A5017783286- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Artificial Intelligence in Healthcare
- Mobile Health and mHealth Applications
- Nursing Diagnosis and Documentation
- Gene expression and cancer classification
- Data Mining Algorithms and Applications
- Cardiac Arrest and Resuscitation
- Bioinformatics and Genomic Networks
- Health Education and Validation
- Digital Mental Health Interventions
- Evolutionary Algorithms and Applications
- Simulation-Based Education in Healthcare
- Chronic Disease Management Strategies
- Machine Learning in Bioinformatics
- Healthcare Education and Workforce Issues
- Explainable Artificial Intelligence (XAI)
- Biomedical Text Mining and Ontologies
- Machine Learning and Data Classification
- Cardiovascular Health and Risk Factors
- Family and Patient Care in Intensive Care Units
- Resilience and Mental Health
- Statistics Education and Methodologies
- Topic Modeling
- Health disparities and outcomes
University of Maribor
2016-2025
University of Edinburgh
2017-2025
Faculty of Public Health
2023
Universität Hamburg
2022
University Medical Center Hamburg-Eppendorf
2022
The University of Sydney
2022
University of Ulster
2022
Trinity College Dublin
2020
Ljubljana University Medical Centre
2020
Queen Margaret University
2020
There is a need of ensuring machine learning models that are interpretable. Higher interpretability the model means easier comprehension and explanation future predictions for end-users. Further, interpretable allow healthcare experts to make reasonable data-driven decisions provide personalized can ultimately lead higher quality service in healthcare. Generally, we classify approaches two groups where first focuses on interpretation (local interpretability) while second summarizes...
Most screening tests for T2DM in use today were developed using multivariate regression methods that are often further simplified to allow transformation into a scoring formula. The increasing volume of electronically collected data opened the opportunity develop more complex, accurate prediction models can be continuously updated machine learning approaches. This study compares learning-based (i.e. Glmnet, RF, XGBoost, LightGBM) commonly used undiagnosed T2DM. performance fasting plasma...
This article examines the potential of generative artificial intelligence (AI), such as ChatGPT (Chat Generative Pre-trained Transformer), in nursing education and associated challenges recommendations for their use. AI offers benefits aiding students with assignments, providing realistic patient scenarios practice, enabling personalized, interactive learning experiences. However, integrating also presents challenges, including academic integrity issues, plagiarism copyright infringements,...
Classification is an important and widely used machine learning technique in bioinformatics. Researchers other end-users of software often prefer to work with comprehensible models where knowledge extraction explanation reasoning behind the classification model are possible.This paper presents extension existing environment a study on visual tuning decision tree classifiers. The motivation for this research comes from need build effective easily interpretable by so called one-button data...
Abstract Use of conversational agents, like chatbots, avatars, and robots is increasing worldwide. Yet, their effectiveness in health care largely unknown. The aim this advanced review was to assess the use agents various fields care. A literature search, analysis, synthesis were conducted February 2022 PubMed CINAHL. included evidence analyzed narratively by employing principles thematic analysis. We reviewed articles on artificial intelligence‐based question‐answering systems Most...
Explainable artificial intelligence is increasingly used in machine learning (ML) based decision-making systems healthcare. However, little research has compared the utility of different explanation methods guiding healthcare experts for patient care. Moreover, it unclear how useful, understandable, actionable and trustworthy these are experts, as they often require technical ML knowledge. This paper presents an dashboard that predicts risk diabetes onset explains those predictions with...
Explanations in interactive machine-learning systems facilitate debugging and improving prediction models. However, the effectiveness of various global model-centric data-centric explanations aiding domain experts to detect resolve potential data issues for model improvement remains unexplored. This research investigates influence that support healthcare optimising models through automated manual configurations. We conducted quantitative (n=70) qualitative (n=30) studies with explore impact...
Background Retention of adult basic life support (BLS) knowledge and skills after professional training declines over time. To combat this, the European Resuscitation Council American Heart Association recommend shorter, more frequent BLS sessions. Emphasizing technology-enhanced learning, such as mobile aims to increase out-of-hospital cardiac arrest (OHCA) survival is becoming integral in nursing education. Objective The aim this study was investigate whether playing a serious smartphone...
In recent years, there has been a shift in orientation towards person-centredness as part of global move humanising and centralising the person within healthcare.Person-centredness, underpinned by robust philosophical theoretical concepts, an increasingly solid footprint policy practice, but research education lag behind.This article considers emergence person-centredness, including person-centred care, how it is positioned healthcare around world, while recognising dominant positioning...
Background Poor oral hygiene is a great public health problem worldwide. Oral care education priority as the maintenance of integral to overall health. Maintaining optimal among children challenging and can be supported by using relevant motivational approaches. Objective The primary aim this study was identify mobile smartphone apps that include gamification features focused on motivating learn, perform, maintain hygiene. Methods We searched six online app stores four search terms (“oral...
Emotional intelligence is an important factor for nursing students’ success and work performance. Although the level of emotional increases with age tends to be higher in women, results different studies on students vary regarding age, study year, gender. A longitudinal was conducted 2016 2019 among undergraduate explore whether changes over time. total 111 participated first year their study, 101 third year. Data were collected using Trait Intelligence Questionnaire Short Form (TEIQue-SF)...
The aim of this study is to use generative artificial intelligence perform bibliometric analysis on abstracts published at European Resuscitation Council (ERC) annual scientific congress and define trends in ERC guidelines topics over the last decade.
Background Constant reviews of the caring behavior nurses and patient satisfaction help to improve quality nursing. The aim our research was explore relationships between level nursing education, perception assistants Watson’s carative factors, satisfaction. Methods A questionnaire survey using a convenience sample 1,098 members teams purposive 1,123 patients in four health care institutions Slovenia conducted August 2012. demographic Caring Nurse-Patient Interactions Scale (nurse version)...
Abstract For conducting research, nurses typically use commercial statistical packages. R software is a free, powerful, and flexible alternative, but less familiar used frequently in nursing research. In this paper, we data from previous study to demonstrate few typical steps exploratory analysis using R. A step‐by‐step description of some basic analyses provided here, including examples specific functions read manipulate the data, calculate scores individual questionnaire items, prepare...
This paper presents an empirical study that aims to explain the relationship between number of samples and stability different gene selection techniques for microarray datasets. Unlike other similar studies where genes in a ranked list is variable, this uses alternative approach observed at are used selection. Three metrics stability, including novel metric bioinformatics, were estimate lists. Results demonstrate univariate methods produce significantly more stable lists than multivariate...