ColonFlag作为基于全血细胞计数的机器学习算法对早期检测结直肠癌的功效:系统回顾

IF 1.6 Q2 MEDICINE, GENERAL & INTERNAL Iranian Journal of Medical Sciences Pub Date : 2024-10-01 DOI:10.30476/ijms.2024.101219.3400
Raeni Dwi Putri, Syifa Alfiah Sujana, Nadhira Nizza Hanifa, Tiffanie Almas Santoso, Murdani Abdullah
{"title":"ColonFlag作为基于全血细胞计数的机器学习算法对早期检测结直肠癌的功效:系统回顾","authors":"Raeni Dwi Putri, Syifa Alfiah Sujana, Nadhira Nizza Hanifa, Tiffanie Almas Santoso, Murdani Abdullah","doi":"10.30476/ijms.2024.101219.3400","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Colorectal cancer (CRC) screening is essential to reduce incidence and mortality rates. However, participation in screening remains suboptimal. ColonFlag, a machine learning algorithm using complete blood count (CBC), identifies individuals at high CRC risk using routinely performed tests. This study aims to review the existing literature assessing the efficacy of ColonFlag across diverse populations in multiple countries.</p><p><strong>Methods: </strong>The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) were followed in reporting this systematic review. Searches were conducted on PubMed, Cochrane, ScienceDirect, and Google Scholar for English articles, using keywords related to CBC, machine learning, ColonFlag, and CRC, covering the first development study from 2016 to August 2023. The Cochrane Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias.</p><p><strong>Results: </strong>A total of 949 articles were identified during the literature search. Ten studies were found to be eligible. ColonFlag yielded Area Under the Curve (AUC) values ranging from 0.736 to 0.82. The sensitivity and specificity ranged from 3.91% to 35.4% and 82.73% to 94%, respectively. The positive predictive values ranged between 2.6% and 9.1%, while the negative predictive values ranged from 97.6% to 99.9%. ColonFlag performed better in shorter time windows, tumors located more proximally, in advanced stages, and in cases of CRC compared to adenoma.</p><p><strong>Conclusion: </strong>While ColonFlag exhibits low sensitivity compared to established screening methods such as the fecal immunochemical test (FIT) or colonoscopy, its potential to detect CRC before clinical diagnosis suggests an opportunity for identifying more cases than regular screening alone.</p>","PeriodicalId":14510,"journal":{"name":"Iranian Journal of Medical Sciences","volume":null,"pages":null},"PeriodicalIF":1.6000,"publicationDate":"2024-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11497321/pdf/","citationCount":"0","resultStr":"{\"title\":\"Efficacy of ColonFlag as a Complete Blood Count-Based Machine Learning Algorithm for Early Detection of Colorectal Cancer: A Systematic Review.\",\"authors\":\"Raeni Dwi Putri, Syifa Alfiah Sujana, Nadhira Nizza Hanifa, Tiffanie Almas Santoso, Murdani Abdullah\",\"doi\":\"10.30476/ijms.2024.101219.3400\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Colorectal cancer (CRC) screening is essential to reduce incidence and mortality rates. However, participation in screening remains suboptimal. ColonFlag, a machine learning algorithm using complete blood count (CBC), identifies individuals at high CRC risk using routinely performed tests. This study aims to review the existing literature assessing the efficacy of ColonFlag across diverse populations in multiple countries.</p><p><strong>Methods: </strong>The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) were followed in reporting this systematic review. Searches were conducted on PubMed, Cochrane, ScienceDirect, and Google Scholar for English articles, using keywords related to CBC, machine learning, ColonFlag, and CRC, covering the first development study from 2016 to August 2023. The Cochrane Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias.</p><p><strong>Results: </strong>A total of 949 articles were identified during the literature search. Ten studies were found to be eligible. ColonFlag yielded Area Under the Curve (AUC) values ranging from 0.736 to 0.82. The sensitivity and specificity ranged from 3.91% to 35.4% and 82.73% to 94%, respectively. The positive predictive values ranged between 2.6% and 9.1%, while the negative predictive values ranged from 97.6% to 99.9%. ColonFlag performed better in shorter time windows, tumors located more proximally, in advanced stages, and in cases of CRC compared to adenoma.</p><p><strong>Conclusion: </strong>While ColonFlag exhibits low sensitivity compared to established screening methods such as the fecal immunochemical test (FIT) or colonoscopy, its potential to detect CRC before clinical diagnosis suggests an opportunity for identifying more cases than regular screening alone.</p>\",\"PeriodicalId\":14510,\"journal\":{\"name\":\"Iranian Journal of Medical Sciences\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.6000,\"publicationDate\":\"2024-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11497321/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iranian Journal of Medical Sciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.30476/ijms.2024.101219.3400\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iranian Journal of Medical Sciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.30476/ijms.2024.101219.3400","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

