http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Ching-Yen Kuo,Liang-Chin Yu,Hou-Chaung Chen,Chien-Lung Chan 대한의료정보학회 2018 Healthcare Informatics Research Vol.24 No.1
Objectives: The aims of this study were to compare the performance of machine learning methods for the prediction of themedical costs associated with spinal fusion in terms of profit or loss in Taiwan Diagnosis-Related Groups (Tw-DRGs) andto apply these methods to explore the important factors associated with the medical costs of spinal fusion. Methods: A dataset was obtained from a regional hospital in Taoyuan city in Taiwan, which contained data from 2010 to 2013 on patients ofTw-DRG49702 (posterior and other spinal fusion without complications or comorbidities). Naïve-Bayesian, support vectormachines, logistic regression, C4.5 decision tree, and random forest methods were employed for prediction using WEKA3.8.1. Results: Five hundred thirty-two cases were categorized as belonging to the Tw-DRG49702 group. The mean medicalcost was US $4,549.7, and the mean age of the patients was 62.4 years. The mean length of stay was 9.3 days. The lengthof stay was an important variable in terms of determining medical costs for patients undergoing spinal fusion. The randomforest method had the best predictive performance in comparison to the other methods, achieving an accuracy of 84.30%,a sensitivity of 71.4%, a specificity of 92.2%, and an AUC of 0.904. Conclusions: Our study demonstrated that the randomforest model can be employed to predict the medical costs of Tw-DRG49702, and could inform hospital strategy in terms ofincreasing the financial management efficiency of this operation.
Pang-Chen Liu,Shun-Kai Yang,Lung-Chin Huang,Huai-Eu Tseng,Fei-Hua Kuo,Tai-Chueh Shih 한국통신학회 2020 한국통신학회 APNOMS Vol.2020 No.09
In recent years, due to customers have higher requirements for 4K/8K video and high-speed internet, telecom operators have begun to deploy FTTH network , but found that it is generally difficult to deploy fiber to the home, so G.fast technology has been favored by most telecom operators around the world and have begun to actively deploy. For the most widely deploy VDSL2 line with maximum rate that can only provide 100M internet service, a intelligent and accurate G.fast 300M high speed service prequalification technology, is a major research topic for telecom operators to promote 300M high-speed internet service. This paper proposes to use AI machine learning to estimate the G.fast line rate by using VDSL2 line attenuation to meet the real-site provision needs of telecommunications operators.