Machine learning-augmented interventions in perioperative care: a systematic review and meta-analysis

IF 9.1 1区医学 Q1 ANESTHESIOLOGY

British journal of anaesthesia Pub Date : 2024-09-24 DOI:10.1016/j.bja.2024.08.007

Divya Mehta , Xiomara T. Gonzalez , Grace Huang , Joanna Abraham

{"title":"Machine learning-augmented interventions in perioperative care: a systematic review and meta-analysis","authors":"Divya Mehta , Xiomara T. Gonzalez , Grace Huang , Joanna Abraham","doi":"10.1016/j.bja.2024.08.007","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>We lack evidence on the cumulative effectiveness of machine learning (ML)-driven interventions in perioperative settings. Therefore, we conducted a systematic review to appraise the evidence on the impact of ML-driven interventions on perioperative outcomes.</div></div><div><h3>Methods</h3><div>Ovid MEDLINE, CINAHL, Embase, Scopus, PubMed, and ClinicalTrials.gov were searched to identify randomised controlled trials (RCTs) evaluating the effectiveness of ML-driven interventions in surgical inpatient populations. The review was registered with PROSPERO (CRD42023433163) and conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Meta-analysis was conducted for outcomes with two or more studies using a random-effects model, and vote counting was conducted for other outcomes.</div></div><div><h3>Results</h3><div>Among 13 included RCTs, three types of ML-driven interventions were evaluated: Hypotension Prediction Index (HPI) (<em>n</em>=5), Nociception Level Index (NoL) (<em>n</em>=7), and a scheduling system (<em>n</em>=1). Compared with the standard care, HPI led to a significant decrease in absolute hypotension (<em>n</em>=421, <em>P</em>=0.003, I<sup>2</sup>=75%) and relative hypotension (<em>n</em>=208, <em>P</em><0.0001, I<sup>2</sup>=0%); NoL led to significantly lower mean pain scores in the post-anaesthesia care unit (PACU) (<em>n</em>=191, <em>P</em>=0.004, I<sup>2</sup>=19%). NoL showed no significant impact on intraoperative opioid consumption (<em>n</em>=339, <em>P</em>=0.31, I<sup>2</sup>=92%) or PACU opioid consumption (<em>n</em>=339, <em>P</em>=0.11, I<sup>2</sup>=0%). No significant difference in hospital length of stay (<em>n</em>=361, <em>P</em>=0.81, I<sup>2</sup>=0%) and PACU stay (<em>n</em>=267, <em>P</em>=0.44, I<sup>2</sup>=0) was found between HPI and NoL.</div></div><div><h3>Conclusions</h3><div>HPI decreased the duration of intraoperative hypotension, and NoL decreased postoperative pain scores, but no significant impact on other clinical outcomes was found. We highlight the need to address both methodological and clinical practice gaps to ensure the successful future implementation of ML-driven interventions.</div></div><div><h3>Systematic review protocol</h3><div>CRD42023433163 (PROSPERO).</div></div>","PeriodicalId":9250,"journal":{"name":"British journal of anaesthesia","volume":"133 6","pages":"Pages 1159-1172"},"PeriodicalIF":9.1000,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"British journal of anaesthesia","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0007091224004732","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ANESTHESIOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

We lack evidence on the cumulative effectiveness of machine learning (ML)-driven interventions in perioperative settings. Therefore, we conducted a systematic review to appraise the evidence on the impact of ML-driven interventions on perioperative outcomes.

Methods

Ovid MEDLINE, CINAHL, Embase, Scopus, PubMed, and ClinicalTrials.gov were searched to identify randomised controlled trials (RCTs) evaluating the effectiveness of ML-driven interventions in surgical inpatient populations. The review was registered with PROSPERO (CRD42023433163) and conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Meta-analysis was conducted for outcomes with two or more studies using a random-effects model, and vote counting was conducted for other outcomes.

