Search Results (2,389)

Cervical range of motion (CROM) has been used in research and clinically for assessing cervical health. Gold-standard goniometers tend to be cumbersome. However, Inertial Measurement Units (IMUs) or vision-based alternatives demand frequent calibration and/or costly hardware; moreover, the subject is aware of being measured and there is a risk of breaching privacy. In response, we have developed a non-contact HPNet system for head pose estimation (HPE) that can use a rear-facing camera to quantify CROM accurately. A Re-parameterized Visual Geometry Group (RepVGG)-D2se model is employed as the backbone of the network, and a Spatial Feature Enhancement (SCFE) module is incorporated to improve feature extraction. HPNet was evaluated on the large-scale Carnegie Mellon University (CMU) Panoptic dataset, achieving a mean absolute error (MAE) of 3.48°, 3.22°and 3.34° for yaw, pitch and roll respectively. Inter-instrument reliability was excellent for all six cervical movements when compared with the research/clinical-grade CROM device, with intraclass correlation coefficients (ICCs) averaging 0.939. Bland–Altman plots confirmed close agreement between the two methods. Cervical movement trajectory curves further confirmed the concordance between the clinical device and our method. The system is fully automatic, requires only a rear-facing camera, effectively preserves patient privacy, and provides accurate cervical posture estimation. This technology may provide a basis for future applications in neck-disorder screening, remote health monitoring, and personalized musculoskeletal wellness management, although further task-specific clinical validation will be required. To date, HPNet has been validated primarily on a computer-based platform and has not yet been deployed on smartphones. Future work will focus on model lightweighting, mobile deployment, and cross-device adaptation to facilitate its practical implementation on mobile devices. Full article

Background: Diabetes mellitus is a major public health concern in Saudi Arabia, affecting approximately 18.3% of adults. Although over 95% of people in the Qassim region own smartphones, limited information exists regarding how and why patients with diabetes utilize digital health technologies. Objective: This study employed an extended Technology Acceptance Model (TAM) incorporating trust, privacy concerns, and self-efficacy to investigate the factors influencing digital health technology adoption among patients with diabetes in Qassim Unaizah, Saudi Arabia. Methods: A cross-sectional study was conducted from November 2025 to January 2026 following institutional review board approval. The quantitative phase utilized a structured survey (n = 203) measuring TAM constructs via validated 5-point Likert scales. Descriptive statistics, Pearson correlations, and one-way ANOVA were performed. Qualitative themes were derived from open ended responses to contextualize quantitative findings. Results: Most participants were male (62.6%), with a mean age of 47.2 years (SD ± 13.1). Smartphone ownership was nearly universal (99.5%), and 82.8% used blood glucose tracking applications. All TAM constructs exhibited significant positive correlations with behavioural intention (p < 0.001): attitude (r = 0.450), perceived usefulness (r = 0.438), self-efficacy (r = 0.394), trust (r = 0.379), ease of use (r = 0.340), and privacy concern (r = 0.309). Mean scores indicated strong acceptance: perceived usefulness (4.31, SD ± 0.39), behavioural intention (4.21, SD ± 0.44), and attitude (4.17, SD ± 0.42). Daily usage was reported by 63.1% of participants, 81.8% expressed satisfaction, and 63.1% reported that digital tools greatly improved their diabetes management. Privacy concerns were notably low (mean 1.70, SD ± 0.89, reverse-coded; Cronbach’s α = 0.921). Supplementary qualitative content analysis of optional open-ended comments (n = 40 respondents) identified six recurring topics: clinical utility, digital literacy, trust, data security awareness, patient empowerment, and social support. Conclusions: Patients with diabetes in Qassim Unaizah demonstrate substantial digital health adoption, predominantly driven by perceived usefulness, positive attitudes, and self-efficacy. The extended TAM effectively explains adoption within this Saudi Arabian context. Findings support interventions emphasizing clinical benefits, user friendly design, and trust building to optimize digital health utilization in diabetes care. Full article

