Chronic low back pain (CLBP) affects over 20% of adults worldwide. Despite the socioeconomic burden caused by this condition, there is no gold standard treatment for CLBP, and its etiology remains nonspecific in 85% of cases. Available evidence indicates that CLBP patients have higher postprandial glycemic responses to beverages that rank high on the glycemic index and that this finding correlates with pain severity. Therefore, understanding modifiable factors that predict blood glucose regulation in CLBP patients could reveal important information for the management of the condition.

This study aimed to (1) examine the relationship between predictor variables and the overall glycemic response, measured by the incremental area under the curve (IAUC), and (2) assess the temporal changes in patients' blood glucose levels immediately after sucrose intake. This dual approach enables a nuanced understanding of both the cumulative and immediate impacts of sucrose intake on glycemic control, facilitating insights into personalized management strategies for mitigating glycemic variability.

A secondary analysis of a case-control randomized controlled crossover trial to identify predictive factors for impaired blood glucose regulation.

Vrije Universiteit Brussel, Belgium.

Individuals with chronic low back pain (CLBP) were randomized to consume either a sucrose or isomaltulose beverage. Body composition, dietary intake, physical activity levels, psychological factors, and blood glucose levels were measured. Multiple linear regression was used to examine the relationship between baseline variables and postprandial glucose response following intake of the high-glycemic index beverages, and a linear mixed model (LMM) was applied to assess the relationship between sucrose intake and identified potential predictors.

Our findings revealed that higher weight (P < 0.001; t = -4.06), higher age (P = 0.003; t = 3.06), higher inflammatory dietary properties (P = 0.025; t = 2.28), worse mental health (P = 0.021; t = 2.34), and lower diet quality (P = 0.002; t = 3.22) were associated with a significant predictive value for altered postprandial sucrose responses.

This study is a secondary analysis of a crossover case-control trial, so causal interpretations should be made cautiously. Additionally, postprandial glucose was measured using a self-monitoring finger-prick device, which lacked real-time data, and the findings were specific to women and may not apply to men.

These results confirm the potential relevance of targeting lifestyle factors in people with CLBP.

Young people living with HIV bear a disproportionate burden of depression, which is associated with poor HIV outcomes. Problem-solving therapy (PST) has been shown to be effective for depression management and can be delivered with fidelity by nonspecialists, especially in resource-limited settings. PST is designed to equip individuals to manage the impact of stressful life events on their mental health. Change My Story is a narrative digital game designed to improve PST engagement among young people living with HIV in Nigeria.

This trial will evaluate the impact of PST alone or PST with Change My Story on mental health outcomes among young people living with HIV in Nigeria.

We will conduct a pilot hybrid implementation-effectiveness randomized controlled trial with 80 young people living with HIV (aged 16-24 years) in Nigeria with depression (9-item Patient Health Questionnaire [PHQ-9] ≥9) over 3 months. Participants will be randomized to receive PST with or without Change My Story. All participants will engage in weekly PST sessions for 6 weeks delivered by trained nonspecialists (clinic HIV adherence counselors). At 6 and 10-12 weeks, scores on PHQ-9 will determine the frequency of PST sessions during the remaining intervention period. Primary implementation outcomes, including engagement, satisfaction, feasibility, acceptability, and appropriateness from the participant perspective, will be assessed using validated scales, programmatic data, and focus group discussions at 3 months. Secondary clinical outcomes will assess changes in depressive symptoms, psychological distress, functional disability, antiretroviral therapy adherence, and HIV viral suppression at 3 and 6 months. Implementation outcomes (all but engagement and satisfaction) will be assessed through validated scales and focus group discussions from the implementer perspective at baseline and 6 months.

