Search Results (197)

Children with complex communication needs, including approximately one-third of children with autism, use augmentative and alternative communication (AAC) to meet their daily communication needs. AAC includes gestures, sign language, picture symbols, and computerized systems to augment or replace speech. Family support and training are essential for effective AAC implementation, but few interventions exist. We describe the iterative development of the FamTAM Intervention—an aided language modeling training and coaching intervention designed to support caregiver implementation and their school-based speech language pathologists (SLPs) preparedness to provide family coaching. We detail the iterative process, including refining the training content and delivery, expert reviews, and interviews with SLPs and caregivers. We also conducted interviews with participants to assess the clarity, feasibility, acceptability, and usability of the intervention. Our findings indicate that participants viewed the FamTAM Intervention as engaging, practical, and aligned with evidence-based AAC practices, while also identifying areas for further refinement. Full article

Background/Objectives: Cognitive stimulation and cognitive training are used as non-pharmacological approaches to support people living with Alzheimer’s disease, but Alzheimer-specific evidence is dispersed across heterogeneous intervention formats. This scoping review mapped structured cognitive stimulation and training interventions evaluated in people with mild-to-moderate Alzheimer’s disease and summarized the cognitive, emotional, functional, and follow-up outcomes reported. Methods: The review was conducted using the Joanna Briggs Institute methodology and reported according to PRISMA-ScR. PubMed, SciELO, PEDro, LILACS, and Google Scholar were searched on 24 February 2025 for studies published between January 2015 and 24 February 2025 in English, Portuguese, or Spanish. Intervention studies were eligible. Two reviewers independently screened records and charted data, with disagreements resolved by a third reviewer. Results: Of 352 records identified, five studies involving 245 participants were included. Interventions comprised virtual-reality cognitive stimulation, conventional cognitive training, group reminiscence therapy, a multicomponent music–reminiscence–reality-orientation intervention, and computerized cognitive training. In the limited technology-assisted evidence, statistically significant changes were reported in global cognition or selected memory, language, attention, and executive outcomes. Conventional cognitive training showed signals of improvement in initiative and temporary stabilization of memory, whereas reminiscence-based interventions primarily reported changes in depressive and neuropsychiatric symptoms. Where longer follow-up was available, benefits diminished over time. Conclusions: The mapped evidence suggests that structured cognitive stimulation and training may produce short-term, outcome-specific benefits in mild-to-moderate Alzheimer’s disease. Given the small and heterogeneous evidence base, these findings represent modality-related patterns within the included studies and should not be interpreted as evidence of comparative effectiveness. Full article

The droplet evaporation method (DEM) is an analytical approach in which substances dissolved or suspended in a liquid self-assemble into characteristic patterns upon evaporation. Applied to blood and blood-derived fluids, DEM has shown potential for diagnostics. In a previous study, we identified optimal temperature and relative humidity (rH) conditions for generating two main pattern features in dried serum and plasma droplets: crystalline structures (favored at high rH) and peripheral cracks (favored at low rH). The aim of the present study was to investigate whether sequential exposure to two humidity conditions, first 45% rH and then 15% rH, during the evaporation phase of a single experiment could combine both structural features and thereby enhance donor-specific pattern characteristics. Droplets of serum and plasma from eight healthy donors were evaporated under three conditions: constant 45% rH, constant 15% rH, and a changing condition (45% rH for 2 h, followed by 15% rH until completely dry). Evaporation temperatures were 24.5 °C for serum and 30.5 °C for plasma. Computerized texture (GLCM) and fractal (LCFD, MFD, BCFD, lacunarity) image analysis was used to correlate image features with serum and plasma parameters and contents. The donor differentiation was performed by a convolutional neural network (CNN) trained on the droplet pattern images. The changing-humidity condition produced patterns combining the central crystalline structures characteristic of the high-rH condition with the peripheral cracks characteristic of the low-rH condition and yielded the highest CNN-based donor classification accuracy for both fluids, 84.4% for serum, 83.3% for plasma, compared with 66.2–80.8% under the stable conditions. Selected image-evaluation parameters further correlated with the blood derivate contents and parameters including glucose, total protein, triglycerides, homocysteine, urea and the age of the donor. These results suggest that sequential humidity exposure substantially enriches the structural information content of DEM patterns and the amount of donor-specific information that can be extracted from them, with potential implications for diagnostic applications. Full article

