Cardiorespiratory fitness estimation in free-living using wearable sensors

Bibliometric Review of the Step Test: A Comprehensive Analysis of Research Trends and Development

BACKGROUND

The step test provides valuable information on cardiorespiratory parameters such as maximal oxygen uptake and heart rate. Cardiorespiratory capacity is critical to health-related fitness, with heart rate recovery after exercise serving as a predictor of mortality risk.

MAIN BODY

The primary objective of this review was to identify trends, key contributors, and emerging themes in the step test literature through 2023 using the Web of Science Core Collection. Bibliometric data extraction and analysis were performed using a dedicated bibliometric software (VOSviewer). The analysis showed continued interest through 2021. The research categories highlight the multidisciplinary nature of the step test, covering cardiovascular systems, respiratory systems, sports sciences, and medicine. It has gained global attention, with 31 countries involved, with Brazil and the United States leading the way. The diversity of contributing nations is increasing, reflecting a growing global interest. With 111 journals involved, such as Respiratory Care and Medicine and Science in Sports and Exercise, step test research is spread across the academic landscape. With 761 contributing researchers, there is a collaborative and diverse community. The top 10 institutions, including the University of Alabama System and Monash University, illustrate the variety of settings in which step test studies are conducted. Step test studies span multiple disciplines, underscoring their adaptability. The clusters identified in this bibliometric analysis of the step test literature guide future research, suggesting avenues for refining protocols, exploring health implications, optimizing tests for specific conditions such as chronic obstructive pulmonary disease, and adapting step tests in diverse populations.

CONCLUSIONS

Practical implications highlight the role of the step test in cardiovascular risk assessment, fitness monitoring, and rehabilitation. This broad review underscores the relevance of the step test in diverse settings, reflecting its adaptability and ease of application across occupational and clinical settings.

Wearable Sensors as a Preoperative Assessment Tool: A Review

Surgery is a common first-line treatment for many types of disease, including cancer. Mortality rates after general elective surgery have seen significant decreases whilst postoperative complications remain a frequent occurrence. Preoperative assessment tools are used to support patient risk stratification but do not always provide a precise and accessible assessment. Wearable sensors (WS) provide an accessible alternative that offers continuous monitoring in a non-clinical setting. They have shown consistent uptake across the perioperative period but there has been no review of WS as a preoperative assessment tool. This paper reviews the developments in WS research that have application to the preoperative period. Accelerometers were consistently employed as sensors in research and were frequently combined with photoplethysmography or electrocardiography sensors. Pre-processing methods were discussed and missing data was a common theme; this was dealt with in several ways, commonly by employing an extraction threshold or using imputation techniques. Research rarely processed raw data; commercial devices that employ internal proprietary algorithms with pre-calculated heart rate and step count were most commonly employed limiting further feature extraction. A range of machine learning models were used to predict outcomes including support vector machines, random forests and regression models. No individual model clearly outperformed others. Deep learning proved successful for predicting exercise testing outcomes but only within large sample-size studies. This review outlines the challenges of WS and provides recommendations for future research to develop WS as a viable preoperative assessment tool.

Human-centred artificial intelligence for mobile health sensing: challenges and opportunities

Advances in wearable sensing and mobile computing have enabled the collection of health and well-being data outside of traditional laboratory and hospital settings, paving the way for a new era of mobile health. Meanwhile, artificial intelligence (AI) has made significant strides in various domains, demonstrating its potential to revolutionize healthcare. Devices can now diagnose diseases, predict heart irregularities and unlock the full potential of human cognition. However, the application of machine learning (ML) to mobile health sensing poses unique challenges due to noisy sensor measurements, high-dimensional data, sparse and irregular time series, heterogeneity in data, privacy concerns and resource constraints. Despite the recognition of the value of mobile sensing, leveraging these datasets has lagged behind other areas of ML. Furthermore, obtaining quality annotations and ground truth for such data is often expensive or impractical. While recent large-scale longitudinal studies have shown promise in leveraging wearable sensor data for health monitoring and prediction, they also introduce new challenges for data modelling. This paper explores the challenges and opportunities of human-centred AI for mobile health, focusing on key sensing modalities such as audio, location and activity tracking. We discuss the limitations of current approaches and propose potential solutions.

