Kristina Zovko

Ms. Kristina Zovko

University of Split Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, Splitsko-Dalmatinska Županija, Croatia
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

19 August 2022 in Electronics
Verified
Journal Article
Open access
PDF file
LRLea Dujić Rodić
Lea Dujić Rodić
Ivo StancicIvo Stancic
Ivo Stancic
KZKristina Zovko
Kristina Zovko
Toni PerkovicToni Perkovic
Toni Perkovic
Petar ŠolićPetar Šolić
Petar Šolić
In the last two decades, Radio Frequency Identification (RFID) technology has attained prominent performance improvement and has been recognized as one of the key enablers of the Internet of Things (IoT) concepts. In parallel, extensive employment of Machine Learning (ML) algorithms in diverse IoT areas has led to numerous advantages that increase successful utilization in different scenarios. The work presented in this paper provides a use-case feasibility analysis of the implementation of ML algorithms for the estimation of ALOHA-based frame size in the RIFD Gen2 system. Findings presented in this research indicate that the examined ML algorithms can be deployed on modern state-of-the-art resource-constrained microcontrollers enhancing system throughput. In addition, such utilization can cope with latency since the execution time is sufficient to meet protocol needs.

3 January 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KZKristina Zovko
Kristina Zovko
YSYANN SADOWSKI
YANN SADOWSKI
Toni PerkovicToni Perkovic
Toni Perkovic
Petar ŠolićPetar Šolić
Petar Šolić
IDIvana Pavlinac Dodig
Ivana Pavlinac Dodig
ZĐZoran Đogaš
Zoran Đogaš
Obstructive Sleep Apnea (OSA) is a prevalent condition that disrupts sleep quality and contributes to significant health risks, necessitating accurate and efficient diagnostic methods. This study introduces a machine learning-based framework aimed at detecting apnea events through analysis of polysomnographic (PSG) and oximetry data. The core component is a Long Short-Term Memory (LSTM) network, which is particularly suited to processing sequential time-series data, capturing complex temporal relationships within physiological signals such as oxygen saturation, heart rate, and airflow. Through extensive feature engineering and preprocessing, the framework optimizes data representation by normalizing, scaling, and encoding input features to enhance computational efficiency and model performance. Key results demonstrate the model’s effectiveness, achieving a balanced accuracy of 79%, precision of 68%, and recall of 76% on the test dataset, with validation set metrics similarly high, supporting the model’s ability to generalize effectively. Comprehensive hyperparameter tuning further contributed to a stable, robust architecture capable of accurately identifying apnea events, providing clinicians with a valuable tool for the early detection and tailored management of OSA. This data-driven framework offers an efficient, reliable solution for OSA diagnostics with the potential to improve clinical decision making and patient outcomes.

6 February 2026 in Sensors
Verified
Journal Article
Open access
PDF file
KZKristina Zovko
Kristina Zovko
Ljiljana ŠerićLjiljana Šerić
Ljiljana Šerić
Toni PerkovicToni Perkovic
Toni Perkovic
IDIvana Pavlinac Dodig
Ivana Pavlinac Dodig
RPRenata Pecotić
Renata Pecotić
Petar ŠolićPetar Šolić
Petar Šolić
Recent advances in deep learning (DL) have enabled the integration of diverse biomedical data for disease prediction and risk stratification. Building on this progress, the overall objective of this study was to develop and evaluate a multimodal DL framework for robust multi-label classification (MLC) of major comorbidities in patients with obstructive sleep apnea (OSA) using physiological time series signals and clinical data. This study proposes a robust framework for multi-label classification (MLC) of comorbidities in patients with OSA using diverse physiological and clinical data sources. We conducted a retrospective observational study including a convenience sample of 144 patients referred for overnight polysomnography at the Sleep Medicine Center (SleepLab Split), University Hospital Centre Split (KBC Split), Split, Croatia. Patients were selected based on predefined inclusion criteria and data availability. A one-dimensional Convolutional Neural Network (1D-CNN) was developed to process and fuse time series signals, oxygen saturation (SpO2), derived SpO2 features, and nasal airflow (FP0), with demographic and physiological parameters, enabling the identification of key comorbidities such as arterial hypertension, diabetes mellitus, and asthma/COPD. The instruments included polysomnography-derived signals (SpO2 and FP0 airflow) and structured demographic/physiological parameters. Signals were preprocessed and used as inputs to the proposed fusion model. The proposed model was trained and fine-tuned using the Optuna hyperparameter optimization framework, addressing class imbalance through weighted loss adjustments. Its performance was comprehensively assessed using multi-label evaluation metrics, including macro/micro F1-score, AUC-ROC, AUC-PR, subset and partial accuracy, Hamming loss, and multi-label confusion matrix (MLCM). The study protocol was approved by the Ethics Committee of the School of Medicine, University of Split (Approval No. 003-08/23-03/0015, Date: 17 October 2023). The 1D-CNN achieved superior predictive performance compared to traditional machine learning (ML) classifiers with macro AUC-ROC = 0.731 and AUC-PR = 0.750. The model demonstrated consistent behavior across age, gender, and BMI groups, indicating strong generalization and minimal demographic bias. In conclusion, the results confirm that SpO2 and airflow signals inherently encode comorbidity-specific physiological patterns, enabling efficient and scalable screening of OSA-related comorbidities without the need for full polysomnography. Although the study is limited by data set size, it provides a methodological basis for the application of multi-label DL models in clinical decision support systems. Future research should focus on the expansion of multi-center datasets, thereby improving model interpretability and potential clinical adoption.