This study is funded by the US National Institutes of Health (funding commenced on March 8, 2024), institutional review board approval was received on April 15, 2024, and recruitment and data collection began in June 2025. Thus far, we have screened 103 youths and enrolled 23 participants. Among enrolled participants, 15 (65%) were male; 1 (4%) had a PHQ-9 score ≥17, and 6 (26%) had suicidal thoughts. We anticipate recruitment will be completed by January 2026 and follow-up by June 2026. We will assess our hypotheses that PST with Change My Story is feasible, acceptable, and appropriate and that individuals receiving PST integrated with Change My Story will have greater engagement, satisfaction, and depression remission compared to those receiving PST alone.

This pilot randomized controlled trial attempts to establish preliminary data on the feasibility, acceptability, appropriateness, and efficacy of task-shifted PST and supplementary mobile health technology on improving HIV and mental health outcomes among young people living with HIV in Nigeria. These findings may serve as a basis for future large-scale interventions.

ClinicalTrials.gov NCT06389565; https://clinicaltrials.gov/study/NCT06389565.

PRR1-10.2196/74199.

Mental disorders, such as anxiety and depression, affect approximately 900 million people worldwide, posing severe challenges to healthcare systems and society. Accurate classification of mental disorders is crucial for effective treatment. However, current diagnostic methods primarily rely on behavioral observation and self-reported questionnaires, which are highly influenced by patient subjectivity and physician expertise. Sleep provides a stable physiological state largely unaffected by subjective emotions. Sleep-related vital signs, such as respiration and heart rate, offer valuable insights into mental health conditions. Therefore, in this study, we propose a novel method for mental disorder classification by monitoring physiological signals during sleep. We utilize a millimeter-wave radar to monitor respiratory and body movement patterns, along with a pulse oximeter to acquire photoplethysmography (PPG) signals. Statistical features extracted based on medical prior knowledge are then input into a deep neural network together with raw physiological signals for mental disorder classification. Experimental results on a real-world dataset of 447 participants validate the effectiveness of our proposed method. This study provides a portable and objective solution for mental disorder classification, contributing to improved diagnostic accuracy and facilitating broader access to mental healthcare resources.Clinical Relevance- This study provides an objective and portable method for classifying mental disorders, which is of significant importance for improving diagnostic accuracy and promoting the decentralization of healthcare resources.

Advancements in neuroscience and deep learning have significantly enhanced bio-signal-based emotion recognition, a critical component in Brain-Machine Interface (BMI) applications for healthcare, human-computer interaction, and human-AI assistant communication. Former studies have proposed Manual Mapping electrode matrices and employing Convolutional Neural Networks (CNNs) to recognize spatial EEG activities. However, this Manual Mapping of EEG electrodes onto matrix grids limits spatial precision and introduces inefficiencies. This study proposes automated channel mapping methods of Orthographic Projection and Stereographic Projection to address these challenges, using Differential Entropy and Power Spectral Density with Linear Dynamical Systems as features. A 3-branch multiscale CNN was trained on open-source dataset, employing a 5-fold cross-classification approach. Experimental results demonstrate that higher-resolution grids (16×16, 24×24) with automated projections significantly outperform Manual Mappings, achieving up to a 4.06% improvement in classification accuracy (p < 0.05). This result indicates that enhancing spatial precision of EEG data improves emotion classification, establishing automated spatial mapping as an advancement in EEG-based emotion recognition.Clinical Relevance-Advancement in emotion classification accuracy can facilitate more reliable diagnostic tools and personalized therapeutic interventions for mental health disorders, such as depression and anxiety.

