Colorectal Cancer Sidedness: Prognostic Implications and the Predictive Role of Artificial Intelligence

Colorectal Cancer Sidedness: Prognostic Implications and the Predictive Role of Artificial Intelligence | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Colorectal Cancer Sidedness: Prognostic Implications and the Predictive Role of Artificial Intelligence Marcelo Portes Rocha Martins, Rafaela Lopes de Figueiredo Andrade, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8789179/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 15 You are reading this latest preprint version Abstract Background Colorectal cancer (CRC) is a biologically heterogeneous disease in which tumor sidedness has emerged as a relevant prognostic factor. Conventional TNM staging does not incorporate several clinically and biologically meaningful variables that may influence outcomes. In this context, artificial intelligence (AI) based approaches offer an opportunity to integrate complex clinicopathological data and improve prognostic stratification. This study aimed to evaluate clinicopathological variables associated with tumor sidedness and to identify clinical predictors of high-risk disease using an AI-based decision tree model. Methods This retrospective cohort study included 71 adults who underwent surgical resection for colorectal adenocarcinoma at a tertiary oncology center between 2020 and 2024 and had complete clinicopathological data available for analysis. Overall and progression-free survival were estimated using the Kaplan–Meier method, and associations between categorical variables were assessed using Fisher’s exact test. Decision tree models were constructed using the J48 (C4.5) algorithm, and model performance was evaluated by leave-one-out cross-validation (LOOCV). Results Left-sided tumors were predominant and more frequently associated with alcohol ingestion (p = 0.04), the use of neoadjuvant chemoradiotherapy (p < 0.01), and higher mortality (p = 0.04), despite more intensive treatment strategies. Right-sided tumors were prevalent in women and were associated with angiolymphatic invasion. In prognostic modeling, positive surgical margins emerged as the strongest predictor of mortality (Full 85.18%; LOOCV 74.07%). Among patients with negative margins, tumor laterality represented the most influential prognostic factor, with right-sided tumors associated with improved survival. Interestingly, younger patients showed shorter progression-free survival (Full 89.09%; LOOCV 76.36%). Conclusions Tumor sidedness constitutes a meaningful prognostic dimension in CRC when integrated with established pathological factors. AI-based decision tree models can capture clinically coherent prognostic signatures and complement traditional staging systems, supporting their role as hypothesis-generating tools for individualized risk assessment and guiding future prospective validation. Colorectal Neoplasms colorectal cancer Prognosis Artificial Intelligence Data Mining Predictive Models Multivariate Analysis Clinical Decision Support Systems Figures Figure 1 Figure 2 Introduction Colorectal cancer (CRC) ranks third worldwide in incidence and is the second major cause of mortality, following lung cancers 1 . Risk factors for CRC can be broadly classified into modifiable and non-modifiable factors. Modifiable risk factors include alcohol 2 and tobacco consumption, psychological stress, obesity 3 , and increased intake of red meat, smoked foods 2 . Non-modifiable risk factors comprise advanced age, male sex, the presence of inflammatory bowel disease, genetic conditions such as familial adenomatous polyposis, a family history of CRC in first-degree relatives, and prior exposure to abdominal or pelvic radiotherapy 3 . The multifactorial etiological nature of CRC results in marked molecular heterogeneity, primarily driven by three major carcinogenic pathways: chromosomal instability (CIN), characterized by sequential mutations in APC , KRAS , TP53 , and SMAD4 ; microsatellite instability (MSI), arising from mismatch repair deficiency due to germline mutations or MLH1 promoter hypermethylation and the CpG island methylator phenotype (CIMP), frequently associated with BRAF mutations and the serrated pathway 4 . In addition to these pathways, alterations in PIK3CA , ultra-mutated tumors harboring POLE/POLD1 mutations, and additional epigenetic changes further contribute to the biological diversity of CRC according to the World Health Organization Classification of Tumors Editorial Board 5 . This interplay of genetic and epigenetic mechanisms underpins clinically relevant differences in tumor behavior, which are also differentially expressed across colon tumor locations 6 . Right-sided colon tumors (RCC) exhibit a higher frequency of PIK3CA mutations, PTEN loss, and KRAS and BRAF alterations, as well as a high prevalence of MSI and mismatch repair deficiency. These features are associated with an increased mutational burden, enhanced neo-antigen generation, and a prominent tumor-infiltrating lymphocytic response 7 . Conversely, left-sided colon tumors (LCC) are linked to APC mutations, an early and defining event in the Wnt/β-catenin signaling pathway, as well as later alterations involving TP53 and, in a subset of cases, HER2 amplification 8 , 9 . Collectively, these molecular differences support the existence of distinct biological pathways driving proximal and distal colorectal carcinogenesis, with important implications for prognosis and therapeutic decision-making 7 . Distinct clinical characteristics according to tumor sidedness have also been previously reported 10 . Approximately 83% of early-onset CRC occurring in individuals without a family history were diagnosed in the LCC. In the same study, RCC was more frequently observed in older individuals and in females 11 . Furthermore, RCC predominantly originated from sessile and/or serrated polyps and tended to present as flatter lesions with a mucinous component, increased T-cell infiltration, and a higher incidence of peritoneal metastases. In contrast, LCCs more commonly affected younger, male patients and were typically sporadic tumors arising from tubular or villous polyps, presenting with a polypoid or exophytic growth pattern into the bowel lumen, with lower immunogenicity and a greater propensity for distant metastases 11 , 12 . Alcohol and tobacco consumption have also been more strongly associated with distal colon and rectal tumors 13 , 14 . Taken together, these consistent clinicopathological and behavioral differences according to tumor sidedness highlight a complex and multifactorial landscape that extends beyond anatomical location, underscoring the need for integrative analytical approaches capable of capturing non-linear interactions among diverse prognostic variables, an area in which artificial intelligence–based methods have shown particular promise 15 – 17 . Machine learning can detect complex patterns in large clinical datasets. These algorithms are trained on previously labeled datasets, enabling them to learn relationships that can subsequently be used to predict outcomes in new patients 18 . Predictive models, such as decision trees, have demonstrated high accuracy in forecasting CRC recurrence and in identifying carcinoembryonic antigen (CEA) levels, tumor location, depth of invasion, lymphatic and venous invasion, and lymph node involvement as relevant predictors 19 . A decision tree model was developed using clinical indicators and preoperative blood cell parameters, demonstrating superior performance in distinguishing benign from malignant ovarian tumors compared to individual imaging or biomarker assessments 20 . Decision trees stand as a foundational paradigm in, uniquely positioned at the intersection of computational rigor and clinical epistemology. Unlike 'black box' models such as neural networks, which often obscure the decision-making process, decision trees operate as 'white box' models, offering high explainability. By generating explicit IF-THEN classification rules, the model allows clinicians to intuitively validate the algorithmic logic against established medical knowledge, facilitating the trustworthy translation of these findings into clinical practice 20 , 21 . In this context, the clinicopathological characteristics that distinguish RCC and LCC constitute a meaningful set of variables that can be incorporated into predictive algorithms to stratify risk of recurrence, disease progression, and mortality. Therefore, the objective of the present study is to systematically characterize the clinicopathological profile of CRC by tumor sidedness, thereby providing a foundation for developing more accurate and clinically applicable intelligent models, as well as for our own AI-based predictive model. Materials and methods Study design This is an observational retrospective cohort study conducted among individuals aged 18 years or older who underwent surgical treatment at Instituto Mário Penna and had a histopathological diagnosis of colorectal adenocarcinoma. Sample selection A total of 71 patients with complete clinicopathological data who agreed to participate in the study were selected from a cohort of 228 individuals who underwent surgeries classified as partial colectomies and/or abdominal rectosigmoidectomies with curative intent at Instituto Mário Penna (Belo Horizonte, Minas Gerais, Brazil) between 2020 and 2024. Complete clinicopathological data were available and analyzed for 71 of these patients. Clinicopathological information was obtained from the patients’ electronic medical records. Inclusion criteria comprised a histopathological diagnosis of colorectal adenocarcinoma, absence of distant metastatic disease, adequate clinical performance status, age ≥ 18 years, and surgical specimens confirming the retrieval of at least 12 lymph nodes during lymphadenectomy. Exclusion criteria included non-adenocarcinoma histological subtypes, prior radiotherapy, metastatic disease at diagnosis, synchronous or metachronous malignancies at the time of surgery, receipt of chemotherapy within five years before sample collection, recurrent CCR, and lack of informed consent. Ethical aspects This study was submitted for review and approval by the Graduate Program Committee in Applied Sciences to Cancer and by the Research Ethics Committee (REC) of Instituto Mário Penna, under protocol number 7,133,749. All procedures were conducted in accordance with the ethical standards of the institutional and national committees responsible for human experimentation and in compliance with the principles of the Declaration of Helsinki of 1975, as revised in 2008. Data analysis Clinicopathological variables were systematically analyzed, including histological subtype, tumor stage and grade, perineural and angiolymphatic invasion, the presence of small infiltrative tumor cell clusters at the tumor–stroma interface consistent with an active invasion phenotype (tumor budding), the number of positive lymph nodes relative to the total number of dissected nodes, CEA levels, and the use of chemotherapy and radiotherapy. Survival outcomes, including progression-free survival and overall survival, were assessed as time-to-event variables. Survival probabilities were estimated using the Kaplan–Meier method, and comparisons between survival curves were performed when appropriate. Associations between categorical variables were assessed using Fisher’s exact test. Statistical analyses were conducted using GraphPad Prism software (version 9.0), and a two-tailed p-value < 0.05 was considered statistically significant. Supervised and unsupervised machine learning techniques were employed to explore and predict clinicopathological data from patients with CRC. Decision tree models and corresponding IF–THEN classification rules were developed using established methodologies from the literature. Tree induction and class relationship analysis were performed using the J48 algorithm, an implementation of the C4.5 algorithm, in WEKA (Waikato Environment for Knowledge Analysis, version 3.8.3; University of Waikato, New Zealand) 22 , 23 . To improve the representation of the minority class in the training set, we used ‘Cost-Sensitive Learning’ during the modeling phase. Model performance, robustness, and generalizability were assessed using leave-one-out cross-validation (LOOCV), with predictive models achieving LOOCV overall accuracy values greater than 70% considered acceptable for further interpretation. To ensure a comprehensive evaluation of model performance, we calculated Sensitivity, Specificity, Matthews Correlation Coefficient (MCC) to indicate the correlation between predicted and observed data, and the F1-Score to assess the model's ability to correctly identify the class. Additionally, the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) was used to evaluate the overall discriminative power of the decision trees, independent of the classification threshold. Results Sample characterization and clinicopathological profile of CCR patients We analyzed the complete clinicopathological data of 71 patients diagnosed with colorectal adenocarcinoma ( Table 1 ) . The cohort comprised 37 females (52%) and 34 (48%) males, with ages ranging from 24 to 95 years (mean 61 ± 12). A significant majority of tumors were located on the left side of the colon, accounting for 61 cases (86%), while 10 tumors (14%) were located on the right side. The assessment of tumor laterality in relation to key clinicopathological variables revealed several descriptive patterns. The RCC occurred more frequently in women, whereas the LCC occurred more frequently in men (p = 0.08). Although no clear age predilection was identified, 39 patients with CCR were aged 62 years or younger. Interestingly, younger patients (≤ 62 years) showed a trend toward reduced overall survival (p = 0.07) and significantly shorter progression-free survival (p = 0.01) (Fig. 1 A and 1 B ) . Distributions of tumor size, angiolymphatic invasion, perineural invasion, and tumor budding were broadly comparable across tumor sides. Similarly, CEA levels and the presence of blood in the stool were observed at comparable frequencies in both groups. Collectively, these findings indicate that baseline clinicopathological features were balanced across tumor laterality. Lifestyle exposures, treatment, and outcomes of CCR patients associated with tumor-sidedness Tobacco exposure was more prevalent in LCC (46%) compared to RCC (10%) patients (p = 0.09). Alcohol consumption further differentiated LCC, with current or recent use being significantly more prevalent in this group (p = 0.04). Therapeutic strategies differed markedly according to tumor laterality. Patients with LCC were substantially more likely to receive neoadjuvant chemotherapy (p < 0.01), whereas RCC were commonly managed with primary surgery followed by adjuvant treatment. Despite this intensified therapy and a statistically more extensive lymph node