Nevin Manimala

J Speech Lang Hear Res. 2025 Oct 8:1-12. doi: 10.1044/2025_JSLHR-24-00677. Online ahead of print.

ABSTRACT

PURPOSE: The aim of this study was to investigate the acoustic patterns of six emotions and a neutral state in Cantonese speech by focusing on the prosodic modulations that convey emotional content in this tonal language, which has six lexical tones.

METHOD: We employed the extended Geneva minimalistic acoustic parameter set to systematically analyze the acoustic features of 3,474 recordings from the Cantonese Audio-Visual Emotional Speech Database. Linear mixed-effects models were fitted to examine variations in acoustic parameters across emotional states. Decision tree models were used to assess the relative contributions of 22 acoustic parameters in classifying emotions.

RESULTS: By fitting linear mixed-effects models, our results revealed statistically significant variations in most of the acoustic parameters across diverse emotional states. The decision tree models showed the relative contributions of 22 acoustic parameters in the classification of emotions, with spectral parameters accounting for 65.45% of the significance in distinguishing all seven emotional states, significantly exceeding other groups of features.

CONCLUSIONS: Our findings highlight the unique characteristics of emotional expression in Cantonese, in which spectral parameters play a more significant role compared to the frequency-related parameters that are often emphasized in nontonal languages. Our results contribute significantly to understanding vocal emotion expression in tonal languages and are particularly useful for designing emotion-recognition systems and hearing aids that are tailored to tonal language environments. Furthermore, these insights have potential implications for enhancing emotional communication and cognitive training interventions for Cantonese-speaking individuals who use hearing aids or have cochlear implants, are on the autism spectrum, or have Alzheimer’s disease.

PMID:41061266 | DOI:10.1044/2025_JSLHR-24-00677

JMIR Res Protoc. 2025 Oct 8;14:e76536. doi: 10.2196/76536.

ABSTRACT

BACKGROUND: Menopause symptoms are common but often inadequately addressed by primary care clinicians due to limited time for discussions and resources. Mobile health apps can play a crucial role in symptom identification and management; yet, many existing menopause-focused apps lack evidence-based content and medical expertise.

OBJECTIVE: The aim of this study is to describe the protocol study design and methodology of a randomized controlled trial to evaluate the effectiveness of the emmii mobile app for improving menopause-related knowledge and shared decision-making compared to a traditional menopause education pamphlet.

METHODS: This randomized controlled trial will recruit women aged 45-55 years with upcoming primary care appointments at Mayo Clinic within 3 weeks of the date of initial outreach. Eligible patients must be English-speaking, able to provide informed consent, and report a Menopause Rating Scale score ≥5, which indicates that they are experiencing significant menopause-related symptoms. Patients will be randomized to have access to either the emmii app (intervention, n=200) or an evidence-based menopause education pamphlet (control, n=200). The emmii app is developed with direct input from primary care clinicians certified by The Menopause Society and offers symptom tracking, personalized treatment recommendations based on a protocol, and a discussion guide to support communication between patients and their primary care clinicians. Outcomes will include a postappointment survey sent to the patients and their primary care clinicians within 1-3 weeks of the appointment, and assessment of patient knowledge, clinical treatment plans, and both the patient and clinician experience. The study will also compare prescribing rates of hormonal and nonhormonal therapies for menopause symptoms between the emmii intervention and control groups to assess for influence on treatment patterns. Data will be analyzed using descriptive statistics, including chi-square tests, Wilcoxon rank sum tests, and multivariable modeling.

RESULTS: Data collection is scheduled to begin in April 2025.

CONCLUSIONS: This protocol outlines the design and methodology of a randomized controlled trial that aims to assess the impact of the emmii app in facilitating menopause care through primary care clinician-patient communication and shared decision-making.

TRIAL REGISTRATION: ClinicalTrials.gov NCT06919887; https://clinicaltrials.gov/ct2/show/NCT06919887.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/76536.

PMID:41061260 | DOI:10.2196/76536

J Med Internet Res. 2025 Oct 8;27:e71034. doi: 10.2196/71034.

ABSTRACT

BACKGROUND: With 28%-35% of individuals aged 65 years and older experiencing incidents of falling, falls are the second leading cause of unintentional injury-related deaths globally. Limited availability of clinical staff often impedes the timely detection and prevention of potential falls. Advances in artificial intelligence (AI) could complement existing fall risk assessment and help better allocate nursing care resources. Yet, many studies are based on small datasets from a single institution, which can restrict the generalizability of the model, and do not investigate important aspects in AI model development, such as fairness across demographic groups.

