Deciphering Optimal Radar Ensemble for Advancing Sleep Posture Prediction through Multiview Convolutional Neural Network (MVCNN) Approach Using Spatial Radio Echo Map (SREM).

Assessing sleep posture, a critical component in sleep tests, is crucial for understanding an individual's sleep quality and identifying potential sleep disorders. However, monitoring sleep posture has traditionally posed significant challenges due to factors such as low light conditions and obstructions like blankets. The use of radar technolsogy could be a potential solution. The objective of this study is to identify the optimal quantity and placement of radar sensors to achieve accurate sleep posture estimation. We invited 70 participants to assume nine different sleep postures under blankets of varying thicknesses. This was conducted in a setting equipped with a baseline of eight radars-three positioned at the headboard and five along the side. We proposed a novel technique for generating radar maps, Spatial Radio Echo Map (SREM), designed specifically for data fusion across multiple radars. Sleep posture estimation was conducted using a Multiview Convolutional Neural Network (MVCNN), which serves as the overarching framework for the comparative evaluation of various deep feature extractors, including ResNet-50, EfficientNet-50, DenseNet-121, PHResNet-50, Attention-50, and Swin Transformer. Among these, DenseNet-121 achieved the highest accuracy, scoring 0.534 and 0.804 for nine-class coarse- and four-class fine-grained classification, respectively. This led to further analysis on the optimal ensemble of radars. For the radars positioned at the head, a single left-located radar proved both essential and sufficient, achieving an accuracy of 0.809. When only one central head radar was used, omitting the central side radar and retaining only the three upper-body radars resulted in accuracies of 0.779 and 0.753, respectively. This study established the foundation for determining the optimal sensor configuration in this application, while also exploring the trade-offs between accuracy and the use of fewer sensors.

Vision Transformers (ViT) for Blanket-Penetrating Sleep Posture Recognition Using a Triple Ultra-Wideband (UWB) Radar System.

Sleep posture has a crucial impact on the incidence and severity of obstructive sleep apnea (OSA). Therefore, the surveillance and recognition of sleep postures could facilitate the assessment of OSA. The existing contact-based systems might interfere with sleeping, while camera-based systems introduce privacy concerns. Radar-based systems might overcome these challenges, especially when individuals are covered with blankets. The aim of this research is to develop a nonobstructive multiple ultra-wideband radar sleep posture recognition system based on machine learning models. We evaluated three single-radar configurations (top, side, and head), three dual-radar configurations (top + side, top + head, and side + head), and one tri-radar configuration (top + side + head), in addition to machine learning models, including CNN-based networks (ResNet50, DenseNet121, and EfficientNetV2) and vision transformer-based networks (traditional vision transformer and Swin Transformer V2). Thirty participants (n = 30) were invited to perform four recumbent postures (supine, left side-lying, right side-lying, and prone). Data from eighteen participants were randomly chosen for model training, another six participants' data (n = 6) for model validation, and the remaining six participants' data (n = 6) for model testing. The Swin Transformer with side and head radar configuration achieved the highest prediction accuracy (0.808). Future research may consider the application of the synthetic aperture radar technique.

Using cardiorespiratory fitness to operationalize vitality: a path analysis on the hierarchical structure of intrinsic capacity.

BACKGROUND: There is a lack of consensus about the operationalization of vitality, which is one of the intrinsic capacity (IC) domains. In particular, no study has investigated whether cardiorespiratory fitness (CRF) can be considered a vitality indicator. OBJECTIVE: To examine whether vitality is the upstream domain of IC, and establish the validity of CRF as a vitality indicator, using maximal oxygen consumption (VO2 max) as a representative. METHODS: 561 older adults from a longitudinal cohort study were included. Variables under consideration were VO2 max, other IC domains, instrumental activities of daily living (IADL), and handgrip strength, which was considered an already validated indicator of vitality. Using handgrip strength as the reference point, path analyses were performed to examine whether VO2 max followed a similar hierarchical structure in predicting change in IADL difficulty through other IC domains. RESULTS: The mean age of the participants was 75.5 years. The path model in which vitality was measured by VO2 max demonstrated adequate fit, which was similar to the model in which vitality was measured by handgrip strength. Regarding the path coefficients, the model using VO2 max demonstrated significant total and indirect effects. Notably, the indirect effect was due to the locomotor domain (standardized coefficient = -0.148, p < .001), but not the cognitive or psychological domain. CONCLUSION: Vitality is the upstream domain of IC. VO2 max can be considered an indicator to operationalize the vitality concept.

