Oct 2026· Frontiers in Public Health· 0 citations· 44 references
Imbalanced Data Classification Techniques
Abstract
Health insurance fraud imposes substantial financial burdens on healthcare systems and reduces the efficiency of healthcare resource utilization worldwide. Traditional fraud detection approaches often struggle to analyse large and complex healthcare claims data, making artificial intelligence (AI) an increasingly important tool for identifying fraudulent activities. This study systematically reviews global and regional evidence on AI applications in health insurance fraud detection, with particular emphasis on methodological approaches, performance evaluation, and implementation challenges. This systematic review followed the PRISMA 2020 guidelines. Seven electronic databases were searched for studies published between 2016 and 2025. Titles and abstracts were screened using the Silvi AI platform, followed by eligibility assessment according to pre-defined inclusion and exclusion criteria. Data were extracted using a standardized framework, and methodological quality was assessed using the Drummond 10-item checklist. From 450 identified records, 33 studies met the eligibility criteria. The included studies demonstrated substantial heterogeneity in datasets, AI methodologies, fraud types, and performance evaluation metrics. Machine learning was the most frequently applied approach, followed by deep learning, graph-based learning, and hybrid AI frameworks. Although AI-based methods consistently improved fraud detection performance, challenges related to dataset imbalance, standardized reporting, interpretability, external validation, and economic evaluation remain significant barriers to widespread implementation. AI demonstrates considerable potential for improving health insurance fraud detection. However, future research should prioritize standardized evaluation frameworks, explainable AI, external validation across diverse healthcare systems, and economic assessment to support the responsible and scalable deployment of AI-enabled fraud detection systems.
The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.
Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson· EUROMICRO Conference on Soft...· 64 citations· ⚡6
The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.
Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al.· arXiv.org· 62 citations· ⚡3
The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.
Zheying Zhang, M. Rayhan, Tomas Herda et al.· International Conference on...· 48 citations· ⚡4
This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.
Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al.· arXiv.org· 44 citations· ⚡2
The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.
Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al.· arXiv.org· 41 citations
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.