Amanda Man Ying Chu

This study presents a dynamic Bayesian network framework that facilitates intuitive, gradual edge changes. We use two conditional dynamics to model the edge additions and deletions, as well as edge selections, separately. In contrast to previous research that employed a mixture network approach—which limits the number of edge changes—or relied on structural priors to induce gradual changes—often leading to ambiguous network evolution—our model fosters more frequent and intuitive edge change dynamics. Moreover, when the maximum number of parents for the nodes in the network is , the correlation matrix can be represented by at most correlations. In contrast, conventional dynamic correlation models necessitate correlations. Consequently, the structure specified by the Bayesian network facilitates dimensionality reduction of the correlation matrix from to . Furthermore, correlations evolve sequentially according to the network structures and the topological ordering, thereby mimicking the information flow among stocks in financial markets, offering a realistic framework for modeling correlation evolution. We implement Markov chain Monte Carlo sampling to estimate the model structures and parameters, and we illustrate the model's efficacy through a portfolio selection application.

Background: Depression is a prevalent mental health condition that significantly affects individuals’ well-being and daily functioning, making early depressive symptom detection crucial. Objectives: This study explores the potential of advancing speech analytics with dimensional sentiment analysis, using valence and arousal scoring to enhance depressive symptom detection in family caregivers. Methods: We recruited 116 family caregivers and assessed their depression levels using the Beck Depression Inventory-II. Participants provided verbal responses to 12 open-ended questions related to family resilience. The extracted words from the responses were analyzed for sentiment using the Chinese Valence-Arousal Words dictionary to determine their valence and arousal ratings. For each participant, we computed various summary statistics (e.g., mean, variance, quantiles) and frequency-domain statistics (e.g., spectral entropy, dominant frequency components) of valence and arousal distributions. These features were then used as predictors in nine different machine learning models evaluated under repeated 5-fold nested cross-validation with cost-sensitive cutoff selection, enabling robust classification of depression levels while prioritizing the identification of true positive cases. Results: Our analysis showed that participants with higher depressive symptoms used words with more extreme valence and arousal scores than those with lower depressive symptoms. The models demonstrated strong predictive utility of these emotional dimensions: the quadratic discriminant analysis (QDA) model achieved an out-of-sample sensitivity of 0.725, a specificity of 0.563, and an AUC of 0.7. These findings support that valence and arousal analysis provides meaningful discriminative power for identifying depressive symptoms. Importantly, the high sensitivity achieved by these models ensures that individuals with elevated symptoms are more reliably detected, thereby reducing the risk of missed cases. Overall, the results suggest strong potential for automated depressive symptom detection based on emotional signal analysis, with cost-sensitive optimization reducing false negatives while maintaining clinically relevant specificity. Conclusions: This study offers proof-of-concept evidence that emotional sentiment analysis of speech using valence and arousal scoring can capture linguistic markers associated with depressive symptoms among family caregivers. With further refinement and validation, this approach lays an important foundation for the development of more robust machine learning models and ultimately contributes to non-intrusive mental health screening tools.

Background: Dementia caregiving entails chronic, fluctuating stress with downstream risks to caregivers’ mental health and quality of care. Mindfulness-based interventions can reduce caregiver stress; however, moment-to-moment fluctuations in stress may limit receptivity to practice at any given time. We developed a brief mindfulness just-in-time adaptive intervention (JITAI) that aims to deliver support at the right moment by using machine learning algorithms to optimize notification timing based on receptivity to engage in brief mindfulness practices. Objective: This study aims to evaluate the feasibility, acceptability, and effectiveness of a brief mindfulness JITAI for caregivers of people with dementia on stress, depressive symptoms, caregiver burden, sleep, quality of life, and trait mindfulness. Methods: A single-arm, pretest or posttest design was adopted. A total of 120 community-dwelling caregivers were recruited to participate in the 18-day intervention, which included 4 days of psychoeducation delivered via videos and phone coaching, alongside an in-app brief, low-dose mindfulness-based stress reduction component. From days 5 to 11, prompts were delivered either by a static machine learning model trained on prior pilot data or at random times, with equal probability. From days 12 to 18, three delivery models were used with equal probability, namely static, random, and adaptive models, which updated per participant using accumulating receptivity data. Feasibility and acceptability were assessed post intervention. Standardized measures of stress, depressive symptoms, caregiver burden, positive aspects of caregiving, sleep, quality of life, and trait mindfulness were collected via phone interviews at baseline and post intervention. Results: Retention was 100%. Most participants (111/120, 92.5%) found the app easy to use, 81.7% (98/120) perceived it as helpful for stress management, and 80% (96/120) would recommend it to other caregivers. Pre-post analyses indicated significant reductions in perceived stress ( P <.001), depressive symptoms ( P <.001), and caregiver burden ( P =.003), as well as a significant increase in positive aspects of caregiving ( P <.001) and subjective sleep quality ( P =.02). Health-related quality of life and trait mindfulness did not change significantly. Conclusions: A brief, smartphone-delivered mindfulness JITAI for caregivers of people with dementia was feasible and acceptable, with high retention and positive user evaluations. Pre-post findings suggest reductions in perceived stress, depressive symptoms, and caregiving burden, alongside increased positive aspects of caregiving and improved sleep, supporting the potential of adaptive, technology-enabled interventions to provide timely support to caregivers.