Longitudinal cardio-respiratory fitness prediction through wearables in free-living environments

Cardiorespiratory fitness is an established predictor of metabolic disease and mortality. Fitness is directly measured as maximal oxygen consumption (VO2max), or indirectly assessed using heart rate responses to standard exercise tests. However, such testing is costly and burdensome because it requires specialized equipment such as treadmills and oxygen masks, limiting its utility. Modern wearables capture dynamic real-world data which could improve fitness prediction. In this work, we design algorithms and models that convert raw wearable sensor data into cardiorespiratory fitness estimates. We validate these estimates' ability to capture fitness profiles in free-living conditions using the Fenland Study (N=11,059), along with its longitudinal cohort (N = 2675), and a third external cohort using the UK Biobank Validation Study (N = 181) who underwent maximal VO2max testing, the gold standard measurement of fitness. Our results show that the combination of wearables and other biomarkers as inputs to neural networks yields a strong correlation to ground truth in a holdout sample (r = 0.82, 95CI 0.80-0.83), outperforming other approaches and models and detects fitness change over time (e.g., after 7 years). We also show how the model's latent space can be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment. These results demonstrate the value of wearables for fitness estimation that today can be measured only with laboratory tests.

Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View

BACKGROUND

Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention.

OBJECTIVE

This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology.

METHODS

We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as "wearables," "machine learning," and "cardiovascular disease." Methodologies were categorized and analyzed according to machine learning-based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready).

RESULTS

After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies' ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies' models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes.

CONCLUSIONS

Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.

Development of a New Submaximal Walk Test to Predict Maximal Oxygen Consumption in Healthy Adults

The aim of the study was to develop a simple submaximal walk test protocol and equation using heart rate (HR) response variables to predict maximal oxygen consumption (VO2max). A total of 60 healthy adults were recruited to test the validity of 3 min walk tests (3MWT). VO2max and HR responses during the 3MWTs were measured. Multiple regression analysis was used to develop prediction equations. As a result, HR response variables including resting HR and HR during walking and recovery at two different cadences were significantly correlated with VO2max. The equations developed using multiple regression analyses were able to predict VO2max values (r = 0.75-0.84; r2 = 0.57-0.70; standard error of estimate (SEE) = 4.80-5.25 mL/kg/min). The equation that predicted VO2max the best was at the cadence of 120 steps per minute, which included sex; age; height; weight; body mass index; resting HR; HR at 1 min, 2 min and 3 min; HR recovery at 1 min and 2 min; and other HR variables calculated based on these measured HR variables (r = 0.84; r2 = 0.70; SEE = 4.80 mL/kg/min). In conclusion, the 3MWT developed in this study is a safe and practical submaximal exercise protocol for healthy adults to predict VO2max accurately, even compared to the well-established submaximal exercise protocols, and merits further investigation.

Wearable Monitoring and Interpretable Machine Learning Can Objectively Track Progression in Patients during Cardiac Rehabilitation

Cardiovascular diseases (CVD) are often characterized by their multifactorial complexity. This makes remote monitoring and ambulatory cardiac rehabilitation (CR) therapy challenging. Current wearable multimodal devices enable remote monitoring. Machine learning (ML) and artificial intelligence (AI) can help in tackling multifaceted datasets. However, for clinical acceptance, easy interpretability of the AI models is crucial. The goal of the present study was to investigate whether a multi-parameter sensor could be used during a standardized activity test to interpret functional capacity in the longitudinal follow-up of CR patients. A total of 129 patients were followed for 3 months during CR using 6-min walking tests (6MWT) equipped with a wearable ECG and accelerometer device. Functional capacity was assessed based on 6MWT distance (6MWD). Linear and nonlinear interpretable models were explored to predict 6MWD. The t-distributed stochastic neighboring embedding (t-SNE) technique was exploited to embed and visualize high dimensional data. The performance of support vector machine (SVM) models, combining different features and using different kernel types, to predict functional capacity was evaluated. The SVM model, using chronotropic response and effort as input features, showed a mean absolute error of 42.8 m (±36.8 m). The 3D-maps derived using the t-SNE technique visualized the relationship between sensor-derived biomarkers and functional capacity, which enables tracking of the evolution of patients throughout the CR program. The current study showed that wearable monitoring combined with interpretable ML can objectively track clinical progression in a CR population. These results pave the road towards ambulatory CR.