Transitions in intrinsic capacity among community-dwelling older people and their associated factors: a multistate modelling analysis.

OBJECTIVES: Trajectory of intrinsic capacity (IC) can be non-linear and discontinuous, which traditional linear models may not be able to handle. This study thus aimed to model the trajectory of IC as transitions between different IC states and examine their associated factors. METHODS: Longitudinal data from a sample of community-dwelling older people aged 60 years or above (n = 1,588) was analysed. A set of 14 self-reported items representing different domains of IC were administered annually to measure IC at four time points. Based on the number of impaired IC domains (i.e., cognitive, locomotor, vitality, sensory, and psychological), participants at each time point were classified into one of three IC states, namely state 1 (0 impaired domain), state 2 (1-2 impaired domains), and state 3 (3-5 impaired domains). Multistate modelling was used to identify factors associated with the transitions from one state to another. RESULTS: The mean age of participants was 75.0 years, and 77.4% of them were female. At baseline, 12.4% were in state 1, 51.8% were in state 2, and 35.8% were in state 3. 62.8% of participants experienced at least one transition between states, among which 12% experienced a transition every year. The transitions occurred mostly between adjacent IC states and could take place back and forth. Age, sex, marital status, perceived financial adequacy, number of chronic diseases, and self-rated health were the factors associated with the transitions. CONCLUSION: Findings may serve as a valuable reference for guiding future policies to optimize IC and promote healthy ageing using a person-centred approach.

SaccpaNet: A Separable Atrous Convolution-based Cascade Pyramid Attention Network to Estimate Body Landmarks Using Cross-modal Knowledge Transfer for Under-blanket Sleep Posture Classification.

The accuracy of sleep posture assessment in standard polysomnography might be compromised by the unfamiliar sleep lab environment. In this work, we aim to develop a depth camera-based sleep posture monitoring and classification system for home or community usage and tailor a deep learning model that can account for blanket interference. Our model included a joint coordinate estimation network (JCE) and sleep posture classification network (SPC). SaccpaNet (Separable Atrous Convolution-based Cascade Pyramid Attention Network) was developed using a combination of pyramidal structure of residual separable atrous convolution unit to reduce computational cost and enlarge receptive field. The Saccpa attention unit served as the core of JCE and SPC, while different backbones for SPC were also evaluated. The model was cross-modally pretrained by RGB images from the COCO whole body dataset and then trained/tested using dept image data collected from 150 participants performing seven sleep postures across four blanket conditions. Besides, we applied a data augmentation technique that used intra-class mix-up to synthesize blanket conditions; and an overlaid flip-cut to synthesize partially covered blanket conditions for a robustness that we referred to as the Post-hoc Data Augmentation Robustness Test (PhD-ART). Our model achieved an average precision of estimated joint coordinate (in terms of PCK@0.1) of 0.652 and demonstrated adequate robustness. The overall classification accuracy of sleep postures (F1-score) was 0.885 and 0.940, for 7- and 6-class classification, respectively. Our system was resistant to the interference of blanket, with a spread difference of 2.5%.

A Comprehensive Assessment Protocol for Swallowing (CAPS): Paving the Way towards Computer-Aided Dysphagia Screening.

