Search Results (19)

Accurate segmentation of key tumor subregions in adult gliomas from Magnetic Resonance Imaging (MRI) is of critical importance for brain tumor diagnosis, treatment planning, and prognosis. However, this task remains poorly investigated and highly challenging due to the considerable variability in shape and appearance of these areas across patients. This study proposes a novel Deep Learning architecture leveraging modality-specific encoding and attention-based refinement for the segmentation of glioma subregions, including peritumoral edema (ED), necrotic core (NCR), and enhancing tissue (ET). The model is trained and validated on the Brain Tumor Segmentation (BraTS) 2023 challenge dataset and benchmarked against a state-of-the-art transformer-based approach. Our architecture achieves promising results, with Dice scores of 0.78, 0.86, and 0.88 for NCR, ED, and ET, respectively, outperforming SegFormer3D while maintaining comparable model complexity. To ensure a comprehensive evaluation, performance was also assessed on standard composite tumor regions, i.e., tumor core (TC) and whole tumor (WT). The statistically significant improvements obtained on all regions highlight the effectiveness of integrating complementary modality-specific information and applying channel-wise feature recalibration in the proposed model. Full article

Chronic pain is prevalent and disproportionately impacts adults with a lower quality of life. Although subjective self-reporting is the “gold standard” for pain assessment, tools are needed to objectively monitor and account for inter-individual differences. This study introduced a novel framework to objectively classify pain intensity levels using physiological signals during Quantitative Sensory Testing sessions. Twenty-four participants participated in the study wearing physiological sensors (blood volume pulse (BVP), galvanic skin response (GSR), electromyography (EMG), respiration rate (RR), skin temperature (ST), and pupillometry). This study employed two analysis plans. Plan 1 utilized a grid search methodology with a 10-fold cross-validation framework to optimize time windows (1–5 s) and machine learning hyperparameters for pain classification tasks. The optimal time windows were identified as 3 s for the pressure session, 2 s for the pinprick session, and 1 s for the cuff session. Analysis Plan 2 implemented a leave-one-out design to evaluate the individual contribution of each sensor modality. By systematically excluding one sensor’s features at a time, the performance of these sensor sets was compared to the full model using Wilcoxon signed-rank tests. BVP emerged as a critical sensor, significantly influencing performance in both pinprick and cuff sessions. Conversely, GSR, RR, and pupillometry demonstrated stimulus-specific sensitivity, significantly contributing to the cuff session but with limited influence in other sessions. EMG and ST showed minimal impact across all sessions, suggesting they are non-critical and suitable for reducing sensor redundancy. These findings advance the design of sensor configurations for personalized pain management. Future research will focus on refining sensor integration and addressing stimulus-specific physiological responses. Full article

Background: Mild Cognitive Impairment (MCI) is a critical transitional phase between normal aging and dementia, and early detection is essential to mitigate cognitive decline. Traditional cognitive assessment tools, such as the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA), exhibit limitations in feasibility, which potentially and partially affects results for early-stage MCI detection. This study developed and tested a supportive cognitive assessment system for MCI auxiliary identification, leveraging eye-tracking features and convolutional neural network (CNN) analysis. Methods: The system employed eye-tracking technology in conjunction with machine learning to build a multimodal auxiliary identification model. Four eye movement tasks and two cognitive tests were administered to 128 participants (40 MCI patients, 57 elderly controls, 31 young adults as reference). We extracted 31 eye movement and 8 behavioral features to assess their contributions to classification accuracy using CNN analysis. Eye movement features only, behavioral features only, and combined features models were developed and tested respectively, to find out the most effective approach for MCI auxiliary identification. Results: Overall, the combined features model achieved a higher discrimination accuracy than models with single feature sets alone. Specifically, the model’s ability to differentiate MCI from healthy individuals, including young adults, reached an average accuracy of 74.62%. For distinguishing MCI from elderly controls, the model’s accuracy averaged 66.50%. Conclusions: Results show that a multimodal model significantly outperforms single-feature models in identifying MCI, highlighting the potential of eye-tracking for early detection. These findings suggest that integrating multimodal data can enhance the effectiveness of MCI auxiliary identification, providing a novel potential pathway for community-based early detection efforts. Full article

