Contraction assessment of abdominal muscles using automated segmentation designed for wearable ultrasound applications.

PURPOSE: Wearable ultrasound devices can be used to continuously monitor muscle activity. One possible application is to provide real-time feedback during physiotherapy, to show a patient whether an exercise is performed correctly. Algorithms which automatically analyze the data can be of importance to overcome the need for manual assessment and annotations and speed up evaluations especially when considering real-time video sequences. They even could be used to present feedback in an understandable manner to patients in a home-use scenario. The following work investigates three deep learning based segmentation approaches for abdominal muscles in ultrasound videos during a segmental stabilizing exercise. The segmentations are used to automatically classify the contraction state of the muscles. METHODS: The first approach employs a simple 2D network, while the remaining two integrate the time information from the videos either via additional tracking or directly into the network architecture. The contraction state is determined by comparing measures such as muscle thickness and center of mass between rest and exercise. A retrospective analysis is conducted but also a real-time scenario is simulated, where classification is performed during exercise. RESULTS: Using the proposed segmentation algorithms, 71% of the muscle states are classified correctly in the retrospective analysis in comparison to 90% accuracy with manual reference segmentation. For the real-time approach the majority of given feedback during exercise is correct when the retrospective analysis had come to the correct result, too. CONCLUSION: Both retrospective and real-time analysis prove to be feasible. While no substantial differences between the algorithms were observed regarding classification, the networks incorporating the time information showed temporally more consistent segmentations. Limitations of the approaches as well as reasons for failing cases in segmentation, classification and real-time assessment are discussed and requirements regarding image quality and hardware design are derived.

Virtual reality exergame in older patients with hypertension: a preliminary study to determine load intensity and blood pressure.

BACKGROUND: Lifestyle changes and physical activity can make an important contribution to reducing the risk factor for high blood pressure (BP). Whether virtual reality (VR) exergames are also appropriate and make a positive contribution to the reduction of BP has not yet been sufficiently investigated. Therefore, the aim of the study was to gain knowledge of the load intensities to be achieved during a VR exergame and to examine the short-term effects on BP. METHODS: For the preliminary study, 22 participants with hypertension over the age of 65 years were analyzed. The study took place in a mobile laboratory truck. All participants visited on two occasions. During visit 1, VR strength endurance training (VR-SET) and during visit 2, VR endurance training (VR-ET) was performed. Each VR session lasted approximately 25 min and was of a moderate intensity. Heart rate (HR) was measured across the entire session, as well as BP before and after the VR exergame. The Rating of Perceived Exertion (RPE) and task load using NASA Task Load Index were determined after each VR session. Included in the statistical analysis were the Shapiro-Wilk test, the paired t-test, the Wilcoxon test and ANOVA for repeated measures. RESULTS: During the "main part" (p < .001), at the "end" (p = .002) and for the "maximum HR" (p < .001), significant load differences between both VR sessions could be determined. In addition, significantly more participants in the VR-SET group achieved a moderate load intensity of at least 40% of heart rate reserve (p = .014). Regarding RPE, participants rated their subjectively perceived exertion significantly higher in the VR-SET than in the VR-ET (p = .028). Systolic BP decreased significantly in both VR sessions when compared before VR session and 5 min after VR session (p = .015; p = .003), as well as before VR session and 10 min after VR session (p = .018; p < .001). CONCLUSIONS: An individual moderate load intensity of 40% can be reached during VR-SET. In addition, a positive short-term effect of the VR exergame on BP behavior (postexercise hypotension) was observed after both VR sessions. The preliminary results indicate that a VR exergaming could lead to blood pressure lowering effects for older people with hypertension. TRIAL REGISTRATION: The study was registered in the German Clinical Trials Register (DRKS-ID: DRKS00022881, 07/09/2020, https://drks.de/search/de/trial/DRKS00022881 ).