Three-dimensional facial scanning is an important tool in reconstructive surgery and burn medicine for objective documentation, treatment planning, and fabrication of patient-specific devices. While professional structured-light scanners provide high geometric accuracy, their cost limits routine implementation. Several low-cost consumer-grade alternatives are available; however, their accuracy for clinically relevant facial applications remains insufficiently validated. Thirty volunteers were initially recruited for facial scanning. Two participants withdrew from further scanning for personal reasons, resulting in a main study cohort of 28 participants. Complete datasets from all 28 participants were available for Artec Eva, Revopoint MIRACO, and Creality CR-Scan 01, whereas 22 Kiri Engine datasets met the predefined quality criteria for smartphone photogrammetry analysis. Facial scans acquired using Revopoint MIRACO, Creality CR-Scan 01, and Kiri Engine were compared with a professional structured-light scanner (Artec Eva) used as the reference system. Six clinically relevant inter-landmark distances were analysed together with global surface deviation relative to Artec Eva reference using Cloud-to-Mesh analysis. Agreement was evaluated using mean signed differences, mean absolute error (MAE), intraclass correlation coefficients (ICC), Bland–Altman analysis, and post-hoc statistical testing. Both MIRACO and CR-Scan demonstrated favourable geometric agreement with the Artec Eva reference. Global surface RMSE relative to Artec Eva reference was 0.72 ± 0.24 mm for MIRACO and 0.57 ± 0.17 mm for CR-Scan, compared with 1.41 ± 0.58 mm for Kiri Engine. More than 90% of facial surface points were within 1 mm of the reference model for MIRACO (91 ± 8%) and CR-Scan (93 ± 7%), whereas Kiri Engine achieved 68 ± 16%. Pooled ICC values ranged from 0.998 to 0.999 across the evaluated systems. Pairwise comparisons showed no significant difference between MIRACO and CR-Scan (p = 0.42), while both significantly outperformed Kiri Engine (p < 0.001). Consumer-grade structured-light scanners demonstrated submillimeter global surface deviations, supporting further investigation for facial surface documentation and monitoring applications. Smartphone photogrammetry showed substantially larger deviations and may be less suitable for applications requiring precise quantitative measurements. Low-cost structured-light systems demonstrated promising geometric performance in healthy volunteers; however, further validation in relevant clinical populations is required before their applicability to reconstructive surgery and burn care workflows can be established. Full article

Road surface hazards remain a persistent concern for vehicle safety, passenger comfort, and the operational continuity of transport infrastructure. Among these hazards, potholes are particularly significant because they can cause tire damage, suspension wear, wheel misalignment, and sudden vehicle instability. In addition to direct mechanical damage, potholes may reduce driving comfort, increase maintenance costs, and degrade traffic efficiency in urban environments where roads are heavily used and rapidly deteriorate. For these reasons, the timely detection of potholes is an important requirement for road safety and infrastructure management. This work presents a tailor-made dataset for road pothole detection in urban environments, referred to as the Bridgestone Dataset (BS Dataset). The dataset was designed to support object detection from vehicle-mounted imagery collected from a test vehicle under realistic road conditions, thereby aligning the training data more closely with the target deployment scenario. The resulting dataset is intended to support real-time monitoring systems for road hazard detection and maintenance planning. The dataset was also designed as a multimodal resource. In addition to pothole bounding-box annotations, it provides accelerometer and GPS signals to characterize the vehicle dynamics during operation which might help identifying hazard severity and the potential risk to the vehicle. To collect the dataset, the authors developed a smartphone application, which supports the acquisition of both images and vehicle telemetry by leveraging the device’s internal sensors. Full article

Smartphone accelerometry could enable longitudinal home-based balance testing, yet its reliability across tasks and outcome measures must be established. We assessed the test–retest reliability and measurement precision of a custom smartphone balance application. Sixty-nine healthy, community-dwelling middle-aged and older adults (ages 41–76 years) performed a 5 s home-based balance assessment weekly for 3 weeks. The assessment was directed by the application, which generated accelerometer-based sway metrics. Participants performed two 30 s trials each of feet together and tandem stance (eyes open, eyes closed) and single leg stance (eyes open only). Intraclass correlation coefficients (ICCs) and relative standard error of measurement (SEM%) were calculated for time-domain and frequency-domain measures. Outcomes achieved good-to-excellent reliability when averaged across three weekly assessments (ICC = 0.59–0.95), particularly mediolaterally. Time-domain measures, particularly mean acceleration (ICC = 0.84–0.92; SEM% = 11.1–23.5%), were the most reliable and precise outcomes overall, while frequency-domain measures showed lower reliability and precision at higher spectral bands (ICC as low as 0.59; SEM% up to 41.5%). As standing tasks became more difficult, reliability and precision declined correspondingly. We conclude that minimally supervised, home-based balance assessment can produce reliable, precise sway measures in healthy, screened, iPhone-owning middle-aged and older adults. This application carries potential for large-scale, remote balance monitoring for research purposes, though validation in more diverse and higher-risk populations will be needed before clinical application can be recommended. Full article

