Faculty of Computer Science and Engineering

Permanent URI for this communityhttps://repository.ukim.mk/handle/20.500.12188/5

The Faculty of Computer Science and Engineering (FCSE) within UKIM is the largest and most prestigious faculty in the field of computer science and technologies in Macedonia, and among the largest faculties in that field in the region. The FCSE teaching staff consists of 50 professors and 30 associates. These include many “best in field” personnel, such as the most referenced scientists in Macedonia and the most influential professors in the ICT industry in the Republic of Macedonia.

Browse

Settings

Author: search.filters.author.Lehocki, Fedor

Search Results

Now showing 1 - 10 of 19
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Scoping Review of Technology Enabled Healthcare Integration - Towards Sustainable Care
    (IEEE, 2025-06-16)
    Loncar-Turukalo, Tatjana
    ;
    ;
    Madevska Bogdanova, Ana
    ;
    Solarevic, Milica
    ;
    Lehocki, Fedor
    Technology serves as a relevant facilitator in integration of care, supporting healthcare across many pillars, such as diagnoses, drug-development, administration and coordination of services, but as well playing a pivotal role in disease prevention and pervasive health monitoring. This study presents the scoping review of the literature corpus related to technology trends supporting healthcare integration. The study explores 5 digital libraries from major publishers, aiming to identify changes in research trends in the decade from 2014 to 2024, and investigate which implementation challenges, barriers and risks present the major focus in healthcare integration. In total 14721 relevant studies were identified and included in collating and summarizing of the results in this work. The study shows that there is a triple increase in the number of studies from 2020 onwards, mainly focused on technology and implementation challenges. The main topic of the studies shifts from Internet of Medical Things (IoMT) until 2019 to AI in healthcare, which gained its momentum by continual advances in AI performance across different tasks. Enhanced health care, holistic care and patient experience are the most targeted benefits and opportunities of integrated care, while security and privacy of health related data remain the main concerns and playground for further research.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Integrated Smart Patch for Heart Rate and Respiratory Rate Monitoring
    (IEEE, 2023-05-29)
    Gogola, Daniel
    ;
    ;
    Bagín, Richard
    ;
    ;
    Madevska Bogdanova, Ana
    A wearable smart patch was designed to monitor the vital parameters of mass casualties’ victims after the first triage. The device captures ECG, PPG, and respiration signals and triggers an alarm if the heart rate (HR) or respiration rate (RR) exceeds the specified limits and indicates a threat to the victim's life. To obtain a robust and reliable solution, the same parameters are derived from two or three independent signals. In this study, ECG signals have been recorded from different positions on the chest, and the performance of several algorithms for HR and RR extraction was tested. The initial measurements show that HR estimation is more accurate and reliable than RR estimation. The best results, considering both, the HR and RR calculations, were achieved when Pan-Tompkins’s algorithm was used, and ECG electrodes were placed vertically on the right anterior chest. Increasing the length of the evaluated ECG signal above 30 seconds did not significantly affect the HR and RR calculation, regardless of the algorithm used.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    CRITICAL OXYGEN SATURATION-LEVEL ESTIMATION FROM PHOTOPLETHYSMOGRAM (PPG): A PRISMA-COMPLIANT SYSTEMATIC REVIEW AND META-ANALYSIS
    (World Scientific, 2024-10-04)
    ;
    ;
    Madevska Bogdanova, Ana
    ;
    ;
    Sidorenko, Marija
    Objectives: Photoplethysmogram (PPG) signals have become a crucial tool in the non-invasive monitoring of oxygen saturation levels (SpO2). The main purpose of the present review is to perform a meta-analysis of the involvement and consideration of critical SpO2 levels (<90%) in the research papers where SpO2 levels are calculated/predicted from PPG and to elaborate on the impact of the critical levels when presenting the evaluation results. Data sources: PubMed, Science Direct, and Scopus were searched for papers published between January 1, 2016, and September 10, 2022. Results: This study produced several results, concerning the main objective as well as other important issues for improving the SpO2 estimation/calculation. We discovered that only 21 out of 75 papers considered SpO2 values that are in the critical