Background: Maternal overnutrition critically influences offspring’s long-term metabolic and cognitive health. While prior research indicates maternal diet can disrupt hippocampal function, the specific impact on spatial memory remains unclear. Methods: Female mice were fed a high-fat diet (HFD) for nine weeks before and during pregnancy. Offspring were weaned onto a standard diet and tested at postnatal day 90 using the dry maze, a spatial reference memory task. Results: HFD-exposed offspring exhibited significant learning acquisition impairments, with prolonged latencies in locating hidden rewards and diminished within-session improvements compared to controls. During the probe trial, they spent significantly less time in the target quadrant, indicating long-term spatial memory retention deficits. Notably, these cognitive impairments occurred independently of body weight differences at testing. Discussion: This study uniquely demonstrates that maternal HFD exposure induces specific spatial memory deficits in adult offspring, potentially through neurodevelopmental alterations preceding metabolic dysfunction. The results highlight the importance of prenatal nutrition in shaping cognitive outcomes later in life. Conclusions: These findings extend our understanding of how prenatal nutrition impacts cognitive aging and disease susceptibility. Given rising obesity rates among women of reproductive age, this research underscores the urgent need for targeted interventions to mitigate the intergenerational effects of maternal overnutrition on brain function. Full article

Medical diagnosis plays a critical role in the early detection and treatment of diseases by examining symptoms and supporting findings through advanced laboratory testing. Early and accurate diagnosis is essential for detecting medical problems and then prescribing the most effective treatment strategies, especially in life-threatening diseases such as leukemia. Leukemia, a blood malignancy, is one of the most prevalent cancer types affecting both adults and children. It is caused by the rapid and uncontrolled growth of abnormal white blood cells in the bone marrow. This accumulation interferes with the production of normal blood cells, leading to a weakened immune deficiency, anemia, and bleeding disorders. Conventional leukemia diagnostic methods are time-consuming, manually intensive, and inefficient. This research study proposes an automatic diagnostics prediction of leukemia by analyzing blood images according to the shape of the blast cells using digital image processing and machine learning. The purpose of blood cell detection is to precisely identify and classify diverse blood cells, detecting anomalies associated with blood cancers like leukemia. This supports early diagnosis and monitoring, which leads to more effective treatments and improved results for cancer patients. To accomplish this task, we use digital image processing techniques and then apply the convolutional neural network (CNN) deep learning algorithm to blood sample images. This research employs a multi-stage methodology, including data preparation, data preprocessing, feature extraction, and then classification. While our model is built on a typical CNN architecture, we make significant advances by using preprocessing techniques and hyperparameter tuning. We have modified its layers combination to include convolutional, pooling, and fully connected layers that are optimized for image characteristics. These layers are fine-tuned for better feature extraction and classification accuracy. This study showed that blood cell detection for diagnosing acute leukemia based on images had 99% accuracy and outperformed other advanced models, including DenseNet121, ResNet-50, Incep-tionv3, MobileNet, and EfficientNet. The comprehensive analysis of the results reveals the highest accuracy of leukemia detection as compared to existing studies in the relevant literature. Full article

Background: Amblyopia is a neurodevelopmental disorder of vision, commonly caused by strabismus or anisometropia during early childhood. While studies demonstrated that perceptual learning improves visual acuity and stereopsis in adults with amblyopia, accompanying changes in visual cortical function remain unclear. Methods: We measured functional magnetic resonance imaging (fMRI) responses before and after perceptual learning in seven adults with amblyopia. Our learning tasks involved dichoptic high-attention-demand tasks that avoided V1 function-related tasks and required high-level cortical functions (e.g., intraparietal sulcus) to train the amblyopic eye. Results: Perceptual learning induced low-level visual cortical function changes, which were strongly associated with the etiology of amblyopia and visual function improvements. Anisometropic amblyopes showed functional improvements across all regions of interest (ROIs: V1, V2, V3, V3A, and hV4), along with improvements in visual acuity and stereoacuity. In contrast, strabismic amblyopes showed robust improvements in visual cortical functions only in individuals who experienced significant gains in visual acuity and stereoacuity. Notably, improvements in V1 functions were significantly correlated with the magnitude of visual acuity and stereoacuity improvements when combining both anisometropic and strabismic amblyopes. Conclusions: Our findings provide evidence that learning occurs in both high-level and low-level cortical processes. Our study suggests that early intervention to correct eye alignment (e.g., strabismus surgery) is critical for restoring both visual and cortical functions in strabismic amblyopia. Full article

Falls among older adults represent a critical global public health problem, as they are one of the main causes of disability in this age group. We have developed an automated approach to identifying fall risk using low-cost, accessible technology. Trunk movement patterns were collected from 181 older people, with and without a history of falls, during the execution of the Mini-BESTest. Data were captured using smartphone sensors (an accelerometer, a gyroscope, and a magnetometer) and classified based on fall history using deep learning algorithms (LSTM). The classification model achieved an overall accuracy of 88.55% a precision of 90.14%, a recall of 87.93%, and an F1 score of 89.02% by combining all signals from the Mini-BESTest tasks. The performance outperformed the metrics we obtained from individual tasks, demonstrating that aggregating all cues provides a more complete and robust assessment of fall risk in older adults. The results suggest that combining signals from multiple tasks allowed the model to better capture the complexities of postural control and dynamic gait, leading to better prediction of falls. This highlights the potential of integrating multiple assessment modalities for more effective fall risk monitoring. Full article