Needs and Attitudes of Older Chronic Back Pain Patients towards a Wearable for Ultrasound Biofeedback during Stabilization Exercises: A Qualitative Analysis.

Chronic back pain has a high prevalence, especially in older adults, and seriously affects sufferers' quality of life. Segmental stabilization exercise (SSE) is often used during physiotherapy to enhance core stability. The execution of SSE requires the selective contraction of deep abdominal and back muscles. Motor learning can be supported using ultrasound imaging as visual biofeedback. ULTRAWEAR is a mobile ultrasound system that provides deep learning-based biofeedback on SSE execution, which is currently under development. We interviewed 15 older chronic back pain patients (CBPPs) to investigate their pain management behavior, experience with SSE, as well as their needs and requirements for ULTRAWEAR. We also gathered information about future-usage scenarios. CBPPs reported a high willingness to use the system as a feedback tool both in physiotherapeutic practices and at home. The automated detection and evaluation of muscle contraction states was highlighted as a major benefit of the system compared to the more subjective feedback provided by traditional methods such as palpation. The system to be developed was perceived as a helpful solution to support learning about SSE.

Virtual reality exergame for supplementing multimodal pain therapy in older adults with chronic back pain: a randomized controlled pilot study.

Immersive Virtual Reality (VR) with head-mounted displays (HMD) can be a promising tool for increasing adherence to exercise in older adults. However, there is little known about the effectiveness of an interactive multimodal therapy in VR for older chronic back pain (CBP) patients. The aim of the exploratory randomized controlled trial was to examine the preliminary effectiveness of a VR multimodal therapy for older adults with CBP in a laboratory setting over a period of four weeks. The intervention group (IG; n = 11) received a multimodal pain therapy in VR (movement therapy and psychoeducation) and the control group (CG; n = 11) received a conventional multimodal pain therapy (chair-based group exercises and psychoeducation in a group setting). Although the VR therapy (IG) did not reach the pain intensity reduction of the CG (IG: MD = 0.64, p = .535; CG: MD = 1.64, p = .07), both groups showed a reduction in pain intensity on the Numeric Rating Scale. The functional capacity in the IG improved from Visit 1, x ¯ = 73.11% to Visit 2, x ¯ = 81.82% (MD = 8.71%; p = .026). In the changes of fear avoidance beliefs and general physical and mental health, no significance was achieved in either group. Although the IG did not reach a significant pain intensity reduction compared to the CG, the results of the present study showed that a pain intensity reduction can be achieved with the current VR application.

[Ethical implications in the development of functional training in mixed and augmented reality environments to treat hypertension in old age: A qualitative content analysis]. / Ethische Implikationen in der Entwicklung eines funktionellen Trainings in einer Mixed- und Augmented Reality Umgebungen zur Behandlung von Hypertonie im Alter: Eine qualitative Inhaltsanalyse.

BACKGROUND: E-Health is of increasing importance in ensuring demand-oriented health care. In addition to technical feasibility, issues concerning the normative requirements for their use are growing. This paper discusses the ethical, legal and social implications of the use of mixed reality (MR) and augmented reality (AR) technologies in the therapy of elderly people with hypertension. It is based on the results of a study conducted as a part of the BMBF project BewARe. METHODS: In the context of the above-mentioned background, an expert workshop was held with various stakeholders in an early phase of the BewARe project in accordance with the MEESTAR model, in which ethical, social and legal requirements for the development and use of AR/MR technologies were anticipated. The results of the workshop were subsequently evaluated using content analysis. RESULTS: Content analysis identified eight main challenges for the development and use of AR/MR technologies in the therapy of elderly people with hypertension: ethical challenges for the decision-making and action capacity of older users (1), stereotyping (2), user-oriented development and implementation (3), data protection (4), support (5), health risks (6), social participation (7), and the need for an integrative approach (8). DISCUSSION: In line with other studies, it can be shown that orientation towards medical guidelines and behavioral principles is essential to promote acceptance and adherence among end users and to minimize potential health risks. In addition, end users should be more strongly involved in the development process to overcome existing user stereotypes and establish qualification strategies for health-promoting use. Finally, legal and health economic framework conditions must be created to ensure data security and sustainable application concepts. CONCLUSION: For a successful diffusion of AR/MR applications in health care, a holistic implementation concept is required which must involve various groups of social actors. In this context, the article discusses eight main challenges that can be understood as current challenges in this process.

