Primož Kocuvan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Primož Kocuvan has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Matjaž Gams
Department of Intelligent Systems, Jožef Stefan Institute, Jamova cesta 39, 1000 Ljubljana, Slovenia
5 shared publications - Tadej Horvat
Department of Intelligent Systems, Jožef Stefan Institute, Ljubljana, Slovenia
2 shared publications - Aleksander Hrastič
Faculty of Electrical Engineering (FE), 1000 Ljubljana, Slovenia
1 shared publication - Andrea Kareska
Faculty of Veterinary Medicine, 1000 Ljubljana, Slovenia
1 shared publication - Devid Palčič
Robotina d.o.o.
1 shared publication - Erik Dovgan
Jozef Stefan Institute
1 shared publication
Latest Publications
- Open Access
- 30 September 2025
- Published by Slovenian Association Informatika in Uporabna informatika
- Vol. 33 (4)
(R)evolucija slovenskega zdravstva z uporabo metod umetne inteligence: ocena finančnih koristi na primeru sistema HomeDOCtor
After years of promises that artificial intelligence (AI) will reform healthcare, healthcare systems around the world and in Slovenia, still face serious problems. In this article, we tested the abilities of the HomeDOCtor and GPT-4o in answering medical questions. Additionally we also analyzed how HomeDOCtor could help with the problem slovenian Healthcare system is facing and what could be the financial benefits of Slovenia by incorporating it into its healthcare system. The test results showed that both HomeDOCtor and GPT‑4o answer medical questions very well, with HomeDOCtor being able to provide users with additional material in its answers. The financial assessment of the savings suggests that the Slovenian healthcare system could save between 19 and 347 million annually by introducing a system like HomeDOCtor.
- 30 September 2025
- Published by Slovenian Association Informatika in Uporabna informatika
- Vol. 33 (4)
Open Access(R)evolucija slovenskega zdravstva z uporabo metod umetne inteligence: ocena finančnih koristi na primeru sistema HomeDOCtor
After years of promises that artificial intelligence (AI) will reform healthcare, healthcare systems around the world and in Slovenia, still face serious problems. In this article, we tested the abilities of the HomeDOCtor and GPT-4o in answering medical questions. Additionally we also analyzed how HomeDOCtor could help with the problem slovenian Healthcare system is facing and what could be the financial benefits of Slovenia by incorporating it into its healthcare system. The test results showed that both HomeDOCtor and GPT‑4o answer medical questions very well, with HomeDOCtor being able to provide users with additional material in its answers. The financial assessment of the savings suggests that the Slovenian healthcare system could save between 19 and 347 million annually by introducing a system like HomeDOCtor.
- Open Access
- 29 July 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (15) , 1843
Evaluating a Nationally Localized AI Chatbot for Personalized Primary Care Guidance: Insights from the HomeDOCtor Deployment in Slovenia
Background/Objectives: The demand for accessible and reliable digital health services has increased significantly in recent years, particularly in regions facing physician shortages. HomeDOCtor, a conversational AI platform developed in Slovenia, addresses this need with a nationally adapted architecture that combines retrieval-augmented generation (RAG) and a Redis-based vector database of curated medical guidelines. The objective of this study was to assess the performance and impact of HomeDOCtor in providing AI-powered healthcare assistance. Methods: HomeDOCtor is designed for human-centered communication and clinical relevance, supporting multilingual and multimedia citizen inputs while being available 24/7. It was tested using a set of 100 international clinical vignettes and 150 internal medicine exam questions from the University of Ljubljana to validate its clinical performance. Results: During its six-month nationwide deployment, HomeDOCtor received overwhelmingly positive user feedback with minimal criticism, and exceeded initial expectations, especially in light of widespread media narratives warning about the risks of AI. HomeDOCtor autonomously delivered localized, evidence-based guidance, including self-care instructions and referral suggestions, with average response times under three seconds. On international benchmarks, the system achieved ≥95% Top-1 diagnostic accuracy, comparable to leading medical AI platforms, and significantly outperformed stand-alone ChatGPT-4o in the national context (90.7% vs. 80.7%, p = 0.0135). Conclusions: Practically, HomeDOCtor eases the burden on healthcare professionals by providing citizens with 24/7 autonomous, personalized triage and self-care guidance for less complex medical issues, ensuring that these cases are self-managed efficiently. The system also identifies more serious cases that might otherwise be neglected, directing them to professionals for appropriate care. Theoretically, HomeDOCtor demonstrates that domain-specific, nationally adapted large language models can outperform general-purpose models. Methodologically, it offers a framework for integrating GDPR-compliant AI solutions in healthcare. These findings emphasize the value of localization in conversational AI and telemedicine solutions across diverse national contexts.