Dysphagia is one of the most common problems among older adults, which might lead to aspiration pneumonia and eventual death. It calls for a feasible, reliable, and standardized screening or assessment method to prompt rehabilitation measures and mitigate the risks of dysphagia complications. Computer-aided screening using wearable technology could be the solution to the problem but is not clinically applicable because of the heterogeneity of assessment protocols. The aim of this paper is to formulate and unify a swallowing assessment protocol, named the Comprehensive Assessment Protocol for Swallowing (CAPS), by integrating existing protocols and standards. The protocol consists of two phases: the pre-test phase and the assessment phase. The pre-testing phase involves applying different texture or thickness levels of food/liquid and determining the required bolus volume for the subsequent assessment. The assessment phase involves dry (saliva) swallowing, wet swallowing of different food/liquid consistencies, and non-swallowing (e.g., yawning, coughing, speaking, etc.). The protocol is designed to train the swallowing/non-swallowing event classification that facilitates future long-term continuous monitoring and paves the way towards continuous dysphagia screening.

Computer-aided screening of aspiration risks in dysphagia with wearable technology: a Systematic Review and meta-analysis on test accuracy.

Aspiration caused by dysphagia is a prevalent problem that causes serious health consequences and even death. Traditional diagnostic instruments could induce pain, discomfort, nausea, and radiation exposure. The emergence of wearable technology with computer-aided screening might facilitate continuous or frequent assessments to prompt early and effective management. The objectives of this review are to summarize these systems to identify aspiration risks in dysphagic individuals and inquire about their accuracy. Two authors independently searched electronic databases, including CINAHL, Embase, IEEE Xplore® Digital Library, PubMed, Scopus, and Web of Science (PROSPERO reference number: CRD42023408960). The risk of bias and applicability were assessed using QUADAS-2. Nine (n = 9) articles applied accelerometers and/or acoustic devices to identify aspiration risks in patients with neurodegenerative problems (e.g., dementia, Alzheimer's disease), neurogenic problems (e.g., stroke, brain injury), in addition to some children with congenital abnormalities, using videofluoroscopic swallowing study (VFSS) or fiberoptic endoscopic evaluation of swallowing (FEES) as the reference standard. All studies employed a traditional machine learning approach with a feature extraction process. Support vector machine (SVM) was the most famous machine learning model used. A meta-analysis was conducted to evaluate the classification accuracy and identify risky swallows. Nevertheless, we decided not to conclude the meta-analysis findings (pooled diagnostic odds ratio: 21.5, 95% CI, 2.7-173.6) because studies had unique methodological characteristics and major differences in the set of parameters/thresholds, in addition to the substantial heterogeneity and variations, with sensitivity levels ranging from 21.7% to 90.0% between studies. Small sample sizes could be a critical problem in existing studies (median = 34.5, range 18-449), especially for machine learning models. Only two out of the nine studies had an optimized model with sensitivity over 90%. There is a need to enlarge the sample size for better generalizability and optimize signal processing, segmentation, feature extraction, classifiers, and their combinations to improve the assessment performance. Systematic Review Registration: (https://www.crd.york.ac.uk/prospero/), identifier (CRD42023408960).

Translation, Cultural Adaptation, and Validation of the Cantonese Version of SarQoL in Hong Kong's Older Population: An Interviewer-Administered Questionnaire for Assessing Sarcopenia-Specific Quality of Life in Fieldwork Practice.

Objective: This study examined the psychometric properties of the Cantonese version of the SarQoL® questionnaire. Participants: A total of 118 (including 60 non-sarcopenic and 58 sarcopenic) community-dwelling older adults aged 65 years or above with Cantonese as their mother tongue. Methods: Translation and cultural adaptation of the SarQoL were conducted using a standardized protocol. To validate the Cantonese SarQoL, psychometric properties including discriminative power, reliability (including internal consistency and test-retest reliability), and construct validity (including convergent and divergent validity), as well as floor and ceiling effects, were assessed. Results: The translation of the questionnaire was completed without significant difficulties. Results indicated that the Cantonese SarQoL had (1) good discriminative power (sarcopenic participants had lower overall scores, mean = 66.1 vs 75.0, p < 0.001; the overall score was negatively predictive of the presence of sarcopenia, adjusted OR = 0.949, 95% CI = [0.912, 0.983]), (2) good internal consistency (Cronbach's alpha = 0.835; correlations between domain and overall scores ranged from 0.576 to 0.868), (3) excellent test-retest agreement (intraclass correlation coefficient = 0.801), (4) good construct validity (convergent: moderate to strong correlations were found between the overall score and almost all of the SF-36 and EQ-5D domains; divergent: weaker correlations were found between the overall score and SF-36 social functioning, ρ = -0.098, and EQ-5D self-care, ρ = -0.331), and (5) no floor or ceiling effect. Conclusion: The Cantonese SarQoL is valid and reliable, and thus can be used as an interviewer-administered questionnaire for assessing sarcopenia-specific quality of life in fieldwork practice.

