急診室內醫療人員及團隊之空間亂度

Spatial Entropy of Medical Teams in the Emergency Room

魏筱蓉(Siao-Rong Wei)

指導教授 ： 陳柏華

國立臺灣大學/工學院/土木工程學研究所/碩士(2019年)

https://doi.org/10.6342/NTU201902421

摘要

團隊合作對於急診室內之搶救作業是非常重要之課題，良好的團隊合作表現能夠提供及時適切的緊急救護，進而提升病患存活的機會。透過觀察，本研究假設團隊組織的整體動態，應與團隊之表現相關。在本研究中，共分析33筆台大醫院急救室內之影片，希望找出團隊動態與其表現之相關性。透過Mask R-CNN模型偵測影片中之相關人員，並針對漏失之偵測進行補償，使用所有成員之平均位置，作為代表團隊之空間位置，用以計算團隊動態之熵(entropy)。再將計算結果與急診醫師評估之團隊表現評分進行比較。本研究使用不同之觀察時間、不同計算時間間隔，以及團隊中不同位置之成員，計算熵，並比較其與團隊表現之關係。從結果可以看出熵能捕捉特定團隊動態。針對未來研究建議，隨著影像技術之發展，自動化從影像中取得之團隊資訊將更多元與精密，能夠用以分析團隊表現。另外醫療團隊領導人角色相當重要，未來亦可針對特定人員進行研究。

關鍵字

電腦視覺 ； entropy ； 團隊動態 ； 團隊表現 ； 人員偵測

並列摘要

Teamwork in the emergency room is critical. Provided with a good teamwork, timely and appropriate emergency medical treatment can be provided, and the fatality rate can be reduced. The research hypothesis of this work is that there is certain relationship between team dynamics and team performance. In this research, observation is through videos collected in the resuscitation room in the National Taiwan University Hospital. There are 33 video clips in total of patients with Out of Hospital Cardiac Arrest. After using Mask R-CNN to detect members in videos and post-processing for compensating lost detections, the average location of members is used as the representation of the team center for the calculation of the spatial entropy. The entropy represents the spatio-temporal complexity of the team dynamics. The entropy were compared with team performance scores determined by emergency medical professions. Different observation periods, sampling intervals and number of members were studied. Preliminary results show that entropy could indicate team dynamics. For future studies, more cases could be studied and the specific study on the team leader could be important for improving medical teamwork in the emergency room.

並列關鍵字

computer vision ； entropy ； team dynamics ； human detection ； team performance

參考文獻

Batty, M. (1974). Spatial Entropy. Geographical Analysis, 6(1), 1–31. https://doi.org/10.1111/j.1538-4632.1974.tb01014.x

Bewley, A., Ge, Z., Ott, L., Ramos, F., &Upcroft, B. (2016). Simple online and realtime tracking. 2016 IEEE International Conference on Image Processing (ICIP), 3464–3468. https://doi.org/10.1109/ICIP.2016.7533003

Cordier, P., France, M. M., Pailhous, J., &Bolon, P. (1994). Entropy as a global variable of the learning process. Human Movement Science, 13(6), 745–763.

Cover, T. M., &Thomas, J. A. (1991). Elements of Information Theory. John Wiley & Sons.

Girdhar, R., Gkioxari, G., Torresani, L., Paluri, M., &Tran, D. (2018). Detect-and-Track: Efficient Pose Estimation in Videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 350–359. https://doi.org/10.1109/CVPR.2018.00044