2nd deadliest cancer
Colorectal cancer is the second deadliest cancer worldwide for both sexes, with over 900,00 annual deaths and 1.9 million annual new cases.2
Overview
Early detection of CRC is crucial
Colorectal cancer is the 2nd deadliest cancer worldwide leading to almost 1 million deaths per year.2 Despite evidence that screening can reduce mortality, population screening is not applied globally evenly and where applied, compliance may appear suboptimal. 1 in 10 colon cancers and 1 in 4 rectal cancers will be diagnosed in adults <50 years old.3 About 5–10% of colon and rectal cancer cases diagnosed are attributed to genetic risks.4
Early detection
With a 5-year survival rate of 90% in early stages, detecting colorectal cancer early may represent a crucial aspect.5
Screening compliance
Participation in CRC screening programs varies greatly between European countries. An analysis showed that the majority of countries achieved participation rates over 45%, with Croatia and the Czech Republic having the lowest participation rates (< 25%), followed by France (34.3%).6
navify® Algorithms, ColonFlag by Medial EarlySign
ColonFlag is a software system that performs algorithm‐based analysis of demographic information and lab test results and provides personal scores to indicate individuals with higher probability of harboring colorectal cancer (CRC) compared to the general population.¹
9 in 10 adults diagnosed at an early stage will still be alive after 5 years.7
Fewer than 35% of colorectal cancers are found at an early stage.7 – partially due to low testing rates. With ColonFlag's increased sensitivity to proximal-side cancer8, it supports physicians in the effort to detect more cancers and at an earlier stage.
~35%early stage diagnosis.7
ColonFlag, a validated model for identification of individuals with higher CRC probability compared with general population1
The medical algorithm ColonFlag uses the results of a conventional complete blood count (CBC) together with demographic information (age, sex)1 to uncover interrelationships between CBC results and subtle changes in their trends of time.
Algorithm parameters
ColonFlag is a software system that performs algorithm‐based analysis of demographic information and lab test results and provides personal scores to indicate individuals with higher probability of harboring colorectal cancer (CRC) compared to the general population.1
Clinical use
Supports healthcare professionals in decision-making and is not intended as a screening or standalone diagnostic tool. It is not intended to rule-out or to be used to waive screening or further diagnosis.1
Indicated target audience
Intended to be used by healthcare organizations and healthcare professionals to aid in identifying individuals, age 40 and above, of the general population who are at increased risk of harboring CRC compared to the general population for whom further evaluation is recommended.1
How CBC can help predict colorectal cancer
Discover the potential of Complete Blood Count (CBC) results in early detection of colorectal cancer (CRC) through the innovative ColonFlag algorithm by Medial EarlySign. This machine-learning-based solution analyzes millions of CBC data points to uncover subtle interrelationships between age, sex and CBC trends, revealing risk patterns.1 Explore how it empowers healthcare professionals to enhance colorectal cancer screening.
Benefits
Enhance colorectal screening: the key advantages of ColonFlag
By leveraging the ColonFlag, healthcare providers can enhance patient screening processes, improve detection rates and ultimately drive better health outcomes in the fight against colorectal cancer.1,9
3 input parameters
Requires straightforward standard parameters: age, gender at birth and CBC test results (current and past CBC results).1
8×more effective
More CRC cases (all stages) detected in the flagged population compared with routine CRC colonoscopy screenings.9
>68%operational impact
Research shows for >68% of patients advised for colonoscopy, 70% completed screening with significant findings.9
Integration via navify Algorithm Suite
Experience a single integrated platform designed for healthcare providers and laboratories that simplifies IT complexity while reducing the risk of vulnerabilities. With integrated Roche and partner medical algorithms, we provide a comprehensive solution that streamlines processes and enhances collaboration.
Single point of contact for customer support
Roche offers centralized customer support for all algorithms in our portfolio to ensure consistency and reliability. We manage issues that arise for all hosted algorithms, streamlining the process and eliminating the need for customers to engage with individual providers.
Security and data privacy
Security and data privacy are central to Roche's operations, founded on a "Security and Privacy by Design" philosophy and ISO/IEC 27001 certification. Our dedicated technical team performs ongoing risk assessments, penetration tests, and network monitoring to minimize IT complexity and vulnerabilities, prioritizing data confidentiality to protect patient information across all partners.
Frequently asked questions
If you don’t find answers to your questions here, we’re happy to provide more information and discuss your needs in detail.
Is ColonFlag a diagnostics tool?
No. ColonFlag is not a diagnostic or screening device but rather an indication of relative risk for colorectal cancer, thus a high score does not indicate malignancy or pathology. It uses algorithmic analysis of demographic data (age and gender) and complete blood count results to generate personal scores, indicating individuals who are more likely to have colorectal cancer (CRC) than the general population. It is important to note that a high score does not indicate malignancy or pathology. In addition, a low score does not indicate low risk or rule out screening or further testing.1
How can ColonFlag benefit my practice?
ColonFlag is intended to support healthcare professionals in decision-making and is not intended as a screening or standalone diagnostic tool.1 ColonFlag can benefit your practice by identifying patients with an elevated risk of CRC.
