优化结肠镜检查的使用,改善无症状患者的结直肠癌风险分层:决策曲线分析。

IF 1.4 4区 医学 Q2 MEDICINE, GENERAL & INTERNAL
Scottish Medical Journal Pub Date : 2024-08-01 Epub Date: 2024-07-23 DOI:10.1177/00369330241266080
James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank
{"title":"优化结肠镜检查的使用,改善无症状患者的结直肠癌风险分层:决策曲线分析。","authors":"James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank","doi":"10.1177/00369330241266080","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.</p><p><strong>Design: </strong>All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.</p><p><strong>Results: </strong>3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.</p><p><strong>Conclusions: </strong>MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.</p>","PeriodicalId":21683,"journal":{"name":"Scottish Medical Journal","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Optimising the use of colonoscopy to improve risk stratification for colorectal cancer in symptomatic patients: A decision-curve analysis.\",\"authors\":\"James Lucocq, Emma Barron, Heather Holmes, Peter D Donnelly, Neil Cruickshank\",\"doi\":\"10.1177/00369330241266080\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Objectives: </strong>Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.</p><p><strong>Design: </strong>All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.</p><p><strong>Results: </strong>3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.</p><p><strong>Conclusions: </strong>MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.</p>\",\"PeriodicalId\":21683,\"journal\":{\"name\":\"Scottish Medical Journal\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.4000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Scottish Medical Journal\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1177/00369330241266080\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/7/23 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q2\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scottish Medical Journal","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1177/00369330241266080","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/23 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

摘要

目的:由于医疗资源紧张,对有症状的患者进行结直肠癌(CRC)检查时,风险分层和患者优先顺序成为基本问题。本研究利用机器学习算法和决策策略来改善结肠镜检查的合理使用:纳入单一卫生局(2018-2021 年)所有接受结肠镜检查以排查 CRC 的无症状患者。使用机器学习算法(NeuralNetwork、randomForest、Logistic回归、Naïve-Bayes和Adaboost),通过人口统计学、症状、粪便免疫化学定量检测(qFIT)和血液学检测对患者进行CRC风险分级。进行决策曲线分析以确定最佳决策策略:结果:共纳入了 3776 名患者(中位年龄为 65 岁;男女比例为 0.9:1.0),其中 217 名患者(5.7%)被确定为 CRC。RandomForrest 对 CRC 的曲线下面积(0.91)和准确率(0.80)最高。在使用决策曲线分析(DCA)时,当接受的 CRC 概率为 1%、2% 和 3% 时,分别有 30%、46% 和 54% 的结肠镜检查得以挽救。与默认的结肠镜检查策略相比,RandomForrest 模型具有更高的净临床效益:结论:与默认结肠镜检查策略相比,考虑到患者和转诊者风险偏好的 MLA 衍生决策策略可减少结肠镜检查需求,并带来净临床效益。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Optimising the use of colonoscopy to improve risk stratification for colorectal cancer in symptomatic patients: A decision-curve analysis.

Objectives: Pressured healthcare resources make risk stratification and patient prioritisation fundamental issues for the investigation of colorectal cancer (CRC) in symptomatic patients. The present study uses machine learning algorithms and decision strategies to improve the appropriate use of colonoscopy.

Design: All symptomatic patients in a single health board (2018-2021) proceeding to colonoscopy to investigate for CRC were included. Machine learning algorithms (NeuralNetwork, randomForest, Logistic regression, Naïve-Bayes and Adaboost) were used to risk-stratify patients for CRC using demographics, symptoms, quantitative faecal immunochemical test (qFIT) and haematological tests. Decision curve analyses were performed to determine the optimal decision strategies.

Results: 3776 patients were included (median age, 65; M:F,0.9:1.0) and CRC was identified in 217 patients (5.7%). qFIT > 400 μg Hb/g was the most important variable (%IncMSE = 78.5). RandomForrest had the highest area under curve (0.91) and accuracy (0.80) for CRC. When utilising decision curve analysis (DCA), 30%, 46% and 54% of colonoscopies were saved at accepted CRC probabilities of 1%, 2% and 3%, respectively. RandomForrest modelling had superior net clinical benefit compared to default colonoscopy strategies.

Conclusions: MLA-derived decision strategies that account for patient and referrer risk preference reduce colonoscopy demand and carry net clinical benefit compared to default colonoscopy strategies.

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
Scottish Medical Journal
Scottish Medical Journal 医学-医学:内科
CiteScore
4.80
自引率
3.70%
发文量
42
审稿时长
>12 weeks
期刊介绍: A unique international information source for the latest news and issues concerning the Scottish medical community. Contributions are drawn from Scotland and its medical institutions, through an array of international authors. In addition to original papers, Scottish Medical Journal publishes commissioned educational review articles, case reports, historical articles, and sponsoring society abstracts.This journal is a member of the Committee on Publications Ethics (COPE).
×
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