Is It Possible to Analyze Kidney Functions, Electrolytes and Volemia Using Artificial Intelligence?
Аутори
Tasić, DanijelaĐorđević, Katarina T.
Galović, Slobodanka
Furundžić, Draško
Dimitrijević, Zorica
Radenković, Sonja
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
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 predic...tions 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
Кључне речи:
cardio-renal syndrome / congestion / electrolytes / heart / kidneyИзвор:
Diagnostics, 2022, 12, 12, 3131-Институција/група
VinčaTY - 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 . .