评估机器学习模型在协助分配美国麻醉学会儿科患者身体状况分类方面的实用性。

IF 4.6 2区 医学 Q1 ANESTHESIOLOGY Anesthesia and analgesia Pub Date : 2024-11-01 Epub Date: 2023-12-13 DOI:10.1213/ANE.0000000000006761
Lynne R Ferrari, Izabela Leahy, Steven J Staffa, Peter Hong, Isabel Stringfellow, Jay G Berry
{"title":"评估机器学习模型在协助分配美国麻醉学会儿科患者身体状况分类方面的实用性。","authors":"Lynne R Ferrari, Izabela Leahy, Steven J Staffa, Peter Hong, Isabel Stringfellow, Jay G Berry","doi":"10.1213/ANE.0000000000006761","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The American Society of Anesthesiologists Physical Status Classification System (ASA-PS) is used to classify patients' health before delivering an anesthetic. Assigning an ASA-PS Classification score to pediatric patients can be challenging due to the vast array of chronic conditions present in the pediatric population. The specific aims of this study were to (1) suggest an ASA-PS score for pediatric patients undergoing elective surgical procedures using machine-learning (ML) methods; and (2) assess the impact of presenting the suggested ASA-PS score to clinicians when making their final ASA-PS assignment. The intent was not to create a new ASA-PS score but to use ML methods to generate a suggested score, along with information on how the score was generated (ie, historical information on patient comorbidities) to assist clinicians when assigning their final ASA-PS score.</p><p><strong>Methods: </strong>A retrospective analysis of 146,784 pediatric surgical encounters from January 1, 2016, to December 31, 2019, using eXtreme Gradient Boosting (XGBoost) methods to predict ASA-PS scores using patients' age, weight, and chronic conditions. SHapley Additive exPlanations (SHAP) were used to assess patient characteristics that contributed most to the predicted ASA-PS scores. The predicted ASA-PS model was presented to a prospective cohort study of 28,677 surgical encounters from December 1, 2021, to October 31, 2022. The predicted ASA-PS score was presented to the anesthesiology provider for review before entering the final ASA-PS score. The study focused on summarizing the available information for the anesthesiologist by using ML methods. The goal was to explore the potential for ML to provide assistance to anesthesiologists by highlighting potential areas of discordance between the variables that generated a given ML prediction and the physician's mental model of the patient's medical comorbidities.</p><p><strong>Results: </strong>For the retrospective analysis, the distribution of predicted ASA-PS scores was 22.7% ASA-PS I, 48.5% II, 23.6% III, 5.1% IV, and 0.04% V. The distribution of clinician-assigned ASA-PS scores was 24.3% for ASA-PS I, 44.5% for ASA-PS II, 24.9% for ASA III, 6.1% for ASA-PS IV, and 0.2% for ASA-V. In the prospective analysis, the final ASA-PS score matched the initial ASA-PS 90.7% of the time and 9.3% were revised after viewing the predicted ASA-PS score. When the initial ASA-PS score and the ML ASA-PS score were discrepant, 19.5% of the cases have a final ASA-PS score which is different from the initial clinician ASA-PS score. The prevalence of multiple chronic conditions increased with ASA-PS score: 34.9% ASA-PS I, 73.2% II, 92.3% III, and 94.4% IV.</p><p><strong>Conclusions: </strong>ML derivation of predicted pediatric ASA-PS scores was successful, with a strong agreement between predicted and clinician-entered ASA-PS scores. Presentation of predicted ASA-PS scores was associated with revision in final scoring for 1-in-10 pediatric patients.</p>","PeriodicalId":7784,"journal":{"name":"Anesthesia and analgesia","volume":null,"pages":null},"PeriodicalIF":4.6000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Assessing the Utility of a Machine-Learning Model to Assist With the Assignment of the American Society of Anesthesiology Physical Status Classification in Pediatric Patients.\",\"authors\":\"Lynne R Ferrari, Izabela Leahy, Steven J Staffa, Peter Hong, Isabel Stringfellow, Jay G Berry\",\"doi\":\"10.1213/ANE.0000000000006761\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The American Society of Anesthesiologists Physical Status Classification System (ASA-PS) is used to classify patients' health before delivering an anesthetic. Assigning an ASA-PS Classification score to pediatric patients can be challenging due to the vast array of chronic conditions present in the pediatric population. The specific aims of this study were to (1) suggest an ASA-PS score for pediatric patients undergoing elective surgical procedures using machine-learning (ML) methods; and (2) assess the impact of presenting the suggested ASA-PS score to clinicians when making their final ASA-PS assignment. The intent was not to create a new ASA-PS score but to use ML methods to generate a suggested score, along with information on how the score was generated (ie, historical information on patient comorbidities) to assist clinicians when assigning their final ASA-PS score.</p><p><strong>Methods: </strong>A retrospective analysis of 146,784 pediatric surgical encounters from January 1, 2016, to December 31, 2019, using eXtreme Gradient Boosting (XGBoost) methods to predict ASA-PS scores using patients' age, weight, and chronic conditions. SHapley Additive exPlanations (SHAP) were used to assess patient characteristics that contributed most to the predicted ASA-PS scores. The predicted ASA-PS model was presented to a prospective cohort study of 28,677 surgical encounters from December 1, 2021, to October 31, 2022. The predicted ASA-PS score was presented to the anesthesiology provider for review before entering the final ASA-PS score. The study focused on summarizing the available information for the anesthesiologist by using ML methods. The goal was to explore the potential for ML to provide assistance to anesthesiologists by highlighting potential areas of discordance between the variables that generated a given ML prediction and the physician's mental model of the patient's medical comorbidities.</p><p><strong>Results: </strong>For the retrospective analysis, the distribution of predicted ASA-PS scores was 22.7% ASA-PS I, 48.5% II, 23.6% III, 5.1% IV, and 0.04% V. The distribution of clinician-assigned ASA-PS scores was 24.3% for ASA-PS I, 44.5% for ASA-PS II, 24.9% for ASA III, 6.1% for ASA-PS IV, and 0.2% for ASA-V. In the prospective analysis, the final ASA-PS score matched the initial ASA-PS 90.7% of the time and 9.3% were revised after viewing the predicted ASA-PS score. When the initial ASA-PS score and the ML ASA-PS score were discrepant, 19.5% of the cases have a final ASA-PS score which is different from the initial clinician ASA-PS score. The prevalence of multiple chronic conditions increased with ASA-PS score: 34.9% ASA-PS I, 73.2% II, 92.3% III, and 94.4% IV.</p><p><strong>Conclusions: </strong>ML derivation of predicted pediatric ASA-PS scores was successful, with a strong agreement between predicted and clinician-entered ASA-PS scores. Presentation of predicted ASA-PS scores was associated with revision in final scoring for 1-in-10 pediatric patients.</p>\",\"PeriodicalId\":7784,\"journal\":{\"name\":\"Anesthesia and analgesia\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Anesthesia and analgesia\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1213/ANE.0000000000006761\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2023/12/13 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"ANESTHESIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Anesthesia and analgesia","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1213/ANE.0000000000006761","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/12/13 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"ANESTHESIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