Maintenance management increasingly depends on effective information flow and coordination between internal teams and external service providers. This study investigates the use of Business Process Model and Notation (BPMN) to support the formalization of Computerized Maintenance Management System (CMMS) workflows and improve transparency, decision-making, and interorganizational coordination. A single case study was conducted in the maintenance department of an electricity distribution company characterized by tacit knowledge, informal communication practices, and limited process formalization. Existing corrective maintenance workflows were analyzed and modeled using BPMN to identify inefficiencies, decision points, and opportunities for improvement. The proposed BPMN models were aligned with CMMS operational states associated with anomaly management and work-order execution processes and supported by a procedural manual. Results obtained during a three-month observation period suggest reductions in training time, email communications, and dependence on individual decision-makers, together with increased use of CMMS workflow functionalities and improved process traceability. These findings provide preliminary evidence, derived from operational indicators within a single case study, that BPMN-supported process formalization may contribute to workflow standardization, operational clarity, and knowledge management in maintenance-intensive environments. Given the single-case design and limited observation period, the results should be interpreted as context-specific and not directly generalizable to the broader energy sector. Full article

Background: Falls and fall-related injuries are common in older adults and are frequently accompanied by fear of falling (FoF), which may lead to activity avoidance and functional decline. Because many interventions target falls or FoF in isolation, we conducted a systematic review and meta-analysis of randomized controlled trials (RCTs) to identify, describe, and evaluate interventions reporting both falls and FoF outcomes in older adults. Methods: This systematic review and meta-analysis were registered in PROSPERO (CRD420251113137) and conducted in accordance with PRISMA guidelines. PubMed, Embase, and Web of Science were searched from inception to 4 November 2025. Eligible studies were English-language RCTs that included adults aged ≥60 years, evaluated nonpharmacological interventions, and reported both FoF and falls. Methodological quality was assessed using the PEDro scale. Random-effects meta-analyses were performed for FoF (Hedges g), and Bayesian random-effects binomial meta-analyses were conducted for falls. Results: Ten RCTs published between 1998 and 2018 (sample sizes per trial: n = 27–540) were included. Interventions included cognitive–behavioral therapy-based programs, Tai Chi, physiotherapist-led strength and balance training, computerized visual feedback, and video-guided home exercise. PEDro scores ranged from 6 to 9 (mean, 7.7). Pooled analyses showed no significant effect on FoF at the end of intervention (g = −0.20, 95% CI −1.45 to 1.05; p = 0.68; high heterogeneity) or at follow-up (g = −0.14, 95% CI −0.60 to 0.33; p = 0.50). For falls, postintervention evidence favored the null (BF₁₀ = 0.16; pooled estimate −0.01, 95% credible interval [CrI] −0.30 to 0.14). Follow-up results were inconclusive (BF₁₀ = 2.07; pooled CrI −0.56 to 0.00), with substantial uncertainty. Conclusions: Across RCTs that measured both outcomes, interventions did not consistently improve both FoF and falls outcomes. These findings may suggest a partial dissociation between psychological and physical fall-related outcomes, highlighting the need for integrated, adequately powered trials that utilize standardized measures and longer follow-up periods. Full article

