| Summary: | 碩士 === 國立臺北科技大學 === 工業工程與管理系碩士班 === 100 === Patient admission and inpatient bed allocation policy can have sophisticate influence on resource utilization for any hospital. With an effective admission process, a hospital can increase its turnover rate, reduce unnecessary bed occupancy, and improve the quality of care. In hospital bed management, early identification of patients’ risk during hospitalization could not only facilitate optimal use of hospital beds, but also ration fair mixes inpatient admissions. A better recognition in critical factors before admission that determine length of stay (LOS), or a capacity to predict an individual patient’s LOS, could promote the development of efficient admission policy and optimize resource management in hospitals.
Using artificial neural network models, this research tried to predict the LOS for patients in cardiology department during the pr-admission stage. We analyzed clinical records of patients discharged from the Cardiology department in a medical center in Taipei during Oct 2010 to Dec 2010. Three main diagnosis of cardiovascular diseases considered are coronary atherosclerosis, heart failure, and acute myocardial infarction. The results showed that the prediction of LOS from our model using pre-admission factors only was more accurate for patients with coronary atherosclerosis. With 88.9% of the prediction were within one-day tolerance for coronary atherosclerosis patients and 70.2% for heart failure or acute myocardial infarction patients within three-day tolerance.
|
|---|