domain. Many papers do not provide access to their databases or disclose the software/models used. Additionally, some studies lack sufficient testing subjects and fail to make their results reproducible. The findings reveal a preference for SpO2 calculation over prediction, limited data availability, undisclosed methodologies, and diverse evaluation metrics hinder replication and direct comparisons between studies. Also, a scoring table is offered that scores higher the papers that are more valuable for SpO2 calculation/prediction.Conclusion: Employing PRISMA guidelines, a comprehensive search across PubMed, Science Direct, and Scopus databases initially extracted 6173 potential papers. Following rigorous screening, 75 papers were selected for detailed analysis, of which only 21 included data from critical SpO2 levels. Furthermore, this research provided information for the filtered 21 paper about the sample size of the study participants, the models utilized to derive the results, the availability of databases, the specific devices employed in the research, the methodologies employed for PPG signal measurement, and the collaborative efforts among authors from different institutions. This information is sublimed in the scoring table which gives higher scoring to those papers that are more valuable for SpO2 calculation/prediction. This study offers references to all these findings that can be used as concrete guidelines for prospective researchers and developers of new sensors for SpO2 estimation/calculation utilizing PPG signals.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Processing MIMIC-III for Evaluation of Various Blood Pressure Estimation Models
    (2023-10)
    ;
    Kuzmanov, Ivan
    ;
    ;
    Lehocki, Fedor
    ;
    Madevska Bogdanova, Ana
    The development of non-invasive easily available blood pressure estimation methods using electrocardiogram - ECG and/or photoplethysmogram - PPG signals has gained increasing attention. However, there is a lack of consistency in the evaluation of these methods due to variations in the size and availability of data in published datasets. Our research involves retrieving, cleaning, and storing a portion of the MIMIC-III database for utilization in model training and testing. This paper outlines our methodology for processing the MIMIC-III database, along with the challenges encountered during the process.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Processing MIMIC-III for Evaluation of Various Blood Pressure Estimation Models
    (2024)
    ;
    Kuzmanov, Ivan
    ;
    ;
    Lehocki, Fedor
    ;
    Madevska Bogdanova, Ana
    The development of non-invasive easily available blood pres- sure estimation methods using electrocardiogram - ECG and/or photo- plethysmogram - PPG signals has gained increasing attention. However, there is a lack of consistency in the evaluation of these methods due to variations in the size and availability of data in published datasets. Our research involves retrieving, cleaning, and storing a portion of the MIMIC-III database for utilization in model training and testing. This paper outlines our methodology for processing the MIMIC-III database, along with the challenges encountered during the process.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Laser-Induced Graphene for Heartbeat Monitoring with HeartPy Analysis
    (MDPI, 2022-08-23)
    Vićentić, Teodora
    ;
    Rašljić Rafajilović, Milena
    ;
    Ilić, Stefan
    ;
    ;
    Madevska Bogdanova, Ana
    The HeartPy Python toolkit for analysis of noisy signals from heart rate measurements is an excellent tool to use in conjunction with novel wearable sensors. Nevertheless, most of the work to date has focused on applying the toolkit to data measured with commercially available sensors. We demonstrate the application of the HeartPy functions to data obtained with a novel graphene-based heartbeat sensor. We produce the sensor by laser-inducing graphene on a flexible polyimide substrate. Both graphene on the polyimide substrate and graphene transferred onto a PDMS substrate show piezoresistive behavior that can be utilized to measure human heartbeat by registering median cubital vein motion during blood pumping. We process electrical resistance data from the graphene sensor using HeartPy and demonstrate extraction of several heartbeat parameters, in agreement with measurements taken with independent reference sensors. We compare the quality of the heartbeat signal from graphene on different substrates, demonstrating that in all cases the device yields results consistent with reference sensors. Our work is a first demonstration of successful application of HeartPy to analysis of data from a sensor in development.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Wearable Patch for Mass Casualty Screening with Graphene Sensors
