Desarrollo y validación de algoritmo predictivo de la longitud total del intestino delgado con técnicas de inteligencia artificial para su aplicación en cirugía bariátrica

IF 1.3 4区医学 Q3 SURGERY

Cirugia Espanola Pub Date : 2025-07-01 DOI:10.1016/j.ciresp.2025.800124

José Fernando Trebolle , Jorge Solano Murillo , Jesús Lobo Cobo , Carmen Pellicer Lostao , Mónica Valero Sabater , Gabriel Tirado Anglés , Irene Cantarero Carmona , María José Luesma Bartolomé

{"title":"Desarrollo y validación de algoritmo predictivo de la longitud total del intestino delgado con técnicas de inteligencia artificial para su aplicación en cirugía bariátrica","authors":"José Fernando Trebolle , Jorge Solano Murillo , Jesús Lobo Cobo , Carmen Pellicer Lostao , Mónica Valero Sabater , Gabriel Tirado Anglés , Irene Cantarero Carmona , María José Luesma Bartolomé","doi":"10.1016/j.ciresp.2025.800124","DOIUrl":null,"url":null,"abstract":"<div><h3>Objective</h3><div>To develop a predictive model of the total length of the small intestine to be applied in bariatric surgery, allowing for the individualization of surgery for each patient.</div></div><div><h3>Methods</h3><div>Two Excel® tables were generated from a FileMaker file. Python was used through a Notebook format in Google™ Collaborator. The methodology included data transformation and scaling (MinMaxScaler), clustering (unsupervised machine learning with KMeans), data interpolation (oversampling machine learning technique SMOTE), modeling (PyCaret model - XGBoost), and validation.</div></div><div><h3>Results</h3><div>The study sample included 1090 cases. Three clusters were obtained to categorize the dataset: low, medium, and high length. The algorithm detected patients in cluster c0 with 62% accuracy and 74% sensitivity, in cluster c1 with 63% accuracy and 50% sensitivity, and in cluster c2 with 86% accuracy and 87% sensitivity. Validation was conducted with a new sample of 54 cases, showing results of 50% accuracy and 42% sensitivity for cluster c0, 58% accuracy and 61% sensitivity for cluster c1, and 30% accuracy and 43% sensitivity for cluster c2.</div></div><div><h3>Conclusions</h3><div>The development of a predictive algorithm for estimating the total length of the small intestine using clustering and machine learning techniques, along with XGBoost classification, is feasible, applicable, and potentially improvable with more data, both in terms of patient numbers and variables to consider.</div></div>","PeriodicalId":50690,"journal":{"name":"Cirugia Espanola","volume":"103 7","pages":"Article 800124"},"PeriodicalIF":1.3000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cirugia Espanola","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009739X2501471X","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"SURGERY","Score":null,"Total":0}

引用次数: 0

Abstract

Objective

To develop a predictive model of the total length of the small intestine to be applied in bariatric surgery, allowing for the individualization of surgery for each patient.

Methods

Two Excel® tables were generated from a FileMaker file. Python was used through a Notebook format in Google™ Collaborator. The methodology included data transformation and scaling (MinMaxScaler), clustering (unsupervised machine learning with KMeans), data interpolation (oversampling machine learning technique SMOTE), modeling (PyCaret model - XGBoost), and validation.

Results

The study sample included 1090 cases. Three clusters were obtained to categorize the dataset: low, medium, and high length. The algorithm detected patients in cluster c0 with 62% accuracy and 74% sensitivity, in cluster c1 with 63% accuracy and 50% sensitivity, and in cluster c2 with 86% accuracy and 87% sensitivity. Validation was conducted with a new sample of 54 cases, showing results of 50% accuracy and 42% sensitivity for cluster c0, 58% accuracy and 61% sensitivity for cluster c1, and 30% accuracy and 43% sensitivity for cluster c2.

Conclusions

The development of a predictive algorithm for estimating the total length of the small intestine using clustering and machine learning techniques, along with XGBoost classification, is feasible, applicable, and potentially improvable with more data, both in terms of patient numbers and variables to consider.

Abstract Image

查看原文本刊更多论文

利用人工智能技术开发和验证用于减肥手术的小肠总长度预测算法

目的建立一种在减肥手术中应用的小肠总长度预测模型，为每位患者提供个体化手术。方法从一个FileMaker文件生成两个Excel®表格。Python通过谷歌™Collaborator中的Notebook格式使用。方法包括数据转换和缩放（MinMaxScaler），聚类（使用KMeans的无监督机器学习），数据插值（过采样机器学习技术SMOTE），建模（PyCaret模型- XGBoost）和验证。结果共纳入1090例病例。得到三个聚类来对数据集进行分类：低、中、高长度。该算法对c类患者的检测准确率为62%，灵敏度为74%；对c1类患者的检测准确率为63%，灵敏度为50%；对c2类患者的检测准确率为86%，灵敏度为87%。用54个病例的新样本进行验证，结果显示簇c0的准确度为50%，灵敏度为42%，簇c1的准确度为58%，灵敏度为61%，簇c2的准确度为30%，灵敏度为43%。结论：利用聚类和机器学习技术以及XGBoost分类，开发一种预测小肠总长度的算法是可行的，适用的，并且在患者数量和需要考虑的变量方面具有潜在的改进潜力。

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

Cirugia Espanola SURGERY-

CiteScore

1.20

自引率

21.10%

发文量

173

审稿时长

53 days

期刊介绍： Cirugía Española, an official body of the Asociación Española de Cirujanos (Spanish Association of Surgeons), will consider original articles, reviews, editorials, special articles, scientific letters, letters to the editor, and medical images for publication; all of these will be submitted to an anonymous external peer review process. There is also the possibility of accepting book reviews of recent publications related to General and Digestive Surgery.