Development of Nursing Diagnosis Program Using Back-propagating Neural Network Model for Self-learning

Kim, Jung Ae

Abstract

With the rapid growth of research and recognition about usefulness and importnace of the Nursing Diagnosis, the demand for application of Nursing Diagnosis has never been stronger. But in clinical field, not many nurses has used Nursing Diagnosis. Especially, nursing student have a difficulty to use Nursing Diagnosis because it demands for high level of capability of analyzing collected data and combining with relevant references. Therefore. this research has developed Nursing Diagnosis Self-learning Program using Back-propagating Neutral Network Model which is based on 98 surgery patients' data for nursing student. The twenty-six nursing diagnoses based on NANDA Taxonomy with 189 cases' reports and aid of 8 nursing experts wee determined to develop the program. To verify the usefulness of Nursing Diagnosis Self-learning Program constructed with the fully trained neural nets, the Program was tested with 70 real patients' data. The simulated output of program was compared with the judgement of the researcher and of two experts of nursing. The misdiagnosis rate of this program was eleven percent. This Program needs input of Signs and Symptoms, risk factors and 'related to' factors and also input the nursing diagnoses which a student selects. And than prints out two types of diagnoses. One is from the system and the other is what the student inputed. And the student makes the final diagnosis by refering the two types of diagnoses. Finally, the program prints out the completed diagnosis which problem combines with etiology in the diagnosis producing module. The program helps students to improve her capacity related to use Nursing Diagnosis.