OBJECTIVE: This study aimed to provide a comprehensive empirical evaluation of the potential of AI in nursing care, focusing on the case of fall risk prediction. To account for demographic and contextual differences in fall incidences, we analyze data from a university and a geriatric hospital in Germany. To the best of our knowledge, these are the largest fall risk prediction datasets to date with heterogeneous data distributions. We focus on 3 key objectives. First, does AI help in improving fall risk prediction? Second, how can AI models be trained safely across different hospitals? Finally, are these models fair?

METHODS: This study used 2 datasets for fall risk prediction: one from a university hospital with 931,726 participants, 10,442 of whom experienced falls, and another from a geriatric hospital with 12,773 participants, 1728 of whom have fallen. State-of-the-art AI models were trained with 3 approaches, including 2 decentralized learning paradigms. First, separate models were trained on data from each hospital; second, models were retrained on the respective other dataset; and federated learning (FL) was applied to both datasets. The performance of these models was compared with the rule-based systems as implemented in clinical practice for fall risk prediction. Additional analyses were conducted to test for model fairness.

RESULTS: Our findings demonstrate that AI models consistently outperform rule-based systems across all experimental setups, with the area under the receiver operating characteristic curve of 0.735 (90% CI 0.727-0.744) for the geriatric hospital, and 0.926 (90% CI 0.924-0.928) for the university hospital. FL did not improve the fall risk prediction in this setting. Our fairness analysis ruled out disparities in model performance between different sex groups, but we found fairness infringements across age groups.

CONCLUSIONS: This study demonstrates that AI models consistently outperform traditional rule-based systems across heterogeneous datasets in predicting fall risk. However, it also reveals the challenges related to demographic shifts and label distribution imbalances, which limited the FL models’ ability to generalize. While the fairness analysis indicated fair results across sex subgroups, age-related disparities emerged. Addressing data imbalances and ensuring broader representation across demographic groups will be crucial for developing more fair and generalizable models.

PMID:41061259 | DOI:10.2196/71034

J Med Internet Res. 2025 Oct 8;27:e73185. doi: 10.2196/73185.

ABSTRACT

BACKGROUND: New media have become vital sources of cancer-related health information. However, concerns about the quality of that information persist.

OBJECTIVE: This study aims to identify characteristics of studies considering cancer-related information on new media (including social media and artificial intelligence chatbots); analyze patterns in information quality across different platforms, cancer types, and evaluation tools; and synthesize the quality levels of the information.

METHODS: We systematically searched PubMed, Web of Science, Scopus, and Medline databases for peer-reviewed studies published in English between 2014 and 2023. The validity of the included studies was assessed based on risk of bias, reporting quality, and ethical approval, using the Joanna Briggs Institute Critical Appraisal and the STROBE (Strengthening the Reporting of Observational Studies in Epidemiology) checklists. Features of platforms, cancer types, evaluation tools, and trends were summarized. Ordinal logistic regression was used to estimate the associations between the conclusion of quality assessments and study features. A random-effects meta-analysis of proportions was conducted to synthesize the overall levels of information quality and corresponding 95% CIs for each assessment indicator.

RESULTS: A total of 75 studies were included, encompassing 297,519 posts related to 17 cancer types across 15 media platforms. Studies focusing on video-based media (odds ratio [OR] 0.02, 95% CI 0.01-0.12), rare cancers (OR 0.32, 95% CI 0.16-0.65), and combined cancer types (OR 0.04, 95% CI 0.01-0.14) were statistically less likely to yield higher quality conclusions compared to those on text-based media and common cancers. The pooled estimates reported moderate overall quality (DISCERN 43.58, 95% CI 37.80-49.35; Global Quality Score 49.91, 95% CI 43.31-56.50), moderate technical quality (Journal of American Medical Association Benchmark Criteria 46.13, 95% CI 38.87-53.39; Health on the Net Foundation Code of Conduct 49.68, 95% CI 19.68-79.68), moderate-high understandability (Patient Education Material Assessment Tool for Understandability 66.92, 95% CI 59.86-73.99), moderate-low actionability (Patient Education Materials Assessment Tool for Actionability 37.24, 95% CI 18.08-58.68; usefulness 48.86, 95% CI 26.24-71.48), and moderate-low completeness (34.22, 95% CI 27.96-40.48). Furthermore, 27.15% (95% CI 21.36-33.35) of posts contained misinformation, 21.15% (95% CI 8.96-36.50) contained harmful information, and 12.46% (95% CI 7.52-17.39) contained commercial bias. Publication bias was detected only in misinformation studies (Egger test: bias -5.67, 95% CI -9.63 to -1.71; P=.006), with high heterogeneity across most outcomes (I²>75%).