Background/Objectives: Disorganization of retinal inner layers (DRIL) is an important and supportive biomarker in optical coherence tomography (OCT) imaging for diagnosing the extent of diabetic macular edema (DME) in patients and anticipating visual outcomes. But the manual DRIL identification is subject to interobserver bias and requires a lot of time and effort from the experts. This research presents a novel, computerized, and clinically guided approach for the classification of DRIL that leverages the central 1 mm foveal region extracted through the annotations provided by the expert ophthalmologists and investigates the effectiveness of a transformer and Masked Auto Encoder (MAE) based foundation model (RETFound) as the primary approach. Methods: We fine-tuned and validated the RETFound model, utilizing accurate foveal center coordinates provided by the experienced ophthalmologists. Our approach emphasizes the macular region that is significant diagnostically, where DME biomarkers manifest more predominantly. To guarantee robust evaluation, the dataset was divided into 85% training and 15% held-out test sets. We performed 5-fold cross-validation exclusively on the training dataset with baseline, conservative, and moderate fine-tuning strategies, and the final model was evaluated on the independent, unseen test set. Convolutional neural network (CNN)-based transfer learning (TL) models (MobileNetV2, EfficientNetB0, InceptionV3, DenseNet121, and DenseNet169) were also assessed for comparative evaluation. Results: The RETFound model yielded the best outcomes under the conservative fine-tuning strategy, achieving a mean test accuracy (AC) of 0.9339 ± 0.0036 and an area under the curve (AUC) of 0.9660 ± 0.0028 on the independent held-out test set across the five fold-trained models. The moderate and baseline evaluations achieved comparatively lower outcomes, highlighting the effectiveness of the conservative approach. The RETFound model consistently outperformed CNN models, exhibiting stability and superior generalization for DRIL classification. We performed statistical validation using the Wilcoxon signed-rank test and 95% confidence intervals to confirm the robustness of the proposed method, and an ablation analysis showed that the fovea-centered region of interest (ROI) guidance consistently improved results when compared with whole OCT analysis. Conclusions: This research demonstrates that the deep-learning (DL) methods assisted by expert clinical knowledge with an anatomically aligned ROI could provide remarkable results in DRIL detection applications. This work attempts to establish an anatomically relevant framework for computerized DRIL identification that focuses on the highly crucial macular region, possibly helping in faster intervention and improved diagnosis in the management of DME. Full article

Background: Intrinsic capacity (IC) is key to promoting healthy aging, and managing declines in IC is crucial for delaying functional deterioration in older adults. Digital health interventions (DHIs) hold promising potential for addressing IC decline. This scoping review aims to synthesize existing evidence by mapping the types of DHIs employed and examining their effects across the five domains of IC in older adults. Methods: The review was conducted following the five-stage framework of Arksey and O’Malley and the PRISMA-ScR guideline. The search was performed across PubMed, Embase, CINAHL, Cochrane Library, PsycINFO, SinoMed, and CNKI databases for studies published between 1 January 2015 and 31 July 2025. Relevant studies were identified using MeSH terms and free-text terms related to “older adults”, “digital health”, and “intrinsic capacity”. Results: Based on the eligibility criteria, 81 studies were included. The DHIs identified encompassed virtual reality, exergames, computerized cognitive training, mHealth, internet-based interventions, telehealth, digital hearing aids, assistive robotics, and visual biofeedback. Most studies focused on single-domain interventions (74%), with cognition being the most targeted (40.7%), while sensory (4.9%) and vitality (2.5%) domains received the least attention. No digital interventions targeted all five IC domains. Regarding efficacy, many DHIs reported statistically significant improvements in one or more IC domains; however, the magnitude and consistency of these effects varied considerably across studies. Conclusions: Preliminary evidence suggests that DHIs show potential in managing declines in IC among older adults. However, evidence quality varies significantly, often derived from small-scale studies. Future research should focus on establishing clinical effectiveness through adequately powered trials and on integrating DHIs into comprehensive intervention strategies that target all domains of IC, with robust evaluation of their outcomes. Full article

Accurate estimation of Body Carcass Fat (BCF) is essential for evaluating the physiological condition of ewes. Traditional assessment via Body Condition Score (BCS) through palpation is inaccurate and subjective. BCF can now be predicted more precisely using objective measurements. This study presents a comparative analysis of eight machine learning (ML) models for predicting BCF in Coopworth ewes, using weight and RGB-image-based body measurements. Four non-linear regression methods and four neural network architectures were evaluated using a dataset of 74 ewes with 13 independent variables. The dataset was partitioned into training (52 ewes), validation (11 ewes), and testing (11 ewes) sets. The Gradient Boosting Regression achieved the highest predictive accuracy with an R² value of 0.9434 using body weight and width, followed by Ensemble Neural Network (R² = 0.9371) using body weight. The findings demonstrate the effectiveness of the Gradient Boosting Regression, Ensemble Neural Network and Random Forest tree-based approaches for morphometric prediction tasks in biological applications. BCF values obtained from image analysis were validated against those derived from computerized tomography (CT), considered the gold standard. These findings highlight the potential of image-guided, ML-driven models for objective, non-invasive, cost-effective assessment of ewe body composition in modern livestock systems. Full article