Estimating Running Performance Combining Non-invasive Physiological Measurements and Training Patterns in Free-Living

In this work, we use data acquired longitudinally, in free-living, to provide accurate estimates of running performance. In particular, we used the HRV4Training app and integrated APIs (e.g. Strava and TrainingPeaks) to acquire different sets of parameters, either via user input, morning measurements of resting physiology, or running workouts to estimate running 10 km running time. Our unique dataset comprises data on 2113 individuals, from world class triathletes to individuals just getting started with running, and it spans over 2 years. Analyzed predictors of running performance include anthropometrics, resting heart rate (HR) and heart rate variability (HRV), training physiology (heart rate during exercise), training volume, training patterns (training intensity distribution over multiple workouts, or training polarization) and previous performance. We build multiple linear regression models and highlight the relative impact of different predictors as well as trade-offs between the amount of data required for features extraction and the models accuracy in estimating running performance (10 km time). Cross-validated root mean square error (RMSE) for 10 km running time estimation was 2.6 minutes (4% mean average error, MAE, 0.87 R²), an improvement of 58% with respect to estimation models using anthropometrics data only as predictors. Finally, we provide insights on the relationship between training and performance, including further evidence of the importance of training volume and a polarized training approach to improve performance.

Estimating Maximal Oxygen Uptake From Daily Activity Data Measured by a Watch-Type Fitness Tracker: Cross-Sectional Study

BACKGROUND

Cardiorespiratory fitness (CRF), an important index of physical fitness, is the ability to inhale and provide oxygen to the exercising muscle. However, despite its importance, the current gold standard for measuring CRF is impractical, requiring maximal exercise from the participants.

OBJECTIVE

This study aimed to develop a convenient and practical estimation model for CRF using data collected from daily life with a wristwatch-type device.

METHODS

A total of 191 subjects, aged 20 to 65 years, participated in this study. Maximal oxygen uptake (VO2 max), a standard measure of CRF, was measured with a maximal exercise test. Heart rate (HR) and physical activity data were collected using a commercial wristwatch-type fitness tracker (Fitbit; Fitbit Charge; Fitbit) for 3 consecutive days. Maximal activity energy expenditure (aEEmax) and slope between HR and physical activity were calculated using a linear regression. A VO2 max estimation model was built using multiple linear regression with data on age, sex, height, percent body fat, aEEmax, and the slope. The result was validated with 2 different cross-validation methods.

RESULTS

aEEmax showed a moderate correlation with VO2 max (r=0.50). The correlation coefficient for the multiple linear regression model was 0.81, and the SE of estimate (SEE) was 3.518 mL/kg/min. The regression model was cross-validated through the predicted residual error sum of square (PRESS). The PRESS correlation coefficient was 0.79, and the PRESS SEE was 3.667 mL/kg/min. The model was further validated by dividing it into different subgroups and calculating the constant error (CE) where a low CE showed that the model does not significantly overestimate or underestimate VO2 max.

CONCLUSIONS

This study proposes a CRF estimation method using data collected by a wristwatch-type fitness tracker without any specific protocol for a wide range of the population.

Cross-Modal Health State Estimation

Individuals create and consume more diverse data about themselves today than any time in history. Sources of this data include wearable devices, images, social media, geo-spatial information and more. A tremendous opportunity rests within cross-modal data analysis that leverages existing domain knowledge methods to understand and guide human health. Especially in chronic diseases, current medical practice uses a combination of sparse hospital based biological metrics (blood tests, expensive imaging, etc.) to understand the evolving health status of an individual. Future health systems must integrate data created at the individual level to better understand health status perpetually, especially in a cybernetic framework. In this work we fuse multiple user created and open source data streams along with established biomedical domain knowledge to give two types of quantitative state estimates of cardiovascular health. First, we use wearable devices to calculate cardiorespiratory fitness (CRF), a known quantitative leading predictor of heart disease which is not routinely collected in clinical settings. Second, we estimate inherent genetic traits, living environmental risks, circadian rhythm, and biological metrics from a diverse dataset. Our experimental results on 24 subjects demonstrate how multi-modal data can provide personalized health insight. Understanding the dynamic nature of health status will pave the way for better health based recommendation engines, better clinical decision making and positive lifestyle changes.