As teachers, we are living and working in times of abundant challenge and change. These challenges transpire across different education levels and sectors, including K–12, vocational, tertiary, and adult learning. Within this vast education ecosystem, a major challenge for all teachers is to allocate time, effort, and resources to ensure that their students receive a quality education with real-world implications, influencing soft-skill attainment, such as teamwork, communication, and critical thinking skills. In this article, the authors discuss, through a theoretical lens, the value of considering a national and universal approach to self- and peer-evaluations of authentic assessment tasks to improve teacher practice in Australia. Currently, there is modest opportunity amongst K–12 and tertiary teachers to comprehensively learn together, limiting cross-fertilisation of practice and interconnectedness, and as a national community of practice. The authors argue in this paper that offering an avenue to share knowledge and practice in authentic assessment design could potentially assist in addressing this challenge. Therefore, the article is dedicated to exploring the barriers and opportunities to advance a national and universal approach to transferable professional development in authentic assessment practice within the Australian education ecosystem. Full article

Fairness Artificial Intelligence (AI) aims to identify and mitigate bias throughout the AI development process, spanning data collection, modeling, assessment, and deployment—a critical facet of establishing trustworthy AI systems. Tackling data bias through techniques like reweighting samples proves effective for promoting fairness. This paper undertakes a systematic exploration of reweighting samples for conventional Machine-Learning (ML) models, utilizing five models for binary classification on datasets such as Adult Income and COMPAS, incorporating various protected attributes. In particular, AI Fairness 360 (AIF360) from IBM, a versatile open-source library aimed at identifying and mitigating bias in machine-learning models throughout the entire AI application lifecycle, is employed as the foundation for conducting this systematic exploration. The evaluation of prediction outcomes employs five fairness metrics from AIF360, elucidating the nuanced and model-specific efficacy of reweighting samples in fostering fairness within traditional ML frameworks. Experimental results illustrate that reweighting samples effectively reduces bias in traditional ML methods for classification tasks. For instance, after reweighting samples, the balanced accuracy of Decision Tree (DT) improves to 100%, and its bias, as measured by fairness metrics such as Average Odds Difference (AOD), Equal Opportunity Difference (EOD), and Theil Index (TI), is mitigated to 0. However, reweighting samples does not effectively enhance the fairness performance of K Nearest Neighbor (KNN). This sheds light on the intricate dynamics of bias, underscoring the complexity involved in achieving fairness across different models and scenarios. Full article

Neurocognitive Disorders (NCDs) pose a significant global health concern, and early detection is crucial for optimizing therapeutic outcomes. In parallel, mobile health apps (mHealth apps) have emerged as a promising avenue for assisting individuals with cognitive deficits. Under this perspective, we pioneered the development of the RODI mHealth app, a unique method for detecting aligned with the criteria for NCDs using a series of brief tasks. Utilizing the RODI app, we conducted a study from July to October 2022 involving 182 individuals with NCDs and healthy participants. The study aimed to assess performance differences between healthy older adults and NCD patients, identify significant performance disparities during the initial administration of the RODI app, and determine critical features for outcome prediction. Subsequently, the results underwent machine learning processes to unveil underlying patterns associated with NCDs. We prioritize the tasks within RODI based on their alignment with the criteria for NCDs, thus acting as key digital indicators for the disorder. We achieve this by employing an ensemble strategy that leverages the feature importance mechanism from three contemporary classification algorithms. Our analysis revealed that tasks related to visual working memory were the most significant in distinguishing between healthy individuals and those with an NCD. On the other hand, processes involving mental calculations, executive working memory, and recall were less influential in the detection process. Our study serves as a blueprint for future mHealth apps, offering a guide for enhancing the detection of digital indicators for disorders and related conditions. Full article

This research focuses on understanding the effectiveness of a university-based induction support program (ISP) instituted to support the graduates of an urban university who completed their preparation during the COVID-19 pandemic. We framed the evaluation of our ISP as participatory action research (PAR) and chose a critical theoretical perspective of adult learning and development as our theoretical lens because of the close alignment with this perspective to our college’s conceptual framework on social justice and equity. Primary data sources consisted of individual interviews with 15 key informants identified by the ISP research team. Data analyses occurred through a recursive and generative process moving between open coding using Nvivo and reflection on the literature related to critical adult learning theory and research on effective induction and coaching models. Findings included (a) the ISP as a liberating space to engage with other educators, (b) the ISP’s role as a university-based program for urban educators, (c) the ISP program’s impact on stakeholders’ professional identity, and (d) the ISP and the concept of criticality. The study also underscored the advantages of using PAR designs for program evaluation and/or accreditation inquiries focusing on continuous improvement. Full article

