Trial Review

The ANZCTR website will be unavailable from 1pm until 3pm (AEDT) on Wednesday the 30th of October for website maintenance. Please be sure to log out of the system in order to avoid any loss of data.

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
ACTRN12622000953730p
Ethics application status
Submitted, not yet approved
Date submitted
22/05/2022
Date registered
6/07/2022
Date last updated
6/07/2022
Date data sharing statement initially provided
6/07/2022
Type of registration
Prospectively registered

Titles & IDs
Public title
Artificial Intelligence and mHealth to Determine the response to a LIfestyle intervention for the primary prevention of Osteoporosis and frailty fractures in Postmenopausal women
Scientific title
Artificial Intelligence and mHealth to Determine the response to a LIfestyle intervention for the primary prevention of Osteoporosis and frailty fractures in Postmenopausal women
Secondary ID [1] 307190 0
None
Universal Trial Number (UTN)
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Osteoporosis 326415 0
Post-menopause 326645 0
Condition category
Condition code
Musculoskeletal 323699 323699 0 0
Osteoporosis
Reproductive Health and Childbirth 323887 323887 0 0
Menstruation and menopause

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
The project is a single-blind (assessor), three-arm, randomized, controlled trial. Eligible participants will be randomly assigned (1: 1: 1) to three groups: (i) a lifestyle modification program increasing impacts and physical activity level with a duration of 9 months (EV), (ii) the same program, but supplemented with strength training at home, twice a week (EV + F), or (iii) an unsupervised control group (CON) that will continue with their usual treatment.
Participants will be scheduled for three days to complete the measurement protocol. On the first day, they will attend the hospital and complete the sociodemographic and clinical information. They will then receive the accelerometer and all the questionnaires to be completed at home. In addition, from the hospital center, the participants will be summoned another day for the biochemical analysis, QCT and densitometry. On a second day, the participants will be summoned to the university laboratory to return the accelerometers and questionnaires, and they will take the physical condition tests. Finally, in a third visit to the laboratory, the participants will be familiarized with the use of the recording bracelet, with the strength training assessment device and with the session recording system (EV + F group). Finally, before the study begin, all participants will receive a daily vitamin D supplement (oral capsule) of 600 IU/day for 1 month. If serum levels are deficient, it will be supplied for 4 months (1 before and the first 3 of the intervention): 1 vial of 25,000 IU per month if <20ng/ml, 1 vial of 25000 IU every 15 days if <15ng/ml, 1 vial of 25,000 IU every week if <10 ng/ml. Calcium intake will be calculated using the 3-day recall and supplemented up to 1200 mg per day.

Intervention (RCT with 3-arms)
A. Program to increase physical activity and impacts
For the intervention, a biosensor -wearable device- (Muvone ®, Secmotic, Spain) will be used, validated for the quantification of mechanical load during physical activity for the implementation of osteoporosis prevention programs. The device is linked to an App (Muvone) that will allow users to quantify the number of steps (including the rate of steps per minute), the impacts and their intensity. Users will be given feedback from the application on the level of achievement of the objectives proposed in the impact program (EV and EV + F). It will be proposed to achieve 50 vertical and multidirectional jumps per day (milestone 1. The number of jumps> 3.9 G per day will be recorded, divided between 3-5 sets of 10-20 repetitions with a minimum 1-2 minute rest between sets (aprox. 15 min per day). A frequency between 4-7 days per week will be used (which will gradually increase in the intervention). In the same way (increasing frequency from 4 to 7 days per week), it will be recommended to reach 10,000 steps per day (milestone 2. The number of daily steps will be recorded) and, as far as possible, at a rapid pace (milestone 3. The number of daily minutes walking at a pace over 110 steps/minute will be recorded, as this is considered the threshold of moderate-vigorous intensity in this age range. Therefore, according to the new WHO guidelines on physical activity and sedentary behavior, it will be quantified whether 150 minutes a week of moderate-vigorous physical activity are achieved. In parallel, the participants in both groups will receive recipes rich in calcium, designed specifically for this study, through the App and will have a calculator to calculate the intake of calcium and other micronutrients through the diet. They will also receive information on osteoporosis and strategies for its prevention (e.g., advice on sun exposure). Different strategies (i.e., accessing app analytics) will be used to monitor adherence to the program.

