Estimating energy expenditure from accelerometer data in healthy adults and patients with type 2 diabetes

Compensatory mechanisms from different exercise intensities in type 2 diabetes: a secondary analysis of a 1-year randomized controlled trial

AIMS

This investigation aimed to determine the effect of different intensities of training on non-exercise physical activity (NEPA) and estimated thermogenesis (NEAT) from a 1-year exercise randomized controlled trial (RCT) in individuals with type 2 diabetes mellitus (T2DM) on non-training days. Additionally, changes in NEPA and estimated NEAT in those who failed (low-responders) or succeeded (high-responders) in attaining exercise-derived clinically meaningful reductions in body weight (BW) and fat mass (FM) (i.e., 6% for FM and 3% for BW) was assessed.

METHODS

Individuals with T2DM (n = 80) were enrolled in a RCT with three groups: resistance training combined with moderate-intensity continuous training (MICT) or high-intensity interval training (HIIT) and a control group. Of the 80 participants, 56 (completed data) were considered for this secondary analysis. NEPA and estimated NEAT were obtained by accelerometry and body composition through dual-energy X-ray absorptiometry.

RESULTS

After adjustments, no time*group interactions were found for estimated NEAT in the MICT (β = - 5.33, p = 0.366) and HIIT (β = - 5.70, p = 0.283), as well as for NEPA in the MICT (β = - 452.83, p = 0.833) and HIIT (β = - 2770.76, p = 0.201), when compared to controls. No compensatory changes in NEPA and estimated NEAT were observed when considering both low-responders and high-responders to FM and BW when compared to controls.

CONCLUSIONS

Both MICT and HIIT did not result in any compensatory changes in estimated NEAT and NEPA with the intervention on non-training days. Moreover, no changes in estimated NEAT and NEPA were found when categorizing our participants as low-responders and high-responders to FM and BW when compared to controls. Trial registration clinicaltrials.gov ID. NCT03144505.

Energy Expenditure Estimation of Tabata by Combining Acceleration and Heart Rate

Tabata training plays an important role in health promotion. Effective monitoring of exercise energy expenditure is an important basis for exercisers to adjust their physical activities to achieve exercise goals. The input of acceleration combined with heart rate data and the application of machine learning algorithm are expected to improve the accuracy of EE prediction. This study is based on acceleration and heart rate to build linear regression and back propagate neural network prediction model of Tabata energy expenditure, and compare the accuracy of the two models. Participants (n = 45; Mean age: 21.04 ± 2.39 years) were randomly assigned to the modeling and validation data set in a 3:1 ratio. Each participant simultaneously wore four accelerometers (dominant hand, non-dominant hand, right hip, right ankle), a heart rate band and a metabolic measurement system to complete Tabata exercise test. After obtaining the test data, the correlation of the variables is calculated and passed to linear regression and back propagate neural network algorithms to predict energy expenditure during exercise and interval period. The validation group was entered into the model to obtain the predicted value and the prediction effect was tested. Bland-Alterman test showed two models fell within the consistency interval. The mean absolute percentage error of back propagate neural network was 12.6%, and linear regression was 14.7%. Using both acceleration and heart rate for estimation of Tabata energy expenditure is effective, and the prediction effect of back propagate neural network algorithm is better than linear regression, which is more suitable for Tabata energy expenditure monitoring.

A recurrent neural network architecture to model physical activity energy expenditure in older people

Through the quantification of physical activity energy expenditure (PAEE), health care monitoring has the potential to stimulate vital and healthy ageing, inducing behavioural changes in older people and linking these to personal health gains. To be able to measure PAEE in a health care perspective, methods from wearable accelerometers have been developed, however, mainly targeted towards younger people. Since elderly subjects differ in energy requirements and range of physical activities, the current models may not be suitable for estimating PAEE among the elderly. Furthermore, currently available methods seem to be either simple but non-generalizable or require elaborate (manual) feature construction steps. Because past activities influence present PAEE, we propose a modeling approach known for its ability to model sequential data, the recurrent neural network (RNN). To train the RNN for an elderly population, we used the growing old together validation (GOTOV) dataset with 34 healthy participants of 60 years and older (mean 65 years old), performing 16 different activities. We used accelerometers placed on wrist and ankle, and measurements of energy counts by means of indirect calorimetry. After optimization, we propose an architecture consisting of an RNN with 3 GRU layers and a feedforward network combining both accelerometer and participant-level data. Our efforts included switching mean to standard deviation for down-sampling the input data and combining temporal and static data (person-specific details such as age, weight, BMI). The resulting architecture produces accurate PAEE estimations while decreasing training input and time by a factor of 10. Subsequently, compared to the state-of-the-art, it is capable to integrate longer activity data which lead to more accurate estimations of low intensity activities EE. It can thus be employed to investigate associations of PAEE with vitality parameters of older people related to metabolic and cognitive health and mental well-being.

Chronic hyperglycemia, hypercholesterolemia, and metabolic syndrome are associated with risk of tendon injury

Tendon injury is a considerable problem affecting both physically active and sedentary people. The aim of this study was to examine the relationship between markers for metabolic disorders (hyperglycemia, hypercholesterolemia, and metabolic syndrome) and the risk of developing tendon injuries requiring referral to a hospital. The Copenhagen City Heart Study is a prospective study of diabetic and non-diabetic individuals from the Danish general population with different physical activity levels. The cohort was followed for 3 years via national registers with respect to tendon injuries. Data from 5856 individuals (median age 62 years) were included. The overall incidence of tendon injury in both upper and lower extremities that required an out-patient or in-house visit to a hospital was ~5.7/1000 person years. Individuals with elevated HbA1c (glycated hemoglobin) even in the prediabetic range (HbA1c>5.7%) had a ~3 times higher risk of tendon injury in the lower extremities only, as compared to individuals with normal HbA1C levels. Hypercholesterolemia (total cholesterol>5 mmol/L) increased risk of tendon injury in the upper extremities by ~1.5 times, and individuals with metabolic syndrome had ~2.5 times higher risk of tendon injury in both upper and lower extremities. In conclusion, these data demonstrate for the first time in a large cohort with different physical activity levels that the indicators for metabolic syndrome are a powerful systemic determinant of tendon injury, and two of its components, hyperglycemia and hypercholesterolemia, each independently make tendons susceptible for damage and injury.