IBM WATSON创伤路径探索者©作为多重创伤后脓毒症的预测因子-降钙素原对识别脓毒性多重创伤患者有用吗?

Cédric Niggli, Philipp Vetter, Jan Hambrecht, Philipp Niggli, Jindřich Vomela, Richard Chaloupka, Hans-Christoph Pape, Ladislav Mica
{"title":"IBM WATSON创伤路径探索者©作为多重创伤后脓毒症的预测因子-降钙素原对识别脓毒性多重创伤患者有用吗?","authors":"Cédric Niggli,&nbsp;Philipp Vetter,&nbsp;Jan Hambrecht,&nbsp;Philipp Niggli,&nbsp;Jindřich Vomela,&nbsp;Richard Chaloupka,&nbsp;Hans-Christoph Pape,&nbsp;Ladislav Mica","doi":"10.26502/jsr.10020272","DOIUrl":null,"url":null,"abstract":"<p><p>IBM and the University Hospital Zurich have developed an online tool for predicting outcomes of a patient with polytrauma, the <i>IBM WATSON Trauma Pathway Explorer<sup>®</sup></i> . The three predicted outcomes are Systemic Inflammatory Response Syndrome (SIRS) and sepsis within 21 days as well as early death within 72 hours since the admission of the patient. The validated <i>Trauma Pathway Explorer<sup>®</sup></i> offers insights into the most common laboratory parameters, such as procalcitonin (PCT). Sepsis is one of the most important complications after polytrauma, which is why it is crucial to detect it early. This study aimed to examine the time-dependent relationship between PCT values and sepsis, based on the WATSON technology. A total of 3653 patients were included, and ongoing admissions are incorporated continuously. Patients were split into two groups (sepsis and non-sepsis), and the PCT value was assessed for 21 days (1, 2, 3, 4, 6, 8, 12, 24, 48 hours, and 3, 4, 5, 7, 10, 14 and 21 days). The Mann-Whitney U-Test was used to evaluate the difference between the two groups. Binary logistic regression was utilized to examine the dependency of prediction. The Closest Top-left Threshold Method provided time-specific thresholds at which the PCT level is predictive for sepsis. At p <0.05, the data were declared significant. R was used to conduct all statistical analyses. The Mann-Whitney U-test showed a significant difference in PCT values in sepsis and non-sepsis patients between 12 and 24 hours, including post-hoc analysis (p <0.05). Likewise, the p-value started to be significant between 12 and 24 hours in the binary logistic regression (p <0.05). The threshold value of PCT to predict sepsis at 24 hours is 0.7μg/l, and at 48 hours 0.5μg/l. The presented time course of PCT levels in polytrauma patients shows the PCT as a separate predictor for sepsis relatively early. Even later, during the 21-day observation period, time-dependent PCT values may be utilized as a benchmark for the early and preemptive detection of sepsis, which may reduce death from septic shock and other deadly infectious episodes.</p>","PeriodicalId":73961,"journal":{"name":"Journal of surgery and research","volume":"5 4","pages":"637-644"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9937584/pdf/","citationCount":"1","resultStr":"{\"title\":\"<i>IBM WATSON Trauma Pathway Explorer©</i> as a Predictor for Sepsis after Polytrauma - Is Procalcitonin Useful for Identifying Septic Polytrauma Patients?\",\"authors\":\"Cédric Niggli,&nbsp;Philipp Vetter,&nbsp;Jan Hambrecht,&nbsp;Philipp Niggli,&nbsp;Jindřich Vomela,&nbsp;Richard Chaloupka,&nbsp;Hans-Christoph Pape,&nbsp;Ladislav Mica\",\"doi\":\"10.26502/jsr.10020272\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>IBM and the University Hospital Zurich have developed an online tool for predicting outcomes of a patient with polytrauma, the <i>IBM WATSON Trauma Pathway Explorer<sup>®</sup></i> . The three predicted outcomes are Systemic Inflammatory Response Syndrome (SIRS) and sepsis within 21 days as well as early death within 72 hours since the admission of the patient. The validated <i>Trauma Pathway Explorer<sup>®</sup></i> offers insights into the most common laboratory parameters, such as procalcitonin (PCT). Sepsis is one of the most important complications after polytrauma, which is why it is crucial to detect it early. This study aimed to examine the time-dependent relationship between PCT values and sepsis, based on the WATSON technology. A total of 3653 patients were included, and ongoing admissions are incorporated continuously. Patients were split into two groups (sepsis and non-sepsis), and the PCT value was assessed for 21 days (1, 2, 3, 4, 6, 8, 12, 24, 48 hours, and 3, 4, 5, 7, 10, 14 and 21 days). The Mann-Whitney U-Test was used to evaluate the difference between the two groups. Binary logistic regression was utilized to examine the dependency of prediction. The Closest Top-left Threshold Method provided time-specific thresholds at which the PCT level is predictive for sepsis. At p <0.05, the data were declared significant. R was used to conduct all statistical analyses. The Mann-Whitney U-test showed a significant difference in PCT values in sepsis and non-sepsis patients between 12 and 24 hours, including post-hoc analysis (p <0.05). Likewise, the p-value started to be significant between 12 and 24 hours in the binary logistic regression (p <0.05). The threshold value of PCT to predict sepsis at 24 hours is 0.7μg/l, and at 48 hours 0.5μg/l. The presented time course of PCT levels in polytrauma patients shows the PCT as a separate predictor for sepsis relatively early. Even later, during the 21-day observation period, time-dependent PCT values may be utilized as a benchmark for the early and preemptive detection of sepsis, which may reduce death from septic shock and other deadly infectious episodes.</p>\",\"PeriodicalId\":73961,\"journal\":{\"name\":\"Journal of surgery and research\",\"volume\":\"5 4\",\"pages\":\"637-644\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9937584/pdf/\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of surgery and research\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.26502/jsr.10020272\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of surgery and research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26502/jsr.10020272","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

