基于人工智能算法的老年急诊围手术期风险指数预测老年急诊普外科预后

IF 1.8 3区医学 Q2 SURGERY

Journal of Surgical Research Pub Date : 2025-04-21 DOI:10.1016/j.jss.2025.03.008

Dequan Xu PhD, Haoxin Zhou PhD, Jie Rong MPH, Xin Xie MPH, Limin Hou PhD

{"title":"基于人工智能算法的老年急诊围手术期风险指数预测老年急诊普外科预后","authors":"Dequan Xu PhD, Haoxin Zhou PhD, Jie Rong MPH, Xin Xie MPH, Limin Hou PhD","doi":"10.1016/j.jss.2025.03.008","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>The objective of this study was to employ artificial intelligence (AI) technology for the development of a model that can accurately forecast the outcome of emergency general surgery (EGS) in elderly patients. Additionally, an innovative visual scoring system called geriatric emergency perioperative risk index (GEPR) was devised based on this model.</div></div><div><h3>Methods</h3><div>A retrospective database of geriatric patients who had undergone EGS was used for the development of the AI model and GEPR. The study employed a specialized algorithm, comprising of four sequential steps namely scale prototype selection, clinical data collection and collation, AI model development, and GEPR development.</div></div><div><h3>Results</h3><div>In total, 1500 patients with the mean age of 69.8 ys were enrolled in the study. RandomForestClassifier algorithm outperformed the other AI models. Based on the feature importance, GEPR was derived, with a total score range of 0–26. The C-statistic of GEPR for in-hospital mortality was 0.872 (95% confidence interval, 0.840–0.905). The observed probability of in-hospital mortality gradually increased from 0% at a score of 0 to 63.3% at a score of 12 and 100% at a score of 15.</div></div><div><h3>Conclusions</h3><div>Using patient-related and technical parameters, a GEPR model derived from AI algorithms for prediction of surgical complications in geriatric EGS was developed. The GEPR model reliably predicts postoperative in-hospital mortality in geriatric EGS patients. Clinical studies are currently being conducted to validate the stability and precision of the GEPR model utilizing the MIMIC-IV database. Further prospective multicenter trials are needed to externally validate the developed model.</div></div>","PeriodicalId":17030,"journal":{"name":"Journal of Surgical Research","volume":"309 ","pages":"Pages 188-198"},"PeriodicalIF":1.8000,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using the Geriatric Emergency Perioperative Risk Index Derived from Artificial Intelligence Algorithms to Predict Outcomes of Geriatric Emergency General Surgery\",\"authors\":\"Dequan Xu PhD, Haoxin Zhou PhD, Jie Rong MPH, Xin Xie MPH, Limin Hou PhD\",\"doi\":\"10.1016/j.jss.2025.03.008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Introduction</h3><div>The objective of this study was to employ artificial intelligence (AI) technology for the development of a model that can accurately forecast the outcome of emergency general surgery (EGS) in elderly patients. Additionally, an innovative visual scoring system called geriatric emergency perioperative risk index (GEPR) was devised based on this model.</div></div><div><h3>Methods</h3><div>A retrospective database of geriatric patients who had undergone EGS was used for the development of the AI model and GEPR. The study employed a specialized algorithm, comprising of four sequential steps namely scale prototype selection, clinical data collection and collation, AI model development, and GEPR development.</div></div><div><h3>Results</h3><div>In total, 1500 patients with the mean age of 69.8 ys were enrolled in the study. RandomForestClassifier algorithm outperformed the other AI models. Based on the feature importance, GEPR was derived, with a total score range of 0–26. The C-statistic of GEPR for in-hospital mortality was 0.872 (95% confidence interval, 0.840–0.905). The observed probability of in-hospital mortality gradually increased from 0% at a score of 0 to 63.3% at a score of 12 and 100% at a score of 15.</div></div><div><h3>Conclusions</h3><div>Using patient-related and technical parameters, a GEPR model derived from AI algorithms for prediction of surgical complications in geriatric EGS was developed. The GEPR model reliably predicts postoperative in-hospital mortality in geriatric EGS patients. Clinical studies are currently being conducted to validate the stability and precision of the GEPR model utilizing the MIMIC-IV database. Further prospective multicenter trials are needed to externally validate the developed model.</div></div>\",\"PeriodicalId\":17030,\"journal\":{\"name\":\"Journal of Surgical Research\",\"volume\":\"309 \",\"pages\":\"Pages 188-198\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2025-04-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Surgical Research\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0022480425001271\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"SURGERY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Surgical Research","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0022480425001271","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"SURGERY","Score":null,"Total":0}