- 29 July 2025
- Published by MDPI AG in Healthcare
- Vol. 13 (15) , 1843
Open AccessEvaluating a Nationally Localized AI Chatbot for Personalized Primary Care Guidance: Insights from the HomeDOCtor Deployment in Slovenia
Background/Objectives: The demand for accessible and reliable digital health services has increased significantly in recent years, particularly in regions facing physician shortages. HomeDOCtor, a conversational AI platform developed in Slovenia, addresses this need with a nationally adapted architecture that combines retrieval-augmented generation (RAG) and a Redis-based vector database of curated medical guidelines. The objective of this study was to assess the performance and impact of HomeDOCtor in providing AI-powered healthcare assistance. Methods: HomeDOCtor is designed for human-centered communication and clinical relevance, supporting multilingual and multimedia citizen inputs while being available 24/7. It was tested using a set of 100 international clinical vignettes and 150 internal medicine exam questions from the University of Ljubljana to validate its clinical performance. Results: During its six-month nationwide deployment, HomeDOCtor received overwhelmingly positive user feedback with minimal criticism, and exceeded initial expectations, especially in light of widespread media narratives warning about the risks of AI. HomeDOCtor autonomously delivered localized, evidence-based guidance, including self-care instructions and referral suggestions, with average response times under three seconds. On international benchmarks, the system achieved ≥95% Top-1 diagnostic accuracy, comparable to leading medical AI platforms, and significantly outperformed stand-alone ChatGPT-4o in the national context (90.7% vs. 80.7%, p = 0.0135). Conclusions: Practically, HomeDOCtor eases the burden on healthcare professionals by providing citizens with 24/7 autonomous, personalized triage and self-care guidance for less complex medical issues, ensuring that these cases are self-managed efficiently. The system also identifies more serious cases that might otherwise be neglected, directing them to professionals for appropriate care. Theoretically, HomeDOCtor demonstrates that domain-specific, nationally adapted large language models can outperform general-purpose models. Methodologically, it offers a framework for integrating GDPR-compliant AI solutions in healthcare. These findings emphasize the value of localization in conversational AI and telemedicine solutions across diverse national contexts.
- Open Access
- 18 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (20) , 4109
Comparison of Large Language Models in Generating Machine Learning Curricula in High Schools
With the rapid advancement of artificial intelligence technologies, the integration of AI concepts into educational curricula represents an increasingly important issue. This paper presents a comparative analysis of four AI large language models, ChatGPT (now GPT-4o), Bard (now Gemini), Copilot, and Auto-GPT, in the last year, progressing from the previous into the newer versions, thus also revealing the progress over time. Tasks were selected from the Valence project, which aims to advance machine learning in high school education with material designed by human experts. The four LLMs were assessed across 13 topics, 35 units, and 12 code segments, focusing on their code generation, definition formulation, and textual task capabilities. The results were analyzed using various metrics to conduct a comprehensive evaluation. Each LLM was allowed up to five attempts to produce outputs closely aligned with human-written materials, with experts providing iterative feedback. This study evaluated the effectiveness and accuracy of these LLMs in educational content creation, offering insights into their potential roles in shaping current and future AI-centric education systems.