摘要

IBM和苏黎世大学医院开发了一种在线工具,用于预测多发性创伤患者的预后,即IBM WATSON创伤路径探索者®。三种预测结果是全身性炎症反应综合征(SIRS)和21天内的败血症以及患者入院后72小时内的早期死亡。经过验证的创伤路径探索者®提供了对最常见的实验室参数的见解,如降钙素原(PCT)。脓毒症是多发创伤后最重要的并发症之一,因此早期发现脓毒症至关重要。本研究旨在研究基于WATSON技术的PCT值与脓毒症之间的时间依赖关系。共纳入3653例患者,持续纳入入院患者。将患者分为脓毒症和非脓毒症两组,评估21天的PCT值(1、2、3、4、6、8、12、24、48小时,以及3、4、5、7、10、14、21天)。使用Mann-Whitney U-Test来评估两组之间的差异。采用二元逻辑回归检验预测的相关性。最接近左上角阈值法提供了PCT水平预测脓毒症的特定时间阈值。在p
本文章由计算机程序翻译,如有差异,请以英文原文为准。

<i>IBM WATSON Trauma Pathway Explorer©</i> as a Predictor for Sepsis after Polytrauma - Is Procalcitonin Useful for Identifying Septic Polytrauma Patients?

<i>IBM WATSON Trauma Pathway Explorer©</i> as a Predictor for Sepsis after Polytrauma - Is Procalcitonin Useful for Identifying Septic Polytrauma Patients?

<i>IBM WATSON Trauma Pathway Explorer©</i> as a Predictor for Sepsis after Polytrauma - Is Procalcitonin Useful for Identifying Septic Polytrauma Patients?

IBM WATSON Trauma Pathway Explorer© as a Predictor for Sepsis after Polytrauma - Is Procalcitonin Useful for Identifying Septic Polytrauma Patients?

IBM and the University Hospital Zurich have developed an online tool for predicting outcomes of a patient with polytrauma, the IBM WATSON Trauma Pathway Explorer® . The three predicted outcomes are Systemic Inflammatory Response Syndrome (SIRS) and sepsis within 21 days as well as early death within 72 hours since the admission of the patient. The validated Trauma Pathway Explorer® offers insights into the most common laboratory parameters, such as procalcitonin (PCT). Sepsis is one of the most important complications after polytrauma, which is why it is crucial to detect it early. This study aimed to examine the time-dependent relationship between PCT values and sepsis, based on the WATSON technology. A total of 3653 patients were included, and ongoing admissions are incorporated continuously. Patients were split into two groups (sepsis and non-sepsis), and the PCT value was assessed for 21 days (1, 2, 3, 4, 6, 8, 12, 24, 48 hours, and 3, 4, 5, 7, 10, 14 and 21 days). The Mann-Whitney U-Test was used to evaluate the difference between the two groups. Binary logistic regression was utilized to examine the dependency of prediction. The Closest Top-left Threshold Method provided time-specific thresholds at which the PCT level is predictive for sepsis. At p <0.05, the data were declared significant. R was used to conduct all statistical analyses. The Mann-Whitney U-test showed a significant difference in PCT values in sepsis and non-sepsis patients between 12 and 24 hours, including post-hoc analysis (p <0.05). Likewise, the p-value started to be significant between 12 and 24 hours in the binary logistic regression (p <0.05). The threshold value of PCT to predict sepsis at 24 hours is 0.7μg/l, and at 48 hours 0.5μg/l. The presented time course of PCT levels in polytrauma patients shows the PCT as a separate predictor for sepsis relatively early. Even later, during the 21-day observation period, time-dependent PCT values may be utilized as a benchmark for the early and preemptive detection of sepsis, which may reduce death from septic shock and other deadly infectious episodes.

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
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信