B. Strength training program at home
Along with the above program, participants assigned to the EV + F group will undergo two weekly unsupervised strength training sessions that will include a 10-minute warm-up period with walking and mobility exercises (e.g. Slowly rock forward onto your toes, lateral lunges…), followed by 20 to 42 minutes of a core-based exercise program. in a circuit training with strength exercises in a staggered progression during the program. The workout will include 2–3 sets of 5–10 exercises. Participants will perform 8 to 20 repetitions of multi-joint exercises aimed at the main muscle groups (especially those involved in the hip and spine), such as squats, deadlifts, hip extensions, hip abductions, knee flexion-extensions or rowing exercises. The total duration of each session will range between approximately 45 min and 1 hour. All exercises will be performed using a Handy Gym Dynamic device (Handy Gym, RecoveryTroop, Spain). This device allows 12 levels of progression and up to a load equivalent to 100 kg (combination of discs with an inertia from 6.3 Kg/cm2 to 15.5 kg/cm2). The load will gradually increase by varying said inertia (from inertia 1-2 blue discs- to inertia 12-2 red discs) and each participant will individualize their effort to reach the intensity designed for each session. Perceived exertion (RPE) will be recorded using a Borg CR-10 scale. The intensity (expressed as RPE) is expected to range between 5 and 10. Through the Handy Gym App, the exercises performed, and the volume (series, repetitions, and times) will be recorded, as well as the associated kinetic variables (e.g., strength and power). Sessions will end with a 5-8 minute recovery period of stretching and relaxation exercises. Again, the adherence to the program will be monitored through the app.

Participants will also receive access to a YouTube channel, which will provide step-by-step instructions for each exercise progression designed specifically for this study. Participants will be contacted weekly (5-10 minute telephone call or via Whatsapp) by a study researcher (physical therapist) to maintain regular interaction, assess progress and reinforce completion of the training diary.
Intervention code [1] 323640 0
Prevention
Comparator / control treatment
C. Control group
Participants randomly assigned to CON will receive general advice face-to-face from medical staff on the positive effects of physical activity and nutritional aspects for the prevention of osteoporosis. The educational information will be designed specifically for this study, This information will be provided on a 30 min session conducted at the beginning of the 9-month intervention period and within the 3-4 month. Participants in this group will carry a wearable device (Muvone ®, Secmotic, Spain), but will not have access to the Muvone App. The adherence to the comparator treatment will be also controlled through the app (e.g., attendance checklists). Participants in the control group will be contacted weekly via Whatsapp to maintain regular interaction,
Control group
Active