Background: Nurse teletriage has emerged as a component of modern healthcare delivery, utilizing telecommunication technologies to assess patient conditions remotely and guide appropriate care decisions. As healthcare systems face increasing demand and the need for cost-effective care delivery, teletriage services have expanded, particularly following the COVID-19 pandemic. Objective: This narrative review examines the current state of nurse teletriage practice, its effectiveness, safety outcomes, and implementation considerations. A comparative analysis with physician-led teletriage models is provided, and the emerging role of artificial intelligence is explored. Methods: A narrative review of the literature was conducted through searches of multiple databases including PubMed/MEDLINE, CINAHL, Cochrane Library, Embase, Web of Science, and Google Scholar. This approach was selected due to the heterogeneous nature of the teletriage literature, which spans diverse study designs, populations, and outcomes that are not amenable to formal systematic synthesis. Peer-reviewed articles published between 1970 and 2024 examining safety outcomes, effectiveness, and implementation frameworks were reviewed. Results: The available evidence suggests that nurse-led teletriage systems, particularly when supported by computerized decision support systems, can improve patient access to care while maintaining safety standards. Studies indicate that telephone triage nursing does not increase mortality, hospitalization rates, or emergency department referrals when properly implemented. One well-documented physician-led model in Israel reported diagnosis accuracy rates of 98.5% and decision reasonableness rates of 92%, though generalizability across settings requires caution. Key success factors appear to include the use of evidence-based protocols, staff training, technology infrastructure, and quality assurance programs. While these findings are promising, the heterogeneous nature of the included studies and absence of formal quality assessment warrant cautious interpretation. Conclusions: Nurse teletriage appears to be an effective and safe approach to healthcare delivery that addresses challenges in modern healthcare systems. The choice between nurse-led and physician-led models should consider population complexity, case types, available resources, and economic factors. Artificial intelligence technologies offer potential opportunities to enhance teletriage, though careful validation is essential. Future research should focus on long-term outcomes, comparative effectiveness across healthcare systems, and rigorous evaluation of AI applications. Highlights: Telephone triage services, where nurses or physicians assess patients remotely and guide them to appropriate care, have become increasingly important in modern healthcare. This narrative review examines the evidence on nurse-led telephone triage, comparing it with physician-led models and exploring emerging technologies like artificial intelligence. The available evidence suggests that nurse-led systems, when supported by appropriate protocols and training, can safely improve patient access to care while reducing healthcare costs. Physician-led models may offer advantages for complex cases but at higher costs. While artificial intelligence shows promise for enhancing triage accuracy, current evidence specific to telephone triage remains limited. Healthcare organizations should carefully consider their population needs, available resources, and local context when implementing teletriage services. Full article

Background/Objectives: This study examined the effects of a computerized naming intervention combined with either cerebellar anodal transcranial direct-current stimulation (A-tDCS) or sham (S-tDCS) on noun and verb naming in Cantonese-speaking persons with chronic stroke-related aphasia (PWA). Methods: A double-blind, randomized, crossover, sham-controlled clinical trial was conducted with six Cantonese-speaking PWA following stroke. Participants received a 60 min computerized naming intervention incorporating audio–visual speech perception cues over five consecutive days, paired with concurrent 20 min of either 2 mA cerebellar A-tDCS or S-tDCS. Generalized linear mixed-effects models (GLMM) and linear mixed-effects models (LME) were used to evaluate naming accuracy and reaction time (RT). Individual variability was further explored through single-case analyses of naming accuracy changes across conditions and grammatical categories. Results: The GLMM showed a significant three-way interaction of condition, grammatical category, and time (p < 0.05). Specifically, the intervention paired with S-tDCS significantly improved verb naming, whereas A-tDCS did not induce significant improvements at the group level, effectively showing significantly smaller gains regarding verb naming compared to S-tDCS. Overall, RT decreased post-treatment across groups, but no significant differences emerged by the tDCS condition. The results support the promising efficacy of the Cantonese computerized audio–visual noun and verb naming therapy. Single-case analyses revealed high inter-individual variability in response to neuromodulation effects on naming and behavioral treatment outcomes. Conclusions: This study contributes to the emerging literature on cerebellar neuromodulation in post-stroke aphasia and underscores the need for larger trials examining grammar-specific (particularly verb-related) effects and polarity-dependent outcomes. It also highlights the value of developing personalized neuromodulation protocols to optimize the efficacy of behavioral language interventions in people with aphasia. Full article