How does ColonFlag work to identify high risk patients?
ColonFlag uses patient age, gender and historical blood count data to identify those at high risk of CRC.It uses a machine learning-based algorithm to analyze the data and calculate a risk score. This helps highlight individuals who might benefit from further diagnostic screening.
Is ColonFlag a validated digital health solution?
ColonFlag was trained and cross-validated using data from 466,107 Israeli patients (Maccabi Health Care Services, MHS), externally validated on an additional set of 139,205 Israeli patients (MHS External Validation) and 25,613 primary care patients from the UKs Health Information Network (THIN) database.10
Worldwide validation with studies in leading institutions around the world (retrospective studies) has been performed including Oxford (UK)11, Kaiser Permanente Northwest - KPNW (US)12, Kaiser Permanente Northern California - KPNC (US)13 and Chinese University of Hong Kong - CUHK (China)14.
Can ColonFlag integrate with existing electronic health record (EHR) systems, and what is the implementation process in a healthcare facility?
Yes, ColonFlag, like all navify Algorithms on navify Algorithm Suite, can integrate into EHR or other clinical data repositories like LIS (Laboratory Information Systems). The integration strategy may vary depending on the customer's IT infrastructure. Please refer to your technical Roche representative to evaluate what integration strategy best fits your institution's infrastructure.
Medial EarlySign
Medial EarlySign develops machine learning-based decision support tools that reveal hidden insights in standard medical data. These insights enable personalized and outcome-based interpretations, providing individualized predictions and treatment options while facilitating the early detection of life-threatening conditions. Our cutting-edge tools offer healthcare organizations a fresh perspective on their data, empowering them with proactive, personalized, and predictive care management capabilities.
Visit website- Method Sheet ColonFlag 3.1. 2024. Material number 09823387001.
- Ferlay J, et al. Global Cancer Observatory: Colorectum [Internet; published 2024; cited 2025 Mar 14]. Available from: https://gco.iarc.who.int/media/globocan/factsheets/cancers/41-colorectum-fact-sheet.pdf.
- REACCT Collaborative, et al. Characteristics of early-onset vs late-onset colorectal cancer: a review. JAMA Surg. 2021 Sep;156(9):865-8745. DOI:10.1001/jamasurg.2021.2380.
- Lynch HT, de la Chapelle A. Hereditary colorectal cancer. N Engl J Med. 2003 Mar;348(10):919-932. DOI:10.1056/NEJMra012242.
- American Cancer Society. Can Colorectal Polyps and Cancer Be Found Early? [Internet; updated 2024 Jan 29; cited 2025 Mar 14]. Available from: https://www.cancer.org/cancer/types/colon-rectal-cancer/detection-diagnosis-staging/detection.html
- Navarro M, et al. Colorectal cancer population screening programs worldwide in 2016: An update. World J Gastroenterol. 2017 May;23(20):3632-3642. DOI: 10.3748/wjg.v23.i20.3632.
- National Center for Chronic Disease Prevention and Health Promotion (NCCDPHP). Health and economic benefits of colorectal cancer interventions [Internet; updated 2024 Oct 16; cited 2025 Mar 14]. Available from: https://www.cdc.gov/nccdphp/priorities/colorectal-cancer.html
- American Cancer Society. Cancer Facts & Figures [Internet; published 2022; cited 2025 Mar 14]. Available from: https://www.cancer.org/content/dam/cancer-org/research/cancer-facts-and-statistics/annual-cancer-facts-and-figures/2022/2022-cancer-facts-and-figures.pdf.
- Underberger D, et al. Collaboration to improve colorectal cancer screening using machine learning, NEJM Catal Innov Care Deliv. 2022;3(4). DOI:10.1056/CAT.21.0170.
- Kinar Y, et al. Development and validation of a predictive model for detection of colorectal cancer in primary care by analysis of complete blood counts: a binational retrospective study. J Am Med Inform Assoc. 2016 Sep;23(5):879–890. DOI:10.1093/jamia/ocv195.
- Birks J, et al. Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records. Cancer medicine. 2017;6(10), 2453–2460. DOI: 10.1002/cam4.1183.
- Hornbrook M, et al. Early colorectal cancer detected by machine learning model using gender, age, and complete blood count data. Dig Dis Sci. 2017 Oct;62(10):2719–2727. DOI:10.1007/s10620-017-4722-8.
- Schneider JL, et al. Validation of an algorithm to identify patients at risk for colorectal cancer based on laboratory test and demographic data in diverse, community-based population. Clin Gastroenterol Hepatol. 2020 Nov;18(12):2734-2741.e6. DOI:10.1016/j.cgh.2020.04.054.
- Ng S, et al. Journal of Gastroenterology and Hepatology. 2017. 32(Suppl 3), 146. Abstract: #P-0960.
- Not every digital product is available in all markets. The use of any third-party app is subject to a separate license agreement with the respective third-party app developer. Roche gives no warranties (express or implied) with regard to any third-party app. Third-party apps might not be available in your country. This website and its content may be accessible worldwide, Roche assumes no liability with regard to the access to the information, which may not be compatible with legislations or regulations in force in your country.