CONCLUSIONS: Meta-analysis results revealed that the overall quality of cancer-related information on social media and artificial intelligence chatbots was moderate, with relatively higher scores for understandability but lower scores for actionability and completeness. A notable proportion of content contained misleading, harmful, or commercially biased information, posing potential risks to users. To support informed decision-making in cancer care, it is essential to improve the quality of information delivered through these media platforms.

TRIAL REGISTRATION: PROSPERO CRD420251058032; https://www.crd.york.ac.uk/PROSPERO/view/CRD420251058032.

PMID:41061257 | DOI:10.2196/73185

JMIR Form Res. 2025 Oct 8;9:e73180. doi: 10.2196/73180.

ABSTRACT

BACKGROUND: Youth are increasingly experiencing psychological distress. Schools are ideal settings for disseminating mental health support, but they are often insufficiently resourced to do so. Digital mental health tools represent a unique avenue to address this gap. The Alongside digital program is one such tool, intended as a universal prevention and early intervention. The platform includes social-emotional learning and self-help wellness features as well as an artificial intelligence-powered chatbot designed to build coping skills.

OBJECTIVE: This evaluation aimed to examine the near-term impact of Alongside app use on students’ self-reported mental health outcomes.

METHODS: We conducted a nonrandomized pilot pragmatic evaluation leveraging anonymized user data. All data came from current Alongside users attending public middle and high schools in Texas and New Mexico, between 10 and 18 years old. Schools were actively engaged in partnership with Alongside and approved all procedures. Users were asked to complete mental health questionnaires upon app registration and at 1 and 3 months post registration. We conducted preregistered analyses as well as exploratory analyses to determine how symptoms changed over time and what factors (eg, demographic and app use) predicted changes in distress.

RESULTS: Analyses revealed statistically significant within-person decreases in overall distress (Young Person’s CORE; primary outcome) from baseline to 1 month with a small effect size (t₄₂=2.21, P=.03, r=0.34); however, there was no evidence that scores significantly decreased from baseline to 3 months (W=1821, n=85, P=.16). We found that at 3 months, identifying as part of the lesbian, gay, bisexual, transgender, queer, and questioning community predicted greater decreases in distress; otherwise, no demographic factors were significant predictors. In a nonregistered exploratory analysis of a subsample of users who reported elevated distress at baseline, decreases in distress were seen at both 1 month (W=128, n=20, P=.02, r=0.52) and 3 months (W=682, n=42, P=.004, r=0.45).

CONCLUSIONS: There may be short-term benefits associated with using the Alongside digital program. Further studies are required to determine potential preventative effects.

PMID:41061253 | DOI:10.2196/73180

JMIR Rehabil Assist Technol. 2025 Oct 8;12:e71379. doi: 10.2196/71379.

ABSTRACT

BACKGROUND: Digitalization is seen as a way to reduce the negative environmental impacts of health care production, but research is still limited.

OBJECTIVE: This study focuses on the assessment of the sustainability aspects of digital services in home care and health care. It demonstrates the approach to identify the climate impacts and social impacts-both positive and negative-on a selection of digital home care and health care services, such as medicine robot services for older home care clients, through 2 Finnish case studies.

METHODS: Impacts are identified from interviews and statistical data collected from public service providers and technology suppliers using both quantitative and qualitative assessments.

RESULTS: While a well-planned and well-implemented digital service is likely to be a climate-friendly option, every digitalization action carries at least some negative impacts. The design, architecture, and practical implementation of these services greatly affect their climate and social impacts.

CONCLUSIONS: This study uses a novel combination of impact assessment methods, highlighting the importance of qualitative understanding alongside quantitative approaches for interpreting results, especially when numerical data are limited. Advocating for multimethod impact assessments is crucial to properly capturing the service context and promoting holistic sustainability thinking.

PMID:41061252 | DOI:10.2196/71379

JMIR Res Protoc. 2025 Oct 8;14:e74988. doi: 10.2196/74988.

ABSTRACT

BACKGROUND: Multiple sclerosis (MS) is a chronic neurological disease of the central nervous system, primarily affecting young adults. Common challenges in MS include fatigue, physical impairments, and cognitive impairments, associated with low levels of physical activity, unemployment, reduced health-related quality of life (HRQoL), and substantial personal and societal costs. Many leave the workforce or reduce hours even when disability is low and despite a desire to increase work hours if the job is adjusted to their needs. Existing services aiming to optimize physical functions and work participation only initiate retrospectively, and there is a lack of knowledge regarding the possible effect of more proactive services.