Background/Objectives: Chronic psychomotor and cognitive slowing after stroke can persist despite standard rehabilitation, especially in young adults with subcortical injuries. Innovative, integrated interventions are crucial for patients who have reached a plateau in their rehabilitation. We present a case of a 41-year-old male with chronic psychomotor and cognitive slowing following a left lenticulostriate infarction (NIHSS score = 5 at onset), who had plateaued after conventional rehabilitation. Methods: Over 4 weeks the patient underwent 20 sessions of a multimodal approach including high-frequency repetitive transcranial magnetic resonance stimulation over the supplementary motor area and bilateral temporo-parietal junctions and simultaneous computerized cognitive training targeting attention and executive function. Both motor and cognitive assessments, along with quantitative EEG (qEEG) evaluations, were conducted before and after the treatment. Results: At the end of treatment, the patient showed significant clinical improvement: speed and coordination in upper extremities (Finger Tapping Test) increased by 66% (dominant hand) and 74% (non-dominant hand), while finger dexterity (Nine-Hole Peg Test) increased by 25% (dominant hand) and 19% (non-dominant hand). Cognitive scores improved in alertness (58%), visual exploration (25%), and flexibility (24%), while divided attention remained stable. qEEG investigation showed increases in alpha (79%), gamma (33%), and beta (10%) power, with topographic shifts in the stimulated regions. Conclusions: These findings highlight the feasibility of combining targeted rTMS and cognitive training to enhance neuroplasticity in the chronic phase of stroke. Clinical recovery was accompanied by normalized cortical rhythms, suggesting qEEG biomarkers may be useful for tracking treatment response. Multimodal precision neurorehabilitation may offer a path forward for patients with persistent cognitive–motor deficits post-stroke. Full article

Background: Mild cognitive impairment (MCI) is a high-risk prodromal stage of dementia. While tablet/computer-based computerized cognitive training (CCT) is widely used, its efficacy and gamification’s role need clarification. Objective: This study aimed to evaluate the effect of tablet/computer-based CCT on global cognition in older adults with MCI and explore the impact of gamification. Methods: We systematically searched five databases for RCTs (through October 2025) involving individuals aged ≥55 with MCI. The intervention was task-based CCT via tablets/computers. Primary outcome was global cognition. We used random-effects meta-analysis and subgroup analyses. Results: Nineteen RCTs (1013 participants) were included. CCT demonstrated a significant, moderate positive effect on global cognition (Hedges’ g = 0.57, 95% CI [0.36, 0.78]). A trend suggesting greater benefits with higher gamification was observed: high (g = 0.71), medium (g = 0.46), and low (g = 0.45) degrees. However, subgroup differences were not statistically significant (p = 0.4333). Results were robust in sensitivity analyses. Conclusions: Tablet/computer-based CCT effectively improves global cognition in MCI. The potential additive value of gamification highlights its promise for enhancing engagement and effects, warranting further investigation in larger trials. This systematic review was registered with PROSPERO (CRD420251231618). Full article

Background/Objectives: Disorganization of the retinal inner layers (DRIL) is an important biomarker of diabetic macular edema (DME) that has a very strong association with visual acuity (VA) in patients. But the unavailability of annotated training data from experts severely limits the adaptability of models pretrained on real-world images owing to significant variations in the domain, posing two primary challenges for the design of efficient computerized DRIL detection methods. Methods: In an attempt to address these challenges, we propose a novel, self-supervision-based learning framework that employs a huge unlabeled optical coherence tomography (OCT) dataset to learn and detect clinically applicable interpretations before fine-tuning with a small proprietary dataset of annotated OCT images. In this research, we introduce a spatial Bootstrap Your Own Latent (BYOL) with a hybrid spatial aware loss function aimed to capture anatomical representations from unlabeled OCT dataset of 108,309 images that cover various retinal abnormalities, and then adapt the learned interpretations for DRIL classification employing 823 annotated OCT images. Results: With an accuracy of 99.39%, the proposed two-stage approach substantially exceeds the direct transfer learning models pretrained on ImageNet. Conclusions: The findings demonstrate the efficacy of domain-specific self-supervised learning for rare retinal pathological detection tasks with limited annotated data. Full article

