Prediction of Severe Acute Pancreatitis at a Very Early Stage of the Disease Using Artificial Intelligence Techniques, Without Laboratory Data or Imaging Tests: The PANCREATIA Study.

IF 7.5 1区 医学 Q1 SURGERY
Sara Villasante, Nair Fernandes, Marc Perez, Miguel Angel Cordobés, Gemma Piella, María Martinez, Concepción Gomez-Gavara, Laia Blanco, Piero Alberti, Ramón Charco, Elizabeth Pando
{"title":"Prediction of Severe Acute Pancreatitis at a Very Early Stage of the Disease Using Artificial Intelligence Techniques, Without Laboratory Data or Imaging Tests: The PANCREATIA Study.","authors":"Sara Villasante, Nair Fernandes, Marc Perez, Miguel Angel Cordobés, Gemma Piella, María Martinez, Concepción Gomez-Gavara, Laia Blanco, Piero Alberti, Ramón Charco, Elizabeth Pando","doi":"10.1097/SLA.0000000000006579","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To evaluate machine learning models' performance in predicting acute pancreatitis severity using early-stage variables while excluding laboratory and imaging tests.</p><p><strong>Summary background data: </strong>Severe acute pancreatitis (SAP) affects approximately 20% of acute pancreatitis (AP) patients and is associated with high mortality rates. Accurate early prediction of SAP and in-hospital mortality is crucial for effective management. Traditional scores such as APACHE-II and BISAP are complex and require laboratory tests, while early predictive models are lacking. Machine learning (ML) has shown promising results in predictive modelling, potentially outperforming traditional methods.</p><p><strong>Methods: </strong>We analysed data from a prospective database of AP patients admitted to Vall d'Hebron Hospital from November 2015 to January 2022. Inclusion criteria were adults diagnosed with AP according to the 2012 Atlanta classification. Data included basal characteristics, current medication, and vital signs. We developed machine learning models to predict SAP, in-hospital mortality, and intensive care unit (ICU) admission. The modelling process included two stages: Stage 0, which used basal characteristics and medication, and Stage 1, which included data from Stage 0 and vital signs.</p><p><strong>Results: </strong>Out of 634 cases, 594 were analysed. The Stage 0 model showed AUC values of 0.698 for mortality, 0.721 for ICU admission, and 0.707 for persistent organ failure. The Stage 1 model improved performance with AUC values of 0.849 for mortality, 0.786 for ICU admission, and 0.783 for persistent organ failure. The models demonstrated comparable or superior performance to APACHE-II and BISAP scores.</p><p><strong>Conclusions: </strong>The ML models showed good predictive capacity for SAP, ICU admission, and mortality using early-stage data without laboratory or imaging tests. This approach could revolutionise AP patients' initial triage and management, providing a personalised prediction method based on early clinical data.</p>","PeriodicalId":8017,"journal":{"name":"Annals of surgery","volume":null,"pages":null},"PeriodicalIF":7.5000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of surgery","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/SLA.0000000000006579","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"SURGERY","Score":null,"Total":0}
引用次数: 0

Abstract

Objective: To evaluate machine learning models' performance in predicting acute pancreatitis severity using early-stage variables while excluding laboratory and imaging tests.

Summary background data: Severe acute pancreatitis (SAP) affects approximately 20% of acute pancreatitis (AP) patients and is associated with high mortality rates. Accurate early prediction of SAP and in-hospital mortality is crucial for effective management. Traditional scores such as APACHE-II and BISAP are complex and require laboratory tests, while early predictive models are lacking. Machine learning (ML) has shown promising results in predictive modelling, potentially outperforming traditional methods.

Methods: We analysed data from a prospective database of AP patients admitted to Vall d'Hebron Hospital from November 2015 to January 2022. Inclusion criteria were adults diagnosed with AP according to the 2012 Atlanta classification. Data included basal characteristics, current medication, and vital signs. We developed machine learning models to predict SAP, in-hospital mortality, and intensive care unit (ICU) admission. The modelling process included two stages: Stage 0, which used basal characteristics and medication, and Stage 1, which included data from Stage 0 and vital signs.

Results: Out of 634 cases, 594 were analysed. The Stage 0 model showed AUC values of 0.698 for mortality, 0.721 for ICU admission, and 0.707 for persistent organ failure. The Stage 1 model improved performance with AUC values of 0.849 for mortality, 0.786 for ICU admission, and 0.783 for persistent organ failure. The models demonstrated comparable or superior performance to APACHE-II and BISAP scores.

Conclusions: The ML models showed good predictive capacity for SAP, ICU admission, and mortality using early-stage data without laboratory or imaging tests. This approach could revolutionise AP patients' initial triage and management, providing a personalised prediction method based on early clinical data.

利用人工智能技术,在没有实验室数据或成像测试的情况下,预测疾病早期阶段的严重急性胰腺炎:PANCREATIA 研究》。
目的评估机器学习模型利用早期变量预测急性胰腺炎严重程度的性能,同时排除实验室和影像学检查:重症急性胰腺炎(SAP)约影响 20% 的急性胰腺炎(AP)患者,并与高死亡率相关。早期准确预测 SAP 和院内死亡率对有效治疗至关重要。传统的评分方法(如 APACHE-II 和 BISAP)非常复杂,需要进行实验室检测,同时缺乏早期预测模型。机器学习(ML)在预测建模方面取得了可喜的成果,有可能超越传统方法:我们分析了 2015 年 11 月至 2022 年 1 月期间入住 Vall d'Hebron 医院的 AP 患者的前瞻性数据库数据。纳入标准为根据 2012 年亚特兰大分类法确诊为 AP 的成人。数据包括基础特征、当前用药和生命体征。我们开发了机器学习模型来预测 SAP、院内死亡率和重症监护室(ICU)入院率。建模过程包括两个阶段:第一阶段包括第一阶段的数据和生命体征:结果:在 634 个病例中,分析了 594 个。第 0 阶段模型显示死亡率的 AUC 值为 0.698,入住重症监护室的 AUC 值为 0.721,持续器官衰竭的 AUC 值为 0.707。第 1 阶段模型的性能有所提高,死亡率的 AUC 值为 0.849,入住重症监护室的 AUC 值为 0.786,器官持续衰竭的 AUC 值为 0.783。这些模型的性能与 APACHE-II 和 BISAP 评分相当或更优:ML模型利用没有实验室或影像学检查的早期数据,对SAP、入住ICU和死亡率显示出良好的预测能力。这种方法可以彻底改变 AP 患者的初始分诊和管理,提供一种基于早期临床数据的个性化预测方法。
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
Annals of surgery
Annals of surgery 医学-外科
CiteScore
14.40
自引率
4.40%
发文量
687
审稿时长
4 months
期刊介绍: The Annals of Surgery is a renowned surgery journal, recognized globally for its extensive scholarly references. It serves as a valuable resource for the international medical community by disseminating knowledge regarding important developments in surgical science and practice. Surgeons regularly turn to the Annals of Surgery to stay updated on innovative practices and techniques. The journal also offers special editorial features such as "Advances in Surgical Technique," offering timely coverage of ongoing clinical issues. Additionally, the journal publishes monthly review articles that address the latest concerns in surgical practice.
×
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