Skip to content
Log in

Author

M. Zivkovic

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access 2026

Artificial Intelligence in Frontend Development: Review, Challenges, and Future Directions

: Artificial intelligence has become an increasingly influential component of modern software development, with a growing impact on frontend engineering practices. This paper presents a structured review of the application of AI in frontend development, with a particular focus on analyzing existing benchmarking studies of widely used AI tools. The study examines how these tools are applied in common frontend tasks, including component generation, styling, debugging, and design-to-code transformation. By synthesizing findings from recent research, the paper identifies key performance patterns across different AI systems, highlighting their strengths in improving development speed and productivity, as well as their limitations in terms of reliability, security, and handling of complex frontend logic. The analysis also reveals a lack of standardized evaluation frameworks tailored specifically to frontend development, as most existing studies rely on general-purpose metrics that do not fully capture user interface and user experience requirements. Based on these observations, the paper outlines several directions for future research, including the development of frontend-specific evaluation criteria, improvements in contextual understanding for complex tasks, and enhanced integration between design and development processes. The findings suggest that, while AI tools provide valuable support in frontend workflows, they currently function most effectively as assistive technologies rather than fully autonomous solutions. This review contributes to a clearer understanding of the current capabilities and limitations of AI in frontend development and highlights opportunities for further advancement in this rapidly evolving field.

Katarina Stojiljković, Dejan Bulaja, Tamara Zivkovic et al. · 0 citations
Conference Open access 2026

Explainable AI in Telemedicine: A Scoping Review of Clinical Usability Gaps and Research Directions for GP-Centred Design

: Remote healthcare services have grown significantly since the COVID-19 pandemic, with AI increasingly deployed in telemedicine for diagnosis support, triage, and monitoring. While Explainable AI (XAI) methods have been proposed to address trust and transparency concerns, their adoption in clinical practice remains limited — particularly in general practice settings where time constraints, diagnostic breadth, and patient-facing communication impose unique demands on explanation design. This paper presents a scoping review of XAI applications in telemedicine, examining 20 studies published between 2022 and 2026 to characterise the methods used, their evaluation approaches, and gaps between technical explainability and clinical usability. SHAP was the dominant method across the corpus, yet only three papers operated in a telemedicine context, and none evaluated XAI with GPs or in primary care. Empirical evaluation with clinical users was rare, small-scale, and methodologically inconsistent, with a median sample size of 21 participants across five empirical studies. We identify systematic gaps in telemedicine context, GP user focus, and HCI integration, and conclude with research directions for human-centred XAI in telemedicine, derived from identified gaps.

Ana Vesic, M. Zivkovic · 0 citations