Chris Easthope Awai

Background: Continuous glucose monitoring (CGM) can facilitate weight management and lower the risk of metabolic diseases by providing real-time feedback on glycemic responses, thereby enabling more informed lifestyle decisions. However, current CGM systems remain constrained by invasiveness, cost, and short sensor lifespan, limiting their practicality for guiding individualized postprandial low-glycemic diets. Objective: Extending earlier proof-of-concept findings, this study aimed to validate an interstitial glucose (IG) machine learning algorithm in real-world environments using multimodal, continuous data collected from wearable sensors and smartwatches. In the long term, we aim to embed a noninvasive, sensor-based algorithm for estimating tissue glucose within mobile health apps and postprandial low-glycemic diet frameworks to enable scalable, personalized prevention strategies. Methods: We conducted a 2-week study phase during which participants continuously wore 2 noninvasive sensor devices: a scientific sensor wristband (Empatica EmbracePlus) and a commercially available smartwatch (Fitbit Sense 2). As a reference measurement, an invasive CGM sensor (Abbott FreeStyle Libre 3) measured IG levels. For metabolic characterization, 1-point fasting blood and urine samples were collected, and deep phenotyping using state-of-the-art nuclear magnetic resonance spectroscopy and bioelectrical impedance analysis was performed. For participants with overweight and obesity, clinical standard parameters focusing on glucose metabolism were analyzed. Results: A total of 74 participants, 34 (46%) healthy controls and 40 (54%) metabolically at-risk (MR) individuals, simultaneously used an invasive CGM device together with 2 noninvasive wristbands over 2 weeks. Healthy controls were characterized by a mean age of 24.53 (SD 3.68) years and a mean BMI of 22.36 (SD 2.16) kg/m². In contrast, the MR cohort had a mean age of 55.38 (SD 15.08) years and a mean BMI of 35.38 (SD 4.91) kg/m². Furthermore, the MR cohort showed elevated fasting glucose levels (mean 107.56, SD 19.26 mg/dL), hemoglobin A _1c levels (mean 5.67%, SD 0.63%), and an increased homeostatic model assessment of insulin resistance index (mean 4.34, SD 3.49), indicating a disturbed glucose metabolism. The proposed long short-term memory network based on feature vectors obtained the best IG prediction performance, with an average root-mean-squared error of 21.04 (SD 8.32) mg/dL and 98.3% of predictions in zones A and B of the Clarke error grid analysis, representing a high level of predictive accuracy. In addition, based on data from a smartwatch, we achieved a comparable average root-mean-squared error of 23.49 (SD 11.46) mg/dL for the overall cohort. Conclusions: This study demonstrates that IG levels can be predicted from multimodal, noninvasive wearable sensor data using a machine learning approach under real-world conditions. While further validation in larger and more diverse cohorts is warranted, this approach represents a promising step toward accessible, personalized glycemic monitoring and dietary guidance as a preventive tool in mobile health apps.

Background: Real-world gait assessment has gained momentum in populations with walking impairments, offering insights beyond standardized tests and supporting the integration of remote monitoring into clinical care. However, its potential remains limited by the lack of validated population- and context-specific digital biomarkers. Objective: The primary objective was to summarize and critically evaluate the current state of real-world gait assessment using wearable sensors in Parkinson disease (PD) and stroke, addressing methodological approaches, sensor configurations, validation strategies, and outcome reporting. The secondary objective was to quantify methodological heterogeneity by reporting pooled means with 95% confidence intervals (CIs) and prediction intervals (PIs) of commonly reported gait parameters. Methods: PubMed, Scopus, Web of Science, and Embase were searched for English-language studies published up to April 20, 2026. Eligible studies used wearable sensors to assess gait quality parameters in real-world settings in at least 5 individuals with PD or poststroke. Laboratory- or rehabilitation-only studies, non–peer-reviewed articles, abstracts, and studies before 2014 were excluded. Methodological quality was assessed with a checklist adapted from Hubble et al. Gait features available in at least 5 reports were included in a meta-analysis using a random-effects model with Hartung-Knapp-Sidik-Jonkman adjustment, deriving 95% CIs and PIs to characterize the pooled estimate and its dispersion. Results: Of 2489 records, 43 reports were included: 37 on PD (2774 participants; mean age 67.89, SD 8.68 years) and 6 on stroke (217 participants; mean age 63.83, SD 11.84 years). Methodological quality was high, but external validity was consistently the weakest domain in both populations. Sensor configurations most commonly consisted of a lower back accelerometer. In total, 13 distinct walking bout definitions were identified, whereas 17 reports provided none, indicating substantial terminological heterogeneity. In PD, 4 gait parameters met the meta-analysis threshold, each showing a PI far wider than its CI, precluding generalization to future settings. For example, gait speed pooled at 0.84 m/s (95% CI 0.77‐0.91; 95% PI 0.56‐1.12), and number of steps per day at 7202 (95% CI 3975‐10,429), the latter with a PI extending below zero, a mathematically impossible range reflecting extreme dispersion. No stroke parameter was reported consistently enough to permit meta-analysis, underscoring a critically underdeveloped evidence base. Conclusions: Unlike previous reviews focusing on single diseases or specific hardware, this review contrasts PD and stroke to highlight shared methodological challenges. Real-world gait assessment in PD is advancing but fragmented, whereas the stroke evidence base remains sparse. The observed variance is compounded by procedural and algorithmic inconsistencies that cannot currently be separated from genuine clinical differences. The methodological groundwork established in PD offers a foundation for early adoption of standardized terminology, validation procedures, and core outcomes, essential for transitioning wearable sensors from exploratory tools to reliable clinical and remote-monitoring instruments.