Outcomes
Primary outcome [1] 331449 0
Serum beta-CrossLaps (ß-CTX) to assess bone resorption and P1NP, to assess bone remodeling
Timepoint [1] 331449 0
Baseline and 9 month post-intervention commencement.
Secondary outcome [1] 409925 0
Whole-body lean mass will be measured by a specialist technician using a DEXA device (Hologic Horizon Wi, Waltham, MA, USA).
Timepoint [1] 409925 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [2] 409926 0
Quantitative computed tomography
Volumetric bone mineral density -BMD- (vBMD), indicating cortical and trabecular microarchitecture values in the right femur and tibia with a spiral QCT scanner (XtremeCT II, Scanco Medical). Three transverse scans will be performed, one in the femur (50% of the estimated bone length of the distal endplate of the femur), one in the proximal tibia (67% of the distal endplate of the tibia) and another in the distal tibia (5 %). For each region of interest, the global, cortical, and trabecular vBMD (g/cm3) will be computed. Regarding the geometry, the cortical cross-sectional area (CSA) and the mean cortical thickness (CTh) will be evaluated.
Timepoint [2] 409926 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [3] 409927 0
Quality of life
The quality of life of the participants will be determined with the Short-Form Health Survey 36 (SF-36). The SF-36 is a generic instrument to assess health-related quality of life. It contains 36 items grouped into 8 dimensions: physical functioning, physical role, body pain, general health, vitality, social functioning, emotional role and mental health. The score ranges from 0 to 100 in each dimension, with higher values indicating better health.
Timepoint [3] 409927 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [4] 409928 0
Symptoms of menopause
Participants will complete the Menopause Rating Scale (MRS) questionnaire, which is a menopause-specific quality of life scale developed and validated to assess the severity of symptoms related to menopause. It consists of 11 items, which cover three dimensions: (1) somatic symptoms, which include vasomotor symptoms, cardiac discomfort, sleep problems, and joint or muscle discomfort (items 1-3 and 11, respectively); (2) psychological symptoms, including depressed mood, irritability, anxiety, and physical or mental exhaustion (items 4 to 7, respectively); and (3) urogenital symptoms, including sexual problems, bladder problems, and vaginal dryness (points 8 to 10, respectively). A five-point rating scale for each item allows participants to describe the perceived severity of symptoms (no complaints, 0; mild, 1; moderate, 2; severe, 3; and extremely severe, 4). The subscales are analyzed by summing the individual scores of the symptom for each subscale. A value of 17 is used as a cut-off point to determine a high MRS score, indicating an impaired quality of life and severe menopausal symptoms.
Timepoint [4] 409928 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [5] 409929 0
Physical function, strength, and muscular power of the lower body
A series of common physical function tests related to the risk of falls will be performed to examine mobility and dynamic balance, including: Timed up and go (TUG), which consists of getting up from a chair without using your hands, walking a distance of 2.44 m, turning around a cone and sitting down again. Two trials will be carried out with 3 min rest between them, registering the best time (in seconds).
Timepoint [5] 409929 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [6] 409930 0
Physical activity. Accelerometry will be used to objectively evaluate physical activity. Participants will be asked to use a triaxial accelerometer (GT3X +, Pensacola, Florida, USA) for 9 consecutive days, beginning on the same day they receive the monitor (e.g., participants who receive the accelerometer on Monday, will carry the device until Tuesday of the following week). The first and last days will be excluded from the analyzes, accounting for a total of 7 days of registration. Participants will be instructed to wear the accelerometer throughout the day (24 h) on the non-dominant hip. They can only remove it to shower, practice water sports and sleep. Only the data of those accelerometers that record at least 4 days with a minimum of 10 hours of recording will be included. The data will be filtered and transformed into counts per minute (CPM) using ActiLife software (v6.13.3, Actigraph, Pensacola, FL, USA). Moderate to vigorous physical activity time (MVPA) will be defined as 100 to 1951 CPM, and >1951 CPM, respectively, based on Freedson cut-off points for adults and will be reported as a percentage of total usage time. For the analysis of the different activity patterns, the GGIR package will be used to treat raw data.
Timepoint [6] 409930 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [7] 410827 0
The Bone Mineral Density (g/cm2) of the lumbar vertebrae (L1-L4) and femur of the right leg (femoral neck, Ward's triangle, and greater trochanter) will be analyzed by a specialist technician outside the study using a DEXA device (Hologic Horizon Wi, Waltham, MA, USA). Values will be converted to T-score and Z-score based on the reference values for a Caucasian female and the bone density of the Spanish population, respectively. The device will be calibrated daily using a phantom.
Timepoint [7] 410827 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [8] 410829 0
The 30 s chair stand test (30 s-CST), in which the number of times in 30 s that the participant can get up from a chair to stand fully from a sitting position with a straight back and feet supported is counted on the ground, without leaning on the arms.
Timepoint [8] 410829 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [9] 410830 0
To assess the speed of the walk, the participants will walk as fast as possible a distance of 5 m. The speed (m·s-1) will be evaluated using a photocell system (Racetime 2; Microgate, Bolzano, Italy).
Timepoint [9] 410830 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [10] 410831 0
To estimate strength gains in response to the training program, isometric strength will be assessed by means of Isokinetic strength in concentric (at angular velocities of 60 and 240°s- 1) and eccentric (120 °·s-1) in flexion and extension of the knee and hip, using an isokinetic dynamometer (Biodex System 4; NY, USA). The peak of the torque of each series will be recorded.
Timepoint [10] 410831 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [11] 410832 0
Muscular power will be assessed using Isokinetic strength in concentric (at angular velocities of 60 and 240°s- 1) and eccentric (120 °·s-1) in flexion and extension of the knee and hip, using an isokinetic dynamometer (Biodex System 4; NY, USA). The average power of each series will be recorded.
Timepoint [11] 410832 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [12] 410833 0
The maximum impulse (N s) and the maximum impulse in relation to the body weight (Ns/kg) of the vertical reaction forces against the ground in a vertical countermovement jump (CMJ) on a platform will be evaluated. force (Kistler, Winterthur, Switzerland). Participants will perform 3 CMJ with 1 min rest between them, registering the best value for future analyzes.
Timepoint [12] 410833 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [13] 410834 0
Accelerometry will be used to objectively evaluate sedentary time. Participants will be asked to use a triaxial accelerometer (GT3X +, Pensacola, Florida, USA) for 9 consecutive days, beginning on the same day they receive the monitor (e.g., participants who receive the accelerometer on Monday, will carry the device until Tuesday of the following week). The first and last days will be excluded from the analyzes, accounting for a total of 7 days of registration. Participants will be instructed to wear the accelerometer throughout the day (24 h) on the non-dominant hip. They can only remove it to shower, practice water sports and sleep. Only the data of those accelerometers that record at least 4 days with a minimum of 10 hours of recording will be included. The data will be filtered and transformed into counts per minute (CPM) using ActiLife software (v6.13.3, Actigraph, Pensacola, FL, USA). Sedentary will be defined as 1 to 99 CPM,
Timepoint [13] 410834 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [14] 411341 0
Whole-body fat mass will be measured by a specialist technician using a DEXA device (Hologic Horizon Wi, Waltham, MA, USA).
Timepoint [14] 411341 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [15] 411342 0
Waist circumference (cm) will be assessed midway between the ribs and the crest of the ileum, with the participant standing (Harpenden tape, Holtain Ltd).
Timepoint [15] 411342 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.
Secondary outcome [16] 411587 0
A stadiometer (SECA, Hamburg, Germany) will be used to measure the height of the subjects without shoes.
Timepoint [16] 411587 0
Baseline, 9 month post-intervention commencement, 12 weeks after finishing the intervention.

