Title :
Predicting Parathyroid Hormone Levels in Diabetic Hemodialysis Patients Using Neural Networks
Author :
Bumanlag, Jesse ; Zarei, Anahita ; Ghazi, Pourya ; Kapre, Sheela ; Frank, Lawrence
Author_Institution :
Sch. of Eng. & Comput. Sci., Univ. of the Pacific, Stockton, CA, USA
Abstract :
Parathyroid Hormone (PTH) is an important biochemical indicator for the medical condition of osteodystrophy in patients on hemodialysis. Prior studies have been conducted to classify hemodialysis patients based on their PTH level, using neural networks. This paper introduces the possibilities of predicting parathyroid hormone levels in the more specific case of diabetic patients. The performance of two different neural network models, a general case and a diabetic case, were examined and compared. Results of this comparison showed improved prediction for PTH levels in patients with diabetes.
Keywords :
biochemistry; diseases; medical diagnostic computing; neural nets; biochemical indicator; diabetic hemodialysis patients; neural networks; osteodystrophy; parathyroid hormone levels; Artificial neural networks; Biochemistry; Blood; Bones; Calcium; Computer networks; Diabetes; Medical diagnostic imaging; Neural networks; Sugar; A1C; Artificial Intelligence; Diabetes; Medicine; Neural Network; Parathyroid;
Conference_Titel :
Computing, Engineering and Information, 2009. ICC '09. International Conference on
Conference_Location :
Fullerton, CA
Print_ISBN :
978-0-7695-3538-8
DOI :
10.1109/ICC.2009.55
