Gregor Štiglic
YOU?
Author Swipe
View article: Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directions
Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directions Open
Retrieval-augmented generation (RAG) has rapidly emerged as a transformative approach for integrating large language models into clinical and biomedical workflows. However, privacy risks, such as protected health information (PHI) exposure…
View article: Human-led and artificial intelligence-automated critical appraisal of systematic reviews: Comparative evaluation
Human-led and artificial intelligence-automated critical appraisal of systematic reviews: Comparative evaluation Open
Large language models can support aspects of critical appraisal evidence but lack contextual reasoning and methodological insight required for complex judgments. While Claude 3.7 Sonnet aligned most closely with human reviewers, human over…
View article: Exploring the Impact of Home-Based Serious Smartphone Resuscitation Gaming on Stress Among Nursing Students Practicing Simulated Adult Basic Life Support: Randomized Waitlist Controlled Trial
Exploring the Impact of Home-Based Serious Smartphone Resuscitation Gaming on Stress Among Nursing Students Practicing Simulated Adult Basic Life Support: Randomized Waitlist Controlled Trial Open
Background Simulation-based training is widely used in resuscitation education, yet limited research exists on how serious smartphone games—especially when used independently at home—impact stress levels during simulated adult basic life s…
View article: Reporting guideline for Chatbot Health Advice studies: the CHART statement
Reporting guideline for Chatbot Health Advice studies: the CHART statement Open
View article: Petal-x Visualization for Lifestyle Change in Patients at Risk of Cardiovascular Diseases: An Evaluation
Petal-x Visualization for Lifestyle Change in Patients at Risk of Cardiovascular Diseases: An Evaluation Open
Cardiovascular diseases (CVDs) are the leading global cause of death and addressing unhealthy lifestyles is essential for reducing CVD risk. Visual explanations, such as the Petal-X dashboard, can support personalized care by improving pat…
View article: Reporting Guideline for Chatbot Health Advice Studies
Reporting Guideline for Chatbot Health Advice Studies Open
Importance The rise in chatbot health advice (CHA) studies is accompanied by heterogeneity in reporting standards, impacting their interpretability. Objective To provide reporting recommendations for studies evaluating the performance of g…
View article: Reporting guideline for chatbot health advice studies: the Chatbot Assessment Reporting Tool (CHART) statement
Reporting guideline for chatbot health advice studies: the Chatbot Assessment Reporting Tool (CHART) statement Open
The Chatbot Assessment Reporting Tool (CHART) is a reporting guideline developed to provide reporting recommendations for studies evaluating the performance of generative artificial intelligence (AI)-driven chatbots when summarizing clinic…
View article: Reporting guideline for Chatbot Health Advice studies: the CHART statement
Reporting guideline for Chatbot Health Advice studies: the CHART statement Open
View article: Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction
Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction Open
Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We…
View article: Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction
Visual-Conversational Interface for Evidence-Based Explanation of Diabetes Risk Prediction Open
Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We…
View article: International Scientific Conference »Research and Education in Nursing«: Book of Abstracts, June 5th 2025, Maribor, Slovenia
International Scientific Conference »Research and Education in Nursing«: Book of Abstracts, June 5th 2025, Maribor, Slovenia Open
University of Maribor Faculty of Health Sciences is organising the lnternational Scientific Conference "Research and Education in Nursing". It will be held on June 5th 2024 in Maribor and will include the most recent findings of domestic a…
View article: Healthcare student engagement with health-related content through Netflix mini-series: a qualitative study
Healthcare student engagement with health-related content through Netflix mini-series: a qualitative study Open
View article: Validation of a Slovenian version of the Healthy Lifestyle and Personal Control Questionnaire (HLPCQ) for use with patients in family medicine
Validation of a Slovenian version of the Healthy Lifestyle and Personal Control Questionnaire (HLPCQ) for use with patients in family medicine Open
The most influential factors for a healthy lifestyle were daily routine, healthy dietary choices, avoidance of harmful dietary habits, organized physical activity, and social and mental balance. The Slovenian version had high factor validi…
View article: Ethical approval and informed consent in mental health research: a scoping review
Ethical approval and informed consent in mental health research: a scoping review Open
Although there is a wide range of scientific papers introducing artificial intelligence techniques in the mental health field, there is a lack of literature assessing the reporting of ethical concerns in such studies. In addition, it is no…
View article: Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients
Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients Open
Background/Objectives: Identifying and decomposing compound ingredients within meal plans presents meal customization and nutritional analysis challenges. It is essential for accurately identifying and replacing problematic ingredients lin…
View article: Classifying the Information Needs of Survivors of Domestic Violence in Online Health Communities Using Large Language Models: Prediction Model Development and Evaluation Study
Classifying the Information Needs of Survivors of Domestic Violence in Online Health Communities Using Large Language Models: Prediction Model Development and Evaluation Study Open
Background Domestic violence (DV) is a significant public health concern affecting the physical and mental well-being of numerous women, imposing a substantial health care burden. However, women facing DV often encounter barriers to seekin…
View article: A Brief Review on Benchmarking for Large Language Models Evaluation in Healthcare