Longitudinal Walking Analysis in Hemiparetic Patients Using Wearable Motion Sensors: Is There Convergence Between Body Sides?

Background: Longitudinal movement parameter analysis of hemiparetic patients over several months could reveal potential recovery trends and help clinicians adapting therapy strategies to maximize recovery outcome. Wearable sensors offer potential for day-long movement recordings in realistic rehabilitation settings including activities of daily living, e.g., walking. The measurement of walking-related movement parameters of affected and non-affected body sides are of interest to determine mobility and investigate recovery trends. Methods: By comparing movement of both body sides, recovery trends across the rehabilitation duration were investigated. We derived and validated selected walking segments from free-living, day-long movement by using rules that do not require data-based training or data annotations. Automatic stride segmentation using peak detection was applied to walking segments. Movement parameters during walking were extracted, including stride count, stride duration, cadence, and sway. Finally, linear regression models over each movement parameter were derived to forecast the moment of convergence between body sides. Convergence points were expressed as duration and investigated in a patient observation study. Results: Convergence was analyzed in walking-related movement parameters in an outpatient study including totally 102 full-day recordings of inertial movement data from 11 hemiparetic patients. The recordings were performed over several months in a day-care centre. Validation of the walking extraction method from sensor data yielded sensitivities up to 80 % and specificity above 94 % on average. Comparison of automatically and manually derived movement parameters showed average relative errors below 6 % between affected and non-affected body sides. Movement parameter variability within and across patients was observed and confirmed by case reports, reflecting individual patient behavior. Conclusion: Convergence points were proposed as intuitive metric, which could facilitate training personalization for patients according to their individual needs. Our continuous movement parameter extraction and analysis, was feasible for realistic, day-long recordings without annotations. Visualizations of movement parameter trends and convergence points indicated that individual habits and patient therapies were reflected in walking and mobility. Context information of clinical case reports supported trend and convergence interpretation. Inconsistent convergence point estimation suggested individually varying deficiencies. Long-term recovery monitoring using convergence points could support patient-specific training strategies in future remote rehabilitation.

A study on nonlinear estimation of submaximal effort tolerance based on the generalized MET concept and the 6MWT in pulmonary rehabilitation

BACKGROUND

The six-minute walk test (6MWT) is considered to be a simple and inexpensive tool for the assessment of functional tolerance of submaximal effort. The aim of this work was 1) to background the nonlinear nature of the energy expenditure process due to physical activity, 2) to compare the results/scores of the submaximal treadmill exercise test and those of 6MWT in pulmonary patients and 3) to develop nonlinear mathematical models relating the two.

METHODS

The study group included patients with the COPD. All patients were subjected to a submaximal exercise test and a 6MWT. To develop an optimal mathematical solution and compare the results of the exercise test and the 6MWT, the least squares and genetic algorithms were employed to estimate parameters of polynomial expansion and piecewise linear models.

RESULTS

Mathematical analysis enabled to construct nonlinear models for estimating the MET result of submaximal exercise test based on average walk velocity (or distance) in the 6MWT.

CONCLUSIONS

Submaximal effort tolerance in COPD patients can be effectively estimated from new, rehabilitation-oriented, nonlinear models based on the generalized MET concept and the 6MWT.

The Double Layer Methodology and the Validation of Eigenbehavior Techniques Applied to Lifestyle Modeling

A novel methodology, the double layer methodology (DLM), for modeling an individual’s lifestyle and its relationships with health indicators is presented. The DLM is applied to model behavioral routines emerging from self-reports of daily diet and activities, annotated by 21 healthy subjects over 2 weeks. Unsupervised clustering on the first layer of the DLM separated our population into two groups. Using eigendecomposition techniques on the second layer of the DLM, we could find activity and diet routines, predict behaviors in a portion of the day (with an accuracy of 88% for diet and 66% for activity), determine between day and between individual similarities, and detect individual’s belonging to a group based on behavior (with an accuracy up to 64%). We found that clustering based on health indicators was mapped back into activity behaviors, but not into diet behaviors. In addition, we showed the limitations of eigendecomposition for lifestyle applications, in particular when applied to noisy and sparse behavioral data such as dietary information. Finally, we proposed the use of the DLM for supporting adaptive and personalized recommender systems for stimulating behavior change.