Efficacy of ColonFlag as a Complete Blood Count-Based Machine Learning Algorithm for Early Detection of Colorectal Cancer: A Systematic Review.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Source:
      Publisher: Shiraz University of Medical Sciences Country of Publication: Iran NLM ID: 8104374 Publication Model: eCollection Cited Medium: Internet ISSN: 1735-3688 (Electronic) Linking ISSN: 02530716 NLM ISO Abbreviation: Iran J Med Sci Subsets: MEDLINE
    • Publication Information:
      Publication: <2001->: Shiraz, Iran : Shiraz University of Medical Sciences
      Original Publication: Shiraz, Iran : Shiraz University, Medical School
    • Subject Terms:
      Blood Cell Count*/methods ; Colorectal Neoplasms*/diagnosis ; Colorectal Neoplasms*/blood ; Early Detection of Cancer*/methods ; Machine Learning*; Humans
    • Abstract:
      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.
      Competing Interests: None declared.
      (Copyright: © Iranian Journal of Medical Sciences.)
    • References:
      Gut. 2023 Feb;72(2):338-344. (PMID: 36604116)
      Dis Markers. 2019 Jan 17;2019:6036979. (PMID: 30800188)
      Aliment Pharmacol Ther. 2016 Apr;43(7):755-64. (PMID: 26858128)
      Am J Physiol Gastrointest Liver Physiol. 2004 Jul;287(1):G7-17. (PMID: 15194558)
      J Gastroenterol. 1994 Feb;29(1):19-23. (PMID: 8199692)
      Prz Gastroenterol. 2019;14(2):89-103. (PMID: 31616522)
      NEJM Evid. 2022 Jan;1(1):EVIDra2100035. (PMID: 38319175)
      Hepatogastroenterology. 2012 May;59(115):713-6. (PMID: 22469713)
      Gastroenterology. 2019 Mar;156(4):843-851.e2. (PMID: 30776340)
      Br J Gen Pract. 2011 May;61(586):e231-43. (PMID: 21619747)
      Nat Rev Cancer. 2013 Nov;13(11):759-71. (PMID: 24154716)
      Br J Gen Pract. 2017 Jun;67(659):e405-e413. (PMID: 28533199)
      Br J Haematol. 2019 Apr;185(2):311-316. (PMID: 30714125)
      J Intern Med. 2021 Apr;289(4):493-507. (PMID: 32929813)
      Cancers (Basel). 2020 Aug 19;12(9):. (PMID: 32825191)
      J Clin Lab Anal. 2017 Sep;31(5):. (PMID: 27686880)
      Ann Intern Med. 2019 Jan 1;170(1):51-58. (PMID: 30596875)
      JCO Clin Cancer Inform. 2018 Dec;2:1-8. (PMID: 30652563)
      Cancer Detect Prev. 2004;28(1):37-42. (PMID: 15041076)
      Eur J Cancer Prev. 2015 Jul;24(4):328-33. (PMID: 25304028)
      Int J Cancer. 2014 May 15;134(10):2403-13. (PMID: 24122750)
      Asian Pac J Cancer Prev. 2015;16(2):753-6. (PMID: 25684520)
      Cancers (Basel). 2023 Mar 24;15(7):. (PMID: 37046609)
      Eur J Public Health. 2016 Feb;26(1):158-68. (PMID: 26370437)
      J Gastroenterol. 1998 Aug;33(4):488-94. (PMID: 9719230)
      Am Surg. 2002 Jun;68(6):582-7. (PMID: 12079143)
      PLoS One. 2018 Nov 27;13(11):e0207848. (PMID: 30481208)
      Dig Dis Sci. 2017 Oct;62(10):2719-2727. (PMID: 28836087)
      Br J Cancer. 2011 May 24;104(11):1779-85. (PMID: 21559011)
      Clin Gastroenterol Hepatol. 2020 Nov;18(12):2734-2741.e6. (PMID: 32360824)
      Cancer Med. 2017 Oct;6(10):2453-2460. (PMID: 28941187)
      Br J Gen Pract. 2012 Jan;62(594):e29-37. (PMID: 22520670)
      PLoS One. 2017 Feb 9;12(2):e0171759. (PMID: 28182647)
      N Engl J Med. 2000 Nov 30;343(22):1603-7. (PMID: 11096167)
      BMJ Open Gastroenterol. 2021 Jun;8(1):. (PMID: 34083226)
      J Am Med Inform Assoc. 2016 Sep;23(5):879-90. (PMID: 26911814)
      Biomarkers. 2012 May;17(3):216-22. (PMID: 22424597)
      Eur J Cancer Prev. 2018 Nov;27(6):530-538. (PMID: 28692587)
      CA Cancer J Clin. 2023 May-Jun;73(3):233-254. (PMID: 36856579)
      Sci Rep. 2018 Jan 18;8(1):1126. (PMID: 29348549)
    • Contributed Indexing:
      Keywords: Blood cell count; Colorectal neoplasms; Electronic health records; Machine learning; Mass screening
    • Publication Date:
      Date Created: 20241025 Date Completed: 20241025 Latest Revision: 20241109
    • Publication Date:
      20241110
    • Accession Number:
      PMC11497321
    • Accession Number:
      10.30476/ijms.2024.101219.3400
    • Accession Number:
      39449776