Aboriginal pregnant women and new mothers face an increased risk of mental health issues, often stemming from historical trauma, including violence and discrimination. These challenges could contribute to complex trauma and adverse perinatal outcomes, highlighting the need for culturally sensitive care. However, non-Aboriginal clinicians often face barriers due to limited cultural knowledge, exacerbated by other factors such as time constraints for training and reliance on one-time training. Large Language Models (LLMs)-based chatbots offer the potential to support self-directed learning and enhance clinicians' self-efficacy through interactive question and answer. However, LLMs also pose challenges, including hallucinatory responses, outdated knowledge, fictitious information, unverifiable references, and difficulty handling domain-specific queries. In this study, we aim to mitigate these challenges by developing a specialized chatbot for improving Aboriginal perinatal mental health question-answering. The chatbot integrates Retrieval-Augmented Generation (RAG) with a semantic search engine, enabling it to retrieve verified external knowledge and provide more accurate, contextually relevant responses without frequent retraining. We evaluate its performance against a baseline GPT-3.5-turbo model and compare LLMs integrated with different RAG techniques to assess improvements in accuracy and reliability.Clinical Relevance- This study shows the potential of the specialized RAG LLM-based chatbot to improve domain-specific, clinically relevant, and on-demand question-answering support for clinicians. By providing accurate, verified information through interactive responses, it may help bridge knowledge gaps, support self-directed learning, and complement existing training.

A sleep forecast allows individuals, and healthcare providers to anticipate and proactively address factors influencing restful rest, ultimately improving mental and physical well-being. This work presents an adaptive spatial and temporal model (AdaST-Sleep) for predicting sleep scores. Our proposed model combines convolutional layers to capture spatial feature interactions between multiple features and recurrent neural network layers to handle longer-term temporal health-related data. A domain classifier is further integrated to generalize across different subjects. We conducted several experiments using five input window sizes (3, 5, 7, 9, 11 days) and five predicting window sizes (1, 3, 5, 7, 9 days). Our approach consistently outperformed four baseline models, achieving its lowest RMSE (0.282) with a seven-day input window and a one-day predicting window. Moreover, the method maintained strong performance even when forecasting multiple days into the future, demonstrating its versatility for real-world applications. Visual comparisons reveal that the model accurately tracks both the overall sleep score level and daily fluctuations. These findings prove that the proposed framework provides a robust and adaptable solution for personalized sleep forecasting using sparse data from commercial wearable devices and domain adaptation techniques.Clinical relevance- This is a method that could be used to inform participants and therapists in life-style interventions with the aim of improving sleep patterns about the participant's progress.

Early detection of burnout is of utmost importance to avoid severe health consequences. Burnout is typically assessed through standardized questionnaires with self-reported information, a technique that could potentially delay its diagnosis. Wearable devices continuously and unobtrusively collect health-related data, making them valuable tools for the early detection of several mental health issues, including burnout syndrome. In this paper we report initial insights on the machine learning prediction of baseline burnout risk across cognitive, emotional, and physical dimensions. Our data consists of the first 30 days of a 9-months longitudinal study with 239 participants, including monthly burnout assessments and health data from smartwatches. Aggregated mean and standard deviation of physiological features over time windows of varying duration were employed as predictors of baseline burnout risk. Models employing sleep, cardiac, and stress features achieved a balanced accuracy of 0.66 and 0.68 in the detection of cognitive weariness and physical fatigue risk, respectively. The prediction of emotional exhaustion risk reached lower performance with a balanced accuracy of 0.55, suggesting the need of integrating additional data sources to reach better-than-chance performance. We expect to improve burnout risk prediction by crafting additional features and exploiting the collected data over their full longitudinal scale.

Electroencephalography (EEG) is a non-invasive neuroimaging technique that records electrical activity in the brain using electrodes placed on the scalp. It provides high temporal resolution, making it valuable for studying brain dynamics, cognitive processes, and neurological disorders. EEG is widely used in clinical and research settings for diagnosing epilepsy, sleep disorders, and mental health conditions. However, EEG signals are often contaminated by artifacts from ocular, muscular, and environmental sources, complicating accurate analysis. Traditional artifact removal methods, such as Independent Component Analysis (ICA) and wavelet transform, require significant computational resources and manual tuning, limiting their effectiveness in real-time applications. To overcome these challenges, this paper presents a deep learning-based framework for automated EEG denoising and simultaneous artifact removal while ensuring efficiency in real-time deployability. Various performance metrics such as relative-root-mean-square (RRMSE), structural similarity index measure (SSIM), and correlation, (CC) are measured to evaluate the model performance. The model achieves an average temporal and spectral RRMSE of 0.214 and 0.217 respectively, average SSIM of 0.964 and CC 0.963 of across various datasets. The model outperforms as compared to the state-of-the-art method with 295 × lesser parameters as compared to prior models. The model is able to denoise the EEG signals from various artifacts simultaneously. The proposed model demonstrates the potential for real-time deployment. The source code is available at https://github.com/dipayandewan94/EDGeNet.

