Georgia Institute of Technology

Pandemic-scale disruptions can trigger disaster-related buying behaviors (DRBBs) that amplify shortages and strain supply chains, making it essential to understand how households adjust essential-goods inventories during crises. Using COVID-19 as an empirical case, this study offers the first multi-country Latin American comparison of DRBBs, measured as revealed changes in household inventory-days, and integrates Prospect Theory and Liquidity Constraints Theory to explain how perceived losses and risk interact with financial capacity. Survey data collected April–June 2020 across seven Latin American countries (N = 1,821) are analyzed using a Poisson rate model with an offset for baseline inventory-days. Results indicate that households with children and those facing greater pandemic severity tend to maintain higher inventory levels of basic supplies, while the effects of income and experienced shortages vary across countries, with reduced purchasing power and constrained access often associated with lower inventory levels. These findings guide targeted interventions to reduce DRBB externalities and protect equitable access to essentials in future crises.

Artificial intelligence is increasingly advancing both fundamental research and clinical applications in schizophrenia. This review surveys recent literature on artificial intelligence driven approaches for schizophrenia diagnosis, treatment, management, and characterization, using multiple data modalities such as neuroimaging, electrophysiology, electronic health records, and genomic data. Recent work shows substantial progress in leveraging machine learning and deep learning for diagnostic label prediction, treatment response modeling, and brain network characterization. While many studies continue to improve feature extraction and classification methods within single modalities, there is a growing trend to utilize multiple data sources to capture the complexity of schizophrenia from a comprehensive perspective. Emerging themes include multimodal fusion methodologies to identify linked correlates of schizophrenia, as well as data-driven approaches to learn subgroups, brain networks, and psychosis continua. The rise of large-scale multimodal datasets, foundation models, and mechanistic interpretability methods holds promise for scalable symptom assessment and biomarker identification, thereby better supporting early intervention and personalized treatment. Current literature highlights a shift from unimodal prediction to holistic, multimodal characterization of schizophrenia. Transforming these artificial intelligence models into clinical tools, however, requires careful attention to patient privacy and data bias, alongside rigorous validation across diverse populations and settings.