資料探勘技術於病人疼痛自控裝置之應用與分析

Data Mining and Analysis in Patient Controlled Analgesia

吳欣儒

指導教授 ： 胡毓志

國立交通大學/資訊學院/資訊科學與工程研究所/碩士(2011年)

https://doi.org/10.6842/NCTU.2011.00652

摘要

病患在接受手術後通常會發生疼痛的現象，嚴重的疼痛可能會影響到傷口的癒合。因此，如何有效地減緩術後疼痛現象是相當重要的。病人疼痛自控止痛法(Patient-Controlled Analgesia ,PCA)相較於傳統肌肉注射止痛法(Intramuscular Injection ,IM)更能有效且快速地減緩疼痛現象。本研究應用資料探勘技術，用以預測病患短期未來之內使用PCA裝置之情況。分析的資料來源為彰化基督教醫院，透過麻醉醫師的協助，我們收集了1099筆病患在術後使用PCA裝置的記錄。我們做了以下的預測分析：(1) 麻醉藥劑量預測，(2) PCA裝置參數設定調整預測。將預測及屬性分析結果提供給麻醉醫師參考，藉此更了解病患使用PCA裝置之情況，而能更有效地為病患減輕術後疼痛。

關鍵字

病人疼痛自控 ； 資料探勘 ； 類別不平衡 ； 資料清理

並列摘要

Effective pain control is particularly important after surgery, as pain can cause significant distress to patients, and affect wound healing. PCA (Patient-Controlled Analgesia) is more effectively and more quickly than IM (Intramuscular Injection) in the management of postoperative pain. By applying data mining techniques, this study aimed to predict the situation that patients using PCA devices in the short-term future. With the assistance of Changhua Christian Hospital, we collected 1099 PCA patient records. We concentrated on two prediction tasks in this study: (1) postoperative analgesic consumption, and (2) PCA setting readjustment. The result of prediction and feature analysis will be available to the anesthesiologist property reference, to better understand the situation of patients using PCA devices, and more effectively reduce postoperative pain for patients.

並列關鍵字

Patient-Controlled-Analgesia ； Data mining ； Class imbalamce ； Data cleaning

參考文獻

1. B. Walder, M. Schafer, H. Henzi, ”Efficacy and safety of patient-controlled opioid analgesia for acute postoperative pain,” Acta Anaesthesiol Scand, pp. 795-804, 2001.

2. S.J. Dolin, J.N. Cashman, J.M. Bland, “Effectiveness of acute postoperative pain management: evidence from published data,” Br J Anaesth, pp. 409–423, 2002.

4. J. B. MacQueen, ”Some Methods for classification and Analysis of Multivariate Observations,” Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, 1,pp.281-297, 1967.

6. I.J. Good, “The Estimation of Probabilities; an Essay on Modern Bayesian Methods,” M.I.T. Press, 1965.

7 . D. Paterson, “Artificial Neural Networks,” Prentice Hall, Singapore, 1996.