Background: Dry eye disease (DED) impairs quality of life. Artificial tears are the first-line treatment, but compliance is generally poor. Patients forget to instil drops or underestimate the importance of regular use. Mobile health (mHealth) applications improve adherence in other chronic conditions, but their role in DED remains unclear. This study evaluated the effectiveness of a smartphone reminder application in improving compliance to a four-times-daily artificial tear regimen and the associated symptom relief among patients with DED. Methods: A masked randomised crossover trial was conducted in 29 women with DED (mean ± SD age 21.2 ± 3.0 years). Participants completed two 14-day study phases: one with app-based reminders and one without, separated by a 7-day washout period. The primary outcome was mean daily drop frequency. Secondary outcomes were self-reported symptom frequency and severity assessed using the Symptom Assessment iN Dry Eye (SANDE). Results: The mean daily drop frequency was higher during the app phase compared with the non-app phase (F = 22.906, p < 0.001) but declined in both phases over time (F = 3.023, p < 0.001). Symptom frequency did not differ between phases but decreased over time (F = 1.993, p = 0.021). Symptom severity remained unchanged with no significant effects by phase or time. Baseline clinical measures did not predict drop use frequency or app-related improvement (p > 0.05). Conclusions: The reminder application increased short-term compliance to artificial tear use, but there was no corresponding reduction in symptoms or signs over two weeks’ usage. Compliance waned over time despite active reminders, suggesting that prompts alone are insufficient for sustaining behaviour change. Future digital interventions for DED should incorporate strategies to enhance motivation, support long-term engagement, and provide personalised education. Full article

Scoliosis is a complex three-dimensional spinal deformity that requires early detection, accurate radiological assessment, individualized treatment planning, and long-term monitoring. In recent years, artificial intelligence (AI) has emerged as a promising tool across multiple stages of scoliosis management, including screening, automated imaging analysis, deformity classification, prediction of progression, surgical planning, postoperative outcome assessment, and patient education. This narrative review summarizes current and emerging applications of AI in scoliosis, with particular emphasis on studies published after 2023. Deep learning algorithms, including convolutional neural networks, U-Net-based architectures, transformer models, and generative approaches, have demonstrated high accuracy in automated Cobb angle measurement, vertebral segmentation, coronal and sagittal parameter assessment, and radiation-free screening using surface topography or smartphone-based photographs. Machine learning models have also shown potential in predicting curve progression, treatment response, risk of postoperative complications, and patient-reported outcomes by integrating radiological, clinical, biomechanical, and, increasingly, multimodal data. In parallel, large language models and generative AI tools are being investigated for patient education, communication support, readability improvement, and research hypothesis generation. Despite these advances, important limitations remain, including limited external validation, dataset heterogeneity, potential algorithmic bias, insufficient interpretability, and incomplete integration into clinical workflows. Moreover, while AI systems show strong performance in automated measurement and screening tasks, their role in complex therapeutic decision-making, such as Lenke classification, fusion-level selection, and autonomous surgical planning, remains experimental. Overall, AI has the potential to improve the precision, efficiency, and personalization of scoliosis care; however, prospective multicentre studies, transparent reporting, explainable model design, and regulatory validation are essential before widespread clinical implementation. Full article