A Brief Review on Benchmarking for Large Language Models Evaluation in Healthcare Open
This paper reviews benchmarking methods for evaluating large language models (LLMs) in healthcare settings. It highlights the importance of rigorous benchmarking to ensure LLMs' safety, accuracy, and effectiveness in clinical applications.…
View article: Review and Comparative Evaluation of Mobile Apps for Cardiovascular Risk Estimation: Usability Evaluation Using mHealth App Usability Questionnaire
Review and Comparative Evaluation of Mobile Apps for Cardiovascular Risk Estimation: Usability Evaluation Using mHealth App Usability Questionnaire Open
Background Cardiovascular diseases (CVD) are the leading cause of death and disability worldwide, and their prevention is a major public health priority. Detecting health issues early and assessing risk levels can significantly improve the…
View article: Enriching Real-world Data with Social Determinants of Health for Health Outcomes and Health Equity: Successes, Challenges, and Opportunities
Enriching Real-world Data with Social Determinants of Health for Health Outcomes and Health Equity: Successes, Challenges, and Opportunities Open
OBJECTIVE: To summarize the recent methods and applications that leverage real-world data such as electronic health records (EHRs) with social determinants of health (SDoH) for public and population health and health equity and identify su…
View article: UM_FHS at TREC 2024 PLABA: Exploration of Fine-tuning and AI agent approach for plain language adaptations of biomedical text
UM_FHS at TREC 2024 PLABA: Exploration of Fine-tuning and AI agent approach for plain language adaptations of biomedical text Open
This paper describes our submissions to the TREC 2024 PLABA track with the aim to simplify biomedical abstracts for a K8-level audience (13-14 years old students). We tested three approaches using OpenAI's gpt-4o and gpt-4o-mini models: ba…
View article: Social Determinants of Healthy Aging: An Investigation using the All of Us Cohort
Social Determinants of Healthy Aging: An Investigation using the All of Us Cohort Open
Introduction The increasing aging population raises significant concerns about the ability of individuals to age healthily, avoiding chronic diseases and maintaining cognitive and physical functions. However, the pathways through which SDO…
View article: Digital Technology in Healthcare: Enhancing Education and Patient Care
Digital Technology in Healthcare: Enhancing Education and Patient Care Open
View article: A five-finger mnemonic for teaching schoolchildren the theoretical components of adult basic life support: a modified reactive Delphi-guided development and memorability pilot test with schoolchildren
A five-finger mnemonic for teaching schoolchildren the theoretical components of adult basic life support: a modified reactive Delphi-guided development and memorability pilot test with schoolchildren Open
View article: <scp>PICOT</scp> questions and search strategies formulation: A novel approach using artificial intelligence automation
<span>PICOT</span> questions and search strategies formulation: A novel approach using artificial intelligence automation Open
Aim The aim of this study was to evaluate and compare artificial intelligence (AI)‐based large language models (LLMs) (ChatGPT‐3.5, Bing, and Bard) with human‐based formulations in generating relevant clinical queries, using comprehensive …
View article: Chapter 7 Review of Data-Driven Generative AI Models for Knowledge Extraction from Scientific Literature in Healthcare
Chapter 7 Review of Data-Driven Generative AI Models for Knowledge Extraction from Scientific Literature in Healthcare Open
This review examines the development of abstractive NLP-based text summarization approaches and compares them to existing techniques for extractive summarization. A brief history of text summarization from the 1950s to the introduction of …
View article: Two scholarly publishing cultures? Open access drives a divergence in European academic publishing practices
Two scholarly publishing cultures? Open access drives a divergence in European academic publishing practices Open
The current system of scholarly publishing is often criticized for being slow, expensive, and not transparent. The rise of open access publishing as part of open science tenets, promoting transparency and collaboration, together with calls…
View article: Data from an International Multi-Centre Study of Statistics and Mathematics Anxieties and Related Variables in University Students (the SMARVUS Dataset)
Data from an International Multi-Centre Study of Statistics and Mathematics Anxieties and Related Variables in University Students (the SMARVUS Dataset) Open
This large, international dataset contains survey responses from N = 12,570 students from 100 universities in 35 countries, collected in 21 languages. We measured anxieties (statistics, mathematics, test, trait, social interaction, perform…
View article: Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models
Identifying and Decomposing Compound Ingredients in Meal Plans Using Large Language Models Open
This study explores the effectiveness of Large Language Models in meal planning, focusing on their ability to identify and decompose compound ingredients. We evaluated three models-GPT-4o, Llama-3 (70b), and Mixtral (8x7b)-to assess their …
View article: Data from an International Multi-Centre Study of Statistics and Mathematics Anxieties and Related Variables in University Students (the SMARVUS Dataset)
Data from an International Multi-Centre Study of Statistics and Mathematics Anxieties and Related Variables in University Students (the SMARVUS Dataset) Open
This large, international dataset contains survey responses from N = 12,570 students from 100 universities in 35 countries, collected in 21 languages. We measured anxieties (statistics, mathematics, test, trait, social interaction, perform…
View article: The Role of Visualization in Estimating Cardiovascular Disease Risk: Scoping Review
The Role of Visualization in Estimating Cardiovascular Disease Risk: Scoping Review Open
Background Supporting and understanding the health of patients with chronic diseases and cardiovascular disease (CVD) risk is often a major challenge. Health data are often used in providing feedback to patients, and visualization plays an…