Suppr超能文献

术中使用机器学习衍生的伤害感受水平监测仪可减少术后前90分钟的疼痛。

Intraoperative use of the machine learning-derived nociception level monitor results in less pain in the first 90 min after surgery.

作者信息

van der Wal Imeen, Meijer Fleur, Fuica Rivka, Silman Zmira, Boon Martijn, Martini Chris, van Velzen Monique, Dahan Albert, Niesters Marieke, Gozal Yaacov

机构信息

Department of Anesthesiology, Leiden University Medical Center, Leiden, Netherlands.

Department of Anesthesiology, Perioperative Medicine and Pain Treatment, Shaare Zedek Medical Center, Jerusalem, Israel.

出版信息

Front Pain Res (Lausanne). 2023 Jan 9;3:1086862. doi: 10.3389/fpain.2022.1086862. eCollection 2022.

Abstract

In this pooled analysis of two randomized clinical trials, intraoperative opioid dosing based on the nociception level-index produced less pain compared to standard care with a difference in pain scores in the post-anesthesia care unit of 1.5 (95% CI 0.8-2.2) points on an 11-point scale. The proportion of patients with severe pain was lower by 70%. Severe postoperative pain remains a significant problem and associates with several adverse outcomes. Here, we determined whether the application of a monitor that detects intraoperative nociceptive events, based on machine learning technology, and treatment of such events reduces pain scores in the post-anesthesia care unit (PACU). To that end, we performed a pooled analysis of two trials in adult patients, undergoing elective major abdominal surgery, on the effect of intraoperative nociception level monitor (NOL)-guided fentanyl dosing on PACU pain was performed. Patients received NOL-guided fentanyl dosing or standard care (fentanyl dosing based on hemodynamic parameters). Goal of the intervention was to keep NOL at values that indicated absence of nociception. The primary endpoint of the study was the median pain score obtained in the first 90 min in the PACU. Pain scores were collected at 15 min intervals on an 11-point Likert scale. Data from 125 patients (55 men, 70 women, age range 21-86 years) were analyzed. Sixty-one patients received NOL-guided fentanyl dosing and 64 standard care. Median PACU pain score was 1.5 points (0.8-2.2) lower in the NOL group compared to the standard care; the proportion of patients with severe pain was 70% lower in the NOL group ( = 0.045). The only significant factor associated with increased odds for severe pain was the standard of care compared to NOL treatment (OR 6.0, 95% CI 1.4 -25.9,  = 0.017). The use of a machine learning-based technology to guide opioid dosing during major abdominal surgery resulted in reduced PACU pain scores with less patients in severe pain.

摘要

在这项对两项随机临床试验的汇总分析中,与标准护理相比,基于伤害感受水平指数的术中阿片类药物给药产生的疼痛更少,在11分制的麻醉后护理单元疼痛评分上有1.5分(95%可信区间0.8 - 2.2)的差异。重度疼痛患者的比例降低了70%。术后重度疼痛仍然是一个重大问题,并与多种不良后果相关。在此,我们确定基于机器学习技术的检测术中伤害性事件的监测器的应用以及对此类事件的治疗是否会降低麻醉后护理单元(PACU)的疼痛评分。为此,我们对两项针对接受择期腹部大手术的成年患者的试验进行了汇总分析,探讨术中伤害感受水平监测器(NOL)引导的芬太尼给药对PACU疼痛的影响。患者接受NOL引导的芬太尼给药或标准护理(基于血流动力学参数的芬太尼给药)。干预目标是将NOL保持在表明无伤害感受的值。该研究的主要终点是在PACU最初90分钟内获得的中位疼痛评分。疼痛评分以11点李克特量表每15分钟收集一次。分析了125例患者(55例男性,70例女性,年龄范围21 - 86岁)的数据。61例患者接受NOL引导的芬太尼给药,64例接受标准护理。与标准护理相比,NOL组的PACU中位疼痛评分低1.5分(0.8 - 2.2);NOL组重度疼痛患者的比例低70%(P = 0.045)。与重度疼痛几率增加相关的唯一显著因素是与NOL治疗相比的护理标准(比值比6.0,95%可信区间1.4 - 25.9,P = 0.017)。在腹部大手术期间使用基于机器学习的技术来指导阿片类药物给药可降低PACU疼痛评分,且重度疼痛患者减少。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1309/9869062/4d23db303983/fpain-03-1086862-g001.jpg

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验