Observational study in cardiac rehabilitation groups phase III: a comparison of perceived and measured training intensity during a moderate-intensity workout.

BACKGROUND: During the last 25 years, the absolute number of cases of cardiovascular disease has increased in Europe. The goal in cardiac rehabilitation (CR) groups phase III is to motivate participants to demonstrate exercises independently of the group and self-reliant in long-term. In this context, it is of great importance to teach participants the appropriate training intensity. Adjusting the intensity of the training in CR groups is essential in order to avoid the dangers of overexertion and undertraining. AIM: This study aimed to examine whether participants in CR groups could correctly assess their exertion and thus achieve their predefined training intensity. DESIGN: Observational study. SETTING: The setting of the study was an outpatient rehabilitation center. POPULATION: Forty-one people from CR groups phase III, with cardiovascular diseases, were included in the study. METHODS: The training focused on moderate-intensity activity. The Borg Scale was used to evaluate how participants rated their exertion. The heart rate was recorded with the Polar M600 during the entire training period to compare it with the estimated exertion. RESULTS: Sixty-five percent (65%) of the participants was trained within their prescribed training intensity. However, they rated the perceived exertion significantly higher than the measured HR (P<0.001). The difference between target training HR and measured HR was also significant (P=0.008). There were significant differences between the groups of moderate-intensity endurance training and moderate-intensity strength endurance training (P=0.002). CONCLUSIONS: The participants in the CR groups could assess their own exertion moderately well. On the one hand, there were difficulties in accurately estimating the perceived exertion compared to the actual exertion. On the other hand, overloading and underloading were hardly detected. CLINICAL REHABILITATION IMPACT: The perception of exertion must be improved by knowing one's own training heart rate and intensity. Therefore, wearables such as smartwatches could be useful monitoring aids for CR groups to check if the predefined training intensity will be reached.

Accuracy of Monocular Two-Dimensional Pose Estimation Compared With a Reference Standard for Kinematic Multiview Analysis: Validation Study.

BACKGROUND: Expensive optoelectronic systems, considered the gold standard, require a laboratory environment and the attachment of markers, and they are therefore rarely used in everyday clinical practice. Two-dimensional (2D) human pose estimations for clinical purposes allow kinematic analyses to be carried out via a camera-based smartphone app. Since clinical specialists highly depend on the validity of information, there is a need to evaluate the accuracy of 2D pose estimation apps. OBJECTIVE: The aim of the study was to investigate the accuracy of the 2D pose estimation of a mobility analysis app (Lindera-v2), using the PanopticStudio Toolbox data set as a reference standard. The study aimed to assess the differences in joint angles obtained by 2D video information generated with the Lindera-v2 algorithm and the reference standard. The results can provide an important assessment of the adequacy of the app for clinical use. METHODS: To evaluate the accuracy of the Lindera-v2 algorithm, 10 video sequences were analyzed. Accuracy was evaluated by assessing a total of 30,000 data pairs for each joint (10 joints in total), comparing the angle data obtained from the Lindera-v2 algorithm with those of the reference standard. The mean differences of the angles were calculated for each joint, and a comparison was made between the estimated values and the reference standard values. Furthermore, the mean absolute error (MAE), root mean square error, and symmetric mean absolute percentage error of the 2D angles were calculated. Agreement between the 2 measurement methods was calculated using the intraclass correlation coefficient (ICC[A,2]). A cross-correlation was calculated for the time series to verify whether there was a temporal shift in the data. RESULTS: The mean difference of the Lindera-v2 data in the right hip was the closest to the reference standard, with a mean value difference of -0.05° (SD 6.06°). The greatest difference in comparison with the baseline was found in the neck, with a measurement of -3.07° (SD 6.43°). The MAE of the angle measurement closest to the baseline was observed in the pelvis (1.40°, SD 1.48°). In contrast, the largest MAE was observed in the right shoulder (6.48°, SD 8.43°). The medians of all acquired joints ranged in difference from 0.19° to 3.17° compared with the reference standard. The ICC values ranged from 0.951 (95% CI 0.914-0.969) in the neck to 0.997 (95% CI 0.997-0.997) in the left elbow joint. The cross-correlation showed that the Lindera-v2 algorithm had no temporal lag. CONCLUSIONS: The results of the study indicate that a 2D pose estimation by means of a smartphone app can have excellent agreement compared with a validated reference standard. An assessment of kinematic variables can be performed with the analyzed algorithm, showing only minimal deviations compared with data from a massive multiview system.

