1 January 2024 in Disaster Medicine and Public Health Preparedness
Objectives: This systematic literature review explores the applications of social network platforms for disaster health care management and resiliency and investigates their potential to enhance decision-making and policy formulation for public health authorities during such events. Methods: A comprehensive search across academic databases yielded 90 relevant studies. Utilizing qualitative and thematic analysis, the study identified the primary applications of social network data analytics during disasters, organizing them into 5 key themes: communication, information extraction, disaster Management, Situational Awareness, and Location Identification. Results: The findings highlight the potential of social networks as an additional tool to enhance decision-making and policymaking for public health authorities in disaster settings, providing a foundation for further research and innovative approaches in this field. Conclusions: However, analyzing social network data has significant challenges due to the massive volume of information generated and the prevalence of misinformation. Moreover, it is important to point out that social network users do not represent individuals without access to technology, such as some elderly populations. Therefore, relying solely on social network data analytics is insufficient for effective disaster health care management. To ensure efficient disaster management and control, it is necessary to explore alternative sources of information and consider a comprehensive approach.
31 July 2026 in International Journal of Data Science and Analytics
This study investigated the effectiveness of Artificial Intelligence (AI) and Machine Learning (ML) approaches for anomaly detection in rheumatology, focusing on their potential to improve clinical insights and identify deviations in disease patterns and diagnostics. This systematic review adhered to the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search was conducted across PubMed, Cochrane Library, Web of Science, Scopus, and EBSCO databases to identify cohort studies that developed and/or validated AI and ML models for anomaly detection in rheumatology. Data were extracted and studies were critically evaluated using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) guidelines and the Prediction Model Risk of Bias Assessment Tool (PROBAST), with the search last updated on January 28, 2025. The systematic search yielded 2,089 unique citations, from which 40 studies met the inclusion criteria. AI and ML models included demonstrated high performance measures. Most studies focused on rheumatoid arthritis, utilising imaging data, biomarkers, and electronic health records. The quality assessment revealed that 72.5% of the studies had a low risk of bias; however, 25% exhibited high risk due to methodological limitations such as insufficient validation and unclear outcome definitions. Reporting standards were generally well adhered to, although critical gaps such as blinding and risk stratification were frequently overlooked. This study identified a predominance of unclear and high risks of bias across many models, highlighting the need for transparency improvements and addressing such limitations. Key areas for enhancement include incorporating robust calibration measures to improve models and performance measures. Graphical abstract
26 December 2025 in Health Services and Outcomes Research Methodology