This work focuses on the application of machine learning techniques to assist the clinicians in the administration of analgesic drug during general anaesthesia. Specifically, the main objective is to propose the basis of an intelligent system capable of making decisions to guide the opioid dose changes based on a new nociception monitor, the analgesia nociception index (ANI). Clinical data were obtained from 15 patients undergoing cholecystectomy surgery. By means of an off-line study, machine learning techniques were applied to analyse the possible relationship between the analgesic dose changes performed by the physician due to the hemodynamic activity of the patients and the evolution of the ANI. After training different classifiers and testing the results under cross validation, a preliminary relationship between the evolution of ANI and the dosage of remifentanil was found. These results evidence the potential of the ANI as a promising index to guide the infusion of analgesia.

中文翻译：

---

手术室中基于计算机的决策系统的机器学习技术：在镇痛中的应用

这项工作的重点是机器学习技术的应用，以协助临床医生在全身麻醉期间使用镇痛药。具体来说，主要目的是提出一种智能系统的基础，该智能系统能够基于新的伤害感受监测器（镇痛伤害感受指数（ANI））做出决策，以指导阿片类药物的剂量变化。临床资料来自15例接受胆囊切除术的患者。通过离线研究，使用机器学习技术来分析由于患者的血液动力学活动而由医生执行的止痛剂量变化与ANI演变之间的可能关系。在训练了不同的分类器并在交叉验证下测试了结果之后，发现ANI的演变与瑞芬太尼的剂量之间存在初步的关系。这些结果证明了ANI作为指导镇痛输注的有希望的指标的潜力。