Search the digital library catalog

Abstract: Healthcare faces significant challenges, including workforce shortages and increasing demands. Socially assistive robots (SARs) have emerged as potential solutions to augment care, but their implementation in hospital wards remains largely unexplored. We conducted a randomized external pilot study (ISRCTN Registry, ISRCTN96689284, registered 24/02/2022) evaluating SAR intervention feasibility and effects on patient engagement and perceived quality of care (co-primary outcomes) and health-related quality of life (secondary outcome) in surgical wards. Patients (N = 229) at University Medical Center Maribor were allocated to SAR intervention (standard care + SAR) or control groups (standard care only). The SAR utilized validated, story-driven conversational capabilities providing standardized patient education, support, and basic triage through predefined dialog flows. While overall effects on patient engagement and perceived care quality were limited, the intervention showed positive impact on pain management. Contextual factors moderated intervention effects, highlighting SAR potential in specific domains. No substantial negative effects were detected. High retention rates demonstrated practical feasibility of SAR implementation in surgical settings.
Keywords: healthcare, socially assistive robots, SARs
Published in DKUM: 08.12.2025; Views: 0; Downloads: 1
Full text (1,08 MB)

Abstract: Localization of a semi-humanoid mobile robot Pepper is proposed based on the particle swarm optimization algorithm (PSO) that is robust to the disturbance perturbations of LIDAR-measured distances from the mobile robot to the walls of the robot real laboratory workspace. The novel PSO, with the avoiding local minima algorithm (PSO-ALM), uses a novel fitness function that can prevent the PSO search from trapping into the local minima and thus prevent the mobile robot from misidentifying the actual location. The fitness function penalizes nonsense solutions by introducing continuous integrity checks of solutions between two different consecutive locations. The proposed methodology enables accurate and real-time global localization of a mobile robot, given the underlying a priori map, with a consistent and predictable time complexity. Numerical simulations and real-world laboratory experiments with different a priori map accuracies have been conducted to prove the proper functioning of the method. The results have been compared with the benchmarks, i.e., the plain vanilla PSO and the built-in robot’s odometrical method, a genetic algorithm with included elitism and adaptive mutation rate (GA), the same GA algorithm with the included ALM algorithm (GA-ALM), the state-of-the-art plain vanilla golden eagle optimization (GEO) algorithm, and the same GEO algorithm with the added ALM algorithm (GEO-ALM). The results showed similar performance with the odometrical method right after recalibration and significantly better performance after some traveled distance. The GA and GEO algorithms with or without the ALM extension gave us similar results according to the accuracy of localization. The optimization algorithms’ performance with added ALM algorithms was much better at not getting caught in the local minimum, while the PSO-ALM algorithm gave us the overall best results
Keywords: mobile robot localization, PSO algorithm, avoid the global minima
Published in DKUM: 17.10.2025; Views: 0; Downloads: 7
Full text (2,95 MB)

Abstract: The growing number of people living with, through and beyond cancer poses a new challenge for sustainable survivorship care solutions. Digital health solutions which incorporate various information and communication technologies are reshaping healthcare; offering huge potential to facilitate health promotion, support healthcare efficiencies, improve access to healthcare and positively impact health outcomes. Digital health solutions include websites and mobile applications, health information technologies, telehealth solutions, wearable devices, AI-supported chatbots and other technologically assisted provision of health information, communication and services. The breadth and scope of digital health solutions necessitate a synthesis of evidence on their use in supportive care in cancer. This umbrella review will identify, synthesise, and compare systematic reviews which have evaluated the efficacy or effectiveness of digital solutions for adult cancer survivorship care with a particular focus on surveillance and management of physical effects, psychosocial effects, new cancer/ recurring cancers and supporting health promotion and disease prevention.
Published in DKUM: 25.07.2025; Views: 0; Downloads: 1
Link to file