Fragility fractures constitute a major global health burden and often result from falls. However, clinical care for fragility fractures is currently organized separately from fall prevention services leading to gaps in integrated care delivery. This joint position paper from the European Geriatric Medicine Society, the Fragility Fracture Network, the World Falls Prevention Society, the European Society for Clinical and Economic Aspects of Osteoporosis, Osteoarthritis and Musculoskeletal Diseases, the International Osteoporosis Foundation, the European Union of Medical Specialists-Geriatric Medicine Section, and the International Association of Gerontology and Geriatrics–European Region highlights the critical need for integrated falls and fracture prevention, with a focus on evidence-based clinical practice, knowledge dissemination, education, policy strategies, and research. We outline existing guidelines on fall and fracture prevention, with particular emphasis on how fracture risk assessment can be incorporated into fall prevention services and on integrating fall assessment into fracture prevention services. We advocate that future implementation guidelines place greater emphasis on fully integrated models of care. Moreover, training and education programs should be designed to encourage interdisciplinary collaboration among healthcare professionals. Integrated fall and fracture prevention services should be recognized as a public health priority and incorporated into national strategies for healthy aging, supported by adequate, dedicated, and sustainable resources including evidence-based exercise provision. Finally, future research should focus on evaluating the (cost) effectiveness of integrated care models and examining their practical implementation in real-world settings.

Three-dimensional instrumented gait analysis is widely used to guide surgical decision-making in children with cerebral palsy (CP), but its interpretation is time-consuming and prone to inter-rater variability. In this single-centre pilot study, we investigated whether a generative large language model (LLM) could consistently generate gait deviation findings and surgical procedure suggestions that align with expert judgement. Kinematic features for lower-limb joints across the gait cycle, stance, and swing were extracted from eight children with unilateral CP using the open-source GaitSharing Toolkit and a structured prompt, then submitted three times per patient to OpenAI’s GPT-5.5 model. The model assessed 28 kinematic deviations and 12 surgical procedure groups using majority voting. One gait analyst and two paediatric orthopaedic surgeons independently rated outputs on a 0–2 ordinal scale, blinded to all clinical information beyond the kinematic curves and diagnosis. Agreement was summarised descriptively as the percentage of the maximum attainable score with 95% confidence intervals (CIs), and quadratic-weighted Cohen’s kappa was used to quantify inter-surgeon agreement. Agreement with the gait expert was highest at the hip (90.6%) and lowest at the knee, particularly in the transverse plane (65.2%). For surgical procedures, agreement with the LLM reached 83.9% and 73.4% for the two surgeons, with the tibialis anterior procedure showing the lowest concordance. Inter-surgeon agreement was 79.2% (95% CI 71.9–85.4) with a kappa of 0.59 (0.47–0.70), indicating moderate agreement. The LLM showed high self-consistency (>90% across runs). These preliminary findings suggest that generative LLMs may be feasible as assistive tools in clinical gait analysis for deviation detection and future treatment planning and should be interpreted as hypothesis-generating, warranting confirmation in larger, more diverse cohorts.