dissection being performed on LCC (p < 0,01), clinical outcomes remained less favorable for this group. Patients harboring LCC experienced a markedly higher death rate than those with RCC ( p = 0.04). Although tumor recurrence and distant metastases occurred more frequently in LCC, these events did not clearly segregate by laterality. Table 1 Association between tumor sidedness and clinicopathological variables in 71 CCR patients Clinical-pathological Features Category RCC (n) LCC (n) p-value Sex Male 2 32 0.08 Female 8 29 Age ≤ 62 years 5 34 0.74 > 62 years 5 27 Tumor size 0–5 cm 6 48 0.33 6–10 cm 4 11 > 11 cm 0 2 Grade Well-differentiated 1 14 0.50 Moderately differentiated 9 42 Poorly differentiated 0 5 Angiolymphatic invasion Yes No 4 6 36 25 0.31 Perineural invasion Yes 8 40 0.48 No 2 21 Tumor budding Yes 2 17 0.71 No 8 44 Number of lymph nodes retrieved 12–27 13 46 0.004 28–42 6 9 > 43 1 6 TNM staging I/II III/IV 3 7 29 32 0.49 CEA (ng/mL) ≤ 3 4 35 0.56 3–5 2 9 > 5 4 17 Chemotherapy No chemotherapy 3 13 < 0.001 Neoadjuvant chemotherapy 0 28 Adjuvant chemotherapy 7 20 Palliative chemotherapy 0 0 Smoking status Never smoker 9 33 0.09 Current smoker 0 7 Former smoker 1 21 Alcohol consumption Non-drinker 10 35 0.04 Current drinker 0 17 Former drinker 0 9 Blood in stool Absent 3 8 0.17 Present 7 53 Distant metastases Yes 1 20 0.26 No 9 41 Tumor recurrence Yes 0 14 0.19 No 10 47 Death Yes 1 28 0.04 No 9 33 Predictive modeling reveals laterality and prognostic clinicopathologic signatures To further delineate clinicopathological features associated with tumor laterality and prognosis, machine learning techniques were initially developed to integrate clinically and pathologically relevant variables and to estimate individualized outcome probabilities. Models focused on tumor laterality achieved the highest performance across both training and validation analyses. Particularly, alcohol exposure emerged as a dominant predictor of LCC (Fig. 2 A and B ). The performance metrics for all generated decision tree models are summarized in Table 2 . As observed, the models demonstrated stability during internal validation, with LOOCV accuracies (70.37% and 89.09%, respectively) consistent with those from the full training dataset, although the model designed to predict tumor laterality in the general cohort (Fig. 2 A ) demonstrated the highest robustness. Prognostic modeling supports the central role of tumor sidedness in stratifying adverse clinical outcomes. In RCC, recurrence risk was lower, whereas in LCC, subsequent risk stratification was primarily driven by tumor size. Tumors larger than 5 cm were associated with an increased risk of recurrence, while tumors ≤ 5 cm were further classified according to perineural invasion status. Notably, and counterintuitively, the absence of perineural invasion was more strongly associated with recurrence than its presence. (Fig. 2 C). This algorithm correctly classified 88.9% (24/27) of cases during training and retained a high predictive accuracy of 62.9% (17/27) under cross-validation (Table 2 ). In the predictive model for mortality stratified by CCR laterality, RCC was associated with more favorable outcomes. LCC was subsequently stratified by angiolymphatic invasion status. In the absence of angiolymphatic invasion, radiotherapy exposure emerged as the next discriminative factor, with improved survival observed among patients who did not receive radiotherapy. Among those who underwent radiotherapy, pathological stage provided further risk stratification, with stages I and II associated with superior survival. In the presence of angiolymphatic invasion, the algorithm identified sex as the principal stratifier, with poorer outcomes in men, while women were further stratified by age, with younger patients exhibiting reduced survival probability. (Fig. 2 D). As shown in Table 2 , the models were stable during internal validation, with LOOCV accuracies (72.73%) consistent with those from the full training dataset (87.27%). To mitigate bias arising from class imbalance, a Cost-Sensitive Learning strategy was employed during training. Misclassification penalty weights were assigned to the minority class for each model (3.0 for Figs. 2 A and 2 C; 6.6 for Fig. 2 B; and 1.4 for Fig. 2 D), while the majority class retained a weight of 1.0. Consequently, the values displayed in the leaf nodes represent re-weighted instances normalized to the total sample size, rather than raw counts. The clinical translation of these values into integer patient counts is detailed in each terminal node of the figures. Predictive Performance of Decision Tree Models The performance metrics for all induced decision tree models are summarized in Table 2 . The laterality tumor prediction models in the general cohort ( Fig. 2 B ) demonstrated the highest overall diagnostic accuracy (89.09%), with a robust MCC (0.627) and a high AUC-ROC (0.83). Notably, this model maintained balanced class sensitivity (0.896 for left-sided tumors and 0.857 for right-sided tumors) and an MCC of 0.421, indicating a moderate-to-strong correlation between prediction and observation. Conversely, models trained on smaller subsets, specifically for recurrence prediction in patients undergoing adjuvant therapy (Fig. 2 C), exhibited signs of overfitting, as indicated by a significant discrepancy between training (88.9%) and validation (62.96%) accuracies and an AUC-ROC. The performance metrics for this model indicate suboptimal predictive power, with a negative MCC (-0.227) and an AUC-ROC below the threshold for discrimination (0.464). These results suggest significant discriminatory challenges, particularly in classifying tumor recurrence, where the model failed to distinguish between categories effectively. The mortality prediction model (Fig. 2 D), however, showed promising generalizability, with a validation accuracy of 72.73% and an F1-score of 0.754 for death and a high AUC-ROC, suggesting that the selected clinicopathological variables have significant prognostic value for survival outcomes. Table 2 Performance metrics and discriminatory power of decision trees for predicting clinicopathological characteristics in CCR patients. Decision tree model Full training LOOCV Class Specificity Sensibility F1-score MCC AUC-ROC Laterality of tumors in adjuvant therapy patients 81.48% (22/27) 70.37% (19/27) LCC 0.75 0.57 0.50 0.299 0.732 RCC 0.57 0.75 0.79 0.299 0.732 Laterality of tumor in the general cohort 90.9% (50/55) 89.09 (49/55) LCC 0.896 0.857 0.667 0.627 0.832 RCC 0.857 0.896 0.935 0.627 0.832 Recurrence of the tumor 88.9% (24/27) 62.963% (17/27) Yes 0 0.773 0.773 -0.227 0.464 No 0.773 0 0 -0.227 0.464 Post-chemotherapy mortality 87.27% (48/55) 72.73% (40/55) Yes 0.739 0.719 0.754 0.452 0.808 No 0.719 0.739 0.694 0.452 0.787 Discussion Colorectal tumors are responsible for approximately 900,000 deaths per year, according to data from the World Health Organization 6 . However, if we delve deeper into this pathology, we will realize that colorectal tumors are not a single entity but behave differently depending on their location. Clinicopathological characteristics differ substantially between tumor locations 24 . RCC is more frequently observed in older patients, shows a female predominance, and is often associated with hereditary predisposition. It typically arises from serrated precursor lesions, exhibits increased T-cell infiltration, and demonstrates a higher propensity for peritoneal metastasis 25 . In contrast, LCC more commonly affects younger male patients, is predominantly sporadic, arises from tubular or villous adenomatous polyps, is less immunogenic, and metastasizes more frequently to the liver or lungs 11 . Our study highlighted and reinforced the heterogeneity of this disease through a clinical-pathological approach, combined with innovative machine learning (ML) using decision tree models, not only to describe but also to develop tools to predict the CRC behavior and prognosis based on laterality. This strategy extends beyond descriptive analysis to develop predictive tools that anticipate tumor behavior and prognosis based on primary tumor laterality. Our model stratified CCR into two distinct groups using predictive decision trees. LCC was predominantly associated with behavioral factors, particularly regular alcohol consumption, unlike RCC. These findings could be consistent with divergent pathogenic pathways. RCC is frequently associated with BRAF mutations and high-frequency microsatellite instability resulting from defective DNA mismatch repair, leading to widespread genomic alterations 26 . In contrast, left-sided tumors typically arise through the conventional adenoma–carcinoma sequence, driven by chromosomal instability with gains, amplifications, losses, or deletions affecting a more limited set of genes, including APC , KRAS, TP53, SMAD4 , and PIK3CA 27 , 28 . These findings can alter not only the treatment but also the prognosis of CRC. In our cohort, despite patients with LCC receiving more intensive treatment modalities, including chemoradiotherapy (p < 0.01), this group demonstrated poorer outcomes, with a significantly higher mortality rate (p = 0.04). This contrasts with the available literature, which consistently indicates a poorer prognosis for RCC. Petrelli et al. published a meta-analysis demonstrating an absolute 19% reduction in the risk of death for LCC compared with RCC tumors, based solely on sidedness 29 , and these results were corroborated by a large retrospective Korean cohort of 1,632 patients, which reported an increased risk of locoregional recurrence in RCC 30 . Meanwhile, contrasting findings have been reported in patients with early-stage tumors. Papers focusing on the initial stages of CRC (I and II) have reported improved survival among patients with RCC, potentially related to the higher prevalence of microsatellite instability–high, a feature associated with a more favorable prognosis in early-stage disease 31 . In addition, a retrospective analysis of the National Cancer Database showed that among patients who did not receive adjuvant chemotherapy, those with RCC had superior overall survival compared with those with LCC 32 . Taken together, these observations highlight the need for integrative, data-driven prognostic approaches that reconcile the stage-dependent, biologically distinct survival patterns associated with tumor laterality, thereby providing a rationale for applying decision tree–based modeling in colorectal cancer. Current evidence indicates that decision trees are reliable statistical predictive models that accurately estimate the risk of clinical events by integrating key prognostic factors in oncology 33 . In many malignancies, including CRC, decision trees have demonstrated superior prognostic performance compared with traditional staging systems 34 . These observations prompted us to explore the feasibility of developing a decision tree to predict the prognostic impact of tumor laterality in CRC. The conventional TNM staging system has well-recognized limitations. Prognostic assessment based exclusively on tumor size, lymph node involvement, and distant metastases fails to account for several clinically relevant variables, including tumor laterality, surgical margin status, alcohol and tobacco exposure, sex, age, and the use of chemoradiotherapy 35 . Accordingly, in the present study, we integrated machine learning techniques with a comprehensive set of clinical and pathological variables to refine survival estimation and to specifically assess the prognostic relevance of tumor laterality. The analyses revealed that laterality was modulated by behavioral factors, particularly alcohol consumption, which was predominantly associated with left-sided CCR in both models (Fig. 2 A and 2 B). The statistical strength of these associations is corroborated by our predictive modeling, which demonstrates an LOOCV accuracy of 89.09% and an AUC-ROC of 0.83 (Table 2 ). This high discriminative power confirms that these variables are not merely correlated but are reliable predictors of tumor sidedness in this cohort. In contrast, RCC was strongly associated with more favorable outcomes and lower recurrence rates, whereas LCC disease was further stratified by tumor size and perineural invasion (Fig. 2 C). However, these specific findings should be interpreted with caution. While the model identified perineural invasion as a decision node, the quantitative metrics indicate overfitting, with accuracy dropping from 88.9% in training to 62.96% in validation. Furthermore, the low AUC-ROC (0.46) suggests limited discriminative power for this specific outcome, indicating that this counterintuitive association may reflect sample size constraints or statistical noise rather than a definitive biological phenomenon. This contrasts with the observed epidemiological evidence. In SEER-based cohorts comprising more than 163,000 patients, LCC has been consistently associated with lower cancer-specific mortality compared with RCC; however, this association is stage-dependent, demonstrating comparable or even more favorable outcomes in early-stage disease and no clear survival advantage in stage III tumors. Given the poorer outcomes observed in LCC, the model enabled a detailed exploration of risk factors and patient subgroups, stratifying them into hierarchical levels according to their relative risk and impact on survival. In patients without angiolymphatic invasion, radiotherapy emerged as the subsequent decision node, whereby the requirement for radiotherapy and more advanced disease stages were associated with an unfavorable prognosis. In the presence of angiolymphatic invasion, prognostic stratification was primarily determined by sex and age, with male patients exhibiting poorer outcomes. Notably, within this branch, younger women (< 62 years) were paradoxically associated with worse survival. These counterintuitive associations highlight the need for further investigation to elucidate the biological and clinical mechanisms underlying these observations. ​​​​In contrast to the recurrence analysis, the mortality risk stratification demonstrated high reliability. The decision tree integrating angiolymphatic invasion, sex, and age achieved a validation accuracy of 72.73% and an AUC-ROC exceeding 0.80 (Table 2 ). These metrics validate the clinical relevance of the identified subgroups, supporting the model's potential utility in identifying patients at high risk of mortality despite the observed complex interactions. Although tumor sidedness has emerged as a relevant prognostic factor in CRC, the available evidence remains heterogeneous and strongly dependent on disease stage and clinical context. Large meta-analyses and pooled analyses of advanced and metastatic disease consistently demonstrate superior outcomes for left-sided tumors, with improved overall survival and treatment response when compared with right-sided cancers 29 , 35 – 37 . In contrast, population-based