Computational Biomechanics of Sleep: A Systematic Mapping Review.

Biomechanical studies play an important role in understanding the pathophysiology of sleep disorders and providing insights to maintain sleep health. Computational methods facilitate a versatile platform to analyze various biomechanical factors in silico, which would otherwise be difficult through in vivo experiments. The objective of this review is to examine and map the applications of computational biomechanics to sleep-related research topics, including sleep medicine and sleep ergonomics. A systematic search was conducted on PubMed, Scopus, and Web of Science. Research gaps were identified through data synthesis on variants, outcomes, and highlighted features, as well as evidence maps on basic modeling considerations and modeling components of the eligible studies. Twenty-seven studies (n = 27) were categorized into sleep ergonomics (n = 2 on pillow; n = 3 on mattress), sleep-related breathing disorders (n = 19 on obstructive sleep apnea), and sleep-related movement disorders (n = 3 on sleep bruxism). The effects of pillow height and mattress stiffness on spinal curvature were explored. Stress on the temporomandibular joint, and therefore its disorder, was the primary focus of investigations on sleep bruxism. Using finite element morphometry and fluid-structure interaction, studies on obstructive sleep apnea investigated the effects of anatomical variations, muscle activation of the tongue and soft palate, and gravitational direction on the collapse and blockade of the upper airway, in addition to the airflow pressure distribution. Model validation has been one of the greatest hurdles, while single-subject design and surrogate techniques have led to concerns about external validity. Future research might endeavor to reconstruct patient-specific models with patient-specific loading profiles in a larger cohort. Studies on sleep ergonomics research may pave the way for determining ideal spine curvature, in addition to simulating side-lying sleep postures. Sleep bruxism studies may analyze the accumulated dental damage and wear. Research on OSA treatments using computational approaches warrants further investigation.

Sonoelastography for Testicular Tumor Identification: A Systematic Review and Meta-Analysis of Diagnostic Test Accuracy.

The objective of this review was to summarize the applications of sonoelastography in testicular tumor identification and inquire about their test performances. Two authors independently searched English journal articles and full conference papers from CINAHL, Embase, IEEE Xplore®, PubMed, Scopus, and Web of Science from inception and organized them into a PIRO (patient, index test, reference test, outcome) framework. Eleven studies (n = 11) were eligible for data synthesis, nine of which (n = 9) utilized strain elastography and two (n = 2) employed shear-wave elastography. Meta-analyses were performed on the distinction between neoplasm (tumor) and non-neoplasm (non-tumor) from four study arms and between malignancy and benignity from seven study arms. The pooled sensitivity of classifying malignancy and benignity was 86.0% (95%CI, 79.7% to 90.6%). There was substantial heterogeneity in the classification of neoplasm and non-neoplasm and in the specificity of classifying malignancy and benignity, which could not be addressed by the subgroup analysis of sonoelastography techniques. Heterogeneity might be associated with the high risk of bias and applicability concern, including a wide spectrum of testicular pathologies and verification bias in the reference tests. Key technical obstacles in the index test were manual compression in strain elastography, qualitative observation of non-standardized color codes, and locating the Regions of Interest (ROI), in addition to decisions in feature extractions. Future research may focus on multiparametric sonoelastography using deep learning models and ensemble learning. A decision model on the benefits-risks of surgical exploration (reference test) could also be developed to direct the test-and-treat strategy for testicular tumors.

