Data Analysis of Impaired Renal and Cardiac Function Using a Combination of Standard Classifiers.

Area of Science:

• Biomarkers in Cardiorenal Syndrome
• Artificial Intelligence in Clinical Diagnostics
• Renal Function Assessment

Background:

• Cardiorenal syndrome (CRS) involves complex interactions between heart and kidney dysfunction.
• Accurate assessment of renal function is crucial for managing patients with CRS.
• Existing biomarkers may have limitations in predicting CRS progression.

Purpose of the Study:

• To evaluate the predictive potential of EPI cystatin C (EPI CysC) in CRS patients.
• To assess EPI CysC in combination with NTproBNP, sodium, and potassium.
• To utilize artificial intelligence (AI) classification models for improved diagnostic accuracy.

Main Methods:

• Inclusion of patients with co-existing cardiovascular and kidney disease.
• Application of five machine learning classifiers: MLP, k-NN, Naive Bayes, Decision Tree, Logistic Regression.
• Analysis of predictive performance of EPI CysC and other biomarkers.

Main Results:

• EPI cystatin C demonstrated the highest predictive potential across MLP, k-NN, and Naive Bayes models.
• The combination of EPI CysC with other parameters showed significant predictive capabilities.
• AI classifiers effectively identified the predictive value of EPI CysC in CRS.

Conclusions:

• EPI cystatin C is a valuable predictive biomarker for cardiorenal syndrome.
• AI-driven analysis enhances the understanding of biomarker utility in complex conditions.
• This approach aids in better diagnosis and treatment planning for CRS patients.