Objective measurement of upper-limb movement quality based on biomechanical data collected in clinical routine has the potential to enable precision neurorehabilitation at scale. However, integrating biomechanical data collection into daily clinical workflows remains challenging. In this exploratory study, we evaluated the usability of two technologies for routine kinematic data collection: an IMU-based version of the instrumented Action Research Arm Test (iARAT-IMU) and a MMC markerless motion capture (MMC) system. First, five physiotherapists independently operated the iARAT-IMU across seven clinical routine assessment sessions at a rehabilitation clinic in Switzerland to quantify learning curves, setup times, and usability. Second, we conducted a preference study in which the same therapists used both, the IMU- and MMC-system, during a standardized drinking task and completed quantitative and qualitative usability assessments focusing on system preference and underlying reasons. Results show that therapists rapidly learned to operate the tablet application for scoring the iARAT; however, the IMU system added approximately 11 min of setup time and sometimes required assistance. In contrast, the MMC workflow required approximately 2 min of additional time - well within the 5-minute maximum indicated a priori by therapists as acceptable for clinical routine and received consistently higher usability ratings. Most therapists preferred this approach due to greater efficiency and reduced patient burden. These findings highlight important design considerations for future digital assessment tools and indicate that MMC systems may offer a more feasible pathway toward routine biomechanical data collection for upper-limb assessments in clinical neurorehabilitation.

Background: Dysarthria is a frequent motor speech disorder following a stroke, affecting up to 42% of survivors and resulting in reduced speech intelligibility and diminished quality of life. Clinical assessments, such as the Frenchay Dysarthria Assessment, Second Edition (FDA-2), rely heavily on the subjective judgment of speech-language pathologists (SLPs), which limits comparability and scalability. Telepractice solutions have the potential to extend access to care, but validated digital tools that combine automatic analysis with clinically usable interfaces remain scarce. Objective: This study aimed to develop and evaluate a web-based application that integrates automatic speech recognition (ASR) and acoustic analysis into a user-centered dashboard for SLPs. Specifically, we investigated: (1) whether ASR can provide intelligibility scores comparable to those of human listeners; (2) the usability of the system in 2 iterative cycles with SLPs; and (3) the feasibility of presenting clinically relevant acoustic features to support telerehabilitation. Methods: A user-centered design process was followed, involving contextual inquiry, requirements gathering, prototype development, and iterative testing with SLPs. The analytical core of the prototype included an ASR module (Whisper Large-v3) to compute intelligibility scores, combining word error rate–based accuracy with sentence-level and word-level alignment. Phoneme-level error highlighting was implemented to identify frequent substitution or deletion patterns. In parallel, an acoustic module extracted clinically relevant measures, including fundamental frequency (mean and range), intensity (mean and variability), and vowel formants (F1–F2 space), supplemented by sustained phonation duration. A pilot validation compared ASR-based intelligibility scores with transcriptions from 8 lay listeners for 3 patients with dysarthria performing the Frenchay Dysarthria Assessment–2 word and sentence tasks. Usability was evaluated in 2 cycles with 8 and 4 SLPs, respectively, using the System Usability Scale and structured questionnaires. Results: In the pilot validation, ASR performance was comparable to, and in some cases better than, untrained human listeners for individuals with mild and moderate dysarthria, though performance declined with severe cases. Both usability cycles yielded excellent System Usability Scale scores (cycle 1: mean 88.4, SD 4.6; cycle 2: mean 91.7, SD 4.1). Core workflow elements, including navigation, session upload, and intelligibility score presentation, were consistently rated highly. Feedback evolved from bug reports and requests for clearer terminology in cycle 1 to suggestions for advanced analytic features in cycle 2, such as additional voice-quality indices and integrated note-taking. Conclusions: The prototype demonstrates that automatic intelligibility scoring and acoustic analysis can be integrated into a clinically usable, web-based dashboard. While current limitations include reliance on English-only phoneme analysis, limited advanced acoustic features, and lack of regulatory compliance, the application achieved excellent usability and shows promise for scalable telerehabilitation. Future work should expand multilingual support, incorporate additional acoustic measures, and validate the tool in larger clinical cohorts.