摘要

背景:大肠癌(CRC)筛查对于降低发病率和死亡率至关重要。然而,参与筛查的情况仍不理想。ColonFlag是一种使用全血细胞计数(CBC)的机器学习算法,它能通过常规检测确定CRC高危人群。本研究旨在回顾现有文献,评估ColonFlag在多个国家不同人群中的疗效:方法:在报告本系统性综述时,遵循了系统性综述和元分析的首选报告项目(PRISMA)。使用与 CBC、机器学习、ColonFlag 和 CRC 相关的关键词,在 PubMed、Cochrane、ScienceDirect 和 Google Scholar 上检索英文文章,涵盖 2016 年至 2023 年 8 月的首次开发研究。使用 Cochrane 预测模型偏倚风险评估工具(PROBAST)评估偏倚风险:在文献检索过程中,共发现了 949 篇文章。发现有 10 项研究符合条件。ColonFlag的曲线下面积(AUC)值从0.736到0.82不等。灵敏度和特异性分别为 3.91% 至 35.4% 和 82.73% 至 94%。阳性预测值介于 2.6% 和 9.1% 之间,阴性预测值介于 97.6% 和 99.9% 之间。与腺瘤相比,ColonFlag 在时间窗口较短、肿瘤位置较近、晚期以及 CRC 病例中的表现更好:尽管与粪便免疫化学检验(FIT)或结肠镜检查等成熟的筛查方法相比,ColonFlag 的灵敏度较低,但它在临床诊断前检测出 CRC 的潜力表明,它有机会比单纯的常规筛查发现更多的病例。
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
Efficacy of ColonFlag as a Complete Blood Count-Based Machine Learning Algorithm for Early Detection of Colorectal Cancer: A Systematic Review.

Background: Colorectal cancer (CRC) screening is essential to reduce incidence and mortality rates. However, participation in screening remains suboptimal. ColonFlag, a machine learning algorithm using complete blood count (CBC), identifies individuals at high CRC risk using routinely performed tests. This study aims to review the existing literature assessing the efficacy of ColonFlag across diverse populations in multiple countries.

Methods: The Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) were followed in reporting this systematic review. Searches were conducted on PubMed, Cochrane, ScienceDirect, and Google Scholar for English articles, using keywords related to CBC, machine learning, ColonFlag, and CRC, covering the first development study from 2016 to August 2023. The Cochrane Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias.

Results: A total of 949 articles were identified during the literature search. Ten studies were found to be eligible. ColonFlag yielded Area Under the Curve (AUC) values ranging from 0.736 to 0.82. The sensitivity and specificity ranged from 3.91% to 35.4% and 82.73% to 94%, respectively. The positive predictive values ranged between 2.6% and 9.1%, while the negative predictive values ranged from 97.6% to 99.9%. ColonFlag performed better in shorter time windows, tumors located more proximally, in advanced stages, and in cases of CRC compared to adenoma.

Conclusion: While ColonFlag exhibits low sensitivity compared to established screening methods such as the fecal immunochemical test (FIT) or colonoscopy, its potential to detect CRC before clinical diagnosis suggests an opportunity for identifying more cases than regular screening alone.

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
Iranian Journal of Medical Sciences
Iranian Journal of Medical Sciences MEDICINE, GENERAL & INTERNAL-
CiteScore
3.20
自引率
0.00%
发文量
84
审稿时长
12 weeks
期刊介绍: The Iranian Journal of Medical Sciences (IJMS) is an international quarterly biomedical publication, which is sponsored by Shiraz University of Medical Sciences. The IJMS intends to provide a scientific medium of com­muni­cation for researchers throughout the globe. The journal welcomes original clinical articles as well as clinically oriented basic science re­search experiences on prevalent diseases in the region and analysis of various regional problems.
期刊最新文献
Comparative Analysis of Surgical Outcomes in Hybrid and Open Esophagectomy for Esophageal Cancer: A Regional Russian Cancer Centre Experience. Efficacy of ColonFlag as a Complete Blood Count-Based Machine Learning Algorithm for Early Detection of Colorectal Cancer: A Systematic Review. Evaluation of Antioxidant Effects of Coenzyme Q10 against Hyperglycemia-Mediated Oxidative Stress by Focusing on Nrf2/Keap1/HO-1 Signaling Pathway in the Liver of Diabetic Rats. Exploring Differentially Expressed Genes and Immune Modulation in Diffuse Large B-Cell Lymphoma through RNA Sequencing Analysis. Foramen Ovale Pulsatility Index as an Early Affected Doppler Study among Abnormal Growth Fetuses: A Recent Insight for Practice Based on a Prospective Study.
×
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