studies focusing on early-stage disease, particularly stage II, have reported outcomes for RCC after adequate surgical resection, equal to or better than those for LCC 31 , 38 , 39 . These findings suggest that tumor laterality does not serve as a uniform prognostic marker across all stages but rather reflects distinct biological behaviors that may confer a survival advantage in early disease while portending worse outcomes in advanced disease. Such stage-dependent and, at times, counterintuitive results underscore the complexity of CRC biology and highlight the need for further prospective studies integrating molecular, clinicopathological, and treatment-related variables to better define the true prognostic role of tumor sidedness. To address the class imbalance between left-sided (n = 61) and right-sided (n = 10) tumors, which could bias the decision tree towards the majority class, we employed a balancing strategy during the modeling phase. Specifically, we used Cost-Sensitive Learning to improve the representation of the minority class in the training set. This approach aims to improve the J48 algorithm's decision boundaries, ensuring that the predictive rules for right-sided tumors reflect robust patterns rather than statistical noise. The effectiveness of this weighting strategy is evidenced by the balanced sensitivity rates achieved in the laterality model (0.896 for LCC and 0.857 for RCC). This confirms that the algorithmic adjustments successfully mitigated bias toward the majority class, enabling reliable identification of right-sided tumor characteristics despite the numerical disparity. The interpretation of these findings warrants caution, given certain inherent limitations, specifically a retrospective, single-center design and the modest sample size, which resulted in an imbalance in tumor laterality. This distribution likely reflects local referral patterns rather than a biological deviation and may have influenced survival estimates, particularly the higher mortality observed in LCC, despite the broader literature often associating right-sided disease with poorer outcomes. Importantly, these constraints do not undermine the study’s core contributions. The analysis provides a detailed characterization of CRC within a well-defined clinical setting, confirms the prognostic relevance of established markers of tumor aggressiveness, and demonstrates the capacity of machine-learning–based decision models to capture coherent, clinically meaningful risk stratification even in relatively small cohorts. Besides, a major strength of this study lies in the deliberate selection of the J48 (C4.5) decision tree algorithm. We prioritized decision trees over more opaque algorithms to ensure transparency in risk stratification. The resulting logical rules (IF-THEN structures) mirror standard clinical reasoning, enabling oncologists to verify the biological coherence of the predictors, such as angiolymphatic and perineural invasion, tumor size, and staging identified by the AI. This transparency is essential for the clinical translational potential of our findings, which is further reinforced by the model's interpretability. Together, these findings underscore their value as hypothesis-generating evidence for future multicenter validation. Conclusion This study demonstrates that tumor sidedness represents a clinically meaningful and biologically grounded prognostic dimension in CCR when interpreted alongside established pathological and treatment-related variables. By integrating clinicopathological data into transparent, decision-tree–based machine learning models, we identified coherent, clinically interpretable risk signatures that extend beyond conventional TNM staging. Right-sided tumors were consistently associated with more favorable survival and lower recurrence in this cohort, whereas left-sided disease exhibited distinct behavioral, therapeutic, and pathological stratifiers linked to adverse outcomes, including alcohol exposure, tumor size, perineural invasion, and angiolymphatic involvement. Although limited by its retrospective, single-center design and modest sample size, this work supports the utility of explainable artificial intelligence as a hypothesis-generating framework for individualized prognostic assessment. Future multicenter, prospective studies incorporating molecular and genomic data are warranted to validate and refine these models and to more precisely define the stage-dependent prognostic role of tumor laterality in colorectal cancer. Abbreviations AI Artificial intelligence AUC-ROC Area Under the Receiver Operating Characteristic Curve CEA Carcinoembryonic antigen CIMP CpG island methylator phenotype CIN Chromosomal instability CRC Colorectal cancer LCC Left-sided colorectal cancer LOOCV Leave-one-out cross-validation MCC Matthews Correlation Coefficient ML Machine learning MSI Microsatellite instability RCC Right-sided colorectal cancer REC Research Ethics Committee Declarations Ethics approval and consent to participate The study was approved by the Research Ethics Committee of Instituto Mário Penna (Belo Horizonte, Brazil), under approval number 25004619.3.3001.5121. All participants provided written informed consent. The study was conducted using anonymized data, ensuring confidentiality and the protection of participants’ identities. Consent for publication Not applicable. Availability of data and materials The datasets generated and/or analyzed during the current study are not publicly available due to ethical and privacy restrictions related to patient data, but are available from the corresponding author upon reasonable request. Competing interests The authors declare no competing interests. Funding This research was supported by the Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG; APQ-02564-22 and APQ-04993-22) and Rede Mineira de Pesquisa Translational em Oncologia (FAPEMIG; RED00059-23). Authors' contributions M.P.R.M. contributed to the conception and planning of the study, data acquisition, data analysis, statistical analyses, and manuscript drafting. R.L.F.A. contributed to data acquisition and statistical analyses. P.H.V.D. contributed to study planning, data analysis and interpretation, statistical analyses, and critical revision of the manuscript. L.C.B. contributed to study planning, data analysis and interpretation, supervised and unsupervised machine learning analyses, critical revision of the manuscript, and supervision of the study. L.R.A. conducted the supervised and unsupervised machine learning analyses. R.R.M.C. critically revised the manuscript and contributed to the supervision of the study. All authors contributed to the interpretation of the results and contributed to the final version of the manuscript. Acknowledgements We thank all patients for their valuable participation in this study. References International Agency for Research on Cancer. Global Cancer Observatory: Cancer Today – Colorectal cancer incidence and mortality visualization [Internet]. Lyon: IARC. 2025 [cited 2026 Jan 31]. Available from: https://gco.iarc.fr/today/en/dataviz/bars?mode=cancer&group_populations=1&types=0_1&sort_by=value1 Vieira AR, Abar L, Chan DSM, Vingeliene S, Polemiti E, Stevens C, et al. Foods and beverages and colorectal cancer risk: a systematic review and meta-analysis of cohort studies, an update of the evidence of the WCRF-AICR Continuous Update Project. Ann Oncol. 2017;28(8):1788–802. 10.1093/annonc/mdx171 . Ullah F, Pillai AB, Omar N, Dima D, Harichand S. Early-Onset Colorectal Cancer: Current Insights. Cancers (Basel). 2023;15(12):3202. 10.3390/cancers15123202 . Roshandel G, Ghasemi-Kebria F, Malekzadeh R, Colorectal Cancer. Epidemiology, Risk Factors, and Prevention. Cancers (Basel). 2024;16(8):1530. 10.3390/cancers16081530 . Arends MJ. Pathways of colorectal carcinogenesis. Appl Immunohistochem Mol Morphol. 2013;21(2):97–102. 10.1097/PAI.0b013e31827ea79e . World Health Organization Classification of Tumours Editorial Board. Digestive system tumours. WHO Classification of Tumours. Volume 1, 5th ed. Lyon: International Agency for Research on Cancer; 2019. Lee MS, et al. PIK3CA and PTEN status in advanced colorectal cancer treated with anti-EGFR therapy. Br J Cancer. 2015;113(3):414–21. Le DT, Durham JN, Smith KN, Wang H, Bartlett BR, Aulakh LK, et al. Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade. Science. 2017;357(6349):409–13. Wang T, Fu J, Huang Y, Fu C. Mechanism of APC truncation involved in colorectal cancer tumorigenesis (Review). Oncol Lett. 2024;29(1):2. 10.3892/ol.2024.14748 . Zeng S, Wang J, Shi Z, Zhao H, Gao J, Li J. The Wnt/β-catenin signaling pathway in colorectal cancer: mechanism and intervention of traditional Chinese medicine and chemical compound. Front Pharmacol. 2025;16:1560714. 10.3389/fphar.2025.1560714 . Molina-Meneses SP, Palacios-Fuenmayor LJ, Molina-Mercado FD, Caycedo-Medina DF, Castaño-Llano R, Gómez-Wolff LR, et al. Colon tumor location: Right side versus left side as a prognostic factor for colon cancer survival: Analysis of a retrospective cohort. Rev Gastroenterol Mex (Engl Ed). 2025;90(3):400–11. Waldstein S, Spengler M, Pinchuk IV, Yee NS. Impact of Colorectal Cancer Sidedness and Location on Therapy and Clinical Outcomes: Role of Blood-Based Biopsy for Personalized Treatment. J Pers Med. 2023;13(7):1114. 10.3390/jpm13071114 . Loree JM, Pereira AAL, Lam M, Willauer AN, Raghav K, Dasari A, et al. Classifying Colorectal Cancer by Tumor Location Rather than Sidedness Highlights a Continuum in Mutation Profiles and Consensus Molecular Subtypes. Clin Cancer Res. 2018;24(5):1062–72. 10.1158/1078-0432.CCR-17-2484 . Jun S, Park H, Kim UJ, Choi EJ, Lee HA, Park B, et al. Cancer risk based on alcohol consumption levels: a comprehensive systematic review and meta-analysis. Epidemiol Health. 2023;45:e2023092. 10.4178/epih.e2023092 . Zhou X, Wang L, Xiao J, Sun J, Yu L, Zhang H, et al. Alcohol consumption, DNA methylation and colorectal cancer risk: Results from pooled cohort studies and Mendelian randomization analysis. Int J Cancer. 2022;151(1):83–94. 10.1002/ijc.33945 . Bhinder B, Gilvary C, Madhukar NS, Elemento O. Artificial Intelligence in Cancer Research and Precision Medicine. Cancer Discov. 2021;11(4):900–15. 10.1158/2159-8290.CD-21-0090 . Jenifer R, Palanisamy G, Nisha JS. A comparative study of artificial intelligence-based approaches for colorectal cancer diagnosis. Discov Appl Sci. 2026;8:68. 10.1007/s42452-025-08000-2 . Russo V, Lallo E, Munnia A, Spedicato M, Messerini L, D'Aurizio R, et al. Artificial Intelligence Predictive Models of Response to Cytotoxic Chemotherapy Alone or Combined to Targeted Therapy for Metastatic Colorectal Cancer Patients: A Systematic Review and Meta-Analysis. Cancers (Basel). 2022;14(16):4012. 10.3390/cancers14164012 . Paixão GMM, Santos BC, Araujo RM, Ribeiro MH, Moraes JL, Ribeiro AL. Machine Learning in Medicine: Review and Applicability. Arq Bras Cardiol. 2022;118(1):95–102. 10.36660/abc.20200596 . Li Y, Zhao X, Zhou Y, Gong L, Peng E. Decision tree model for predicting ovarian tumor malignancy based on clinical markers and preoperative circulating blood cells. BMC Med Inf Decis Mak. 2025;25(1):94. 10.1186/s12911-025-02934-8 . Kayikcioglu E, Onder AH, Bacak B, Serel TA. Machine learning for predicting colon cancer recurrence. Surg Oncol. 2024;54:102079. 10.1016/j.suronc.2024.102079 . Salzberg SL. C4.5: Programs for Machine Learning by J. Ross Quinlan. Mach Learn. 1994;16(3):235–40. 10.1007/BF00993309 . Frank E, Hall M, Holmes G, Kirkby R, Pfahringer B, Witten IH, et al. Weka—A Machine Learning Workbench for Data Mining. In: Maimon O, Rokach L, editors. Data Mining and Knowledge Discovery Handbook. Boston: Springer; 2009. pp. 1269–77. 10.1007/978-0-387-09823-4_66 . Szostek J, Serafin M, Mąka M, Jabłońska B, Mrowiec S. Right-Sided Versus Left-Sided Colon Cancer—A 5-Year Single-Center Observational Study. Cancers (Basel). 2025;17(3):537. 10.3390/cancers17030537 . Sweetser S, Smyrk TC, Sinicrope FA. Serrated colon polyps as precursors to colorectal cancer. Clin Gastroenterol Hepatol. 2013;11(7):760–7. 10.1016/j.cgh.2012.12.004 . Baran B, Mert Ozupek N, Yerli Tetik N, Acar E, Bekcioglu O, Baskin Y. Difference Between Left-Sided and Right-Sided Colorectal Cancer: A Focused Review of Literature. Gastroenterol Res. 2018;11(4):264–73. 10.14740/gr1062w . Cancer Genome Atlas Network. Comprehensive molecular characterization of human colon and rectal cancer. Nature. 2012;487(7407):330–7. 10.1038/nature11252 . Guinney J, Dienstmann R, Wang X, de Reyniès A, Schlicker A, Soneson C, et al. The consensus molecular subtypes of colorectal cancer. Nat Med. 2015;21(11):1350–6. 10.1038/nm.3967 . Petrelli F, Tomasello G, Borgonovo K, Ghidini M, Turati L, Dallera P, et al. Prognostic Survival Associated with Left-Sided vs Right-Sided Colon Cancer: A Systematic Review and Meta-Analysis. JAMA Oncol. 2017;3(2):211–9. 10.1001/jamaoncol.2016.4227 . Park JH, Kim MJ, Park SC, Hong CW, Sohn DK, Han KS, et al. Difference in time to locoregional recurrence between patients with right-sided and left-sided colon cancers. Dis Colon Rectum. 2015;58(9):831–7. 10.1097/DCR.0000000000000418 . Wang S, Xu X, Guan J, Huo R, Liu M, Jiang C, et al. Better survival of right-sided than left-sided stage II colon cancer: a propensity scores matching analysis based on SEER database. Turk J Gastroenterol. 2020;31(11):805–13. 10.5152/tjg.2020.19163 . Mukkamalla SKR, Huynh DV, Somasundar PS, Rathore R. Adjuvant chemotherapy and tumor sidedness in stage II colon cancer: Analysis of the National Cancer data base. Front Oncol. 2020;10:568417. 10.3389/fonc.2020.568417 . Souza-Silva R, Calixto-Lima L, Varea Maria Wiegert E, de Oliveira LC. Decision tree algorithm to predict mortality in incurable cancer: a new prognostic model. BMJ Support Palliat Care. 2024:spcare-2023-004581. 10.1136/spcare-2023-004581 Li X, Li D, Qin S, Ye H, Lin M. Nomogram model for predicting long-term survival in esophageal cancer patients with metastasis after treatment: a SEER-based study. J Thorac Dis. 2024;16(10):6587–601. 10.21037/jtd-24-1100 . Feng H, Zhang J, Zhang Y, et al. Association of tumor size with prognosis in colon cancer: a Surveillance, Epidemiology, and End Results (SEER) database analysis. Surgery. 2021;169(5):1116–23. 10.1016/j.surg.2020.11.012 . Quirke P, Steele R, Monson J, Grieve R, Khanna S, Couture J, et al. Effect of the plane of surgery achieved on local recurrence in patients with operable rectal cancer: a prospective study using data from the MRC CR07 and NCIC-CTG CO16 randomised clinical trial. Lancet. 2009;373(9666):821–8. 10.1016/S0140-6736(09)60485-2 . Arnold D, Lueza B, Douillard JY, Peeters M, Lenz HJ, Venook A, et al. Prognostic and predictive value of primary tumour side in patients with RAS wild-type metastatic colorectal cancer treated with chemotherapy and EGFR directed antibodies in six randomized trials. Ann Oncol. 2017;28(8):1713–29. 