Anastasia Terzi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Anastasia Terzi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Stamatia Bibi
University of Western Macedonia, Kozani, Greece
6 shared publications - Christina Zoi
Department of Electrical and Computer Engineering, University of Western Macedonia
2 shared publications - Panos Bonotis
Department of Electrical and Computer Engineering, University of Western Macedonia
2 shared publications - Pantelis Angelidis
University of Western Macedonia
2 shared publications - Eleni Akritidou
Department of Electrical and Computer Engineering, University of Western Macedonia Greece
1 shared publication - Konstantinos Semertzidis
University of Western Macedonia
1 shared publication
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 60-74
Ontology-Based Generation of GDPR Consent Forms Using Large Language Models
- 2 September 2026
- Published by Springer Nature
- p. 60-74
Ontology-Based Generation of GDPR Consent Forms Using Large Language Models
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 2394-2398
An Empirical Study of LLMs for Engineering Medical Consent
The process of obtaining patient informed consent for personal health information management and agreement on treatments has in recent years become a significant burden for healthcare providers, who often struggle to integrate complex consent requirements into existing clinical workflows. The difficulty increases as consent requirements must be continuously updated and maintained to accommodate new templates and regulatory specifications. Recent advances in Large Language Models (LLMs) offer potential on automating the engineering of medical consent. This paper examines the capabilities of popular LLMs (LLaMa, Gemma, DeepSeek and Phi-3) to be used as collaborative tools to help clinicians generate high-quality, compliant, and patient-centric consent forms from natural language inputs. We identified key clinical challenges and evaluated each LLM’s ability to address them through tasks in formalization, comprehensibility, and compliance. Qualitative expert feedback shows that LLMs are effective companions, but a “one-size-fits-all” approach is insufficient. The paper provides useful implications to practitioners that helps them select the appropriate LLM for consent requirements engineering based on the context of the consent requirement.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 2394-2398
Open AccessAn Empirical Study of LLMs for Engineering Medical Consent
The process of obtaining patient informed consent for personal health information management and agreement on treatments has in recent years become a significant burden for healthcare providers, who often struggle to integrate complex consent requirements into existing clinical workflows. The difficulty increases as consent requirements must be continuously updated and maintained to accommodate new templates and regulatory specifications. Recent advances in Large Language Models (LLMs) offer potential on automating the engineering of medical consent. This paper examines the capabilities of popular LLMs (LLaMa, Gemma, DeepSeek and Phi-3) to be used as collaborative tools to help clinicians generate high-quality, compliant, and patient-centric consent forms from natural language inputs. We identified key clinical challenges and evaluated each LLM’s ability to address them through tasks in formalization, comprehensibility, and compliance. Qualitative expert feedback shows that LLMs are effective companions, but a “one-size-fits-all” approach is insufficient. The paper provides useful implications to practitioners that helps them select the appropriate LLM for consent requirements engineering based on the context of the consent requirement.
- Open Access
- 21 May 2026
- Published by IOS Press
- Vol. 336, 2384-2388
Profile-Aware Consent Management: A Conceptual Framework
Managing user consent for personal data remains a persistent challenge across domains such as healthcare, digital services, and research. Static consent mechanisms often fail to reflect user diversity, evolving preferences, and continuous regulatory changes. As part of the CONSENT project, this paper introduces a conceptual framework for Profile-aware Consent Management. The proposed framework leverages user profiling, adaptive form generation, and automated consenting agents to personalize and simplify the consent process while maintaining compliance and transparency. Building upon multi-stakeholder insights gathered from clinicians, citizens, IT managers, and GDPR experts, the study identifies the major pain points in current consent workflows and translates them into technical design requirements. The resulting framework envisions an AI-powered, profile-aware system that dynamically adapts consent presentation and decisions to user needs, supported by a regulatory compliance backbone.
- 21 May 2026
- Published by IOS Press
- Vol. 336, 2384-2388
Open AccessProfile-Aware Consent Management: A Conceptual Framework
Managing user consent for personal data remains a persistent challenge across domains such as healthcare, digital services, and research. Static consent mechanisms often fail to reflect user diversity, evolving preferences, and continuous regulatory changes. As part of the CONSENT project, this paper introduces a conceptual framework for Profile-aware Consent Management. The proposed framework leverages user profiling, adaptive form generation, and automated consenting agents to personalize and simplify the consent process while maintaining compliance and transparency. Building upon multi-stakeholder insights gathered from clinicians, citizens, IT managers, and GDPR experts, the study identifies the major pain points in current consent workflows and translates them into technical design requirements. The resulting framework envisions an AI-powered, profile-aware system that dynamically adapts consent presentation and decisions to user needs, supported by a regulatory compliance backbone.
- 1 May 2026
- Published by Springer Nature
- p. 289-301
Evaluating Large Language Models for Consent Engineering in Data-Driven Applications
- 1 May 2026
- Published by Springer Nature
- p. 289-301
Evaluating Large Language Models for Consent Engineering in Data-Driven Applications
- Open Access
Opening Software Research Data 5Ws+1H
Open Science describes the movement of making any research artifact available to the public, fostering sharing and collaboration. While sharing the source code is a popular Open Science practice in software research and development, there is still a lot of work to be done to achieve the openness of the whole research and development cycle from the conception to the preservation phase. In this direction, the software engineering community faces significant challenges in adopting open science practices due to the complexity of the data, the heterogeneity of the development environments and the diversity of the application domains. In this paper, through the discussion of the 5Ws+1H (Why, Who, What, When, Where, and How) questions that are referred to as the Kipling’s framework, we aim to provide a structured guideline to motivate and assist the software engineering community on the journey to data openness. Also, we demonstrate the practical application of these guidelines through a use case on opening research data.
Open AccessOpening Software Research Data 5Ws+1H
Open Science describes the movement of making any research artifact available to the public, fostering sharing and collaboration. While sharing the source code is a popular Open Science practice in software research and development, there is still a lot of work to be done to achieve the openness of the whole research and development cycle from the conception to the preservation phase. In this direction, the software engineering community faces significant challenges in adopting open science practices due to the complexity of the data, the heterogeneity of the development environments and the diversity of the application domains. In this paper, through the discussion of the 5Ws+1H (Why, Who, What, When, Where, and How) questions that are referred to as the Kipling’s framework, we aim to provide a structured guideline to motivate and assist the software engineering community on the journey to data openness. Also, we demonstrate the practical application of these guidelines through a use case on opening research data.
- 13 July 2024
- Published by Springer Nature
- p. 137-152
Using Code from ChatGPT: Finding Patterns in the Developers’ Interaction with ChatGPT
- 13 July 2024
- Published by Springer Nature
- p. 137-152
Using Code from ChatGPT: Finding Patterns in the Developers’ Interaction with ChatGPT
- Open Access
- 24 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 193-198
Enhancing User Experience: Virtual Assistants in Greek University Helpdesk Service
- 24 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 193-198
Open AccessEnhancing User Experience: Virtual Assistants in Greek University Helpdesk Service