TY - JOUR AU - Tawfiq, Nada Elya PY - 2022/08/25 Y2 - 2024/03/28 TI - Chronic Kidney Disease Diagnose using Radial Basis Function Network (RBFN) JF - Academic Journal of Nawroz University JA - ACAD J NAWROZ UNIV VL - 11 IS - 3 SE - Articles DO - 10.25007/ajnu.v11n3a1427 UR - https://journals.nawroz.edu.krd/index.php/ajnu/article/view/1427 SP - 289-294 AB - <p>Fast and accurate diagnosis of the diseases consider one of the major challenges in giving proper treatment. Different techniques have their own limitations in terms of accuracy and time. Neural network technique used as a powerful discriminating classifier for tasks in medical diagnosis for early detection of diseases.  It had already been applied in diagnose many diseases, like chronic kidney disease (CKD) which is one of the leading causes of death contributed by other illnesses such as diabetes, hypertension, lupus, anemia or weak bones that lead to bone fractures. In this paper, a deep learning method to perform a both feature extraction and the classification for CKD detection using Radial Basis Function Network as <a href="https://en.wikipedia.org/wiki/Activation_function">activation function</a> . This network has great ability of accurate and speed diagnosing, so it is useful to use it in medicine to give the doctors or medical team the right diagnoses. Better performance in terms of accuracy, specificity and sensitivity will be selected as classification model. To test the performance of RBF model, a CDK dataset is employed which contains the clinical manifestations of six diseases as a sample. After applying training method, the network will match these manifestations with the manifestations obtained from sample patients to decide right disease which was entered to the program, the result, shows good performance, low error ratio, high accuracy.</p> ER -