背景:美国麻醉医师协会身体状况分类系统(ASA-PS)用于在实施麻醉前对患者的健康状况进行分类。由于儿科患者的慢性疾病种类繁多,给儿科患者进行 ASA-PS 分级是一项挑战。本研究的具体目的是:(1) 使用机器学习(ML)方法为接受择期手术的儿科患者建议 ASA-PS 评分;(2) 评估临床医生在最终分配 ASA-PS 时提出 ASA-PS 评分建议的影响。我们的目的不是创建一个新的 ASA-PS 评分,而是使用 ML 方法生成一个建议评分,并提供有关评分生成方式的信息(即有关患者合并症的历史信息),以协助临床医生进行最终的 ASA-PS 评分:对 2016 年 1 月 1 日至 2019 年 12 月 31 日期间的 146784 例儿科手术病例进行回顾性分析,采用 eXtreme Gradient Boosting (XGBoost) 方法,利用患者的年龄、体重和慢性疾病预测 ASA-PS 评分。使用 SHapley Additive exPlanations (SHAP) 评估对 ASA-PS 预测得分贡献最大的患者特征。在一项前瞻性队列研究中,对 2021 年 12 月 1 日至 2022 年 10 月 31 日期间的 28,677 例手术进行了 ASA-PS 预测。在输入最终的 ASA-PS 评分之前,会将预测的 ASA-PS 评分提交给麻醉科医生进行审核。该研究的重点是通过使用 ML 方法为麻醉医师总结可用信息。其目的是通过强调产生特定 ML 预测的变量与医生对患者医疗合并症的心理模型之间可能存在的不一致之处,探索 ML 为麻醉医生提供帮助的潜力:在回顾性分析中,预测的 ASA-PS 评分分布为:22.7% ASA-PS I、48.5% ASA-PS II、23.6% ASA-PS III、5.1% ASA-PS IV 和 0.04% ASA-V。在前瞻性分析中,90.7% 的情况下最终的 ASA-PS 评分与最初的 ASA-PS 评分一致,9.3% 的情况下在查看预测的 ASA-PS 评分后进行了修改。当初始 ASA-PS 评分和 ML ASA-PS 评分不一致时,19.5% 的病例的最终 ASA-PS 评分与临床医生的初始 ASA-PS 评分不同。多种慢性疾病的患病率随 ASA-PS 评分的增加而增加:ASA-PS I 级占 34.9%,II 级占 73.2%,III 级占 92.3%,IV 级占 94.4%:预测的儿科ASA-PS评分的ML推导是成功的,预测的ASA-PS评分与临床医生输入的ASA-PS评分之间有很强的一致性。在十分之一的儿科患者中,预测的 ASA-PS 评分与最终评分的修改有关。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Assessing the Utility of a Machine-Learning Model to Assist With the Assignment of the American Society of Anesthesiology Physical Status Classification in Pediatric Patients.

