Background: Functional neuroimaging has been utilized to study blood flow in the brain. Techniques such as fMRI have been used to characterize these networks in disorders ranging from depression to schizophrenia. Like fMRI, single photon emission computed tomography (SPECT) also captures blood flow activity however through radioactive tracers, and has been used to study psychiatric disorders. While studies utilizing SPECT in schizophrenia populations have been conducted, investigation of aberrant brain networks in SPECT studies is lacking. We implement a novel approach which extracts fMRI-guided networks from SPECT data. We then use subject specific expressions of each network as input to a classifier model to evaluate degree of diagnostic differences in SPECT data. Methods: 213 subjects (137 schizophrenia patients and 76 healthy controls) were used for the analysis. Classification input data was based on loading parameters generated from spatially constrained independent component analysis (ICA) using a set of networks/components derived from fMRI. Fifty-three SPECT components were estimated guided by the NeuroMark fMRI 1.0 template. We then used a support vector machine (SVM) approach which has previously been identified as a useful algorithm for identifying case/control differences in schizophrenia. Results and Conclusion: Linear SVM test results resulted in classifier scores of 83%. Components associated with the auditory, subcortical and sensorimotor networks ranked highest, indicating loading parameters were expressed in brain regions associated with these networks. In conclusion, SPECT data appears to be comparable to resting fMRI data regarding ability to predict individual subject diagnoses.

Revolutionizing Writing Education: The Role of AI Feedback in Enhancing Engagement In a typical writing class, the imbalance between teachers and students often limits opportunities for comprehensive feedback. Leveraging GenAI tools can address this challenge by fostering interactions that optimize learning outcomes. Unlike traditional Automated Writing Evaluation systems, which focus on rule-based grammar corrections, ChatGPT’s generative capabilities enable deeper engagement by providing personalized feedback tailored to learners’ needs, addressing both lower- and higher-order concerns. Previous studies, including Wilson and Czik (2016) and Jiang et al. (2023), have highlighted the role of traditional AWE systems in managing lower-order concerns, freeing up teacher time for higher-order skills. However, these systems lack the adaptability and interactivity of GenAI tools. Recent research by Su et al. (2023) and Jacob et al. (2023) demonstrates ChatGPT’s potential to enhance critical thinking and support authentic writing, although the studies are limited by narrow focus areas and small sample sizes. This pilot study explores ChatGPT’s role in promoting engagement in writing. Two participants, selected based on language proficiency, completed surveys, writing tasks, and feedback sessions with ChatGPT. Screencast data were analyzed to identify language-related episodes (LREs), and stimulated recall interviews captured reflections on integration in writing. Preliminary findings suggest that ChatGPT fosters satisfaction and engagement, highlighting its potential to enhance critical digital literacy and writing outcomes. This study underscores the importance of integrating AI tools into writing education to create more dynamic and effective learning environments.

In a visually saturated world, capturing attention across diverse audiences is essential for effective design. Attention processes involve a complex interplay of neuroscience, psychology, and phenomenology. Recent advancements in deep learning have enabled significant achievements in saliency prediction, where deep models automatically learn features and generate attention maps using data from neuroscience, eye-tracking, and mathematical metrics. AI-driven attention mapping tools—such as Attention Insight, and Expoze, released in 2024— offer innovative solutions for visual engagement. However, these models face notable limitations, particularly in cross-cultural adaptability and semantic understanding. This study explores these challenges and potentials, focusing specifically on Middle Eastern designers. Using a multidisciplinary approach that incorporates neuroscience, psychology, and eye-tracking studies, this research investigates how AI-driven tools predict attention patterns and whether they can effectively accommodate non-Western visual and cultural elements. By generating and analyzing attention maps for Middle Eastern design works and collecting qualitative feedback designers, the study examines the strengths, biases, and gaps inherent in these AI models. Key findings reveal that while these tools could be useful at identifying visual focal points and enhancing workflows, they often fail to interpret culturally specific symbols, typography, and color meanings. These limitations underscore the need for more inclusive datasets and critical awareness when applying AI in global design contexts. This research contributes to the development of culturally adaptive AI tools, supporting cross-cultural design practices. The presentation invites dialogue on creating inclusive technologies that empower designers to connect with diverse audiences worldwide.