| Summary: | 碩士 === 國立勤益科技大學 === 工業工程與管理系 === 95 === Purpose: To develop and compare the ability of several autpmated classifiers to different triage scales based on the quantitative assessment of summary data reports from emergency department database in a Chinese population in Taiwan.
Methods: One randomly selected public of 2,000 patients with emergency department. Measurements of triage variables (Complains of, medical history, respiration, temperature, pulse, diastolic, systolic, SaO2) were obtained by emergency department database. With the emergency department database parameters used as input, ability were generated by three methods, to classify public as triage scales: multi-group discriminant analysis (MDA), multinomial logistic regession (MLR), back-propagation neural networks (BPNN). Classification accuracy was determined by 10-fold cross-validation.
Results: With emergency department database parameters used as input, automated classifiers show promise for discriminating between triage scales. The ability under the histogram were 91.02% (MDA), 89.55% (MLR) and 95.10% (BPNN).
|
|---|
