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, FedorSubject: search.filters.subject.Oxygen saturation

Search Results

Now showing 1 - 3 of 3
  • 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,
    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,
    Machine learning based SpO2 prediction from PPG signal's characteristics features
    (IEEE, 2022-06-22)
    ;
    Mitrova, Hristina
    ;
    Madevska Bogdanova, Ana
    ;
    Lehocki, Fedor
    Continuous monitoring of blood oxygen saturation level (SpO2) during the second triage in the high casualty event and determining the hemostability of a patient/victim until arrival to a medical facility, is essential in emergency situations. Using a SmartPatch device attached to a victim's chest that contains a Photoplethysmogram Waveforms (PPG) sensor, one can obtain the SpO2 parameter. Our interest in the process of the SmartPatch prototype development is to investigate the monitoring of a blood oxygen saturation level by using the embedded PPG sensor. We explore acquiring the Sp02 by extracting the set of features from the PPG signal utilizing two Python toolkits, HeartPy and Neurokit, in order to model the Machine learning predictors, using multiple regressors. 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 - MAE (1.45), MSE (3.85), RMSE (1.96) and RMSLE (0.02) scores are achieved with the Random Forest regressor in the experiment with 7 features extracted from the both toolkits.