10.1093/annonc/mdx175 . Venook AP, Niedzwiecki D, Lenz H, et al. Effect of First-Line Chemotherapy Combined With Cetuximab or Bevacizumab on Overall Survival in Patients With KRAS Wild-Type Advanced or Metastatic Colorectal Cancer: A Randomized Clinical Trial. JAMA. 2017;317(23):2392–401. 10.1001/jama.2017.7105 . Warschkow R, Sulz MC, Marti L, Tarantino I, Schmied BM, Cerny T, et al. Better survival in right-sided versus left-sided stage I - III colon cancer patients. BMC Cancer. 2016;16:554. 10.1186/s12885-016-2412-0 . Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 Mar, 2026 Reviewers agreed at journal 27 Feb, 2026 Reviews received at journal 27 Feb, 2026 Reviewers agreed at journal 27 Feb, 2026 Reviews received at journal 26 Feb, 2026 Reviews received at journal 25 Feb, 2026 Reviewers agreed at journal 25 Feb, 2026 Reviews received at journal 25 Feb, 2026 Reviewers agreed at journal 25 Feb, 2026 Reviewers agreed at journal 25 Feb, 2026 Reviewers invited by journal 25 Feb, 2026 Editor invited by journal 24 Feb, 2026 Editor assigned by journal 10 Feb, 2026 Submission checks completed at journal 10 Feb, 2026 First submitted to journal 04 Feb, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8789179","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":597646038,"identity":"81efb31b-f4e7-415e-9750-eb9aaeb9eec1","order_by":0,"name":"Marcelo Portes Rocha Martins","email":"","orcid":"","institution":"Faculdade de Ciências Médicas de Minas Gerais","correspondingAuthor":false,"prefix":"","firstName":"Marcelo","middleName":"Portes Rocha","lastName":"Martins","suffix":""},{"id":597646039,"identity":"b86eff1e-06d0-469a-b97c-1c6d1c976b0d","order_by":1,"name":"Rafaela Lopes de Figueiredo Andrade","email":"","orcid":"","institution":"OncoTag-Desenvolvimento de Produtos e Serviços para Saúde Humana","correspondingAuthor":false,"prefix":"","firstName":"Rafaela","middleName":"Lopes de Figueiredo","lastName":"Andrade","suffix":""},{"id":597646040,"identity":"a899ee88-af8c-40f1-b31b-55288ee8aaa2","order_by":2,"name":"Pedro Henrique Villar Delfino","email":"","orcid":"","institution":"OncoTag-Desenvolvimento de Produtos e Serviços para Saúde Humana","correspondingAuthor":false,"prefix":"","firstName":"Pedro","middleName":"Henrique Villar","lastName":"Delfino","suffix":""},{"id":597646041,"identity":"37af9da9-c32b-4ff1-b22c-d7da2f9f7a11","order_by":3,"name":"Laurence Rodrigues do Amaral","email":"","orcid":"","institution":"Universidade Federal de Uberlândia","correspondingAuthor":false,"prefix":"","firstName":"Laurence","middleName":"Rodrigues do","lastName":"Amaral","suffix":""},{"id":597646042,"identity":"3b1feb44-0502-4dfd-a63f-470387115809","order_by":4,"name":"Letícia da Conceição Braga","email":"","orcid":"","institution":"Instituto Mário Penna","correspondingAuthor":false,"prefix":"","firstName":"Letícia","middleName":"da Conceição","lastName":"Braga","suffix":""},{"id":597646043,"identity":"0c32462c-0526-4d63-863f-0014ca760d19","order_by":5,"name":"Roberta Rayra Martins Chaves","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABb0lEQVRIie2RPUvDQBiALwjJEs16wY/8hYZA6lDaH+JyIdAuySAFQZR6ErguRtcW/0RdSjdbAnUJdS1ExFBw6tAgSIRDfC39HAS7ieQZ7uPlnrv33hehjIw/iTyb8XQsIPF7ItONReeHckig6wpZKOXNlWA1AbJYrSr5ut8bnaZFpNx6r3jCH7Udye9NXs5rR4pkX05S3i5SyWtjofM8U/bCga2HxEb4qW+qTRbpTB7YmPQDt3kVe6rPIpvK/RMshNX5p7FjqpRsoRwmhrFNIyJCBBGx67aGFkMQgescEwuMLJX8ByUXoFTeDM4HRNTGoHzW3HtQBM5Bgci6YgqUBKA4+giJXXhFNpHFttwWhlEWoyKCyKoCmau0/CDjoXMc+8yGvzgGtq4DtxHG3u4+g1TlcvXQChcK1CehhbMDpVFpdVNe1LR6qCfpe829qVfiZMyjkiIFd8Oksyz5sjs/AEVY69EvKG1yOCMjI+M/8gUPForIIoPJxgAAAABJRU5ErkJggg==","orcid":"","institution":"Faculdade de Ciências Médicas de Minas Gerais","correspondingAuthor":true,"prefix":"","firstName":"Roberta","middleName":"Rayra Martins","lastName":"Chaves","suffix":""}],"badges":[],"createdAt":"2026-02-04 17:23:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8789179/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8789179/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103733597,"identity":"dacb3c36-9b6c-4822-9e06-5ade4bb3e7e9","added_by":"auto","created_at":"2026-03-02 09:28:48","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":102006,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eThe outcomes at 60 months after treatment, by age group (≤62 years vs. \u0026nbsp;\u0026gt;62 years).\u003c/strong\u003e (a) Kaplan-Meier curves showing overall survival stratified by age. Time is expressed in months. Survival distributions were compared using the log-rank (Mantel-Cox) test (P = 0.0775). (b) Kaplan-Meier curves showing progression-free survival stratified by age. Time is expressed in months. Survival distributions were compared using the log-rank (Mantel-Cox) test (P = 0.0197).\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8789179/v1/5cbb643fa9cb5df5b1355941.png"},{"id":103733535,"identity":"5ce488bd-02ba-40c6-9697-a44fbf8dcb09","added_by":"auto","created_at":"2026-03-02 09:28:44","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":212149,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eDecision tree models for different clinicopathological data of patients with CRC\u003c/strong\u003e. (a, b) Classification of \u0026nbsp;colorectal tumor laterality based on alcohol use (Yes) or non-use (No) and \u0026nbsp;radiotherapy, where \"No\" means not undergoing treatment and \u0026nbsp;\"Yes\" means undergoing treatment. (c) Predictive decision tree for \u0026nbsp;tumor recurrence based on tumor size (≤5 cm or \u0026gt;5 cm) and presence (Yes) or \u0026nbsp;absence (No) of perineural invasion. (d) Predictive model for death based on \u0026nbsp;CRC laterality, presence (Yes) or absence (No) of angiolymphatic invasion, \u0026nbsp;radiotherapy, tumor staging (Stages I, II or III, IV), sex (Female or Male) \u0026nbsp;and patient age (≤62 years or \u0026gt;62 years).\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8789179/v1/eb4564812c92be9dfe5095d6.png"},{"id":103733813,"identity":"8e73b40e-15e6-4312-82db-e4eb9bcd09bb","added_by":"auto","created_at":"2026-03-02 09:29:41","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1291815,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8789179/v1/6570866b-a338-4544-b8bb-675953b22165.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Colorectal Cancer Sidedness: Prognostic Implications and the Predictive Role of Artificial Intelligence","fulltext":[{"header":"Introduction","content":"\u003cp\u003eColorectal cancer (CRC) ranks third worldwide in incidence and is the second major cause of mortality, following lung cancers\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. Risk factors for CRC can be broadly classified into modifiable and non-modifiable factors. Modifiable risk factors include alcohol\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e and tobacco consumption, psychological stress, obesity\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e, and increased intake of red meat, smoked foods\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e. Non-modifiable risk factors comprise advanced age, male sex, the presence of inflammatory bowel disease, genetic conditions such as familial adenomatous polyposis, a family history of CRC in first-degree relatives, and prior exposure to abdominal or pelvic radiotherapy\u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe multifactorial etiological nature of CRC results in marked molecular heterogeneity, primarily driven by three major carcinogenic pathways: chromosomal instability (CIN), characterized by sequential mutations in \u003cem\u003eAPC\u003c/em\u003e, \u003cem\u003eKRAS\u003c/em\u003e, \u003cem\u003eTP53\u003c/em\u003e, and \u003cem\u003eSMAD4\u003c/em\u003e; microsatellite instability (MSI), arising from mismatch repair deficiency due to germline mutations or \u003cem\u003eMLH1\u003c/em\u003e promoter hypermethylation and the CpG island methylator phenotype (CIMP), frequently associated with \u003cem\u003eBRAF\u003c/em\u003e mutations and the serrated pathway\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. In addition to these pathways, alterations in \u003cem\u003ePIK3CA\u003c/em\u003e, ultra-mutated tumors harboring \u003cem\u003ePOLE/POLD1\u003c/em\u003e mutations, and additional epigenetic changes further contribute to the biological diversity of CRC according to the World Health Organization Classification of Tumors Editorial Board\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e\u003c/sup\u003e. This interplay of genetic and epigenetic mechanisms underpins clinically relevant differences in tumor behavior, which are also differentially expressed across colon tumor locations\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eRight-sided colon tumors (RCC) exhibit a higher frequency of \u003cem\u003ePIK3CA\u003c/em\u003e mutations, \u003cem\u003ePTEN\u003c/em\u003e loss, and KRAS and BRAF alterations, as well as a high prevalence of MSI and mismatch repair deficiency. These features are associated with an increased mutational burden, enhanced neo-antigen generation, and a prominent tumor-infiltrating lymphocytic response\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e. Conversely, left-sided colon tumors (LCC) are linked to \u003cem\u003eAPC\u003c/em\u003e mutations, an early and defining event in the Wnt/β-catenin signaling pathway, as well as later alterations involving \u003cem\u003eTP53\u003c/em\u003e and, in a subset of cases, \u003cem\u003eHER2\u003c/em\u003e amplification\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e,\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e. Collectively, these molecular differences support the existence of distinct biological pathways driving proximal and distal colorectal carcinogenesis, with important implications for prognosis and therapeutic decision-making\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eDistinct clinical characteristics according to tumor sidedness have also been previously reported\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e. Approximately 83% of early-onset CRC occurring in individuals without a family history were diagnosed in the LCC. In the same study, RCC was more frequently observed in older individuals and in females\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e. Furthermore, RCC predominantly originated from sessile and/or serrated polyps and tended to present as flatter lesions with a mucinous component, increased T-cell infiltration, and a higher incidence of peritoneal metastases. In contrast, LCCs more commonly affected younger, male patients and were typically sporadic tumors arising from tubular or villous polyps, presenting with a polypoid or exophytic growth pattern into the bowel lumen, with lower immunogenicity and a greater propensity for distant metastases\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e,\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eAlcohol and tobacco consumption have also been more strongly associated with distal colon and rectal tumors\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e,\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e. Taken together, these consistent clinicopathological and behavioral differences according to tumor sidedness highlight a complex and multifactorial landscape that extends beyond anatomical location, underscoring the need for integrative analytical approaches capable of capturing non-linear interactions among diverse prognostic variables, an area in which artificial intelligence\u0026ndash;based methods have shown particular promise\u003csup\u003e\u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eMachine learning can detect complex patterns in large clinical datasets. These algorithms are trained on previously labeled datasets, enabling them to learn relationships that can subsequently be used to predict outcomes in new patients\u003csup\u003e\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u003c/sup\u003e. Predictive models, such as decision trees, have demonstrated high accuracy in forecasting CRC recurrence and in identifying carcinoembryonic antigen (CEA) levels, tumor location, depth of invasion, lymphatic and venous invasion, and lymph node involvement as relevant predictors\u003csup\u003e\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u003c/sup\u003e. A decision tree model was developed using clinical indicators and preoperative blood cell parameters, demonstrating superior performance in distinguishing benign from malignant ovarian tumors compared to individual imaging or biomarker assessments\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e\u003c/sup\u003e. Decision trees stand as a foundational paradigm in, uniquely positioned at the intersection of computational rigor and clinical epistemology. Unlike 'black box' models such as neural networks, which often obscure the decision-making process, decision trees operate as 'white box' models, offering high explainability. By generating explicit IF-THEN classification rules, the model allows clinicians to intuitively validate the algorithmic logic against established medical knowledge, facilitating the trustworthy translation of these findings into clinical practice\u003csup\u003e\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e,\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn this context, the clinicopathological characteristics that distinguish RCC and LCC constitute a meaningful set of variables that can be incorporated into predictive algorithms to stratify risk of recurrence, disease progression, and mortality. Therefore, the objective of the present study is to systematically characterize the clinicopathological profile of CRC by tumor sidedness, thereby providing a foundation for developing more accurate and clinically applicable intelligent models, as well as for our own AI-based predictive model.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy design\u003c/h2\u003e \u003cp\u003eThis is an observational retrospective cohort study conducted among individuals aged 18 years or older who underwent surgical treatment at Instituto M\u0026aacute;rio Penna and had a histopathological diagnosis of colorectal adenocarcinoma.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eSample selection\u003c/h3\u003e\n\u003cp\u003eA total of 71 patients with complete clinicopathological data who agreed to participate in the study were selected from a cohort of 228 individuals who underwent surgeries classified as \u003cem\u003epartial colectomies\u003c/em\u003e and/or \u003cem\u003eabdominal rectosigmoidectomies\u003c/em\u003e with curative intent at Instituto M\u0026aacute;rio Penna (Belo Horizonte, Minas Gerais, Brazil) between 2020 and 2024. Complete clinicopathological data were available and analyzed for 71 of these patients. Clinicopathological information was obtained from the patients\u0026rsquo; electronic medical records.\u003c/p\u003e \u003cp\u003eInclusion criteria comprised a histopathological diagnosis of colorectal adenocarcinoma, absence of distant metastatic disease, adequate clinical performance status, age\u0026thinsp;\u0026ge;\u0026thinsp;18 years, and surgical specimens confirming the retrieval of at least 12 lymph nodes during lymphadenectomy.