Background: The American Society of Anesthesiologists Physical Status Classification System (ASA-PS) is used to classify patients' health before delivering an anesthetic. Assigning an ASA-PS Classification score to pediatric patients can be challenging due to the vast array of chronic conditions present in the pediatric population. The specific aims of this study were to (1) suggest an ASA-PS score for pediatric patients undergoing elective surgical procedures using machine-learning (ML) methods; and (2) assess the impact of presenting the suggested ASA-PS score to clinicians when making their final ASA-PS assignment. The intent was not to create a new ASA-PS score but to use ML methods to generate a suggested score, along with information on how the score was generated (ie, historical information on patient comorbidities) to assist clinicians when assigning their final ASA-PS score.

Methods: A retrospective analysis of 146,784 pediatric surgical encounters from January 1, 2016, to December 31, 2019, using eXtreme Gradient Boosting (XGBoost) methods to predict ASA-PS scores using patients' age, weight, and chronic conditions. SHapley Additive exPlanations (SHAP) were used to assess patient characteristics that contributed most to the predicted ASA-PS scores. The predicted ASA-PS model was presented to a prospective cohort study of 28,677 surgical encounters from December 1, 2021, to October 31, 2022. The predicted ASA-PS score was presented to the anesthesiology provider for review before entering the final ASA-PS score. The study focused on summarizing the available information for the anesthesiologist by using ML methods. The goal was to explore the potential for ML to provide assistance to anesthesiologists by highlighting potential areas of discordance between the variables that generated a given ML prediction and the physician's mental model of the patient's medical comorbidities.

Results: For the retrospective analysis, the distribution of predicted ASA-PS scores was 22.7% ASA-PS I, 48.5% II, 23.6% III, 5.1% IV, and 0.04% V. The distribution of clinician-assigned ASA-PS scores was 24.3% for ASA-PS I, 44.5% for ASA-PS II, 24.9% for ASA III, 6.1% for ASA-PS IV, and 0.2% for ASA-V. In the prospective analysis, the final ASA-PS score matched the initial ASA-PS 90.7% of the time and 9.3% were revised after viewing the predicted ASA-PS score. When the initial ASA-PS score and the ML ASA-PS score were discrepant, 19.5% of the cases have a final ASA-PS score which is different from the initial clinician ASA-PS score. The prevalence of multiple chronic conditions increased with ASA-PS score: 34.9% ASA-PS I, 73.2% II, 92.3% III, and 94.4% IV.

Conclusions: ML derivation of predicted pediatric ASA-PS scores was successful, with a strong agreement between predicted and clinician-entered ASA-PS scores. Presentation of predicted ASA-PS scores was associated with revision in final scoring for 1-in-10 pediatric patients.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Anesthesia and analgesia
Anesthesia and analgesia 医学-麻醉学
CiteScore
9.90
自引率
7.00%
发文量
817
审稿时长
2 months
期刊介绍: Anesthesia & Analgesia exists for the benefit of patients under the care of health care professionals engaged in the disciplines broadly related to anesthesiology, perioperative medicine, critical care medicine, and pain medicine. The Journal furthers the care of these patients by reporting the fundamental advances in the science of these clinical disciplines and by documenting the clinical, laboratory, and administrative advances that guide therapy. Anesthesia & Analgesia seeks a balance between definitive clinical and management investigations and outstanding basic scientific reports. The Journal welcomes original manuscripts containing rigorous design and analysis, even if unusual in their approach.
期刊最新文献
A Little Blue Butterfly. A Paradigm for Shared Decision-Making in Pediatric Anesthesia Practice for Children with Autism for the Generalist Clinician. Association Between Two Muscle-Related Parameters and Postoperative Complications in Patients Undergoing Colorectal Tumor Resection Surgery. Cannabinoids and General Anesthetics: Revisiting Molecular Mechanisms of Their Pharmacological Interactions. Consensus Statement on Pain Management for Pregnant Patients with Opioid-Use Disorder from the Society for Obstetric Anesthesia and Perinatology, Society for Maternal-Fetal Medicine, and American Society of Regional Anesthesia and Pain Medicine.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1