
• Pinto BM, Floyd A. Theories underlying health promotion interventions among cancer survivors. Semin Oncol Nurs. 2008 Aug;24(3):153-63. doi: 10.1016/j.soncn.2008.05.003.
• Shamizadeh T, Jahangiry L, Sarbakhsh P, Ponnet K. Social cognitive theory-based intervention to promote physical activity among prediabetic rural people: a cluster randomized controlled trial. Trials. 2019 Feb 4;20(1):98. doi: 10.1186/s13063-019-3220-z.
• Niemiro GM, Rewane A, Algotar AM. Exercise and Fitness Effect on Obesity. 2023 Nov 17. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing; 2024 Jan-. Available from http://www.ncbi.nlm.nih.gov/books/NBK539893/

Study record dates

Study Major Dates

• Study Start (Actual): April 5, 2024
• Primary Completion (Actual): July 5, 2024
• Study Completion (Actual): August 5, 2024

Study Registration Dates

• First Submitted: September 25, 2023
• First Submitted That Met QC Criteria: January 16, 2024
• First Posted (Actual): January 26, 2024

Study Record Updates

• Last Update Posted (Actual): October 28, 2024
• Last Update Submitted That Met QC Criteria: October 24, 2024
• Last Verified: October 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Nutrition Disorders; Overnutrition; Body Weight; Overweight
• Other Study ID Numbers: ETKU10/201

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The data of this research will be shared with researchers who request it via e-mail.
• IPD Sharing Time Frame: The data will be available after the statistical analysis have completed. All the relevant data will be kept without any time restriction
• IPD Sharing Access Criteria: The data of this research will be available for the researchers who are planning a systematic review/metanalysis on this issue and have a PROSPERO record.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF; CSR

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No