Background/Objectives: Motor abnormalities are frequently observed in schizophrenia, but accessible methods for objective gait quantification remain limited. This exploratory controlled-setting study examined whether markerless smartphone-based video analysis combined with interpretable machine learning could quantify gait-related motor phenotypes in individuals with schizophrenia. Methods: Gait videos were collected from 100 individuals with schizophrenia and 35 healthy controls using a single-site, single-device, standardized recording setup. MediaPipe Pose was used to extract skeletal landmarks and derive 12 image-plane spatiotemporal and estimated two-dimensional knee-kinematic gait features. After temporal segmentation and quality control, 404 usable gait segments derived from 135 participants were analyzed as repeated segment-level observations. Decision Tree and Support Vector Machine models were applied for exploratory segment-level group-separation analysis using segment-wise 15-fold cross-validation after the full post-quality-control dataset had been balanced before fold allocation. Results: Several extracted gait features differed between groups, particularly image-plane ankle displacement, mean step displacement, displacement velocity, step characteristics, and knee-joint motion. In the Decision Tree model, image-plane ankle displacement served as the primary root node, indicating its central role in internal segment-level group separation. However, the healthy control group was substantially younger and not age-matched. In addition, the segment-level statistical comparisons did not account for within-participant clustering. Accordingly, the reported p values and confidence intervals may overstate statistical precision. Separately, segment-wise cross-validation allowed segments from the same participant to occur across folds and resampling was performed before fold partitioning. Because oversampling was performed with replacement, duplicated segment instances could also occur across training and validation folds. Consequently, the statistical findings should be interpreted as exploratory segment-level patterns rather than participant-level inference, and the machine-learning performance estimates should be regarded only as potentially optimistic apparent internal segment-level results and should not be regarded as evidence of participant-level generalization, diagnostic validity, screening accuracy, or clinical applicability. Conclusions: Markerless video-based gait analysis with interpretable machine learning may provide a feasible research-support approach for quantifying gait-related motor phenotypes in individuals with schizophrenia. These findings should not be interpreted as evidence for participant-level clinical classification, diagnostic or screening validity, clinical utility, or readiness for deployment, or as proof of cross-device or cross-environment reproducibility. Future studies require matched controls, psychiatric comparison groups, subject-wise validation, external datasets, calibrated gait measures, systematic cross-configuration reproducibility testing, and privacy-preserving data governance. Full article

The rapid development of wireless communication systems has increased the complexity of smartphone antenna design. Modern terminals are required to simultaneously support Sub-1 GHz cellular bands, 5G New Radio (NR), millimeter-wave communication, satellite links, and emerging sensing services within limited physical space. As a result, multiband operation has become a central challenge for mobile terminals. This paper reviews the recent research advances in multiband smartphone antennas, organized according to the evolution from single-antenna to multi-antenna architectures and including both Sub-6 GHz and millimeter-wave applications. Single-antenna Sub-3 GHz techniques, multiband multi-antenna systems, dual-band millimeter-wave antennas, and integrated Sub-6 GHz/millimeter-wave architectures are systematically summarized. The key technologies, including multi-mode cooperation, characteristic-mode design, multiple-input multiple-output (MIMO) decoupling, and shared-aperture integration, are discussed. The emerging B5G/6G-oriented technologies are also highlighted. This review provides an overview of current design strategies and future trends for next-generation multiband smartphone antennas. Full article

The LiDAR sensor embedded in recent iPhone Pro devices offers new opportunities for rapid, low-cost, and spatially detailed assessment of outdoor recreational infrastructure. Framed within mobile sensing and IoT-based environmental monitoring, this proof-of-concept case study evaluates a smartphone-based LiDAR workflow for localized hiking trail assessment under dense canopy conditions. Four independent surveys of a degraded hiking trail section were conducted to assess inter-survey repeatability, agreement with conventional field measurements, and practical field applicability. The resulting three-dimensional models reproduced trail morphology, including incised tread sections, exposed roots, rocky surfaces, and localized irregularities relevant to trail-condition assessment. Repeated registrations demonstrated consistent cloud-to-cloud comparison metrics, while comparisons with field reference measurements showed good agreement in the representation of cross-sectional morphology and exposed root characteristics. Continuous surface reconstruction additionally supported exploratory identification of potential runoff pathways and relative surface depressions. Although limited to a single trail section and one smartphone–application combination (iPhone 13 Pro with Scaniverse), the evaluated workflow demonstrates potential as a rapid, accessible, and relatively low-cost approach for localized trail-condition assessment and provides a foundation for further evaluation in hiking trail monitoring. Full article