Virtual Reality-Based Immersive Rehabilitation for Cognitive- and Behavioral-Impairment-Related Eating Disorders: A VREHAB Framework Scoping Review.

Virtual reality (VR) technology is one of the promising directions for rehabilitation, especially cognitive rehabilitation. Previous studies demonstrated successful rehabilitation in motor, cognitive, and sensorial functions using VR. The objective of this review is to summarize the current designs and evidence on immersive rehabilitation interventions using VR on cognitive- or behavioral-related eating disorders, which was mapped using a VREHAB framework. Two authors independently searched electronic databases, including PubMed, Web of Science, Scopus, CINAHL, EMBASE, and Cochrane Library. Ten (n = 10) articles were eligible for review. Treatments for anorexia nervosa and binge eating disorder/bulimia nervosa were reported through enhanced/experimental cognitive behavior therapy (ECT), cue exposure therapy (CET), and body exposure therapy (BET) via the virtual environment. Some studies reported that the VR effects were superior or comparable to traditional treatments, while the effects may last longer using VR technology. In addition, VR was perceived as acceptable and feasible among patients and therapists and could be valuable for supplementing existing therapies, relieving manpower and caregiver burdens. Future studies may consider incorporating haptic, smell, and biofeedback to improve the experience, and thus the effects of the treatments for the users.

Depth-Camera-Based Under-Blanket Sleep Posture Classification Using Anatomical Landmark-Guided Deep Learning Model.

Emerging sleep health technologies will have an impact on monitoring patients with sleep disorders. This study proposes a new deep learning model architecture that improves the under-blanket sleep posture classification accuracy by leveraging the anatomical landmark feature through an attention strategy. The system used an integrated visible light and depth camera. Deep learning models (ResNet-34, EfficientNet B4, and ECA-Net50) were trained using depth images. We compared the models with and without an anatomical landmark coordinate input generated with an open-source pose estimation model using visible image data. We recruited 120 participants to perform seven major sleep postures, namely, the supine posture, prone postures with the head turned left and right, left- and right-sided log postures, and left- and right-sided fetal postures under four blanket conditions, including no blanket, thin, medium, and thick. A data augmentation technique was applied to the blanket conditions. The data were sliced at an 8:2 training-to-testing ratio. The results showed that ECA-Net50 produced the best classification results. Incorporating the anatomical landmark features increased the F1 score of ECA-Net50 from 87.4% to 92.2%. Our findings also suggested that the classification performances of deep learning models guided with features of anatomical landmarks were less affected by the interference of blanket conditions.

Healthcare inequalities in emergency visits and hospitalisation at the end of life: a study of 395 019 public hospital records.

OBJECTIVES: To investigate whether there were any socioeconomic disparities in utilisation of hospital care services during end of life in Hong Kong. METHODS: Secondary data analyses were conducted using frequency of the accident and emergency (A&E) department visits and hospital admissions during the last year of life in all public hospitals from 2004 to 2014 in Hong Kong. A total of 1 237 044 A&E records from 357 853 patients, and 1 878 982 admission records from 375 506 patients were identified for analyses. In total, 395 019 unique deceased patients were identified from both datasets. RESULTS: Regression analyses showed that comprehensive social security assistance (CSSA) recipients used A&E services 1.29 times more than the non-recipients. Being either a CSSA recipient or an elderly home resident was more likely to be admitted to hospitals and stayed longer. Elderly home residents tended to stay longer than those from the community in the earlier months during the last year of life regardless of CSSA status; however, non-elderly home residents surpassed the residents in the duration of stay at hospitals towards the later months of the last year of life. There were also significant differences in hospital utilisation across various districts of residence. CONCLUSIONS: People of lower socioeconomic position tend to have higher emergency visits and hospitalisation during their last year of life in Hong Kong, implying the presence of health inequality during end of life. However, due to Hong Kong's largely pro-rich primary care system, the predominantly public A&E and inpatient services may inadvertently act as a mitigator of such health inequalities.