Eligibility
Key inclusion criteria
Inclusion criteria
- Postmenopausal women older than 40 years with greater than 8 years after menopause (“early postmenopausal women”).
- Sedentary women (defined as not performing regular physical activity greater than 150 min of moderate-vigorous physical activity per week in the last six months).
- Willing to give consent to participate in the study.
Minimum age
40 Years
Maximum age
50 Years
Sex
Females
Can healthy volunteers participate?
No
Key exclusion criteria
Exclusion criteria
- Surgically induced menopause or cancer treatment.
- Low BMI (<18 kg / m2).
- Excessive alcohol consumption (greater than 3 drinks per day).
- Smoker
- Unstable cardiovascular disease.
- Rheumatoid arthritis.
- Chronic kidney disease
- Diagnosis of conditions that alter bone metabolism (hypo/hypercalcemia, hyperthyroidism, hypo/hypergonadism).
- Upper or lower limb fracture in the last 6 months.
- Mobility problems or requiring assistance to walk.
- Participation in physical exercise programs in the 6 months prior to the study.
- Regular use of glucocorticoids or hormone replacement therapy in the past 3 months.
- Unwillingness to complete the study requirements.

Study design
Purpose of the study
Prevention
Allocation to intervention
Randomised controlled trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
The sequence will be prepared by a member of the research team without clinical participation in the trial.
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Eligible participants will be randomly assigned (1: 1: 1) to three groups using a computerised sequence generation.
Masking / blinding
Blinded (masking used)
Who is / are masked / blinded?