Background: Family caregivers experience significant stress due to intensive caregiving activities, making them highly susceptible to adverse psychosocial health conditions. Early detection of this stress is crucial for timely interventions to prevent disease progression and long-term disability. Objective: This study aimed to develop and validate the Linguistic and Acoustic Speech Analytics Program, a novel machine learning approach capable of providing a fusion analysis of linguistic and acoustic speech features to enhance the effectiveness of psychosocial stress assessment. Methods: This quantitative study analyzed speech data collected from 100 Chinese family caregivers. Participants responded to 12 open-ended questions, and their voices were recorded for linguistic and acoustic feature extraction. Various machine learning classifiers, including support vector machine, were developed to process speech data. A key methodological step was the application of an orthogonalization procedure to decorrelate acoustic features from linguistic features before fusion analysis. The classifiers were then trained to evaluate psychosocial stress levels based on the processed and fused linguistic and acoustic speech features. Model performance was measured using receiver operating characteristic-area under the curve, F ₁ -score, and accuracy. Results: The linear support vector machine model emerged as the top performer, achieving a receiver operating characteristic-area under the curve of 78.28%, an F ₁ -score of 75.27%, and an accuracy of 73%. These results demonstrate the model’s strong capability in identifying stressed participants based on their speech. Critically, the fusion of linguistic and acoustic features significantly outperformed models using either feature type alone. Furthermore, the orthogonalization procedure proved essential, as decorrelating features before fusion markedly enhanced classification accuracy compared to using non-orthogonalized features. Conclusions: This study demonstrates that fusion analysis of linguistic and acoustic features effectively identifies psychosocial stress among family caregivers. It also emphasizes the importance of proper feature processing when combining multiple features extracted from the same audio sample. These findings provide valuable insights for developing machine learning models for psychosocial stress assessment and addressing various psychosocial conditions in different contexts, supporting population mental health management.

Medication administration is a fundamental component of nursing practices, with direct implications for patient safety, health outcomes, and healthcare qua

Family caregivers face stress, especially those facing financial burdens. Therefore, it is crucial to evaluate non-financial social support intervention’s effectiveness and identify demographic factors linked to higher caregiver depression risk. We attempted to investigate whether social support could protect caregivers from experiencing depression. We introduced non-financial social support by offering a range of workshops and activities to help reduce stress experienced by the caregivers. We recruited 462 informal family caregivers from a Hong Kong nonprofit organization. They completed the Beck Depression Inventory-II (BDI-II) and a demographic characteristics questionnaire before and after the intervention. The effectiveness of the intervention was analyzed with ANOVA on pre- and post-intervention BDI-II scores. The research findings suggested that the intervention effectively reduced family caregivers’ depression levels. The intervention was more effective for caregivers facing financial difficulties. Additionally, this study revealed that single-family caregivers are more susceptible to depression. This research validates the effectiveness of our intervention for family caregivers in preventing them from developing depression. Policymakers should subsidize social welfare organizations to offer more non-financial interventions and social support for caregivers within the community.

The increasing prevalence of parenting stress has significant implications for the psychological well-being of both parents and children. In view of this, our study sought to examine the mediating and moderating role of family resilience in the association between child-friendly family and parenting stress. Our analysis involved a sample of 316 parents who dedicated a minimum of 14 h per week to caring for their children. The parents were invited to complete three validated instruments—the parenting stress index short form (PSI), the family resilience assessment scale (FRAS), and inventory of the child-friendly family (ICF)—to evaluate their level of parenting stress, family resilience, and child-friendly family, respectively. We tested the mediation model by applying structural equation model analysis. It was found that child-friendly family negatively correlated with parenting stress (path coefficient = −0.56, p < 0.001). This relationship is mediated by family resilience. That is “child-friendly family” leads to increased “family resilience” (path coefficient = 0.68, p < 0.01), which in turn leads to lower “parenting stress” (path coefficient = −0.30, p < 0.05). The mediation effect ratio was 26.70%. We used multiple regression analysis to test the moderation model and found that family resilience did not play a moderating role between child-friendly family and parenting stress. This study holds particular significance for two key reasons: Firstly, it elucidates the relationship between child-friendly family, family resilience, and parenting stress, highlighting the potential of creating a child-friendly family to reduce parenting stress through the enhancement of family resilience. Secondly, our findings provide valuable evidence for the development of innovative approaches that effectively and sustainably alleviate parenting stress.

There is growing interest in accommodating network structure in panel data models. We consider dynamic network Poisson autoregressive (DN-PAR) models for panel count data, enabling their use in regard to a time-varying network structure. We develop a Bayesian Markov chain Monte Carlo technique for estimating the DN-PAR model, and conduct Monte Carlo experiments to examine the properties of the posterior quantities and compare dynamic and constant network models. The Monte Carlo results indicate that the bias in the DN-PAR models is negligible, while the constant network model suffers from bias when the true network is dynamic. We also suggest an approach for extracting the time-varying network from the data. The empirical results for the count data for confirmed cases of COVID-19 in the United States indicate that the extracted dynamic network models outperform the constant network models in regard to the deviance information criterion and out-of-sample forecasting.