TY  - JOUR
AU  - Tasić, Danijela
AU  - Furundžić, Draško
AU  - Đorđević, Katarina Lj.
AU  - Galović, Slobodanka
AU  - Dimitrijević, Zorica
AU  - Radenković, Sonja
PY  - 2023
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/10848
AB  - We examine the significance of the predictive potential of EPI cystatin C (EPI CysC) in combination with NTproBNP, sodium, and potassium in the evaluation of renal function in patients with cardiorenal syndrome using standard mathematical classification models from the domain of artificial intelligence. The criterion for the inclusion of subjects with combined impairment of heart and kidney function in the study was the presence of newly discovered or previously diagnosed clinically manifest cardiovascular disease and acute or chronic kidney disease in different stages of evolution. In this paper, five standard classifiers from the field of machine learning were used for the analysis of the obtained data: ensemble of neural networks (MLP), ensemble of k-nearest neighbors (k-NN) and naive Bayes classifier, decision tree, and a classifier based on logistic regression. The results showed that in MLP, k-NN, and naive Bayes, EPI CysC had the highest predictive potential. Thus, our approach with utility classifiers recognizes the essence of the disorder in patients with cardiorenal syndrome and facilitates the planning of further treatment.
T2  - Journal of Personalized Medicine
T1  - Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers
VL  - 13
IS  - 3
SP  - 437
DO  - 10.3390/jpm13030437
ER  - 

@article{
author = "Tasić, Danijela and Furundžić, Draško and Đorđević, Katarina Lj. and Galović, Slobodanka and Dimitrijević, Zorica and Radenković, Sonja",
year = "2023",
abstract = "We examine the significance of the predictive potential of EPI cystatin C (EPI CysC) in combination with NTproBNP, sodium, and potassium in the evaluation of renal function in patients with cardiorenal syndrome using standard mathematical classification models from the domain of artificial intelligence. The criterion for the inclusion of subjects with combined impairment of heart and kidney function in the study was the presence of newly discovered or previously diagnosed clinically manifest cardiovascular disease and acute or chronic kidney disease in different stages of evolution. In this paper, five standard classifiers from the field of machine learning were used for the analysis of the obtained data: ensemble of neural networks (MLP), ensemble of k-nearest neighbors (k-NN) and naive Bayes classifier, decision tree, and a classifier based on logistic regression. The results showed that in MLP, k-NN, and naive Bayes, EPI CysC had the highest predictive potential. Thus, our approach with utility classifiers recognizes the essence of the disorder in patients with cardiorenal syndrome and facilitates the planning of further treatment.",
journal = "Journal of Personalized Medicine",
title = "Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers",
volume = "13",
number = "3",
pages = "437",
doi = "10.3390/jpm13030437"
}

Tasić, D., Furundžić, D., Đorđević, K. Lj., Galović, S., Dimitrijević, Z.,& Radenković, S.. (2023). Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers. in Journal of Personalized Medicine, 13(3), 437.
https://doi.org/10.3390/jpm13030437

Tasić D, Furundžić D, Đorđević KL, Galović S, Dimitrijević Z, Radenković S. Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers. in Journal of Personalized Medicine. 2023;13(3):437.
doi:10.3390/jpm13030437 .

Tasić, Danijela, Furundžić, Draško, Đorđević, Katarina Lj., Galović, Slobodanka, Dimitrijević, Zorica, Radenković, Sonja, "Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers" in Journal of Personalized Medicine, 13, no. 3 (2023):437,
https://doi.org/10.3390/jpm13030437 . .

TY  - JOUR
AU  - Tasić, Danijela
AU  - Đorđević, Katarina T.
AU  - Galović, Slobodanka
AU  - Furundžić, Draško
AU  - Dimitrijević, Zorica
AU  - Radenković, Sonja
PY  - 2022
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/10565
AB  - Markers used in everyday clinical practice cannot distinguish between the permanent impairment of renal function. Sodium and potassium values and their interdependence are key parameters in addition to volemia for the assessment of cardiorenal balance. The aim of this study was to investigate volemia and electrolyte status from a clinical cardiorenal viewpoint under consideration of renal function utilizing artificial intelligence. In this paper, an analysis of five variables: B-type natriuretic peptide, sodium, potassium, ejection fraction, EPI creatinine-cystatin C, was performed using an algorithm based on the adaptive neuro fuzzy inference system. B-type natriuretic peptide had the greatest influence on the ejection fraction. It has been shown that values of both Na+ and K+ lead to deterioration of the condition and vital endangerment of patients. To identify the risk of occurrence, the model identifies a prognostic biomarker by random regression from the total data set. The predictions obtained from this model can help optimize preventative strategies and intensive monitoring for patients identified as at risk for electrolyte disturbance and hypervolemia. This approach may be superior to the traditional diagnostic approach due to its contribution to more accurate and rapid diagnostic interpretation and better planning of further patient treatment
T2  - Diagnostics
T1  - Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?
VL  - 12
IS  - 12
SP  - 3131
DO  - 10.3390/diagnostics12123131
ER  - 

@article{
author = "Tasić, Danijela and Đorđević, Katarina T. and Galović, Slobodanka and Furundžić, Draško and Dimitrijević, Zorica and Radenković, Sonja",
year = "2022",
abstract = "Markers used in everyday clinical practice cannot distinguish between the permanent impairment of renal function. Sodium and potassium values and their interdependence are key parameters in addition to volemia for the assessment of cardiorenal balance. The aim of this study was to investigate volemia and electrolyte status from a clinical cardiorenal viewpoint under consideration of renal function utilizing artificial intelligence. In this paper, an analysis of five variables: B-type natriuretic peptide, sodium, potassium, ejection fraction, EPI creatinine-cystatin C, was performed using an algorithm based on the adaptive neuro fuzzy inference system. B-type natriuretic peptide had the greatest influence on the ejection fraction. It has been shown that values of both Na+ and K+ lead to deterioration of the condition and vital endangerment of patients. To identify the risk of occurrence, the model identifies a prognostic biomarker by random regression from the total data set. The predictions obtained from this model can help optimize preventative strategies and intensive monitoring for patients identified as at risk for electrolyte disturbance and hypervolemia. This approach may be superior to the traditional diagnostic approach due to its contribution to more accurate and rapid diagnostic interpretation and better planning of further patient treatment",
journal = "Diagnostics",
title = "Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?",
volume = "12",
number = "12",
pages = "3131",
doi = "10.3390/diagnostics12123131"
}

Tasić, D., Đorđević, K. T., Galović, S., Furundžić, D., Dimitrijević, Z.,& Radenković, S.. (2022). Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?. in Diagnostics, 12(12), 3131.
https://doi.org/10.3390/diagnostics12123131

Tasić D, Đorđević KT, Galović S, Furundžić D, Dimitrijević Z, Radenković S. Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?. in Diagnostics. 2022;12(12):3131.
doi:10.3390/diagnostics12123131 .

Tasić, Danijela, Đorđević, Katarina T., Galović, Slobodanka, Furundžić, Draško, Dimitrijević, Zorica, Radenković, Sonja, "Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?" in Diagnostics, 12, no. 12 (2022):3131,
https://doi.org/10.3390/diagnostics12123131 . .