Introduction: Voice-based digital biomarkers have emerged as a promising approach for distinguishing individuals with neurodegenerative disorders, particularly Parkinson’s disease (PD), from healthy subjects (HS). With the increasing availability of smartphone and web-based recording tools, voice data can be collected efficiently in both clinical and remote settings. However, further validation is required before such approaches can be translated into routine clinical practice. Methods: This study used a cross-sectional analysis at the recording level, treating repeated recordings from the same participant as separate observations collected at Vito Fazzi Hospital in Lecce, Italy. Speech recordings from individuals with Parkinson’s disease (PD) and healthy controls were collected using the dedicated Talia smartphone and web application. Sustained vowel phonation (/a/) was analyzed as the primary speech task. Following data acquisition, feature extraction was performed as a crucial step in the speech analysis pipeline, as the quality and relevance of the extracted features directly influence the ability of machine learning models to discriminate between Parkinson’s disease (PD) patients and healthy controls. To capture various aspects of speech impairment associated with PD, a comprehensive set of acoustic features was extracted, including long-term features (pitch, jitter, and shimmer), nonlinear descriptors such as Recurrence Period Density Entropy (RPDE), and short-term feature based on Mel-Frequency Cepstral Coefficients (MFCCs). These features were subsequently used to develop and evaluate machine learning models for the classification of Parkinson’s disease and healthy subjects. Feature selection was performed using SHAP to identify the most informative vocal biomarkers. Model performance was assessed using five independent random train–test splits (70% training and 30% testing), supported by an internal five-fold cross-validation procedure within the training data. Multiple machine learning models were developed and evaluated, including Random Forest, Logistic Regression, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, Decision Tree, Artificial Neural Network, and Gradient Boosting. Results: The evaluated models demonstrated strong recording-level classification performance. Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) achieved the highest accuracy scores (0.9545 and 0.9494, respectively), along with superior recall (up to 0.9500), precision (up to 0.9551), and F1-score (up to 0.9525). Both models also exhibited excellent discriminative ability, with ROC-AUC values reaching 0.9882 (ANN) and 0.9893 (KNN). In contrast, Naive Bayes and Decision Tree showed comparatively lower performance across all metrics. Log-loss analysis further confirmed the robustness of ANN and KNN, which achieved the lowest values (0.2552 and 0.2510, respectively), indicating well-calibrated predictions. Overall, the findings highlight the consistency and generalizability of ANN and KNN across cross-validation splits. Conclusions: This study demonstrates that machine learning models, particularly ANN and KNN, can effectively differentiate Parkinson’s disease from healthy conditions using voice recordings. The integration of explainable AI for feature selection enhances model transparency and clinical relevance. However, the reported performance estimates were obtained from a recording-level analysis and should be interpreted as preliminary findings. Further studies involving larger cohorts and participant-level validation strategies are required to determine the generalizability and clinical applicability of these approaches. Full article

Objective: The long-term management of cardiovascular diseases (CVDs) requires comprehensive rehabilitation strategies aimed at optimizing functional recovery and promoting behavioral changes. These interventions may include digital technologies that emerged as promising approaches to facilitate lifestyle changes, such as dietary behavior and physical activity (PA). Aim: This review aimed to synthesize the current evidence for the potential impact of remotely delivered nutrition interventions with or without a combination of PA interventions on biochemical biomarkers, cardiovascular indexes, anthropometric parameters, levels of PA, exercise and functional capacity, adherence to the Mediterranean Diet (MD), diet quality and quality of life, rehospitalization, urgent visits, death and acute events in adults (≥18 years) with CVDs. Secondary outcomes were accessibility, safety, usability, and adherence. Methods: The PubMed, Web of Science, and Scopus databases were comprehensively searched up to 2026 for Randomized Controlled Trials (RCTs) published in English, following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. The methodological quality was assessed using the revised Cochrane Risk of bias tool for RCTs (RoB2). Results: 11 RCTs met the inclusion criteria. Sample sizes ranged from 66 to 879 participants. The duration of the interventions varied from 4 weeks to 12 months. The interventions were delivered remotely using a range of digital health technologies, including web-based programs, mobile phones, wearable devices, smartphone applications, and mini-apps. Favorable changes were observed in diet quality and in adherence to MD and PA levels, with no intervention-related adverse events reported. The RoB2 assessment indicated that the majority of included studies (6 out of 11) were classified as having some concerns regarding risk of bias. Conclusions: Remotely combined nutrition and PA interventions are a feasible and effective approach for improving mainly patient-reported outcomes in adults with CVDs. These findings support integrating remote multimodal rehabilitation into routine cardiovascular care and highlight the potential of telehealth-based models to enhance patients’ access to rehabilitation services. Full article