Movement Training in Augmented Reality for Older Adults with Essential Hypertension: A Qualitative Study Determining Training Requirements.

Objective: Physical activity is a key component of maintaining and promoting the health of older people. New technologies from the fields of augmented reality (AR) and virtual reality (VR) could help to increase the motivation of older people and positively influence their health behavior. To be able to respond specifically to the needs and expectations when developing an exergame for seniors with hypertension, the aim of this study was to determine the requirements for movement training within an intelligent AR system. Materials and Methods: Eleven seniors aged 65 years or older with essential hypertension and five experts from the cardiological field were interviewed using a semistructured interview and were examined with a task-based approach. In the task-based application, both VR and AR demos were used. Results: The results presented in this article refer to requirements for the development of a movement training within an exergame for older adults with hypertension. We found that on the one hand, group effects and, on the other, natural environments have a high motivational character. Furthermore, communication and interaction represent a decisive criterion for participation during exercises. Regarding the training concept the experts, in particular, recommended endurance-related activities. In addition, vital data and performance monitoring should be used to evaluate success, to signal warnings and to provide additional motivation. Conclusions: This requirement analysis enabled 45 requirements to be obtained, which will be taken into account in the training application of an AR system and in the development of an interactive multiuser AR exergame.

Virtual reality in pain therapy: a requirements analysis for older adults with chronic back pain.

BACKGROUND: Today immersive environments such as Virtual Reality (VR) offer new opportunities for serious gaming in exercise therapy and psychoeducation. Chronic back pain (CBP) patients could benefit from exergames in VR. The requirements in older CBP patients for a VR pain therapy have not yet been determined in studies. The aim of the study was to perform a requirements analysis for the user group of geriatric patients with CBP for a VR exergame. The objective was to find out the expectations, desires, preferences and barriers in order to collect them as requirements for this vulnerable group and to determine frameworks of therapy by physiotherapists and psychotherapists. METHODS: We conducted a requirements analysis through semi-structured interviews with 10 elderly participants with CBP. Furthermore, two focus groups were conducted with three physiotherapists and two psychotherapists to determine frameworks of therapy programs for the target group. The qualitative data were transcribed and examined through a structuring content analysis. Subsequently, the results of the analysis were prioritized by all participants of the study. RESULTS: The results of the requirements analysis indicate mandatory requirements for the overall system, hardware, software and gamification elements. The key requirements were target-group-specific applications of the VR exergame through e.g. individual briefing, user-friendly handling, inclusion of movement limitations, presentation of everyday scenarios in combination with biofeedback, age-appropriate feedback through praise and awards and a maximum exercise duration of 30 min and 15 min of relaxation. CONCLUSION: It should be possible to use the determined requirements productively to create user-friendly VR exergames that motivate elderly chronic back pain patients to perform exercises regularly. TRIAL REGISTRATION: The study is registered in the German Clinical Trials Register (DRKS-ID: DRKS00015294 12.10.2018).