Our research aims to bridge the gap between artificial intelligence (AI) and healthcare to improve patient outcomes, support healthcare professionals and enhance the efficiency of healthcare delivery. We primarily focus on applying AI models in healthcare, particularly explainable predictive models for managing chronic diseases such as diabetes, and integrating them into clinical practice. Our aim is to ensure accuracy and explainability for both patients and healthcare professionals.

 In their study Gosak, et al. (2023) focused on exploring models for predicting diabetes-related complications, such as diabetic foot syndrome. These models can contribute to the early identification of high-risk patients, thereby enabling prevention and better disease management. In another study, we examined the importance of explainability in AI models, comparing different methods of local and global interpretability (Kopitar, et al., 2020).

 We have also examined the potential role of generative AI in healthcare. In a study by Kocbek et al. (2022), we investigated the effectiveness of AI in generating concise summaries of scientific literature. We highlighted the potential of these summaries to enable healthcare professionals to make decisions more quickly. We also explored the use of generative AI and visual analytics (Oogen, et al., 2021).

 In our research, we examine the impact of generative AI tools, such as ChatGPT, on nursing education. We focus particularly on how these tools can be used to provide a more personalised and interactive learning experience for individual students (Gosak, et al., 2024). We integrate these tools into the teaching process at all three levels of study to enhance the learning experience, boost interactivity, and promote critical thinking. Through providing practical examples, we familiarise students with the application of AI in healthcare, encouraging them to develop their understanding of, and proficiency in, using it.      

Gosak, L., Pruinelli, L., Topaz, M. and Štiglic, G., 2024. The ChatGPT effect and transforming nursing education with generative AI: discussion paper. Nurse Education in Practice, 75, p.103888.

Gosak, L., Svensek, A., Lorber, M., & Stiglic, G. (2023). Artificial Intelligence based prediction of diabetic foot risk in patients with diabetes: a literature review. Applied Sciences, 13(5), 2823.

Kocbek, P., Gosak, L., Musović, K. and Stiglic, G., 2022, June. Generating Extremely Short Summaries from the Scientific Literature to Support Decisions in Primary Healthcare: A Human Evaluation Study. In International Conference on Artificial Intelligence in Medicine (pp. 373-382). Cham: Springer International Publishing.

Kopitar, L., Cilar, L., Kocbek, P. and Stiglic, G., 2019, June. Local vs. global interpretability of machine learning models in type 2 diabetes mellitus screening. In International Workshop on Knowledge Representation for Health Care (pp. 108-119). Cham: Springer International Publishing.

Ooge, J., Stiglic, G. and Verbert, K., 2022. Explaining artificial intelligence with visual analytics in healthcare. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 12(1), p.e1427.