LITERATURE UPDATE
Lymphoma 0.6%
Adenocarcinoma 97.4%
neuroendocrine tumour 1.5%
Low-grade
Neuroendocrine cancer 0.3%
Squamous cell carcinoma 0.3%
Relative incidence of colorectal cancers.
The findings indicate that while AI in CRC is an evolving research field, there are few plans or implementations reported on how to incorporate AI specifically in yoCRC. Potential limitations of this review include the limited number of databases searched and the scope of search queries used. Nonetheless, this review highlights the need for more targeted research on AI applications in yoCRC. Future research can build upon the foundation of AI in CRC with adjustments to account for the increasing incidence of yoCRC.
Differences in characteristics and outcomes between early-onset colorectal cancer and late-onset colorectal cancers Liao CK, Hsu YJ, Chern YJ et al. Eur J Surg Oncol. 2024 Dec;50(12):108687. doi: 10.1016/j.ejso.2024.108687.
Colorectal cancer (CRC) represents a significant health burden worldwide, with a notable increase in early-onset colorectal cancer (EOCRC) cases, defined as those diagnosed before the age of 50 years. Using data from Taiwan’s national
cancer registry and a retrospective cohort from Chang Gung Memorial Hospital, this study analysed CRC cases diagnosed between 2008 and 2019. The analysis compared the EOCRC and late-onset CRC (LOCRC) groups in terms of clinicopathological characteristics, pre-diagnostic symptoms, and survival outcomes. The analysis revealed a continuous
increase in the annual incidence of EOCRC, with colon cancer and rectal cancer rising by 3.2 % and 3.3 %, respectively.
Patients with EOCRC presented with more aggressive disease characteristics, such as signet-ring cell adenocarcinoma, mucinous adenocarcinoma, and poorly differentiated grade. Advanced stages at diagnosis, stages III and IV, were more common with EOCRC (62.4 %) than with LOCRC (50.3 %). Patients with EOCRC reported rectal bleeding, changes in bowel habits, and abdominal pain more frequently than those in the LOCRC group. There is a strong association between stool-related symptoms and left-sided CRC. Despite similar surgical outcomes, the five-year cancer-specific survival rate of patients with stage IV EOCRC was significantly lower than that of patients with LOCRC (32.8% vs. 51.9%, P=0.012). This study highlights a persistent rise in the incidence of EOCRC, with patients presenting with more aggressive disease and experiencing inferior survival. These findings underscore the importance of heightened awareness and early detection strategies for CRC, especially in younger populations, to improve the prognosis.
Predicting Early-Onset Colorectal Cancer in Individuals Below Screening Age Using Machine Learning and Real-World Data: Case Control Study Sun C, Mobley E, Quillen M et al. JMIR Cancer. 2025 Jun 19;11:e64506. doi: 10.2196/64506.
Colorectal cancer is now the leading cause of cancer-related deaths among young Americans. Accurate early prediction and a thorough understanding of the risk factors for early-onset colorectal cancer (EOCRC)
54
WWW.PATHOLOGYINPRACTICE.COM February 2026
are vital for effective prevention and treatment, particularly for patients below the recommended screening age. This study aims to predict EOCRC using machine learning (ML) and structured electronic health record data for individuals under the screening age of 45 years, with the aim of exploring potential risk and protective factors that could support early diagnosis. The authors identified a cohort of patients under the age of 45 years from the OneFlorida+ Clinical Research Consortium. Given the distinct pathology of colon cancer (CC) and rectal cancer (RC), they created separate prediction models for each cancer type with various ML algorithms. They assessed multiple prediction time windows (ie, 0, 1, 3 and 5 years) and ensured robustness through propensity score matching to account for confounding variables including sex, race, ethnicity, and birth year. They conducted a comprehensive performance evaluation using metrics including area under the curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. Both linear (ie, logistic regression, support vector machine) and non-linear (ie, Extreme Gradient Boosting and random forest) models were assessed to enable rigorous comparison across different classification strategies. In addition, they used the Shapley Additive Explanations to interpret the models and identify key risk and protective factors associated with EOCRC. The final cohort included 1358 CC
cases with 6790 matched controls, and 560 RC cases with 2800 matched controls. The RC group had a more balanced sex distribution (2:3 male-to-female) compared to the CC group (2:5 male-to- female), and both groups showed diverse racial and ethnic representation. The authors’ predictive models demonstrated reasonable results, with AUC scores for CC prediction of 0.811, 0.748, 0.689, and 0.686 at 0, 1, 3 and 5 years before diagnosis, respectively. For RC prediction, AUC scores were 0.829, 0.771, 0.727 and 0.721 across the same time windows. Key predictive features across both cancer types included immune and digestive system disorders, secondary malignancies, and underweight status. In addition, blood diseases emerged as prominent indicators specifically for CC. The authors’ findings demonstrate
the potential of ML models leveraging electronic health record data to facilitate the early prediction of EOCRC in individuals under 45 years. By uncovering important risk factors and achieving promising predictive performance, this study provides preliminary insights that could inform future efforts toward earlier detection and prevention in younger populations.
PPi
Mikael Häggström, M.D. CC0 Wikimedia Commons
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56
