Department of Anesthesiology, the Second Affiliated Hospital of Nanjing Medical University, Nanjing, China.
Department of Anesthesiology, The People's Hospital of Pizhou, Pizhou Hospital affiliated to Xuzhou Medical University, Xuzhou, Jiangsu, China.
BMC Anesthesiol. 2023 Aug 19;23(1):281. doi: 10.1186/s12871-023-02240-8.
The application of artificial intelligence patient-controlled analgesia (AI-PCA) facilitates the remote monitoring of analgesia management, the implementation of mobile ward rounds, and the automatic recording of all types of key data in the clinical setting. However, it cannot quantify the quality of postoperative analgesia management. This study aimed to establish an index (analgesia quality index (AQI)) to re-monitor and re-evaluate the system, equipment, medical staff and degree of patient matching to quantify the quality of postoperative pain management through machine learning.
Utilizing the wireless analgesic pump system database of the Cancer Hospital Affiliated with Nantong University, this retrospective observational study recruited consecutive patients who underwent postoperative analgesia using AI-PCA from June 1, 2014, to August 31, 2021. All patients were grouped according to whether or not the AQI was used to guide the management of postoperative analgesia: The control group did not receive the AQI guidance for postoperative analgesia and the experimental group received the AQI guidance for postoperative analgesia. The primary outcome was the incidence of moderate-to-severe pain (numeric rating scale (NRS) score ≥ 4) and the second outcome was the incidence of total adverse reactions. Furthermore, indicators of AQI were recorded.
A total of 14,747 patients were included in this current study. The incidence of moderate-to-severe pain was 26.3% in the control group and 21.7% in the experimental group. The estimated ratio difference was 4.6% between the two groups (95% confidence interval [CI], 3.2% to 6.0%; P < 0.001). There were significant differences between groups. Otherwise, the differences in the incidence of total adverse reactions between the two groups were nonsignificant.
Compared to the traditional management of postoperative analgesia, application of the AQI decreased the incidence of moderate-to-severe pain. Clinical application of the AQI contributes to improving the quality of postoperative analgesia management and may provide guidance for optimum pain management in the postoperative setting.
人工智能患者自控镇痛(AI-PCA)的应用便于远程监测镇痛管理,实现移动查房,并自动记录临床环境中的所有关键数据类型。但是,它无法量化术后镇痛管理的质量。本研究旨在建立一个指数(镇痛质量指数(AQI)),通过机器学习重新监测和重新评估系统、设备、医务人员和患者匹配程度,以量化术后疼痛管理的质量。
利用南通大学附属肿瘤医院的无线镇痛泵系统数据库,本回顾性观察性研究招募了 2014 年 6 月 1 日至 2021 年 8 月 31 日期间使用 AI-PCA 进行术后镇痛的连续患者。所有患者根据是否使用 AQI 指导术后镇痛管理进行分组:对照组未接受 AQI 指导术后镇痛,实验组接受 AQI 指导术后镇痛。主要结局是中重度疼痛(数字评分量表(NRS)评分≥4)的发生率,次要结局是总不良反应的发生率。此外,还记录了 AQI 指标。
本研究共纳入 14747 例患者。对照组中重度疼痛的发生率为 26.3%,实验组为 21.7%。两组之间的估计比值差异为 4.6%(95%置信区间[CI],3.2%至 6.0%;P<0.001)。组间差异有统计学意义。否则,两组总不良反应发生率的差异无统计学意义。
与传统的术后镇痛管理相比,应用 AQI 降低了中重度疼痛的发生率。AQI 的临床应用有助于提高术后镇痛管理的质量,并可为术后最佳疼痛管理提供指导。