- 18 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (20) , 4109
Open AccessComparison of Large Language Models in Generating Machine Learning Curricula in High Schools
With the rapid advancement of artificial intelligence technologies, the integration of AI concepts into educational curricula represents an increasingly important issue. This paper presents a comparative analysis of four AI large language models, ChatGPT (now GPT-4o), Bard (now Gemini), Copilot, and Auto-GPT, in the last year, progressing from the previous into the newer versions, thus also revealing the progress over time. Tasks were selected from the Valence project, which aims to advance machine learning in high school education with material designed by human experts. The four LLMs were assessed across 13 topics, 35 units, and 12 code segments, focusing on their code generation, definition formulation, and textual task capabilities. The results were analyzed using various metrics to conduct a comprehensive evaluation. Each LLM was allowed up to five attempts to produce outputs closely aligned with human-written materials, with experts providing iterative feedback. This study evaluated the effectiveness and accuracy of these LLMs in educational content creation, offering insights into their potential roles in shaping current and future AI-centric education systems.
- Open Access
- 13 November 2023
- Published by Slovenian Association Informatika in Informatica
- Vol. 47 (4)
An Efficient Meta-Platform for Providing Expert Medical Help to Italian and Slovenian Users
When dealing with medical issues, Google and similar search engines can be of great help. A user inputs a couple of words about a particular medical issue and receives a list of replies that hopefully provide also the desired answer. The problem is that it is far from easy and fast to find the most proper answer in the huge list of related web pages, with some of them even misleading or harmful. Experience shows that a large proportion of the population falls for inadequate medical advices, some alternative and some even dangerous. This paper presents a novel meta-platform for electronic and mobile health-related services with its main purpose to provide proper quality information to a user with a medical issue, kind of an expert medical “doctor Google”. The platform is centered around “services” and human help. A “service” is an intermediate medical concept between a user and the expert of related feed-backs which redirects a user to another website, video, or other multimedia item that contains important more detailed information of proper quality for a user. A user can also search for the related medical issues, e.g., further-links through a local search upon services, and also ask a human or an AI chatbot/assistant. The platform is dedicated to Italian and Slovenian users in Italian, Slovenian and English language.
- 13 November 2023
- Published by Slovenian Association Informatika in Informatica
- Vol. 47 (4)
Open AccessAn Efficient Meta-Platform for Providing Expert Medical Help to Italian and Slovenian Users
When dealing with medical issues, Google and similar search engines can be of great help. A user inputs a couple of words about a particular medical issue and receives a list of replies that hopefully provide also the desired answer. The problem is that it is far from easy and fast to find the most proper answer in the huge list of related web pages, with some of them even misleading or harmful. Experience shows that a large proportion of the population falls for inadequate medical advices, some alternative and some even dangerous. This paper presents a novel meta-platform for electronic and mobile health-related services with its main purpose to provide proper quality information to a user with a medical issue, kind of an expert medical “doctor Google”. The platform is centered around “services” and human help. A “service” is an intermediate medical concept between a user and the expert of related feed-backs which redirects a user to another website, video, or other multimedia item that contains important more detailed information of proper quality for a user. A user can also search for the related medical issues, e.g., further-links through a local search upon services, and also ask a human or an AI chatbot/assistant. The platform is dedicated to Italian and Slovenian users in Italian, Slovenian and English language.