Background: Digital assessment technologies, such as optical motion capture and inertial measurement units, enable detailed kinematic analysis and continuous monitoring of upper limb activity in persons with neurological conditions. While such digital metrics of functioning are increasingly recognized in research, their uptake in clinical neurorehabilitation is limited. It remains unclear which digital metrics of functioning clinicians perceive as most meaningful and how these are integrated into patient-centered care. Understanding clinicians’ information needs and reasoning processes is a prerequisite for implementing digital assessment technology. Objective: This study aims to characterize how rehabilitation professionals perceive, prioritize, and integrate digital metrics of functioning into clinical reasoning and to identify features that would support their routine use. Methods: Three 90-minute focus groups were conducted in 3 Swiss neurorehabilitation centers, involving 11 clinicians with diverse professional backgrounds (5 physiotherapists, 4 occupational therapists, 1 movement scientist, and 1 medical practitioner). Participants discussed essential parameter domains and individually rated the relevance and meaningfulness of 17 kinematic metrics for the well-studied drinking task and 10 established arm use performance metrics. Verbatim transcripts were analyzed using reflexive thematic analysis, and rating data were summarized descriptively. Results: Five main themes were identified. (1) Functional requirements to interpret movement quality and performance (active/passive range of motion, strength, selective muscle control, and grasp) form the basis for interpreting movement. (2) Essential aspects of movement quality (smoothness, efficiency, and compensatory movement) are valued when aligned with observable task execution. (3) Added value of real-world performance (hourly activity profiles, arm-use symmetry, and functional workspace) represents the reference for patient-centered reasoning. (4) Individualizing what matters , including diagnosis-specific preferences, shapes assessment selection. (5) Blending clinical eye and reference data reflects clinicians’ reliance on visual judgment complemented by normative values. Intuitive metrics such as task duration, number of movement units, and range of motion were favored, whereas confidence was lower in more complex metrics (eg, jerk and interjoint coordination). Conclusions: Clinicians value intuitive digital metrics of functioning when they are clearly linked to patient-centered outcomes and supported by normative references. The findings highlight the need for targeted educational strategies and digital competency training that help clinicians interpret digital metrics and integrate them with contextual information and clinical reasoning.

Three-dimensional instrumented gait analysis (3D-IGA) is widely used to guide surgical decision-making in children with cerebral palsy (CP), but its interpretation is time-consuming and prone to inter-rater variability. We investigated whether a generative large language model (LLM) could consistently generate gait deviation findings and surgical procedure suggestions that align with expert judgement. Kinematic features for lower-limb joints across the gait cycle, stance, and swing were extracted from eight children with unilateral CP using the open-source GaitSharing Toolkit and a structured prompt, then submitted three times per patient to OpenAI's GPT-5.5 model. The model assessed 28 kinematic deviations and 12 surgical procedure groups using majority voting. One gait analyst rated the deviations, and two paediatric orthopaedic surgeons independently rated the procedures on a 0–2 ordinal scale, blinded to all clinical information beyond the kinematic curves and diagnosis. Agreement with the gait expert averaged 84.7% in the sagittal plane and was lowest at the knee (62.6%). Surgeons’ agreement with the LLM reached 83.9% and 73.5%, with the tibialis anterior procedure showing the lowest concordance. Inter-surgeon agreement was 79.2%. The LLM showed high self-consistency (>90% across runs). This work demonstrates the potential of generative LLMs as assistive tools in clinical gait analysis for deviation detection and future treatment planning.

Objective: In Parkinson's disease (PD), gait-related digital mobility outcomes (DMOs) show promise for monitoring mobility decline, but convergent validity remains limited. To improve convergent validity, demonstrating convergence with motor severity scales and PD-specific neural mechanisms underlying mobility has been proposed. However, severity scales capture both PD-specific and non-specific factors. Requiring mechanistic evidence may favor DMOs that converge with underlying mechanisms, while those converging only with severity scales may be overlooked despite capturing broader mobility dimensions. Here, we asked whether PD-specific neural mechanisms underlying mobility enhanced the convergence of DMOs with motor severity scales - so that integrating mechanistic evidence in validation could improve (and not impede) convergent validity. Method: Principal component analysis was applied to task-based functional neuroimaging data to identify a measure associated with PD motor network dysfunction. An optimization problem was then formulated in which deep learning examined the convergence of a signal-based DMO with motor severity in laboratory and real-world contexts, and Tracing Gradient Descent assessed the influence of the identified measure on DMO-severity convergence. Results: Greater PD motor network dysfunction was associated with reduced Attractor Complexity Index (ACI) values (rho=-0.54). Strong DMO-severity convergence was found across contexts (rho=|0.81-0.82|). Reduced ACI (i.e., greater PD motor network dysfunction) markedly enhanced DMO-severity convergence across contexts (rrb=|0.63-0.29|). Conclusion: PD-specific neural mechanisms underlying mobility enhanced the convergence of a DMO with severity scales. Significance: Integrating mechanistic validation into DMO validation could improve convergent (and construct) validity, a prerequisite for regulatory approval and adoption in clinical trials and practice.