Background: Objective breast assessment is relevant in aesthetic, reconstructive, and oncoplastic breast surgery. Smartphones and tablets are widely available devices that may offer an accessible means for three-dimensional (3D) breast surface imaging, with potential relevance for preoperative assessment, surgical planning, and outcome evaluation. However, the available evidence is heterogeneous, and the validity of different devices, applications, and workflows remains unclear. This narrative review aimed to summarize the evidence on smartphone-based 3D surface imaging. Methods: A structured literature search was conducted in PubMed, Embase, Web of Science, and EBSCOhost. Only original studies that used smartphone- or tablet-based breast assessment were included. Data extraction included devices, software, population/material, outcomes, comparators, validation metrics, and limitations. Reporting completeness was assessed using an adapted GRRAS-based appraisal. Results: A total of 9 studies representing approximately 7 independent datasets were included. Only two studies assessed volumetry as one of the primary aims. The evidence base was small and heterogeneous. Most studies were patient-based, while the remaining studies used phantom or model-based designs. Feasibility was demonstrated for selected device–application–workflow combinations, predominantly involving iPhones and the 3D Scanner App, but these findings were not generalizable to smartphone-based 3D breast imaging as a whole. Evidence was more favorable for selected linear anthropometric measurements than for volumetry. Key limitations included breast ptosis, inframammary fold (IMF) geometry, posterior boundary definition, software, and operator dependence. Three of the included reports had potentially overlapping cohorts. Due to substantial heterogeneity in devices, applications, comparators, outcomes, and validation metrics, meta-analysis was not performed. Conclusions: Current evidence is limited to a small number of heterogeneous, predominantly single-center datasets and supports only workflow-specific feasibility for selected anthropometric and surface-based measurements. These findings should not be generalized across smartphone devices, applications, or reconstruction workflows. Breast volumetry remains insufficiently validated and is supported by only two non-comparable studies. Future studies should provide more detailed reporting that focuses on objective characteristics of the workflow and outcomes, including predefined analyses of agreement and measurement error. Full article

Background/Objectives: Sensor-based movement assessment is increasingly used to quantify movement execution quality and support feedback-guided rehabilitation exercise, particularly in home-based and remote rehabilitation contexts. However, exercise adherence, movement execution quality, and rehabilitation progress remain difficult to monitor continuously and objectively outside direct therapist supervision. This scoping review aimed to map the current applications of sensor-based biofeedback and movement-quality assessment systems for rehabilitation exercise and to identify evidence gaps. Methods: This review followed established scoping review methodology and PRISMA-ScR guidance. PubMed/MEDLINE, Web of Science Core Collection, and IEEE Xplore were searched, and Google Scholar was used for supplementary searching. English-language studies published from January 2014 to May 2026 were eligible if they involved rehabilitation-related populations, sensor-based movement assessment, biofeedback, or training guidance. Data were charted and narratively synthesized according to rehabilitation context, sensor technology, movement-quality metrics, computational approaches, feedback strategies, real-time or remote functions, and reported outcomes. Results: Fifty-five studies published between 2015 and 2026 were included. The evidence covered neurological, musculoskeletal and orthopedic, balance and vestibular, fall-prevention, home-based, and telerehabilitation applications. Technologies included inertial sensors, smartphones, vision/depth cameras, surface electromyography, pressure/force sensors, and multisensor systems. Movement-quality metrics included range of motion, postural stability, gait characteristics, loading, muscle activation, movement correctness, repetition count, and task completion quality. Feedback was visual, auditory, vibrotactile, app-based, avatar-based, therapist-facing, or remote-platform-based. Most evidence came from feasibility, technical validation, algorithmic validation, and small-sample clinical studies. Conclusions: Sensor-based systems may help translate rehabilitation exercise performance into quantifiable and feedback-enabled information. Future research should strengthen real-world validation, standardize task-specific movement-quality metrics, and clarify how feedback mechanisms can support individualized rehabilitation progression. Full article