\u003c/p\u003e \u003cp\u003eExclusion criteria included non-adenocarcinoma histological subtypes, prior radiotherapy, metastatic disease at diagnosis, synchronous or metachronous malignancies at the time of surgery, receipt of chemotherapy within five years before sample collection, recurrent CCR, and lack of informed consent.\u003c/p\u003e\n\u003ch3\u003eEthical aspects\u003c/h3\u003e\n\u003cp\u003e This study was submitted for review and approval by the Graduate Program Committee in Applied Sciences to Cancer and by the Research Ethics Committee (REC) of Instituto M\u0026aacute;rio Penna, under protocol number 7,133,749.\u003c/p\u003e \u003cp\u003e All procedures were conducted in accordance with the ethical standards of the institutional and national committees responsible for human experimentation and in compliance with the principles of the Declaration of Helsinki of 1975, as revised in 2008.\u003c/p\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eData analysis\u003c/h2\u003e \u003cp\u003eClinicopathological variables were systematically analyzed, including histological subtype, tumor stage and grade, perineural and angiolymphatic invasion, the presence of small infiltrative tumor cell clusters at the tumor\u0026ndash;stroma interface consistent with an active invasion phenotype (tumor budding), the number of positive lymph nodes relative to the total number of dissected nodes, CEA levels, and the use of chemotherapy and radiotherapy. Survival outcomes, including progression-free survival and overall survival, were assessed as time-to-event variables. Survival probabilities were estimated using the Kaplan\u0026ndash;Meier method, and comparisons between survival curves were performed when appropriate.\u003c/p\u003e \u003cp\u003eAssociations between categorical variables were assessed using Fisher\u0026rsquo;s exact test. Statistical analyses were conducted using GraphPad Prism software (version 9.0), and a two-tailed p-value\u0026thinsp;\u0026lt;\u0026thinsp;0.05 was considered statistically significant.\u003c/p\u003e \u003cp\u003eSupervised and unsupervised machine learning techniques were employed to explore and predict clinicopathological data from patients with CRC. Decision tree models and corresponding IF\u0026ndash;THEN classification rules were developed using established methodologies from the literature. Tree induction and class relationship analysis were performed using the J48 algorithm, an implementation of the C4.5 algorithm, in WEKA (Waikato Environment for Knowledge Analysis, version 3.8.3; University of Waikato, New Zealand) \u003csup\u003e\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e,\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e\u003c/sup\u003e. To improve the representation of the minority class in the training set, we used \u0026lsquo;Cost-Sensitive Learning\u0026rsquo; during the modeling phase.\u003c/p\u003e \u003cp\u003eModel performance, robustness, and generalizability were assessed using leave-one-out cross-validation (LOOCV), with predictive models achieving LOOCV overall accuracy values greater than 70% considered acceptable for further interpretation. To ensure a comprehensive evaluation of model performance, we calculated Sensitivity, Specificity, Matthews Correlation Coefficient (MCC) to indicate the correlation between predicted and observed data, and the F1-Score to assess the model's ability to correctly identify the class. Additionally, the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) was used to evaluate the overall discriminative power of the decision trees, independent of the classification threshold.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eSample characterization and clinicopathological profile of CCR patients\u003c/h2\u003e \u003cp\u003eWe analyzed the complete clinicopathological data of 71 patients diagnosed with colorectal adenocarcinoma \u003cb\u003e(\u003c/b\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003cb\u003e)\u003c/b\u003e. The cohort comprised 37 females (52%) and 34 (48%) males, with ages ranging from 24 to 95 years (mean 61\u0026thinsp;\u0026plusmn;\u0026thinsp;12). A significant majority of tumors were located on the left side of the colon, accounting for 61 cases (86%), while 10 tumors (14%) were located on the right side.\u003c/p\u003e \u003cp\u003eThe assessment of tumor laterality in relation to key clinicopathological variables revealed several descriptive patterns. The RCC occurred more frequently in women, whereas the LCC occurred more frequently in men (p\u0026thinsp;=\u0026thinsp;0.08). Although no clear age predilection was identified, 39 patients with CCR were aged 62 years or younger. Interestingly, younger patients (\u0026le;\u0026thinsp;62 years) showed a trend toward reduced overall survival (p\u0026thinsp;=\u0026thinsp;0.07) and significantly shorter progression-free survival (p\u0026thinsp;=\u0026thinsp;0.01) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eA and \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003eB\u003cb\u003e)\u003c/b\u003e. Distributions of tumor size, angiolymphatic invasion, perineural invasion, and tumor budding were broadly comparable across tumor sides. Similarly, CEA levels and the presence of blood in the stool were observed at comparable frequencies in both groups. Collectively, these findings indicate that baseline clinicopathological features were balanced across tumor laterality.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eLifestyle exposures, treatment, and outcomes of CCR patients associated with tumor-sidedness\u003c/h3\u003e\n\u003cp\u003eTobacco exposure was more prevalent in LCC (46%) compared to RCC (10%) patients (p\u0026thinsp;=\u0026thinsp;0.09). Alcohol consumption further differentiated LCC, with current or recent use being significantly more prevalent in this group (p\u0026thinsp;=\u0026thinsp;0.04). Therapeutic strategies differed markedly according to tumor laterality. Patients with LCC were substantially more likely to receive neoadjuvant chemotherapy (p\u0026thinsp;\u0026lt;\u0026thinsp;0.01), whereas RCC were commonly managed with primary surgery followed by adjuvant treatment. Despite this intensified therapy and a statistically more extensive lymph node dissection being performed on LCC (p\u0026thinsp;\u0026lt;\u0026thinsp;0,01), clinical outcomes remained less favorable for this group. Patients harboring LCC experienced a markedly higher death rate than those with RCC (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.04). Although tumor recurrence and distant metastases occurred more frequently in LCC, these events did not clearly segregate by laterality.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eAssociation between tumor sidedness and clinicopathological variables in 71 CCR patients\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClinical-pathological Features\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCategory\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRCC (n)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eLCC (n)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ep-value\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eSex\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.08\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFemale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eAge\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;62 years\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.74\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;62 years\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eTumor size\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0\u0026ndash;5 cm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.33\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e6\u0026ndash;10 cm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e11\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;11 cm\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eGrade\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eWell-differentiated\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.50\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModerately differentiated\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e42\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePoorly differentiated\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAngiolymphatic invasion\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e36\u003c/p\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.31\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003ePerineural invasion\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.48\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eTumor budding\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.71\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e44\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eNumber of lymph nodes retrieved\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e12\u0026ndash;27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.004\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e28\u0026ndash;42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;43\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTNM staging\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eI/II\u003c/p\u003e \u003cp\u003eIII/IV\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e29\u003c/p\u003e \u003cp\u003e32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e0.49\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eCEA (ng/mL)\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026le;\u0026thinsp;3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.56\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u0026ndash;5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e\u0026gt;\u0026thinsp;5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003e\u003cb\u003eChemotherapy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo chemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"3\" rowspan=\"4\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNeoadjuvant chemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAdjuvant chemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePalliative chemotherapy\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eSmoking status\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNever smoker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.09\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCurrent smoker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFormer smoker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e\u003cb\u003eAlcohol consumption\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNon-drinker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"2\" rowspan=\"3\"\u003e \u003cp\u003e0.04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCurrent drinker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFormer drinker\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eBlood in stool\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAbsent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePresent\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e53\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eDistant metastases\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e41\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eTumor recurrence\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e47\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e\u003cb\u003eDeath\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e0.04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e33\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003ePredictive modeling reveals laterality and prognostic clinicopathologic signatures\u003c/h3\u003e\n\u003cp\u003eTo further delineate clinicopathological features associated with tumor laterality and prognosis, machine learning techniques were initially developed to integrate clinically and pathologically relevant variables and to estimate individualized outcome probabilities. Models focused on tumor laterality achieved the highest performance across both training and validation analyses. Particularly, alcohol exposure emerged as a dominant predictor of LCC (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eA \u003cb\u003eand B\u003c/b\u003e). The performance metrics for all generated decision tree models are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. As observed, the models demonstrated stability during internal validation, with LOOCV accuracies (70.37% and 89.09%, respectively) consistent with those from the full training dataset, although the model designed to predict tumor laterality in the general cohort (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eA\u003cb\u003e)\u003c/b\u003e demonstrated the highest robustness.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003ePrognostic modeling supports the central role of tumor sidedness in stratifying adverse clinical outcomes. In RCC, recurrence risk was lower, whereas in LCC, subsequent risk stratification was primarily driven by tumor size. Tumors larger than 5 cm were associated with an increased risk of recurrence, while tumors\u0026thinsp;\u0026le;\u0026thinsp;5 cm were further classified according to perineural invasion status. Notably, and counterintuitively, the absence of perineural invasion was more strongly associated with recurrence than its presence. (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eC). This algorithm correctly classified 88.9% (24/27) of cases during training and retained a high predictive accuracy of 62.9% (17/27) under cross-validation (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eIn the predictive model for mortality stratified by CCR laterality, RCC was associated with more favorable outcomes. LCC was subsequently stratified by angiolymphatic invasion status. In the absence of angiolymphatic invasion, radiotherapy exposure emerged as the next discriminative factor, with improved survival observed among patients who did not receive radiotherapy. Among those who underwent radiotherapy, pathological stage provided further risk stratification, with stages I and II associated with superior survival. In the presence of angiolymphatic invasion, the algorithm identified sex as the principal stratifier, with poorer outcomes in men, while women were further stratified by age, with younger patients exhibiting reduced survival probability. (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eD). As shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e, the models were stable during internal validation, with LOOCV accuracies (72.73%) consistent with those from the full training dataset (87.27%).