针对因疑似尿路癌转诊至二级医疗机构的血尿患者的 IDENTIFY 风险计算器的机器学习和外部验证。

IF 4.8 2区 医学 Q1 UROLOGY & NEPHROLOGY European urology focus Pub Date : 2024-12-01 Epub Date: 2024-06-21 DOI:10.1016/j.euf.2024.06.004
Sinan Khadhouri, Artsiom Hramyka, Kevin Gallagher, Alexander Light, Simona Ippoliti, Marie Edison, Cameron Alexander, Meghana Kulkarni, Eleanor Zimmermann, Arjun Nathan, Luca Orecchia, Ravi Banthia, Pietro Piazza, David Mak, Nikolaos Pyrgidis, Prabhat Narayan, Pablo Abad Lopez, Faisal Nawaz, Trung-Thanh Tran, Francesco Claps, Donnacha Hogan, Juan Gomez Rivas, Santiago Alonso, Ijeoma Chibuzo, Beatriz Gutierrez Hidalgo, Jessica Whitburn, Jeremy Teoh, Gautier Marcq, Alexandra Szostek, Jasper Bondad, Petros Sountoulides, Tom Kelsey, Veeru Kasivisvanathan
{"title":"针对因疑似尿路癌转诊至二级医疗机构的血尿患者的 IDENTIFY 风险计算器的机器学习和外部验证。","authors":"Sinan Khadhouri, Artsiom Hramyka, Kevin Gallagher, Alexander Light, Simona Ippoliti, Marie Edison, Cameron Alexander, Meghana Kulkarni, Eleanor Zimmermann, Arjun Nathan, Luca Orecchia, Ravi Banthia, Pietro Piazza, David Mak, Nikolaos Pyrgidis, Prabhat Narayan, Pablo Abad Lopez, Faisal Nawaz, Trung-Thanh Tran, Francesco Claps, Donnacha Hogan, Juan Gomez Rivas, Santiago Alonso, Ijeoma Chibuzo, Beatriz Gutierrez Hidalgo, Jessica Whitburn, Jeremy Teoh, Gautier Marcq, Alexandra Szostek, Jasper Bondad, Petros Sountoulides, Tom Kelsey, Veeru Kasivisvanathan","doi":"10.1016/j.euf.2024.06.004","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups.</p><p><strong>Objective: </strong>To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms.</p><p><strong>Design, setting, and participants: </strong>Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed.</p><p><strong>Outcome measurements and statistical analysis: </strong>The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined.</p><p><strong>Results and limitations: </strong>There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups.</p><p><strong>Conclusions: </strong>The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer.</p><p><strong>Patient summary: </strong>We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.</p>","PeriodicalId":12160,"journal":{"name":"European urology focus","volume":" ","pages":"1034-1042"},"PeriodicalIF":4.8000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine Learning and External Validation of the IDENTIFY Risk Calculator for Patients with Haematuria Referred to Secondary Care for Suspected Urinary Tract Cancer.\",\"authors\":\"Sinan Khadhouri, Artsiom Hramyka, Kevin Gallagher, Alexander Light, Simona Ippoliti, Marie Edison, Cameron Alexander, Meghana Kulkarni, Eleanor Zimmermann, Arjun Nathan, Luca Orecchia, Ravi Banthia, Pietro Piazza, David Mak, Nikolaos Pyrgidis, Prabhat Narayan, Pablo Abad Lopez, Faisal Nawaz, Trung-Thanh Tran, Francesco Claps, Donnacha Hogan, Juan Gomez Rivas, Santiago Alonso, Ijeoma Chibuzo, Beatriz Gutierrez Hidalgo, Jessica Whitburn, Jeremy Teoh, Gautier Marcq, Alexandra Szostek, Jasper Bondad, Petros Sountoulides, Tom Kelsey, Veeru Kasivisvanathan\",\"doi\":\"10.1016/j.euf.2024.06.004\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups.</p><p><strong>Objective: </strong>To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms.</p><p><strong>Design, setting, and participants: </strong>Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed.</p><p><strong>Outcome measurements and statistical analysis: </strong>The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined.</p><p><strong>Results and limitations: </strong>There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups.</p><p><strong>Conclusions: </strong>The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer.</p><p><strong>Patient summary: </strong>We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.</p>\",\"PeriodicalId\":12160,\"journal\":{\"name\":\"European urology focus\",\"volume\":\" \",\"pages\":\"1034-1042\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"European urology focus\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.euf.2024.06.004\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/6/21 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"UROLOGY & NEPHROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"European urology focus","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.euf.2024.06.004","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/21 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"UROLOGY & NEPHROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