Abstract: Aims and Objective: The aim of this study was to explore the feasibility, usability and acceptance of integrating Clinical Decision Support Systems with Socially Assistive Robots into hospital grand rounds. Background: Adopting Clinical Decision Support Systems in healthcare faces challenges such as complexity, poor integration with workflows, and concerns about data privacy and quality. Issues such as too many alerts, confusing errors, and difficulty using the technology in front of patients make adoption challenging and prevent it from fitting into daily workflows. Making Clinical Decision Support System simple, intuitive and user-friendly is essential to enable its use in daily practice to improve patient care and decision-making. Methods: This six-month pilot study had two participant groups, with total of 40 participants: a longitudinal intervention group (n =8) and a single-session evaluation group (n=32). Participants were medical doctors at the University Clinical Center Maribor. The intervention involved implementing a Clinical Decision Support System delivered via a Socially Assistive Robot during hospital grand rounds. We developed a system that employed the HL7 FHIR standard for integrating data from hospital monitors, electronic health records, and patient-reported outcomes into a single dashboard. A Pepper-based SAR provided patient specific recommendations through a voice and SAR tablet enabled interface. Key evaluation metrics were assessed using the System Usability Scale (SUS) and the Unified Theory of Acceptance, Use of Technology (UTAUT2) questionnaire, including Effort Expectancy, Performance Expectancy and open ended questions. The longitudinal group used the system for 6 months and completed the assessments twice, after one week and at the end of the study. The single-session group completed the assessment once, immediately after the experiment. Qualitative data were gathered through open-ended questions. Data analysis included descriptive statistics, paired t-tests, and thematic analysis. Results: System usability was rated highly across both groups, with the longitudinal group reporting consistently excellent scores (M =82.08 at final evaluation) compared to the acceptable scores of the single-session group (M =68.96). Extended exposure improved user engagement, reflected in significant increases in Effort Expectancy and Habit over time. Participants found the system enjoyable to use, and while no significant changes were seen in Performance Expectancy, feedback emphasized its efficiency in saving time and improving access to clinical data, supporting its feasibility and acceptability. Conclusions: This research supports the potential of robotic technologies to transform CDSS into more interactive, efficient, and user-friendly tools for healthcare professionals. The paper also suggests further research directions and technical improvements to maximize the impact of innovative technologies in healthcare.
Keywords: clinical decision support systems, clinical decision-making, hospital grand rounds, patient data integration, perceived quality of care, socially assistive robots, usability and familiarity, user experience questionnaire, workload reduction
Published in DKUM: 30.05.2025; Views: 0; Downloads: 3
Full text (3,02 MB)

Abstract: Patient-reported health data, especially patient-reported outcomes measures, are vital for improving clinical care but are often limited by memory bias, cognitive load, and inflexible questionnaires. Patients prefer conversational symptom reporting, highlighting the need for robust methods in symptom extraction and conversational intelligence. This study presents a weakly-supervised pipeline for training and evaluating medical Named Entity Recognition (NER) models across eight languages, with a focus on low-resource settings. A merged English medical corpus, annotated using the Stanza i2b2 model, was translated into German, Greek, Spanish, Italian, Portuguese, Polish, and Slovenian, preserving the entity annotations medical problems, diagnostic tests, and treatments. Data augmentation addressed the class imbalance, and the fine-tuned BERT-based models outperformed baselines consistently. The English model achieved the highest F1 score (80.07%), followed by German (78.70%), Spanish (77.61%), Portuguese (77.21%), Slovenian (75.72%), Italian (75.60%), Polish (75.56%), and Greek (69.10%). Compared to the existing baselines, our models demonstrated notable performance gains, particularly in English, Spanish, and Italian. This research underscores the feasibility and effectiveness of weakly-supervised multilingual approaches for medical entity extraction, contributing to improved information access in clinical narratives—especially in under-resourced languages.
Keywords: low-resource languages, machine translation, medical entity extraction, NER, NLP, patient-reported outcomes, weakly-supervised learning
Published in DKUM: 19.05.2025; Views: 0; Downloads: 4
Full text (338,94 KB)