\u003c/p\u003e \u003cp\u003eTo mitigate bias arising from class imbalance, a Cost-Sensitive Learning strategy was employed during training. Misclassification penalty weights were assigned to the minority class for each model (3.0 for Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eA and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eC; 6.6 for Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eB; and 1.4 for Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eD), while the majority class retained a weight of 1.0. Consequently, the values displayed in the leaf nodes represent re-weighted instances normalized to the total sample size, rather than raw counts. The clinical translation of these values into integer patient counts is detailed in each terminal node of the figures.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003ePredictive Performance of Decision Tree Models\u003c/h2\u003e \u003cp\u003eThe performance metrics for all induced decision tree models are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The laterality tumor prediction models in the general cohort \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eB\u003cb\u003e)\u003c/b\u003e demonstrated the highest overall diagnostic accuracy (89.09%), with a robust MCC (0.627) and a high AUC-ROC (0.83). Notably, this model maintained balanced class sensitivity (0.896 for left-sided tumors and 0.857 for right-sided tumors) and an MCC of 0.421, indicating a moderate-to-strong correlation between prediction and observation. Conversely, models trained on smaller subsets, specifically for recurrence prediction in patients undergoing adjuvant therapy (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eC), exhibited signs of overfitting, as indicated by a significant discrepancy between training (88.9%) and validation (62.96%) accuracies and an AUC-ROC. The performance metrics for this model indicate suboptimal predictive power, with a negative MCC (-0.227) and an AUC-ROC below the threshold for discrimination (0.464). These results suggest significant discriminatory challenges, particularly in classifying tumor recurrence, where the model failed to distinguish between categories effectively. The mortality prediction model (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eD), however, showed promising generalizability, with a validation accuracy of 72.73% and an F1-score of 0.754 for death and a high AUC-ROC, suggesting that the selected clinicopathological variables have significant prognostic value for survival outcomes.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance metrics and discriminatory power of decision trees for predicting clinicopathological characteristics in CCR patients.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDecision tree model\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFull training\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLOOCV\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eClass\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSpecificity\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSensibility\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eF1-score\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eMCC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eAUC-ROC\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eLaterality of tumors in adjuvant therapy patients\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e81.48% (22/27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e70.37% (19/27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eLCC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.732\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRCC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.299\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.732\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eLaterality of tumor in the general cohort\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e90.9% (50/55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e89.09 (49/55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eLCC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.896\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.857\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.667\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.832\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRCC\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.857\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.896\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.935\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.627\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.832\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003eRecurrence of the tumor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e88.9% (24/27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e62.963%\u003c/p\u003e \u003cp\u003e(17/27)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.773\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.773\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e-0.227\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.464\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.773\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e-0.227\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.464\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003ePost-chemotherapy mortality\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e87.27% (48/55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\" morerows=\"1\" rowspan=\"2\"\u003e \u003cp\u003e72.73% (40/55)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eYes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.739\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.754\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.452\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.808\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNo\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.719\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.739\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.694\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c8\"\u003e \u003cp\u003e0.452\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c9\"\u003e \u003cp\u003e0.787\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eColorectal tumors are responsible for approximately 900,000 deaths per year, according to data from the World Health Organization\u003csup\u003e\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e. However, if we delve deeper into this pathology, we will realize that colorectal tumors are not a single entity but behave differently depending on their location. Clinicopathological characteristics differ substantially between tumor locations\u003csup\u003e\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u003c/sup\u003e. RCC is more frequently observed in older patients, shows a female predominance, and is often associated with hereditary predisposition. It typically arises from serrated precursor lesions, exhibits increased T-cell infiltration, and demonstrates a higher propensity for peritoneal metastasis\u003csup\u003e\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eIn contrast, LCC more commonly affects younger male patients, is predominantly sporadic, arises from tubular or villous adenomatous polyps, is less immunogenic, and metastasizes more frequently to the liver or lungs\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e\u003c/sup\u003e. Our study highlighted and reinforced the heterogeneity of this disease through a clinical-pathological approach, combined with innovative machine learning (ML) using decision tree models, not only to describe but also to develop tools to predict the CRC behavior and prognosis based on laterality. This strategy extends beyond descriptive analysis to develop predictive tools that anticipate tumor behavior and prognosis based on primary tumor laterality.\u003c/p\u003e \u003cp\u003eOur model stratified CCR into two distinct groups using predictive decision trees. LCC was predominantly associated with behavioral factors, particularly regular alcohol consumption, unlike RCC. These findings could be consistent with divergent pathogenic pathways. RCC is frequently associated with \u003cem\u003eBRAF\u003c/em\u003e mutations and high-frequency microsatellite instability resulting from defective DNA mismatch repair, leading to widespread genomic alterations\u003csup\u003e\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u003c/sup\u003e. In contrast, left-sided tumors typically arise through the conventional adenoma\u0026ndash;carcinoma sequence, driven by chromosomal instability with gains, amplifications, losses, or deletions affecting a more limited set of genes, including \u003cem\u003eAPC\u003c/em\u003e, \u003cem\u003eKRAS, TP53, SMAD4\u003c/em\u003e, and \u003cem\u003ePIK3CA\u003c/em\u003e\u003csup\u003e\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e,\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e\u003c/sup\u003e. These findings can alter not only the treatment but also the prognosis of CRC.\u003c/p\u003e \u003cp\u003eIn our cohort, despite patients with LCC receiving more intensive treatment modalities, including chemoradiotherapy (p\u0026thinsp;\u0026lt;\u0026thinsp;0.01), this group demonstrated poorer outcomes, with a significantly higher mortality rate (p\u0026thinsp;=\u0026thinsp;0.04). This contrasts with the available literature, which consistently indicates a poorer prognosis for RCC. Petrelli et al. published a meta-analysis demonstrating an absolute 19% reduction in the risk of death for LCC compared with RCC tumors, based solely on sidedness\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u003c/sup\u003e, and these results were corroborated by a large retrospective Korean cohort of 1,632 patients, which reported an increased risk of locoregional recurrence in RCC\u003csup\u003e\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eMeanwhile, contrasting findings have been reported in patients with early-stage tumors. Papers focusing on the initial stages of CRC (I and II) have reported improved survival among patients with RCC, potentially related to the higher prevalence of microsatellite instability\u0026ndash;high, a feature associated with a more favorable prognosis in early-stage disease\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. In addition, a retrospective analysis of the National Cancer Database showed that among patients who did not receive adjuvant chemotherapy, those with RCC had superior overall survival compared with those with LCC\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e. Taken together, these observations highlight the need for integrative, data-driven prognostic approaches that reconcile the stage-dependent, biologically distinct survival patterns associated with tumor laterality, thereby providing a rationale for applying decision tree\u0026ndash;based modeling in colorectal cancer.\u003c/p\u003e \u003cp\u003eCurrent evidence indicates that decision trees are reliable statistical predictive models that accurately estimate the risk of clinical events by integrating key prognostic factors in oncology\u003csup\u003e\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e. In many malignancies, including CRC, decision trees have demonstrated superior prognostic performance compared with traditional staging systems\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u003c/sup\u003e. These observations prompted us to explore the feasibility of developing a decision tree to predict the prognostic impact of tumor laterality in CRC.\u003c/p\u003e \u003cp\u003eThe conventional TNM staging system has well-recognized limitations. Prognostic assessment based exclusively on tumor size, lymph node involvement, and distant metastases fails to account for several clinically relevant variables, including tumor laterality, surgical margin status, alcohol and tobacco exposure, sex, age, and the use of chemoradiotherapy\u003csup\u003e\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u003c/sup\u003e. Accordingly, in the present study, we integrated machine learning techniques with a comprehensive set of clinical and pathological variables to refine survival estimation and to specifically assess the prognostic relevance of tumor laterality. The analyses revealed that laterality was modulated by behavioral factors, particularly alcohol consumption, which was predominantly associated with left-sided CCR in both models (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eA and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eB). The statistical strength of these associations is corroborated by our predictive modeling, which demonstrates an LOOCV accuracy of 89.09% and an AUC-ROC of 0.83 (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). This high discriminative power confirms that these variables are not merely correlated but are reliable predictors of tumor sidedness in this cohort. In contrast, RCC was strongly associated with more favorable outcomes and lower recurrence rates, whereas LCC disease was further stratified by tumor size and perineural invasion (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e2\u003c/span\u003eC). However, these specific findings should be interpreted with caution. While the model identified perineural invasion as a decision node, the quantitative metrics indicate overfitting, with accuracy dropping from 88.9% in training to 62.96% in validation. Furthermore, the low AUC-ROC (0.46) suggests limited discriminative power for this specific outcome, indicating that this counterintuitive association may reflect sample size constraints or statistical noise rather than a definitive biological phenomenon. This contrasts with the observed epidemiological evidence. In SEER-based cohorts comprising more than 163,000 patients, LCC has been consistently associated with lower cancer-specific mortality compared with RCC; however, this association is stage-dependent, demonstrating comparable or even more favorable outcomes in early-stage disease and no clear survival advantage in stage III tumors.\u003c/p\u003e \u003cp\u003eGiven the poorer outcomes observed in LCC, the model enabled a detailed exploration of risk factors and patient subgroups, stratifying them into hierarchical levels according to their relative risk and impact on survival. In patients without angiolymphatic invasion, radiotherapy emerged as the subsequent decision node, whereby the requirement for radiotherapy and more advanced disease stages were associated with an unfavorable prognosis. In the presence of angiolymphatic invasion, prognostic stratification was primarily determined by sex and age, with male patients exhibiting poorer outcomes. Notably, within this branch, younger women (\u0026lt;\u0026thinsp;62 years) were paradoxically associated with worse survival. These counterintuitive associations highlight the need for further investigation to elucidate the biological and clinical mechanisms underlying these observations. ​​​​In contrast to the recurrence analysis, the mortality risk stratification demonstrated high reliability. The decision tree integrating angiolymphatic invasion, sex, and age achieved a validation accuracy of 72.73% and an AUC-ROC exceeding 0.80 (Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). These metrics validate the clinical relevance of the identified subgroups, supporting the model's potential utility in identifying patients at high risk of mortality despite the observed complex interactions.