Predictive Optimization of Patient No-Show Management in Primary Healthcare Using Machine Learning

Journal of Medical Systems, Journal Year: 2025, Volume and Issue: 49(1)

Published: Jan. 14, 2025

Language: Английский

---

Large scale summarization using ensemble prompts and in context learning approaches

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 25, 2025

The field of Information Assurance (IA) and Cybersecurity has seen substantial evolution, driven by advancements in technology the increasing sophistication threats digital age. This study employs Large Language Models (LLMs), as well other advanced NLP techniques, to conduct a comprehensive analysis literature from 1967 2024. By analyzing corpus more than 62,000 documents extracted Scopus, our approach involves methodology that includes two main phases: topic detection using BERTopic automatic summarization with LLMs across various periods (annual decades). designing targeted queries extract relevant papers, textual data, applying prompting techniques for summarization, we integrate computational models handle large volumes data. Our results demonstrate an ensemble methods (Ev2) outperforms traditional density-based approaches, improvements ranging 16.7% 29.6% keyword definition tasks. It generates summaries outperform 5 out 7 tested metrics while maintaining logical integrity bibliographic references. illuminate shifts focus within decades, revealing key breakthroughs forecasting emerging areas significance.

Language: Английский

---

Mapping Data-Driven Research Impact Science: The Role of Machine Learning and Artificial Intelligence

Metrics, Journal Year: 2025, Volume and Issue: 2(2), P. 5 - 5

Published: April 2, 2025

In an era of evolving scholarly ecosystems, machine learning (ML) and artificial intelligence (AI) have become pivotal in advancing research impact analysis. Despite their transformative potential, the fragmented body literature this domain necessitates consolidation to provide a comprehensive understanding applications multidimensional assessment. This study bridges gap by employing bibliometric methodologies, including co-authorship analysis, citation burst detection, advanced topic modelling using BERTopic, analyse curated corpus 1608 articles. Guided three core questions, investigates how ML AI enhance evaluation, identifies dominant outlines future directions. The findings underscore potential augment traditional indicators uncovering latent patterns collaboration networks, institutional influence, knowledge dissemination. particular, scalability semantic depth BERTopic thematic extraction, combined with visualisation capabilities tools such as CiteSpace VOSviewer, novel insights into dynamic interplay contributions across dimensions. Theoretically, extends scientometric discourse integrating computational techniques reconfiguring established paradigms for assessing contributions. Practically, it provides actionable researchers, institutions, policymakers, enabling enhanced strategic decision-making visibility impactful research. By proposing robust, data-driven framework, lays groundwork holistic equitable addressing its academic, societal, economic

Language: Английский

---

On the Responsible Use of Automation in Systematic Reviews

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 308 - 321

Published: Jan. 1, 2025

Language: Английский

---