Main Article Content
CKD is a deadly disease that has been posing a challenge to mankind. Determining the timeline between treatment and hemodialysis has become crucial hence the intervention of bioengineering for precision and accuracy in CKD management. Machine Learning (ML) was utilized as AI algorithm in harmonizing the four established surrogates of chronic kidney failure diagnosis (SEUCR) by predicting the timeline for kidney failure. The machine sorted the SEUCR data of 1,129 susceptible CKD patients with 70% utilized in training and 30% for testing and predicted at 81% accuracy that with Creatinine (0 -14); Sodium [138 – Max limit (200)] & Urea insignificant, the kidneys are normal; Sodium [(138 – max limit (200)], Urea 0-20 & Creatinine insignificant, the kidneys are normal and Urea 0-20, Creatinine (0- 3.4) & Sodium at max limit (200), the kidneys are normal. Other arbitrary points in the engine outside the points in a, b, and c above yielded abnormal kidneys scenarios.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.