21 November 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
KZKristina Zovko
Kristina Zovko
YSYANN SADOWSKI
YANN SADOWSKI
Toni PerkovicToni Perkovic
Toni Perkovic
Petar ŠolićPetar Šolić
Petar Šolić
IDIvana Pavlinac Dodig
Ivana Pavlinac Dodig
ZĐZoran Đogaš
Zoran Đogaš
Obstructive Sleep Apnea (OSA) is a prevalent condition that disrupts sleep quality and contributes to significant health risks, necessitating accurate and efficient diagnostic methods. This study introduces a machine learning-based framework aimed at detecting and predicting apnea events through analysis of polysomnographic (PSG) and oximetry data. The core component is a Long Short-Term Memory (LSTM) network, which is particularly suited to processing sequential time-series data, capturing complex temporal relationships within physiological signals such as oxygen saturation, heart rate, and airflow. Through extensive feature engineering and preprocessing, the framework optimizes data representation by normalizing, scaling, and encoding input features to enhance computational efficiency and model performance. Key results demonstrate the model’s effectiveness, achieving an accuracy of 79%, precision of 68%, and recall of 76% on the test dataset, with validation set metrics similarly high, supporting the model’s ability to generalize effectively. Comprehensive hyperparameter tuning further contributed to a stable, robust architecture capable of accurately identifying apnea events, providing clinicians with a valuable tool for early detection and tailored management of OSA. This data-driven framework offers an efficient, reliable solution for OSA diagnostics, with the potential to improve clinical decision-making and patient outcomes.

2 December 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
KZKristina Zovko
Kristina Zovko
Ljiljana ŠerićLjiljana Šerić
Ljiljana Šerić
Toni PerkovicToni Perkovic
Toni Perkovic
IDIvana Pavlinac Dodig
Ivana Pavlinac Dodig
RPRenata Pecotić
Renata Pecotić
Petar ŠolićPetar Šolić
Petar Šolić
Recent advances in Deep Learning (DL) have enabled the integration of diverse biomedical data for disease prediction and risk stratification. Building on this progress, this study proposes a robust framework for Multi Label Classification (MLC) of comorbidities in patients with Obstructive Sleep Apnea (OSA) using diverse physiological and clinical data sources. A one-dimensional Convolutional Neural Network (1D-CNN) was developed to process and fuse time series signals, oxygen saturation (SpO2), derived SpO2 features, and nasal airflow (FP0), with demographic and physiological parameters, enabling the identification of key comorbidities such as arterial hypertension, diabetes mellitus, and asthma/COPD. The proposed model was trained and fine tuned using the Optuna hyperparameter optimization framework, addressing class imbalance through weighted loss adjustments. Its performance was comprehensively assessed using multi label evaluation metrics, including macro/micro F1-score, AUC-ROC, AUC-PR, subset and partial accuracy, Hamming loss, and Multi Label Confusion Matrix (MLCM) . The 1D-CNN achieved superior predictive performance compared to traditional Machine Learning (ML) classifiers with macro AUC-ROC = 0.7305 and AUC-PR = 0.7497. The model demonstrated consistent behavior across age, gender, and BMI groups, indicating strong generalization and minimal demographic bias. The results confirm that SpO2 and airflow signals inherently encode comorbidity specific physiological patterns, enabling efficient and scalable screening of OSA related comorbidities without the need for full polysomnography. Although the study is limited by data set size, it provides a methodological basis for the application of multi label DL models in clinical decision support systems. Future research should focus on the expansion of multicenter datasets, thereby improving model interpretability and potential clinical adoption.