Wearable and phone sensor data hold great potential for monitoring depression, yet effective integration of these diverse data sources remains challenging. Transforming these complex data into a learned embedding space provides a lower-dimensional representation that preserves essential temporal patterns while capturing the intricate inter-modal relationships. In this study, we evaluate how different fusion strategies for generating multimodal embeddings impact the effectiveness of clustering in identifying depression symptoms. We used a longitudinal dataset integrating physiological and social data such as electrocardiogram, accelerometer, respiration rate, and mobility/Bluetooth interaction data, collected over 35 days. An embedding-based approach using long short-term memory (LSTM) autoencoders was employed to learn latent space representations, followed by the application of K-Means and Gaussian Mixture Models (GMM) clustering algorithms to identify patterns within this learned space. Weekly Beck Depression Inventory-II (BDI-II) scores, held-out during training, served as the ground truth for performance evaluation. A custom metric, the BDI-Variance Ratio Clustering Score (BDI-VRCS), was developed to quantitatively assess clustering efficacy across different embedding spaces. Early fusion implementation with LSTM and GMM achieved the highest BDI-VRCS of 0.3309, outperforming both mid and late fusion strategies (0.112 and 0.132, respectively). This highlights the value of early integration of multimodal data, with social features playing a key role in capturing depressive symptoms.Clinical relevance- This study highlights the potential of integrating physiological and social data using multimodal fusion strategies to enhance depression monitoring and support the development of holistic, data-driven tools for early detection and personalized mental health interventions.

Osteoarthritis of the knee (knee OA) is a prevalent condition that negatively impacts a patient's quality of life by affecting various aspects of daily living, including ambulation, mental health, and sleep. Although several engineering treatments for knee OA have been developed, no orthotic device has been successfully implemented owing to challenges such as cost, size, and aesthetic concerns. The present study aimed to develop a cost-effective and aesthetically unobtrusive tool for the prevention and treatment of knee OA. Recent studies have focused on rotational movements of the lower leg in knee OA, demonstrating that inducing such movements may be effective in preventing and alleviating knee OA by reducing the knee adduction moment. In this study, we propose a novel insole-based tool with low manufacturing costs that can be embedded into shoes without altering the appearance of the shoes. This device incorporates a rotational guidance mechanism that generates rotational motion when the body weight is applied to the insole. This mechanism uses the force applied during normal walking; therefore, it does not require external power and allows the production of lightweight devices. Initially, finite element method (FEM) simulations were conducted to establish the correlation between the internal configuration of the rotation-inducing mechanism and resulting rotation angle. Based on these findings, a prototype of the rotation-inducing mechanism was fabricated and its rotational angle and stability were comprehensively evaluated. Finally, an insole incorporating the rotation-inducing mechanism (rotation-inducing insole) was developed, and a series of experiments were conducted to assess its effect on walking. The results showed that the rotation-inducing mechanism can adjust the rotation angle by modifying its internal structure. By adjusting the rotation angle, the mechanism can be applied to treat symptoms of varying severity. In addition, rotation-inducing insoles promoted external rotation of the lower leg during gait and affected walking patterns. These findings suggest that utilizing rotation-inducing insoles to control lower leg rotational movement could contribute to the prevention and improvement of knee OA.