\u003c/p\u003e \u003cp\u003eAlthough tumor sidedness has emerged as a relevant prognostic factor in CRC, the available evidence remains heterogeneous and strongly dependent on disease stage and clinical context. Large meta-analyses and pooled analyses of advanced and metastatic disease consistently demonstrate superior outcomes for left-sided tumors, with improved overall survival and treatment response when compared with right-sided cancers\u003csup\u003e\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e,\u003cspan additionalcitationids=\"CR36\" citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e. In contrast, population-based studies focusing on early-stage disease, particularly stage II, have reported outcomes for RCC after adequate surgical resection, equal to or better than those for LCC\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e,\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e,\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e\u003c/sup\u003e. These findings suggest that tumor laterality does not serve as a uniform prognostic marker across all stages but rather reflects distinct biological behaviors that may confer a survival advantage in early disease while portending worse outcomes in advanced disease. Such stage-dependent and, at times, counterintuitive results underscore the complexity of CRC biology and highlight the need for further prospective studies integrating molecular, clinicopathological, and treatment-related variables to better define the true prognostic role of tumor sidedness.\u003c/p\u003e \u003cp\u003eTo address the class imbalance between left-sided (n\u0026thinsp;=\u0026thinsp;61) and right-sided (n\u0026thinsp;=\u0026thinsp;10) tumors, which could bias the decision tree towards the majority class, we employed a balancing strategy during the modeling phase. Specifically, we used Cost-Sensitive Learning to improve the representation of the minority class in the training set. This approach aims to improve the J48 algorithm's decision boundaries, ensuring that the predictive rules for right-sided tumors reflect robust patterns rather than statistical noise. The effectiveness of this weighting strategy is evidenced by the balanced sensitivity rates achieved in the laterality model (0.896 for LCC and 0.857 for RCC). This confirms that the algorithmic adjustments successfully mitigated bias toward the majority class, enabling reliable identification of right-sided tumor characteristics despite the numerical disparity.\u003c/p\u003e \u003cp\u003eThe interpretation of these findings warrants caution, given certain inherent limitations, specifically a retrospective, single-center design and the modest sample size, which resulted in an imbalance in tumor laterality. This distribution likely reflects local referral patterns rather than a biological deviation and may have influenced survival estimates, particularly the higher mortality observed in LCC, despite the broader literature often associating right-sided disease with poorer outcomes. Importantly, these constraints do not undermine the study\u0026rsquo;s core contributions. The analysis provides a detailed characterization of CRC within a well-defined clinical setting, confirms the prognostic relevance of established markers of tumor aggressiveness, and demonstrates the capacity of machine-learning\u0026ndash;based decision models to capture coherent, clinically meaningful risk stratification even in relatively small cohorts. Besides, a major strength of this study lies in the deliberate selection of the J48 (C4.5) decision tree algorithm. We prioritized decision trees over more opaque algorithms to ensure transparency in risk stratification. The resulting logical rules (IF-THEN structures) mirror standard clinical reasoning, enabling oncologists to verify the biological coherence of the predictors, such as angiolymphatic and perineural invasion, tumor size, and staging identified by the AI. This transparency is essential for the clinical translational potential of our findings, which is further reinforced by the model's interpretability. Together, these findings underscore their value as hypothesis-generating evidence for future multicenter validation.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study demonstrates that tumor sidedness represents a clinically meaningful and biologically grounded prognostic dimension in CCR when interpreted alongside established pathological and treatment-related variables. By integrating clinicopathological data into transparent, decision-tree\u0026ndash;based machine learning models, we identified coherent, clinically interpretable risk signatures that extend beyond conventional TNM staging. Right-sided tumors were consistently associated with more favorable survival and lower recurrence in this cohort, whereas left-sided disease exhibited distinct behavioral, therapeutic, and pathological stratifiers linked to adverse outcomes, including alcohol exposure, tumor size, perineural invasion, and angiolymphatic involvement. Although limited by its retrospective, single-center design and modest sample size, this work supports the utility of explainable artificial intelligence as a hypothesis-generating framework for individualized prognostic assessment. Future multicenter, prospective studies incorporating molecular and genomic data are warranted to validate and refine these models and to more precisely define the stage-dependent prognostic role of tumor laterality in colorectal cancer.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cdiv class=\"DefinitionList\"\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArtificial intelligence\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eAUC-ROC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eArea Under the Receiver Operating Characteristic Curve\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCEA\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCarcinoembryonic antigen\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCIMP\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eCpG island methylator phenotype\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCIN\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eChromosomal instability\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eCRC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eColorectal cancer\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eLCC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eLeft-sided colorectal cancer\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eLOOCV\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eLeave-one-out cross-validation\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMCC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMatthews Correlation Coefficient\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eML\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMachine learning\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eMSI\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eMicrosatellite instability\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eRCC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eRight-sided colorectal cancer\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv class=\"DefinitionListEntry\"\u003e \u003cdiv class=\"Term\"\u003e\u003cb\u003eREC\u003c/b\u003e\u003c/div\u003e \u003cdiv class=\"Description\"\u003e \u003cp\u003eResearch Ethics Committee\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cem\u003eEthics approval and consent to participate\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe study was approved by the Research Ethics Committee of Instituto M\u0026aacute;rio Penna (Belo Horizonte, Brazil), under approval number 25004619.3.3001.5121. All participants provided written informed consent. The study was conducted using anonymized data, ensuring confidentiality and the protection of participants\u0026rsquo; identities.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003cem\u003eConsent for publication\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAvailability of data and materials\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets generated and/or analyzed during the current study are not publicly available due to ethical and privacy restrictions related to patient data, but are available from the corresponding author upon reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003cem\u003eCompeting interests\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eFunding\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eThis research was supported by the Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG; APQ-02564-22 and APQ-04993-22) and Rede Mineira de Pesquisa Translational em Oncologia (FAPEMIG; RED00059-23).\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAuthors\u0026apos; contributions\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eM.P.R.M. contributed to the conception and planning of the study, data acquisition, data analysis, statistical analyses, and manuscript drafting. R.L.F.A. contributed to data acquisition and statistical analyses. P.H.V.D. contributed to study planning, data analysis and interpretation, statistical analyses, and critical revision of the manuscript. L.C.B. contributed to study planning, data analysis and interpretation, supervised and unsupervised machine learning analyses, critical revision of the manuscript, and supervision of the study. L.R.A. conducted the supervised and unsupervised machine learning analyses. R.R.M.C. critically revised the manuscript and contributed to the supervision of the study. All authors contributed to the interpretation of the results and contributed to the final version of the manuscript.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAcknowledgements\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003eWe thank all patients for their valuable participation in this study.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eInternational Agency for Research on Cancer. Global Cancer Observatory: Cancer Today \u0026ndash; Colorectal cancer incidence and mortality visualization [Internet]. Lyon: IARC. 2025 [cited 2026 Jan 31]. Available from: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://gco.iarc.fr/today/en/dataviz/bars?mode=cancer\u0026amp;group_populations=1\u0026amp;types=0_1\u0026amp;sort_by=value1\u003c/span\u003e\u003cspan address=\"https://gco.iarc.fr/today/en/dataviz/bars?mode=cancer\u0026amp;group_populations=1\u0026amp;types=0_1\u0026amp;sort_by=value1\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVieira AR, Abar L, Chan DSM, Vingeliene S, Polemiti E, Stevens C, et al. Foods and beverages and colorectal cancer risk: a systematic review and meta-analysis of cohort studies, an update of the evidence of the WCRF-AICR Continuous Update Project. Ann Oncol. 2017;28(8):1788\u0026ndash;802. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/annonc/mdx171\u003c/span\u003e\u003cspan address=\"10.1093/annonc/mdx171\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUllah F, Pillai AB, Omar N, Dima D, Harichand S. Early-Onset Colorectal Cancer: Current Insights. Cancers (Basel). 2023;15(12):3202. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers15123202\u003c/span\u003e\u003cspan address=\"10.3390/cancers15123202\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRoshandel G, Ghasemi-Kebria F, Malekzadeh R, Colorectal Cancer. Epidemiology, Risk Factors, and Prevention. Cancers (Basel). 2024;16(8):1530. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers16081530\u003c/span\u003e\u003cspan address=\"10.3390/cancers16081530\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArends MJ. Pathways of colorectal carcinogenesis. Appl Immunohistochem Mol Morphol. 2013;21(2):97\u0026ndash;102. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/PAI.0b013e31827ea79e\u003c/span\u003e\u003cspan address=\"10.1097/PAI.0b013e31827ea79e\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWorld Health Organization Classification of Tumours Editorial Board. Digestive system tumours. WHO Classification of Tumours. Volume 1, 5th ed. Lyon: International Agency for Research on Cancer; 2019.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee MS, et al. PIK3CA and PTEN status in advanced colorectal cancer treated with anti-EGFR therapy. Br J Cancer. 2015;113(3):414\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLe DT, Durham JN, Smith KN, Wang H, Bartlett BR, Aulakh LK, et al. Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade. Science. 2017;357(6349):409\u0026ndash;13.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang T, Fu J, Huang Y, Fu C. Mechanism of APC truncation involved in colorectal cancer tumorigenesis (Review). Oncol Lett. 2024;29(1):2. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3892/ol.2024.14748\u003c/span\u003e\u003cspan address=\"10.3892/ol.2024.14748\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZeng S, Wang J, Shi Z, Zhao H, Gao J, Li J. The Wnt/β-catenin signaling pathway in colorectal cancer: mechanism and intervention of traditional Chinese medicine and chemical compound. Front Pharmacol. 2025;16:1560714. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fphar.2025.1560714\u003c/span\u003e\u003cspan address=\"10.3389/fphar.2025.1560714\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMolina-Meneses SP, Palacios-Fuenmayor LJ, Molina-Mercado FD, Caycedo-Medina DF, Casta\u0026ntilde;o-Llano R, G\u0026oacute;mez-Wolff LR, et al. Colon tumor location: Right side versus left side as a prognostic factor for colon cancer survival: Analysis of a retrospective cohort. Rev Gastroenterol Mex (Engl Ed). 2025;90(3):400\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWaldstein S, Spengler M, Pinchuk IV, Yee NS. Impact of Colorectal Cancer Sidedness and Location on Therapy and Clinical Outcomes: Role of Blood-Based Biopsy for Personalized Treatment. J Pers Med. 2023;13(7):1114. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/jpm13071114\u003c/span\u003e\u003cspan address=\"10.3390/jpm13071114\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLoree JM, Pereira AAL, Lam M, Willauer AN, Raghav K, Dasari A, et al. Classifying Colorectal Cancer by Tumor Location Rather than Sidedness Highlights a Continuum in Mutation Profiles and Consensus Molecular Subtypes. Clin Cancer Res. 2018;24(5):1062\u0026ndash;72. