人工智慧融合於醫療照護之研究

Integrating Artificial Intelligence Into Healthcare Research

蔡及時(Kup-Sze CHOI)

《護理雜誌》 67卷5期 (2020/10) Pp. 12-18

https://doi.org/10.6224/JN.202010_67(5).03

摘要

人工智慧技術在近十多年的迅速發展，為許多產業帶來了創新和發展契機，它在健康照顧的應用也是充滿潛力。本文旨在通過介紹人工智慧技術融合於醫療照護之研究，推動更多醫療照護者從事相關的跨領域研究。文中首先介紹人工智慧技術的基本概念，闡述兩種主要的機器學習方法，即監督學習與無監督學習，並討論人工神經網路和決策樹這兩種常用的演算法。接著討論三項將人工智慧技術用於醫療照護的研究，包括預測手術後死亡率，估計老人生活品質和罹患失智症的風險。最後論述人工智慧融合於醫療照護之研究所面臨的一些挑戰，即類別不平衡，數據缺失和缺乏數據，和可行的因應方法。

關鍵字

人工智慧 ； 醫療照護

並列摘要

The rapid development of artificial intelligence (AI) technologies in recent decades has led to innovation and new development opportunities in many industries. The application of AI technologies in the medical and healthcare sector offers significant potential benefit. In this paper, the integration of AI into healthcare research is introduced to encourage more medical and healthcare experts to research this promising cross-disciplinary area. After introducing the basic concepts that underlie AI, the two major schools of machine learning approaches, namely 'supervised learning' and 'unsupervised learning', are discussed. Next, two commonly used algorithms (artificial neural networks and decision trees) are discussed. The paper then focuses on three healthcare applications of AI technologies, including predicting postoperative mortality, quality of life in older adults, and risk of dementia. Finally, the challenges to integrating AI into healthcare research such as class imbalance, missing data, and data scarcity are discussed along with feasible approaches to resolving these challenges.

並列關鍵字

artificial intelligence ； healthcare

參考文獻

Caetano, N., Cortez, P., & Laureano, R. M. S. (2015). Using data mining for prediction of hospital length of stay: An application of the CRISP-DM methodology. In J. Cordeiro, S. Hammoudi, L. Maciaszek, O. Camp, & J. Filipe (Eds.), Enterprise information systems (pp. 149–166). Springer. https://doi.org/10.1007/978-3-319-22348-3_9

Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., Cannon, T. D., Krystal, J. H., & Corlett, P. R. (2016). Cross-trial prediction of treatment outcome in depression: A machine learning approach. The Lancet Psychiatry, 3(3), 243–250. https://doi.org/10.1016/S2215-0366(15)00471-X

De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O'Donoghue, B., Visentin, D., van den Driessche, G., Lakshminarayanan, B., Meyer, C., Mackinder, F., Bouton, S., Ayoub, K., Chopra, R., King, D., Karthikesalingam, A., ... Ronneberger, O. (2018). Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature Medicine, 24(9), 1342–1350. https://doi.org/10.1038/s41591-018-0107-6

Doyle-Lindrud, S. (2015). Watson will see you now: A supercomputer to help clinicians make informed treatment decisions. Clinical Journal of Oncology Nursing, 19(1), 31–32. https://doi.org/10.1188/15.CJON.31-32

Koutsouleris, N., Kahn, R. S., Chekroud, A. M., Leucht, S., Falkai, P., Wobrock, T., Derks, E. M., Fleischhacker, W. W., & Hasan, A. (2016). Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: A machine learning approach. The Lancet Psychiatry, 3(10), 935–946. https://doi.org/10.1016/S2215-0366(16)30171-7