    (2022)
    Vićentić, Teodora
    ;
    Rašljić Rafajilović, Milena
    ;
    Ilić, Stefan
    ;
    ;
    Madevska Bogdanova, Ana
    Wearable sensors are reaching maturity, at the same time as technologies for communicating physiological data and those for analyzing massive amounts of data. The combination of the three technologies invites for applications in mass screening of personal health through smart algorithm deployment on data from wearable patches. We propose and present an architecture for a wearable patch to be used in mass casualty emergency situations, or for hospital bedside monitoring. The proposed patch will contain multiple sensors of physiological parameters. We propose to create respiration and heartbeat sensors made of laser induced graphene. We show that graphene on flexible substrates can be utilized in conjunction with the Python heart rate analysis toolkit - HeartPy to reliably acquire physiological data from human subjects.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Deep Learning Approach to Estimate SpO2 from PPG Signals
    (ACM, 2022-09-18)
    ;
    Madevska Bogdanova, Ana
    ;
    Mitrova, Hristina
    ;
    Sidorenko, Marija
    ;
    Lehocki, Fedor
    Blood oxygen saturation level (SpO2) is one of the vital parameters determining the hemostability of a patient, besides heart rate (HR), respiratory rate (RR) and blood preasure (BP). In emergency situations with a high number of injured persons, during the second triage until arrival to a medical facility, continuously following the SpO2 level in real time is of outmost importance. Using a smart patch-like device attached to a injured’s chest that contains a Photoplethysmogram (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the smart patch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the SpO2 by extracting the set of features from the PPG signal utilizing Python toolkit HeartPy in order to model a Deep neural network regressor. The PPG signal is preprocessed by various filtering techniques to remove low/high frequency noise. The model was trained and tested using the clinical data collected from 52 subjects with SpO2 levels varying from 83 - 100%. The best experimental results considering the SpO2 interval [83,95) were achieved with a PPG signal of 10 seconds length (MAPE 2.00% and 7.21% of big errors defined as absolute percentage errors (APE) equal or greater than 5).
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Estimation of Respiratory Rate from ECG signal in Python programming language
    (2022-09)
    Žňava, Eduard
    ;
    Lehocki, Fedor
    ;
    Tyšler, Milan
    ;
    Madevska Bogdanova, Ana
    ;
    In case of mass casualties, it is necessary to obtain different vital signs including respiratory rate effectively and accurately. The more physiological signals are measured individually - the more time it takes to obtain multiple vital signs. In addition, a lot of technical equipment is needed. Because of that, it is effective to derive multiple vital signs from measurement of one single physiological signal. It is possible to derive respiratory rate from ECG signal. In this paper, we are constructing an appropriate solution based on different methods for extraction of respiratory rate from ECG signal using Python programming language together with suitable Python libraries for data processing. We managed to implement three methods and validate the accuracy of the calculations by Pearson’s and Spearman’s coefficients of correlation, as well as by root mean square error between of the RR calculated from derived and measured respiration signal. For the best method, we completed the algorithm reaching the coefficients of correlation equal to 0.703 and 0.700. The root mean square error is equal to 1.84 breaths per minute.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Using Cuffless Non-Invasive Methods for Blood Pressure Estimation: Description of the Selected Solutions
    (2022-09)
    Andrashikova, Barbora
    ;
    Lehocki, Fedor
    ;
    Tyshler, Milan
    ;
    Madevska Bogdanova, Ana
    ;
    Kuzmanov, Ivan
    Blood pressure is a crucial vital sign used as an indicator of patient’s medical state. However, the standard methods of measuring blood pressure continuously are not convenient enough in order to be used versatilely. Critical and life threatening situations such as civil disasters require measuring blood pressure as fast and as accurately as possible without the need of manual calibration. In this paper, we introduce several existing blood pressure estimation techniques using machine learning and deep learning algorithms based on ECG and/or PPG signals acquired from a wearable sensor.