研究背景IDENTIFY 研究利用大型多中心国际队列中血尿转诊患者的特征,建立了一个预测尿路癌的模型。除了计算个人的癌症风险外,该模型还提出了将个人划分为极低风险人群的阈值:从外部验证 IDENTIFY 血尿风险计算器,并比较传统回归与机器学习算法:对转诊至二级医疗机构的新发血尿患者进行前瞻性数据收集。收集的数据包括 IDENTIFY 风险计算器中的患者变量、癌症结果和 TNM 分期。结果测量和统计分析:结果测量和统计分析:确定了尿路癌检测的接收者操作特征曲线下面积(AUC)、校准系数、大样本校准(CITL)和布赖尔评分:验证队列中有 3582 名患者。开发队列和验证队列匹配良好。在验证队列中,IDENTIFY 风险计算器的 AUC 为 0.78。在仅对尿路癌流行国家进行的子分析中,其AUC提高到0.80,校准斜率为1.04,CITL为0.24,Brier评分为0.14。最佳机器学习模型是随机森林模型,其验证队列的AUC为0.76。在验证队列中,没有癌症被分层为极低风险组。大多数癌症被分层为中高风险组,高风险组中的癌症更具侵袭性:IDENTIFY风险计算器在预测因血尿转诊患者的癌症方面表现良好。泌尿科医生可利用该工具更好地为患者提供癌症风险咨询,将诊断资源优先用于合适的患者,并避免对癌症风险极低的患者进行不必要的侵入性手术。患者摘要:我们之前开发了一种计算器,可根据患者的个人特征预测血尿患者的癌症风险。我们对这一风险计算器进行了验证,并在另一组患者身上进行了测试,以确保它能发挥预期的作用。大多数被发现患有癌症的患者往往属于高危人群,他们所患的癌症类型更具侵袭性,风险更高。临床医生可以利用这一工具,根据计算器快速追踪高风险患者,并对他们进行更彻底的调查。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Machine Learning and External Validation of the IDENTIFY Risk Calculator for Patients with Haematuria Referred to Secondary Care for Suspected Urinary Tract Cancer.

Background: The IDENTIFY study developed a model to predict urinary tract cancer using patient characteristics from a large multicentre, international cohort of patients referred with haematuria. In addition to calculating an individual's cancer risk, it proposes thresholds to stratify them into very-low-risk (<1%), low-risk (1-<5%), intermediate-risk (5-<20%), and high-risk (≥20%) groups.

Objective: To externally validate the IDENTIFY haematuria risk calculator and compare traditional regression with machine learning algorithms.

Design, setting, and participants: Prospective data were collected on patients referred to secondary care with new haematuria. Data were collected for patient variables included in the IDENTIFY risk calculator, cancer outcome, and TNM staging. Machine learning methods were used to evaluate whether better models than those developed with traditional regression methods existed.

Outcome measurements and statistical analysis: The area under the receiver operating characteristic curve (AUC) for the detection of urinary tract cancer, calibration coefficient, calibration in the large (CITL), and Brier score were determined.

Results and limitations: There were 3582 patients in the validation cohort. The development and validation cohorts were well matched. The AUC of the IDENTIFY risk calculator on the validation cohort was 0.78. This improved to 0.80 on a subanalysis of urothelial cancer prevalent countries alone, with a calibration slope of 1.04, CITL of 0.24, and Brier score of 0.14. The best machine learning model was Random Forest, which achieved an AUC of 0.76 on the validation cohort. There were no cancers stratified to the very-low-risk group in the validation cohort. Most cancers were stratified to the intermediate- and high-risk groups, with more aggressive cancers in higher-risk groups.

Conclusions: The IDENTIFY risk calculator performed well at predicting cancer in patients referred with haematuria on external validation. This tool can be used by urologists to better counsel patients on their cancer risks, to prioritise diagnostic resources on appropriate patients, and to avoid unnecessary invasive procedures in those with a very low risk of cancer.

Patient summary: We previously developed a calculator that predicts patients' risk of cancer when they have blood in their urine, based on their personal characteristics. We have validated this risk calculator, by testing it on a separate group of patients to ensure that it works as expected. Most patients found to have cancer tended to be in the higher-risk groups and had more aggressive types of cancer with a higher risk. This tool can be used by clinicians to fast-track high-risk patients based on the calculator and investigate them more thoroughly.

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
European urology focus
European urology focus Medicine-Urology
CiteScore
10.40
自引率
3.70%
发文量
274
审稿时长
23 days
期刊介绍: European Urology Focus is a new sister journal to European Urology and an official publication of the European Association of Urology (EAU). EU Focus will publish original articles, opinion piece editorials and topical reviews on a wide range of urological issues such as oncology, functional urology, reconstructive urology, laparoscopy, robotic surgery, endourology, female urology, andrology, paediatric urology and sexual medicine. The editorial team welcome basic and translational research articles in the field of urological diseases. Authors may be solicited by the Editor directly. All submitted manuscripts will be peer-reviewed by a panel of experts before being considered for publication.
期刊最新文献
Five-year Follow-up of the Urodynamics for Prostate Surgery Trial; Randomised Evaluation of Assessment Methods-A Noninferiority Randomised Controlled Trial of Urodynamics. Suction Ureteral Access Sheaths for Renal Stone Treatment: Essential for Every Case: For. Targeting the Autonomic Nervous System for Treatment of Urinary Incontinence. Intrarenal Pressure During Ureteroscopy. Preoperative Magnetic Resonance Imaging Membranous Urethral Length as a Predictor of Urinary Continence After Radical Prostatectomy: A Systematic Review and Meta-analysis.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1