OBJECTIVE: The objective of this study is to investigate the effects of a comprehensive multidisciplinary intervention, CoreDISTparticipation, delivered across health care levels (hospitals and municipalities) and sectors (health and employment/welfare), on barriers to work, physical activity, and physical functions; fatigue; and HRQoL for employed people with multiple sclerosis (pwMS) and to perform a health economic evaluation.

METHODS: This prospective, single-blinded randomized controlled trial (RCT) will include 115 pwMS with Expanded Disability Status Scale (EDSS) scores of 0-4 randomly allocated to either a CoreDISTparticipation intervention group or usual care (control group). The CoreDISTparticipation intervention includes (1) information videos, hospital outpatient physiotherapist assessments, and meetings with employment consultants; (2) group-based physiotherapy in municipalities for 60 minutes over 6 weeks, one indoor CoreDIST balance session, one outdoor CoreDIST balance and high-intensity interval session, and tailored work follow-up; and (3) 6 weeks of digitally supported independent training, twice weekly. Assessments will be conducted at baseline, week 9, and week 16. Primary outcomes include Multiple Sclerosis Work Difficulties Questionnaire-23 – Norwegian version (MSWDQ-23NV) and ActiGraph wGT3x-BT monitor scores. Secondary outcomes include Trunk Impairment Scale – modified Norwegian Version (TIS-modNV), Mini Balance Evaluation Systems Test (MiniBESTest), AccuGait Optimized force platform, 6-minute walk test (6MWT), Multiple Sclerosis Walking Scale-12, Multiple Sclerosis Impact Scale-29 – Norwegian version, EQ-5D-5L, and Fatigue Severity Scale – Norwegian version scores. The study will identify effects of CoreDISTparticipation versus usual care on work barriers, physical activity, balance, walking, fatigue, and quality of life, along with a health economic evaluation. Descriptive statistics and repeated measures mixed models will be performed using IBM SPSS version29.

RESULTS: We completed the enrolment phase and enrolled and randomized 115 participants in two phases by August 1, 2024. The 15-week retests were completed in December 2024, and data collection is estimated to be completed by September 2025. Results are expected to be published in the first quarter of 2026.

CONCLUSIONS: CoreDISTparticipation is an innovative approach proactively addressing physical functions, physical activity, and work participation. If effective, it can offer a low-cost approach that potentially may enhance the quality of life and workforce sustainability and reduce societal costs.

TRIAL REGISTRATION: ClinicalTrials.gov NCT06110468; https://www.clinicaltrials.gov/study/NCT06110468.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/74988.

PMID:41061251 | DOI:10.2196/74988

JMIR Aging. 2025 Oct 8;8:e76981. doi: 10.2196/76981.

ABSTRACT

BACKGROUND: Neuroimaging is crucial in the diagnosis of Alzheimer disease (AD). In recent years, artificial intelligence (AI)-based neuroimaging technology has rapidly developed, providing new methods for accurate diagnosis of AD, but its performance differences still need to be systematically evaluated.

OBJECTIVE: This study aims to conduct a systematic review and meta-analysis comparing the diagnostic performance of AI-assisted fluorine-18 fluorodeoxyglucose positron emission tomography (18F-FDG PET) and structural magnetic resonance imaging (sMRI) for AD.

METHODS: Databases including Web of Science, PubMed, and Embase were searched from inception to January 2025 to identify original studies that developed or validated AI models for AD diagnosis using 18F-FDG PET or sMRI. Methodological quality was assessed using the TRIPOD-AI (Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis-Artificial Intelligence) checklist. A bivariate mixed-effects model was employed to calculate pooled sensitivity, specificity, and summary receiver operating characteristic curve area (SROC-AUC).

RESULTS: A total of 38 studies were included, with 28 moderate-to-high-quality studies analyzed. Pooled SROC-AUC values were 0.94 (95% CI 0.92-0.96) for sMRI and 0.96 (95% CI 0.94-0.98) for 18F-FDG PET, demonstrating statistically significant intermodal differences (P=.02). Subgroup analyses revealed that for machine learning, pooled SROC-AUCs were 0.89 (95% CI 0.86-0.92) for sMRI and 0.95 (95% CI 0.92-0.96) for 18F-FDG PET, while for deep learning, these values were 0.96 (95% CI 0.94-0.97) and 0.97 (95% CI 0.96-0.99), respectively. Meta-regression identified heterogeneity arising from study quality stratification, algorithm types, and validation strategies.

CONCLUSIONS: Both AI-assisted 18F-FDG PET and sMRI exhibit high diagnostic accuracy in AD, with 18F-FDG PET demonstrating superior overall diagnostic performance compared to sMRI.

