ACAleksandar M. Corac

Aleksandar M. Corac

*This is an algorithmically generated author record based on publicly available information.

Aleksandar M. Corac has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Applying eXplainable AI Techniques to Interpret Machine Learning Predictive Models for the Analysis of Problematic Internet Use among Adolescents

    by Aleksandar S. Stanimirovic, Mina S. Nikolic, Jelena J. Jovic, Dragana I. Ignjatovic Ristic, Aleksandar M. Corac, Leonid V. Stoimenov, Zoran H. Peric

    This research focusses on the potential application of artificial intelligence (AI) techniques in the analysis of behavioural addictions, specifically addressing problematic Internet use among adolescents. Using tabular data from a representative sample from Serbian high schools, the authors investigated the feasibility of employing eXplainable AI (XAI) techniques, placing special emphasis on feature selection and feature importance methods. The results indicate a successful application to tabular data, with global interpretations that effectively describe predictive models. These findings align with previous research, which confirms both relevance and accuracy. Interpretations of individual predictions reveal the impact of features, especially in cases of misclassified instances, underscoring the significance of XAI techniques in error analysis and resolution. Although AI’s influence on the medical domain is substantial, the current state of XAI techniques, although useful, is not yet advanced enough for the reliable interpretation of predictions. Nevertheless, XAI techniques play a crucial role in problem identification and the validation of AI models.


  • Open Access

    Assessing psychometric properties of the Serbian version of the Metacognitive Awareness Inventory (MAI)

    by Zoran Bukumirić, Dejana Stanisavljević, Nataša Milić, Anđa Ćirković, Jelena Milin-Lazović, Marko Savić, Nina Rajović, Aleksandar Ćorac, Jelena Jović, Aleksandra Stolić, et al.

    Introduction: Metacognition, which refers to the ability to oversee and regulate one's cognitive activities, plays a crucial role in medical education. Evaluating metacognitive awareness is particularly important for university students, as it impacts their learning strategies and academic performance. The objective of this study was to examine the psychometric characteristics of the Serbian adaptation of the Metacognitive Awareness Inventory (MAI), with an emphasis on its construct validity and internal consistency. Materials and methods: This was a cross-sectional study conducted at the Faculty of Medicine University of Belgrade, on third-year medical students during October 2024. The psychometric properties of the Serbian version of the MAI were evaluated by assessing its factorial structure and internal consistency. The MAI consists of 52 items, comprising two primary components: 'Knowledge of Cognition' and 'Regulation of Cognition'. The subcomponent of "knowledge of cognition" were categorized into declarative knowledge, procedural knowledge, and conditional knowledge, whereas "regulation of cognition" subcomponent were classified into planning, information management strategies, comprehension monitoring, debugging, and evaluation. Results: A total of 426 medical students were included in the study. The mean age of the respondents was 21.3 ± 1.4 years, and the majority were females (68.5%). The mean score of the scale was 199.0. The internal consistency analysis of the Serbian version of the MAI questionnaire yielded a Cronbach's a of 0.94, and a McDonald's o of 0.95 for the entire scale, which indicates excellent scale reliability. The Serbian version of the MAI questionnaire was validated using confirmatory factor analysis, supporting both the hypothesized eight-factor and two-factor structures. The eight-factor model showed good fit indices (IFI = 0.908, CFI = 0.905, RMSEA = 0.042), with statistically significant factor loadings (p < 0.05). Similarly, the two-factor model demonstrated adequate fit (IFI = 0.921, CFI = 0.918, RMSEA = 0.039), with all loadings also significant (p < 0.05). Conclusion: The present study revealed the Serbian version of MAI as reliable and valid tool for identifying medical students' metaconginive awareness.