Differential microcyte anemia diagnosis with hierarchical soft computing

• Main Authors: Jehn-shan Yeh, 葉振山
• Other Authors: C.H. Cheng
• Format: Others
• Language: zh-TW
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/25392753160839942734

碩士 === 國立雲林科技大學 === 資訊管理系碩士班 === 92 === Anemia is the common hematological disorder. It’s difficult to differential both of thalassemia (THA) and Iron deficiency anemia (IDA) often seen belongs to microcyte anemia. The CBCs is objective clinically that physician diagnoses anemia in proportion 1:4 between Iron deficiency anemia with thalassemia because of two anemia express the feature similarly with MCV less than 80 fL (fluid ounces). It will be more serious to the therapy of the patient when physicians do the same diagnosis. It’s novel to use soft computing that include FCM, Competitive learning, and ANFIS that parallels the human mind to process imprecision and uncertain in circumstance. It suit for to assist with physicians to diagnose clinically of the anemia that with the imprecision and uncertain. There are 98% accurate rate inferred in 50 cases refer with documented diagnosis of hospital, it’s more accurate than diagnose by experienced. There are 92% of accurate rate employ ANFIS with 13 rules and 95.3% of accuracy rate when the inference value is 13.6. It improve the discriminant function to differential microcyte that Mantzer index only have accuracy rate 82% to identity THA and only have 90.6% accuracy rate to identity IDA and England index have accuracy rate 91.5% to identity THA. It’s obvious the hierarchical soft computing cut-off the time and cost than cooperate some of discriminate functions to differential microcyte.