Background/Objectives: The management of high-risk pregnancies remains a major clinical challenge, particularly regarding the optimal timing of delivery, which has significant implications for both perinatal outcomes and healthcare costs. In this context, computerized cardiotocography (cCTG) offers an objective, non-invasive and cost-effective method for fetal surveillance, providing quantitative measures of heart rate dynamics that reflect autonomic regulation and oxygenation status. This study aimed to develop and validate regression-based machine learning models capable of predicting the duration of neonatal hospitalization—an objective and quantifiable indicator of neonatal well-being—using cCTG parameters obtained outside of labor, binary clinical variables describing the presence or absence of pregnancy pathologies, and gestational age at monitoring and at delivery. Methods: A total of 694 singleton high-risk pregnancies complicated by gestational diabetes, preexisting diabetes, intrahepatic cholestasis of pregnancy, pregnancy-induced or preexisting hypertension, or fetal growth restriction were enrolled. Twenty clinically relevant features derived from cCTG recordings and perinatal data were used to train and evaluate four regression algorithms: Random Forest, CatBoost, XGBoost, and LightGBM against a linear regression model with Ridge regularization serving as a benchmark. Results: Random Forest achieved the highest generalization performance (test R² = 0.8226; RMSE = 3.41 days; MAE = 2.02 days), outperforming CatBoost (R² = 0.7059), XGBoost (R² = 0.6911), LightGBM (R² = 0.6851) and the linear regression benchmark with Ridge regularization (R² = 0.5699) while showing a consistent train–validation–test profile (0.9428 → 0.8042 → 0.8226). The error magnitude (≈2 days on average) is clinically interpretable for neonatal resource planning, supporting the model’s practical utility. These findings justify selecting Random Forest as the final predictor and its integration into a clinician-facing application for real-time length-of-stay estimation. Conclusions: Machine learning models integrating cCTG features with maternal clinical factors can accurately predict neonatal hospitalization duration in pregnancies complicated by maternal or fetal disease. This approach provides a clinically interpretable and non-invasive decision support tool that may enhance delivery planning, optimize neonatal resource allocation, and improve perinatal care outcomes. Full article

Background/Objectives: Executive function (EF) impairments are found in a variety of neurodegenerative disorders, including in Primary Progressive Aphasia (PPA), which is primarily characterized by language impairments. The goal of this preliminary investigation was to evaluate the hypothesis that, by targeting domain-general EFs, domain-specific functions—specifically, language processing—might also be improved in this population. Methods: This case series included four Greek-speaking individuals with PPA who underwent behavioral and neurostimulation treatment daily for 15 consecutive sessions. Behavioral treatment was performed through Computerized Cognitive Training (CCT) that targeted various EF functions. Neurostimulation treatment included alpha-rhythm transcranial alternating current stimulation (tACS) over the left dorsolateral prefrontal cortex (DLPFC), previously implicated in EF functioning. EF and language performance was assessed before (pre-) and after (post-) treatment and was also compared against the performance of healthy control individuals. Results: The pre- to post-treatment comparisons showed improvements primarily in EF functions, with heterogeneous improvements in language functions across the four cases. Except for one task (N-back), in which all four patients showed numerical improvement, the pattern of numerical gains differed across patients. Conclusions: While the treatment protocol targeted EF functioning, improvements were found for both EF and language processes (albeit more variable across patients). These results support the hypothesis that improvement in domain-general functions may lead to improvements in domain-specific functions as well. These preliminary findings can be used as guiding evidence for the design of future, large-scale clinical trials that will allow us to generalize conclusions to the broader PPA population. Full article