The Star Excursion Balance Test (SEBT) is a common assessment used across clinical and research settings to test dynamic standing balance. The primary measure of this test is maximal reaching distance performed by the non-stance limb. Response time (RT) is a critical cognitive component of dynamic balance control and the faster the RT, the better the postural control and recovery from a postural perturbation. However, the measure of RT has not been done in conjunction with SEBT, especially with musculoskeletal fatigue. The purpose of this study is to examine RT during a SEBT, creating a modified SEBT (mSEBT), with a secondary goal to examine the effects of muscular fatigue on RT during SEBT. Sixteen healthy young male and female adults [age: 20 ± 1 years; height: 169.48 ± 8.2 cm; weight: 67.93 ± 12.7 kg] performed the mSEBT in five directions for three trials, after which the same was repeated with a response time task using Blazepod™ with a random stimulus. Participants then performed a low-intensity musculoskeletal fatigue task and completed the above measures again. A 2 × 2 × 3 repeated measures ANOVA was performed to test for differences in mean response time across trials, fatigue states, and leg reach as within-subjects factors. All statistical analyses were conducted in JASP at an alpha level of 0.05. RT was significantly faster over the course of testing regardless of reach leg or fatigue state (p = 0.023). Trial 3 demonstrated significantly lower RT compared to Trial 1 (p = 0.021). No significant differences were found between fatigue states or leg reach. These results indicate that response times during the mSEBT with RT is a learned skill that can improve over time. Future research should include an extended familiarization period to remove learning effects and a greater fatigue state to test for differences in RT during the mSEBT. Full article

The work of libraries during the COVID-19 pandemic, as facilitators of reliable information on health issues, has shown that these entities can play an active role as verification agents in the fight against disinformation (false information that is intended to mislead), focusing on media and informational literacy. To help citizens, these entities have developed a wide range of actions that range from online seminars, to learning how to evaluate the quality of a source, to video tutorials or the creation of repositories with resources of various natures. To identify the most common media literacy practices in the face of fake news (news that conveys or incorporates false, fabricated, or deliberately misleading information), this exploratory study designed an ad hoc analysis sheet, validated by the inter-judge method, which allowed one to classify the practices of N = 216 libraries from all over the world. The results reveal that the libraries most involved in this task are those belonging to public universities. Among the actions carried out to counteract misinformation, open-access materials that favor self-learning stand out. These resources, aimed primarily at university students and adults in general, are aimed at acquiring skills related to fact-checking and critical thinking. Therefore, libraries vindicate their role as components of the literacy triad, together with professors and communication professionals. Full article

The COVID-19 pandemic has critically impacted the health and safety of the population of the world, especially the health and well-being of older adults. Socially assistive robots (SARs) have been used to help to mitigate the effects of the pandemic including loneliness and isolation, and to alleviate the workload of both formal and informal caregivers. This paper presents the first extensive survey and discussion on just how socially assistive robots have specifically helped this population, as well as the overall impact on health and the acceptance of such robots during the pandemic. The goal of this review is to answer research questions with respect to which SARs were used during the pandemic and what specific tasks they were used for, and what the enablers and barriers were to the implementation of SARs during the pandemic. We will also discuss lessons learned from their use to inform future SAR design and applications, and increase their usefulness and adoption in a post-pandemic world. More research is still needed to investigate and appreciate the user experience of older adults with SARs during the pandemic, and we aim to provide a roadmap for researchers and stakeholders. Full article

The learning of writing skills involves the re-engagement of previously established independent procedures. Indeed, the writing deficit an adult may acquire after left hemispheric brain injury is caused by either an impairment to the lexical route, which processes words as a whole, to the sublexical procedure based on phoneme-to-grapheme conversion rules, or to both procedures. To date, several approaches have been proposed for writing disorders, among which, interventions aimed at restoring the sub-lexical procedure were successful in cases of severe agraphia. In a randomized double-blind crossover design, fourteen chronic Italian post-stroke aphasics underwent dual transcranial direct current stimulation (tDCS) (20 min, 2 mA) with anodal and cathodal current simultaneously placed over the left and right temporo-parietal cortex, respectively. Two different conditions were considered: (1) real, and (2) sham, while performing a writing task. Each experimental condition was performed for ten workdays over two weeks. After real stimulation, a greater amelioration in writing with respect to the sham was found. Relevantly, these effects generalized to different language tasks not directly treated. This evidence suggests, for the first time, that dual tDCS associated with training is efficacious for severe agraphia. Our results confirm the critical role of the temporo-parietal cortex in writing skills. Full article