引用次数: 0

摘要

引言本研究的目的是利用人工智能（AI）技术开发一种能够准确预测老年患者急诊普外科手术（EGS）结果的模型。方法在开发人工智能模型和 GEPR 时，使用了老年普外科急诊患者的回顾性数据库。研究采用了一种专门的算法，包括四个连续步骤，即量表原型选择、临床数据收集和整理、人工智能模型开发和 GEPR 开发。随机森林分类器算法的表现优于其他人工智能模型。根据特征的重要性得出了 GEPR，总分范围为 0-26。院内死亡率的 GEPR C 统计量为 0.872（95% 置信区间，0.840-0.905）。观察到的院内死亡概率从 0 分时的 0% 逐渐增加到 12 分时的 63.3%，再到 15 分时的 100%。结论利用患者相关参数和技术参数，开发出了一个源自人工智能算法的 GEPR 模型，用于预测老年 EGS 的手术并发症。GEPR 模型能可靠地预测老年 EGS 患者的术后院内死亡率。目前正在进行临床研究，利用 MIMIC-IV 数据库验证 GEPR 模型的稳定性和精确性。还需要进一步开展前瞻性多中心试验，从外部验证所开发的模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Using the Geriatric Emergency Perioperative Risk Index Derived from Artificial Intelligence Algorithms to Predict Outcomes of Geriatric Emergency General Surgery

Introduction

The objective of this study was to employ artificial intelligence (AI) technology for the development of a model that can accurately forecast the outcome of emergency general surgery (EGS) in elderly patients. Additionally, an innovative visual scoring system called geriatric emergency perioperative risk index (GEPR) was devised based on this model.

Methods

A retrospective database of geriatric patients who had undergone EGS was used for the development of the AI model and GEPR. The study employed a specialized algorithm, comprising of four sequential steps namely scale prototype selection, clinical data collection and collation, AI model development, and GEPR development.

Results

In total, 1500 patients with the mean age of 69.8 ys were enrolled in the study. RandomForestClassifier algorithm outperformed the other AI models. Based on the feature importance, GEPR was derived, with a total score range of 0–26. The C-statistic of GEPR for in-hospital mortality was 0.872 (95% confidence interval, 0.840–0.905). The observed probability of in-hospital mortality gradually increased from 0% at a score of 0 to 63.3% at a score of 12 and 100% at a score of 15.

Conclusions

Using patient-related and technical parameters, a GEPR model derived from AI algorithms for prediction of surgical complications in geriatric EGS was developed. The GEPR model reliably predicts postoperative in-hospital mortality in geriatric EGS patients. Clinical studies are currently being conducted to validate the stability and precision of the GEPR model utilizing the MIMIC-IV database. Further prospective multicenter trials are needed to externally validate the developed model.

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

Journal of Surgical Research 医学-外科

CiteScore

3.90

自引率

4.50%

发文量

627

审稿时长

138 days

期刊介绍： The Journal of Surgical Research: Clinical and Laboratory Investigation publishes original articles concerned with clinical and laboratory investigations relevant to surgical practice and teaching. The journal emphasizes reports of clinical investigations or fundamental research bearing directly on surgical management that will be of general interest to a broad range of surgeons and surgical researchers. The articles presented need not have been the products of surgeons or of surgical laboratories. The Journal of Surgical Research also features review articles and special articles relating to educational, research, or social issues of interest to the academic surgical community.