Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jul;69(7):2611-2620.
doi: 10.1007/s10620-024-08427-4. Epub 2024 Apr 25.

Development and Validation of a Colorectal Cancer Prediction Model: A Nationwide Cohort-Based Study

Ofer Isakov  1   2   3 , Dan Riesel  1 , Michael Leshchinsky  1 , Galit Shaham  1 , Ben Y Reis  2   3   4   5 , Dan Keret  6 , Zohar Levi  7 , Baruch Brener  8   9 , Ran Balicer  1   3   10 , Noa Dagan  1   3   11 , Samah Hayek  12   13
Affiliations

Development and Validation of a Colorectal Cancer Prediction Model: A Nationwide Cohort-Based Study

Ofer Isakov et al. Dig Dis Sci. 2024 Jul.

Erratum in

Abstract

Background: Early diagnosis of colorectal cancer (CRC) is critical to increasing survival rates. Computerized risk prediction models hold great promise for identifying individuals at high risk for CRC. In order to utilize such models effectively in a population-wide screening setting, development and validation should be based on cohorts that are similar to the target population.

Aim: Establish a risk prediction model for CRC diagnosis based on electronic health records (EHR) from subjects eligible for CRC screening.

Methods: A retrospective cohort study utilizing the EHR data of Clalit Health Services (CHS). The study includes CHS members aged 50-74 who were eligible for CRC screening from January 2013 to January 2019. The model was trained to predict receiving a CRC diagnosis within 2 years of the index date. Approximately 20,000 EHR demographic and clinical features were considered.

Results: The study includes 2935 subjects with CRC diagnosis, and 1,133,457 subjects without CRC diagnosis. Incidence values of CRC among subjects in the top 1% risk scores were higher than baseline (2.3% vs 0.3%; lift 8.38; P value < 0.001). Cumulative event probabilities increased with higher model scores. Model-based risk stratification among subjects with a positive FOBT, identified subjects with more than twice the risk for CRC compared to FOBT alone.

Conclusions: We developed an individualized risk prediction model for CRC that can be utilized as a complementary decision support tool for healthcare providers to precisely identify subjects at high risk for CRC and refer them for confirmatory testing.

Keywords: Colorectal cancer; Colorectal cancer screening; Machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Cumulative incidence of CRC during the follow-up by risk percentiles. A Cumulative incidence of CRC throughout the follow-up period demonstrating a higher cumulative incidence in the top risk percentiles. Cumulative incidence was also calculated for all subjects who survived without a CRC diagnosis after 1 (B) and 2 (C) years
Fig. 2
Fig. 2
Cumulative incidence of CRC by risk class and FOBT combination. A Three-year cumulative incidence of CRC stratified by FOBT result and model risk class (±). Risk class was defined by setting a risk score threshold resulting in the same rate of subjects predicted positive as the rate of positive FOBT in the cohort. B Cumulative incidence was also calculated for all subjects who survived without a CRC diagnosis after 1 year
Fig. 3
Fig. 3
Association between lab values and slopes and CRC risk. Risk scores are plotted vs. last lab values for the top six labs selected by the model as important discriminatory features. Scores are stratified by whether the calculated slope of lab values was negative (red) or positive (blue) during the 3 years prior to the index date
See this image and copyright information in PMC

References

    1. Cancer (IARC) TIA for R on. Global Cancer Observatory [Internet]. [cited 2023 Mar 20]. Available from: https://gco.iarc.fr/.
    1. Xi Y, Xu P. Global colorectal cancer burden in 2020 and projections to 2040. Translational Oncology [Internet]. Neoplasia Press; 2021 [cited 2023 Mar 20];14. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8273208/. - PMC - PubMed
    1. US Preventive Services Task Force, Davidson KW, Barry MJ, Mangione CM, Cabana M, Caughey AB et al. Screening for colorectal cancer: US Preventive Services Task Force recommendation statement. JAMA 2021;325:1965–77. - PubMed
    1. Atkin WS, Edwards R, Kralj-Hans I, Wooldrage K, Hart AR, Northover JMA et al. Once-only flexible sigmoidoscopy screening in prevention of colorectal cancer: a multicentre randomised controlled trial. Lancet. 2010;375:1624–1633. - PubMed
    1. Bretthauer M, Løberg M, Wieszczy P, Kalager M, Emilsson L, Garborg K et al. Effect of colonoscopy screening on risks of colorectal cancer and related death. N Engl J Med 2022;387:1547–56. - PubMed

Publication types