PMID:41061249 | DOI:10.2196/76981

J Speech Lang Hear Res. 2025 Oct 8:1-16. doi: 10.1044/2025_JSLHR-25-00162. Online ahead of print.

ABSTRACT

PURPOSE: This study is the first step in a project aimed at developing an intervention program for new hearing aid (HA) users and their relatives in the Province of Quebec, Canada. The objectives were to describe the experience of a first HA fitting from the perspective of adults with hearing loss and their relatives, to identify facilitators and barriers to the fitting process, and to identify elements that should be included in an intervention program to support HA adoption and use. Satisfaction regarding HAs and fitting services was also assessed after fitting.

METHOD: A mixed-methods design combining qualitative and quantitative data sources was used. Interviews were conducted with 10 new HA users, seven relatives, and 10 hearing care professionals. HA users also completed a questionnaire to assess their satisfaction with HAs and services after fitting. A qualitative content analysis was done on the data obtained from the interviews, and descriptive statistics were used to analyze data on satisfaction.

RESULTS: Identified facilitators and barriers to HA fitting for new users were related to professional services, HAs, relatives, and personal factors. Elements for inclusion in the intervention program were categorized into two groups: information to provide and support to offer. Participants reported a high satisfaction level with HAs (M = 87.6 ± 7.5%).

CONCLUSIONS: Several factors can influence the success of a first HA fitting, including aspects related to technology, professional services, and psychosocial elements. Participants suggested important components to include in the intervention for first-time fittings. These results will be used to develop an intervention program for new HA users and their relatives.

SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.30235315.

PMID:41061248 | DOI:10.1044/2025_JSLHR-25-00162

Neurology. 2025 Nov 11;105(9):e214270. doi: 10.1212/WNL.0000000000214270. Epub 2025 Oct 8.

ABSTRACT

BACKGROUND AND OBJECTIVES: Concomitant use of tramadol and antidepressants with potent inhibition of the cytochrome P450 2D6 (CYP2D6) enzyme is postulated to increase risk of seizures in older adults; yet, such an association has not been empirically tested in populations. We aimed to examine the association of concomitant tramadol and CYP2D6-inhibiting vs CYP2D6-neutral antidepressant use and the risk of seizures among older nursing home (NH) residents.

METHODS: This population-based cohort study was conducted using a 100% Medicare NH sample from January 2010 to December 2021. We included long-term residents aged 65 years or older who initiated antidepressants on existing tramadol use (tramadol-antidepressant users) or initiated tramadol on existing antidepressant use (antidepressant-tramadol users). Patients were followed up until the end of 1 year, NH discharge, death, or study end. The key exposure was concomitant use of tramadol with CYP2D6-inhibiting vs CYP2D6-neutral antidepressants. The key outcome was incident rates of medical encounters with a diagnosis of seizure and analyzed using negative binomial or Poisson regression models adjusted for baseline covariates (e.g., pain status and depressive, physical, and cognitive function) through the inverse probability of treatment weighting.

RESULTS: We identified 11,162 concomitant tramadol-antidepressant users (mean [SD] age, 86.2 [8.5] years; 9,077 [81.3%] female) and 58,994 concomitant antidepressant-tramadol users (mean [SD] age, 85.3 [8.4] years; 47,053 [79.8%] female). The incidence rate of seizures was 16.10 and 20.17 per 100 patient-years, respectively, for the tramadol-antidepressant and antidepressant-tramadol group. In both subgroups, co-use of tramadol with CYP2D6-inhibiting (vs with CYP2D6-neutral) antidepressants was associated with higher adjusted incidence rate ratios of seizures (1.09 [95% CI 1.02-1.18] and 1.06 [95% CI 1.03-1.10]). Findings were corroborated by a negative control exposure analysis in which co-use of hydrocodone with CYPD2D6-inhibiting (vs CYP2D6-neutral) antidepressants was not associated with risk of seizures.

DISCUSSION: Concomitant use of tramadol with CYP2D6-inhibiting vs CYP2D6-neutral antidepressants was associated with increased risk of seizures. Findings are only generalizable to long-term NH populations and are subject to residual confounding. Clinicians should be mindful of seizure risk in older patients who use tramadol concomitantly with antidepressants, particularly CYP2D6-inhibiting antidepressants.

CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that the combination of tramadol and CYP2D6-inhibiting antidepressants is associated with a higher risk of seizures compared with the combination of tramadol and CYP2D6-neutral antidepressants.

PMID:41061201 | DOI:10.1212/WNL.0000000000214270