- Open Access
Predicting a Fall Based on Gait Anomaly Detection: A Comparative Study of Wrist-Worn Three-Axis and Mobile Phone-Based Accelerometer Sensors
Falls by the elderly pose considerable health hazards, leading not only to physical harm but a number of other related problems. A timely alert about a deteriorating gait, as an indication of an impending fall, can assist in fall prevention. In this investigation, a comprehensive comparative analysis was conducted between a commercially available mobile phone system and two wristband systems: one commercially available and another representing a novel approach. Each system was equipped with a singular three-axis accelerometer. The walk suggestive of a potential fall was induced by special glasses worn by the participants. The same standard machine-learning techniques were employed for the classification with all three systems based on a single three-axis accelerometer, yielding a best average accuracy of 86%, a specificity of 88%, and a sensitivity of 86% via the support vector machine (SVM) method using a wristband. A smartphone, on the other hand, achieved a best average accuracy of 73% also with an SVM using only a three-axis accelerometer sensor. The significance analysis of the mean accuracy, sensitivity, and specificity between the innovative wristband and the smartphone yielded a p-value of 0.000. Furthermore, the study applied unsupervised and semi-supervised learning methods, incorporating principal component analysis and t-distributed stochastic neighbor embedding. To sum up, both wristbands demonstrated the usability of wearable sensors in the early detection and mitigation of falls in the elderly, outperforming the smartphone.
Open AccessPredicting a Fall Based on Gait Anomaly Detection: A Comparative Study of Wrist-Worn Three-Axis and Mobile Phone-Based Accelerometer Sensors
Falls by the elderly pose considerable health hazards, leading not only to physical harm but a number of other related problems. A timely alert about a deteriorating gait, as an indication of an impending fall, can assist in fall prevention. In this investigation, a comprehensive comparative analysis was conducted between a commercially available mobile phone system and two wristband systems: one commercially available and another representing a novel approach. Each system was equipped with a singular three-axis accelerometer. The walk suggestive of a potential fall was induced by special glasses worn by the participants. The same standard machine-learning techniques were employed for the classification with all three systems based on a single three-axis accelerometer, yielding a best average accuracy of 86%, a specificity of 88%, and a sensitivity of 86% via the support vector machine (SVM) method using a wristband. A smartphone, on the other hand, achieved a best average accuracy of 73% also with an SVM using only a three-axis accelerometer sensor. The significance analysis of the mean accuracy, sensitivity, and specificity between the innovative wristband and the smartphone yielded a p-value of 0.000. Furthermore, the study applied unsupervised and semi-supervised learning methods, incorporating principal component analysis and t-distributed stochastic neighbor embedding. To sum up, both wristbands demonstrated the usability of wearable sensors in the early detection and mitigation of falls in the elderly, outperforming the smartphone.
- Open Access
- 15 December 2022
- Published by Slovenian Association Informatika in Informatica
- Vol. 46 (4)
Applications of the Insieme Platform: A Case Study
The information society has significantly changed the field of medicine. Several decades ago when a person got sick, a doctor examined a patient and prescribed some medicine with a patient more or less unaware of the true nature of the problem. Even if explained, many patients did not understand much due to the lack of medical knowledge. Today, knowledge is widely accessible through the web and many patients try to self-diagnose or at least get another opinion using popular search engines and specialized web applications. However, many of them provide misinformation due to the lack of proper education of the provider or the lack of understanding of the user. To overcome these issues, we developed a verified medical platform (Insieme platform) that includes medical data, applications and services. This article provides a list of applications in the Insieme platform, their descriptions and how to use them.
- 15 December 2022
- Published by Slovenian Association Informatika in Informatica
- Vol. 46 (4)
Open AccessApplications of the Insieme Platform: A Case Study
The information society has significantly changed the field of medicine. Several decades ago when a person got sick, a doctor examined a patient and prescribed some medicine with a patient more or less unaware of the true nature of the problem. Even if explained, many patients did not understand much due to the lack of medical knowledge. Today, knowledge is widely accessible through the web and many patients try to self-diagnose or at least get another opinion using popular search engines and specialized web applications. However, many of them provide misinformation due to the lack of proper education of the provider or the lack of understanding of the user. To overcome these issues, we developed a verified medical platform (Insieme platform) that includes medical data, applications and services. This article provides a list of applications in the Insieme platform, their descriptions and how to use them.