The people assessing the outcomes
The people analysing the results/data
Intervention assignment
Parallel
Other design features
Phase
Not Applicable
Type of endpoint/s
Statistical methods / analysis

The data collected from different sources (i.e., medical records, images, biochemical analyses, physical fitness, quality of life and qualitative information from different interviews) contains user information on the response to the treatment. From this data, we intend to design a machine learning (ML) algorithm that could learn from past behavior and would then be able to forecast future ones. ML is the study of algorithms that can automatically learn from data to make new decisions. Current ML methods include Neural Networks, Support Vector Machines, or Random Forests. The available data for the ML model must be of high quality and can be any data deemed useful for the purpose of prediction. This data is split in two parts (data splitting), the so-called training and test data. First, the algorithm must learn the relationship between the outcome of interest (response to treatment or adherence) and the potential contributing factors (also called predictors/covariates/explanatory variables) from the training data set. The test data can then be used to test the prediction capacity of the algorithm learned from the training data. It is important that this quality check is not achieved on the training data, but on unseen data, hence the data splitting at the beginning. The quality and size of the data sets are important parameters for the quality of the results. To improve the quality of these large and complex datasets and to ensure optimal operation of the ML algorithms, data preprocessing methods (imputation, standardization, discretization), dimension reduction and feature selection will be applied. Most ML procedures further require parameter tuning, a sort of optimization of parameters that cannot be estimated directly from the data (e.g., number of trees to be used in a Random Forest). When the entire ML pipeline is fitted on the training data, the outcome of the test data is predicted. Since we know the true outcome of the test data, this allows us to evaluate our established prediction model. Finally, well-performing models provide an idea of the most important risk factors, by observing which factors have the largest influence on these models. All analyses were performed in Python using the XGBoost application.

Recruitment
Recruitment status
Not yet recruiting
Date of first participant enrolment
Anticipated
1/09/2022
Actual
Date of last participant enrolment
Anticipated
1/11/2022
Actual
Date of last data collection
Anticipated
30/06/2023
Actual
Sample size
Target
114
Accrual to date
Final
Recruitment outside Australia
Country [1] 24836 0
Spain
State/province [1] 24836 0
Sevilla
Country [2] 24837 0
Portugal
State/province [2] 24837 0
Lisbon

Funding & Sponsors
Funding source category [1] 311496 0
University
Name [1] 311496 0
University of Seville
Country [1] 311496 0
Spain
Primary sponsor type
University
Name
University of Seville
Address
C/ San Fernando s/n. E-41005, Seville (Spain)
Country
Spain
Secondary sponsor category [1] 312896 0
None
Name [1] 312896 0
Address [1] 312896 0
Country [1] 312896 0

Ethics approval
Ethics application status
Submitted, not yet approved
Ethics committee name [1] 310956 0
University of Seville
Ethics committee address [1] 310956 0
Ethics committee country [1] 310956 0
Spain
Date submitted for ethics approval [1] 310956 0
31/05/2022
Approval date [1] 310956 0
Ethics approval number [1] 310956 0

Summary
Brief summary
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 119490 0
Prof Borja Sañudo
Address 119490 0
University of Seville. C/ San Fernando s/n. E-41005, Seville (Spain)
Country 119490 0
Spain
Phone 119490 0
+34652387090
Fax 119490 0
Email 119490 0
[email protected]
Contact person for public queries
Name 119491 0
Borja Sañudo
Address 119491 0
University of Seville. C/ San Fernando s/n. E-41005, Seville (Spain)
Country 119491 0
Spain
Phone 119491 0
+34652387090
Fax 119491 0
Email 119491 0
[email protected]
Contact person for scientific queries
Name 119492 0
Borja Sañudo
Address 119492 0
University of Seville. C/ San Fernando s/n. E-41005, Seville (Spain)
Country 119492 0
Spain
Phone 119492 0
+34652387090
Fax 119492 0
Email 119492 0
[email protected]

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
Yes
What data in particular will be shared?
Individual participant data underlying published results only.
When will data be available (start and end dates)?
Immediately following publication, no end date.
Available to whom?
Only researchers who provide a methodologically sound proposal.
Available for what types of analyses?
Any purpose.
How or where can data be obtained?
Principal Investigator ([email protected])


What supporting documents are/will be available?

No Supporting Document Provided



Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
No additional documents have been identified.