Results

Among 13 included RCTs, three types of ML-driven interventions were evaluated: Hypotension Prediction Index (HPI) (n=5), Nociception Level Index (NoL) (n=7), and a scheduling system (n=1). Compared with the standard care, HPI led to a significant decrease in absolute hypotension (n=421, P=0.003, I²=75%) and relative hypotension (n=208, P<0.0001, I²=0%); NoL led to significantly lower mean pain scores in the post-anaesthesia care unit (PACU) (n=191, P=0.004, I²=19%). NoL showed no significant impact on intraoperative opioid consumption (n=339, P=0.31, I²=92%) or PACU opioid consumption (n=339, P=0.11, I²=0%). No significant difference in hospital length of stay (n=361, P=0.81, I²=0%) and PACU stay (n=267, P=0.44, I²=0) was found between HPI and NoL.

Conclusions

HPI decreased the duration of intraoperative hypotension, and NoL decreased postoperative pain scores, but no significant impact on other clinical outcomes was found. We highlight the need to address both methodological and clinical practice gaps to ensure the successful future implementation of ML-driven interventions.

Systematic review protocol

CRD42023433163 (PROSPERO).

查看原文本刊更多论文

围手术期护理中的机器学习增强干预：系统回顾和荟萃分析。

背景我们缺乏有关围手术期机器学习（ML）驱动的干预措施累积效果的证据。因此，我们进行了一项系统性综述，以评估有关 ML 驱动的干预措施对围术期结果的影响的证据。我们检索了 MEDLINE、CINAHL、Embase、Scopus、PubMed 和 ClinicalTrials.gov，以确定评估 ML 驱动的干预措施在外科住院患者中的有效性的随机对照试验 (RCT)。该综述已在 PROSPERO（CRD42023433163）上注册，并按照《系统综述和元分析首选报告项目》（PRISMA）指南进行。采用随机效应模型对有两项或更多研究的结果进行了 Meta 分析，并对其他结果进行了计票。结果在 13 项纳入的 RCT 中，评估了三种 ML 驱动的干预措施：低血压预测指数（HPI）（5 例）、痛觉水平指数（NoL）（7 例）和调度系统（1 例）。与标准护理相比，HPI 显著降低了绝对低血压（421 人，P=0.003，I2=75%）和相对低血压（208 人，P<0.0001，I2=0%）；NoL 显著降低了麻醉后护理病房（PACU）的平均疼痛评分（191 人，P=0.004，I2=19%）。NoL对术中阿片类药物消耗量（n=339，P=0.31，I2=92%）或PACU阿片类药物消耗量（n=339，P=0.11，I2=0%）无明显影响。HPI和NoL的住院时间（n=361，P=0.81，I2=0%）和PACU住院时间（n=267，P=0.44，I2=0）无明显差异。我们强调需要解决方法学和临床实践两方面的差距，以确保未来成功实施 ML 驱动的干预措施。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

British journal of anaesthesia 医学-麻醉学

CiteScore

13.50

自引率

7.10%

发文量

488

审稿时长

27 days

期刊介绍： The British Journal of Anaesthesia (BJA) is a prestigious publication that covers a wide range of topics in anaesthesia, critical care medicine, pain medicine, and perioperative medicine. It aims to disseminate high-impact original research, spanning fundamental, translational, and clinical sciences, as well as clinical practice, technology, education, and training. Additionally, the journal features review articles, notable case reports, correspondence, and special articles that appeal to a broader audience. The BJA is proudly associated with The Royal College of Anaesthetists, The College of Anaesthesiologists of Ireland, and The Hong Kong College of Anaesthesiologists. This partnership provides members of these esteemed institutions with access to not only the BJA but also its sister publication, BJA Education. It is essential to note that both journals maintain their editorial independence. Overall, the BJA offers a diverse and comprehensive platform for anaesthetists, critical care physicians, pain specialists, and perioperative medicine practitioners to contribute and stay updated with the latest advancements in their respective fields.