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1158/1078-0432.CCR-17-2484\u003c/span\u003e\u003cspan address=\"10.1158/1078-0432.CCR-17-2484\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJun S, Park H, Kim UJ, Choi EJ, Lee HA, Park B, et al. Cancer risk based on alcohol consumption levels: a comprehensive systematic review and meta-analysis. Epidemiol Health. 2023;45:e2023092. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.4178/epih.e2023092\u003c/span\u003e\u003cspan address=\"10.4178/epih.e2023092\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhou X, Wang L, Xiao J, Sun J, Yu L, Zhang H, et al. Alcohol consumption, DNA methylation and colorectal cancer risk: Results from pooled cohort studies and Mendelian randomization analysis. Int J Cancer. 2022;151(1):83\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1002/ijc.33945\u003c/span\u003e\u003cspan address=\"10.1002/ijc.33945\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhinder B, Gilvary C, Madhukar NS, Elemento O. Artificial Intelligence in Cancer Research and Precision Medicine. Cancer Discov. 2021;11(4):900\u0026ndash;15. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1158/2159-8290.CD-21-0090\u003c/span\u003e\u003cspan address=\"10.1158/2159-8290.CD-21-0090\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJenifer R, Palanisamy G, Nisha JS. A comparative study of artificial intelligence-based approaches for colorectal cancer diagnosis. Discov Appl Sci. 2026;8:68. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/s42452-025-08000-2\u003c/span\u003e\u003cspan address=\"10.1007/s42452-025-08000-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRusso V, Lallo E, Munnia A, Spedicato M, Messerini L, D'Aurizio R, et al. Artificial Intelligence Predictive Models of Response to Cytotoxic Chemotherapy Alone or Combined to Targeted Therapy for Metastatic Colorectal Cancer Patients: A Systematic Review and Meta-Analysis. Cancers (Basel). 2022;14(16):4012. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers14164012\u003c/span\u003e\u003cspan address=\"10.3390/cancers14164012\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePaix\u0026atilde;o GMM, Santos BC, Araujo RM, Ribeiro MH, Moraes JL, Ribeiro AL. Machine Learning in Medicine: Review and Applicability. Arq Bras Cardiol. 2022;118(1):95\u0026ndash;102. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.36660/abc.20200596\u003c/span\u003e\u003cspan address=\"10.36660/abc.20200596\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi Y, Zhao X, Zhou Y, Gong L, Peng E. Decision tree model for predicting ovarian tumor malignancy based on clinical markers and preoperative circulating blood cells. BMC Med Inf Decis Mak. 2025;25(1):94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12911-025-02934-8\u003c/span\u003e\u003cspan address=\"10.1186/s12911-025-02934-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKayikcioglu E, Onder AH, Bacak B, Serel TA. Machine learning for predicting colon cancer recurrence. Surg Oncol. 2024;54:102079. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.suronc.2024.102079\u003c/span\u003e\u003cspan address=\"10.1016/j.suronc.2024.102079\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalzberg SL. C4.5: Programs for Machine Learning by J. Ross Quinlan. Mach Learn. 1994;16(3):235\u0026ndash;40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/BF00993309\u003c/span\u003e\u003cspan address=\"10.1007/BF00993309\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFrank E, Hall M, Holmes G, Kirkby R, Pfahringer B, Witten IH, et al. Weka\u0026mdash;A Machine Learning Workbench for Data Mining. In: Maimon O, Rokach L, editors. Data Mining and Knowledge Discovery Handbook. Boston: Springer; 2009. pp. 1269\u0026ndash;77. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1007/978-0-387-09823-4_66\u003c/span\u003e\u003cspan address=\"10.1007/978-0-387-09823-4_66\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSzostek J, Serafin M, Mąka M, Jabłońska B, Mrowiec S. Right-Sided Versus Left-Sided Colon Cancer\u0026mdash;A 5-Year Single-Center Observational Study. Cancers (Basel). 2025;17(3):537. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3390/cancers17030537\u003c/span\u003e\u003cspan address=\"10.3390/cancers17030537\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSweetser S, Smyrk TC, Sinicrope FA. Serrated colon polyps as precursors to colorectal cancer. Clin Gastroenterol Hepatol. 2013;11(7):760\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.cgh.2012.12.004\u003c/span\u003e\u003cspan address=\"10.1016/j.cgh.2012.12.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBaran B, Mert Ozupek N, Yerli Tetik N, Acar E, Bekcioglu O, Baskin Y. Difference Between Left-Sided and Right-Sided Colorectal Cancer: A Focused Review of Literature. Gastroenterol Res. 2018;11(4):264\u0026ndash;73. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.14740/gr1062w\u003c/span\u003e\u003cspan address=\"10.14740/gr1062w\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCancer Genome Atlas Network. Comprehensive molecular characterization of human colon and rectal cancer. Nature. 2012;487(7407):330\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/nature11252\u003c/span\u003e\u003cspan address=\"10.1038/nature11252\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuinney J, Dienstmann R, Wang X, de Reyni\u0026egrave;s A, Schlicker A, Soneson C, et al. The consensus molecular subtypes of colorectal cancer. Nat Med. 2015;21(11):1350\u0026ndash;6. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1038/nm.3967\u003c/span\u003e\u003cspan address=\"10.1038/nm.3967\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePetrelli F, Tomasello G, Borgonovo K, Ghidini M, Turati L, Dallera P, et al. Prognostic Survival Associated with Left-Sided vs Right-Sided Colon Cancer: A Systematic Review and Meta-Analysis. JAMA Oncol. 2017;3(2):211\u0026ndash;9. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jamaoncol.2016.4227\u003c/span\u003e\u003cspan address=\"10.1001/jamaoncol.2016.4227\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePark JH, Kim MJ, Park SC, Hong CW, Sohn DK, Han KS, et al. Difference in time to locoregional recurrence between patients with right-sided and left-sided colon cancers. Dis Colon Rectum. 2015;58(9):831\u0026ndash;7. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1097/DCR.0000000000000418\u003c/span\u003e\u003cspan address=\"10.1097/DCR.0000000000000418\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang S, Xu X, Guan J, Huo R, Liu M, Jiang C, et al. Better survival of right-sided than left-sided stage II colon cancer: a propensity scores matching analysis based on SEER database. Turk J Gastroenterol. 2020;31(11):805\u0026ndash;13. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5152/tjg.2020.19163\u003c/span\u003e\u003cspan address=\"10.5152/tjg.2020.19163\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMukkamalla SKR, Huynh DV, Somasundar PS, Rathore R. Adjuvant chemotherapy and tumor sidedness in stage II colon cancer: Analysis of the National Cancer data base. Front Oncol. 2020;10:568417. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.3389/fonc.2020.568417\u003c/span\u003e\u003cspan address=\"10.3389/fonc.2020.568417\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSouza-Silva R, Calixto-Lima L, Varea Maria Wiegert E, de Oliveira LC. Decision tree algorithm to predict mortality in incurable cancer: a new prognostic model. BMJ Support Palliat Care. 2024:spcare-2023-004581. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1136/spcare-2023-004581\u003c/span\u003e\u003cspan address=\"10.1136/spcare-2023-004581\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi X, Li D, Qin S, Ye H, Lin M. Nomogram model for predicting long-term survival in esophageal cancer patients with metastasis after treatment: a SEER-based study. J Thorac Dis. 2024;16(10):6587\u0026ndash;601. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.21037/jtd-24-1100\u003c/span\u003e\u003cspan address=\"10.21037/jtd-24-1100\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFeng H, Zhang J, Zhang Y, et al. Association of tumor size with prognosis in colon cancer: a Surveillance, Epidemiology, and End Results (SEER) database analysis. Surgery. 2021;169(5):1116\u0026ndash;23. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/j.surg.2020.11.012\u003c/span\u003e\u003cspan address=\"10.1016/j.surg.2020.11.012\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQuirke P, Steele R, Monson J, Grieve R, Khanna S, Couture J, et al. Effect of the plane of surgery achieved on local recurrence in patients with operable rectal cancer: a prospective study using data from the MRC CR07 and NCIC-CTG CO16 randomised clinical trial. Lancet. 2009;373(9666):821\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1016/S0140-6736(09)60485-2\u003c/span\u003e\u003cspan address=\"10.1016/S0140-6736(09)60485-2\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArnold D, Lueza B, Douillard JY, Peeters M, Lenz HJ, Venook A, et al. Prognostic and predictive value of primary tumour side in patients with RAS wild-type metastatic colorectal cancer treated with chemotherapy and EGFR directed antibodies in six randomized trials. Ann Oncol. 2017;28(8):1713\u0026ndash;29. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1093/annonc/mdx175\u003c/span\u003e\u003cspan address=\"10.1093/annonc/mdx175\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVenook AP, Niedzwiecki D, Lenz H, et al. Effect of First-Line Chemotherapy Combined With Cetuximab or Bevacizumab on Overall Survival in Patients With KRAS Wild-Type Advanced or Metastatic Colorectal Cancer: A Randomized Clinical Trial. JAMA. 2017;317(23):2392\u0026ndash;401. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1001/jama.2017.7105\u003c/span\u003e\u003cspan address=\"10.1001/jama.2017.7105\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWarschkow R, Sulz MC, Marti L, Tarantino I, Schmied BM, Cerny T, et al. Better survival in right-sided versus left-sided stage I - III colon cancer patients. BMC Cancer. 2016;16:554. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.1186/s12885-016-2412-0\u003c/span\u003e\u003cspan address=\"10.1186/s12885-016-2412-0\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Colorectal Neoplasms, colorectal cancer, Prognosis, Artificial Intelligence, Data Mining, Predictive Models, Multivariate Analysis, Clinical Decision Support Systems","lastPublishedDoi":"10.21203/rs.3.rs-8789179/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8789179/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eColorectal cancer (CRC) is a biologically heterogeneous disease in which tumor sidedness has emerged as a relevant prognostic factor. Conventional TNM staging does not incorporate several clinically and biologically meaningful variables that may influence outcomes. In this context, artificial intelligence (AI) based approaches offer an opportunity to integrate complex clinicopathological data and improve prognostic stratification. This study aimed to evaluate clinicopathological variables associated with tumor sidedness and to identify clinical predictors of high-risk disease using an AI-based decision tree model.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis retrospective cohort study included 71 adults who underwent surgical resection for colorectal adenocarcinoma at a tertiary oncology center between 2020 and 2024 and had complete clinicopathological data available for analysis. Overall and progression-free survival were estimated using the Kaplan\u0026ndash;Meier method, and associations between categorical variables were assessed using Fisher\u0026rsquo;s exact test. Decision tree models were constructed using the J48 (C4.5) algorithm, and model performance was evaluated by leave-one-out cross-validation (LOOCV).\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eLeft-sided tumors were predominant and more frequently associated with alcohol ingestion (p\u0026thinsp;=\u0026thinsp;0.04), the use of neoadjuvant chemoradiotherapy (p\u0026thinsp;\u0026lt;\u0026thinsp;0.01), and higher mortality (p\u0026thinsp;=\u0026thinsp;0.04), despite more intensive treatment strategies. Right-sided tumors were prevalent in women and were associated with angiolymphatic invasion. In prognostic modeling, positive surgical margins emerged as the strongest predictor of mortality (Full 85.18%; LOOCV 74.07%). Among patients with negative margins, tumor laterality represented the most influential prognostic factor, with right-sided tumors associated with improved survival. Interestingly, younger patients showed shorter progression-free survival (Full 89.09%; LOOCV 76.36%).\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eTumor sidedness constitutes a meaningful prognostic dimension in CRC when integrated with established pathological factors. AI-based decision tree models can capture clinically coherent prognostic signatures and complement traditional staging systems, supporting their role as hypothesis-generating tools for individualized risk assessment and guiding future prospective validation.\u003c/p\u003e","manuscriptTitle":"Colorectal Cancer Sidedness: Prognostic Implications and the Predictive Role of Artificial Intelligence","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-02 09:25:57","doi":"10.21203/rs.3.rs-8789179/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-02T09:08:01+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"318099500000126188164406529489761224143","date":"2026-02-27T14:21:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-27T07:45:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"67736294286251094951986863245730155179","date":"2026-02-27T07:18:09+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-26T15:09:27+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-25T19:35:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73418801229016130204387742228622823588","date":"2026-02-25T19:10:50+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-25T15:46:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"101320839874762521771458136331368644568","date":"2026-02-25T15:00:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"196870862902866528779650491849070038611","date":"2026-02-25T11:26:06+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-25T11:05:02+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-24T10:27:17+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-10T11:47:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-10T11:41:27+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2026-02-04T17:21:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9b9225c1-8bb9-477b-a6fe-57d409fd8efd","owner":[],"postedDate":"March 2nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-30T07:09:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-02 09:25:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8789179","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8789179","identity":"rs-8789179","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}