Machine learning model for prediction of permanent stoma after anterior resection of rectal cancer: A multicenter study.

BACKGROUND: The conversion from a temporary to a permanent stoma (PS) following rectal cancer surgery significantly impacts the quality of life of patients. However, there is currently a lack of practical preoperative tools to predict PS formation. The purpose of this study is to establish a preoperative predictive model for PS using machine learning algorithms to guide clinical practice. METHODS: In this retrospective study, we analyzed clinical data from a total of 655 patients who underwent anterior resection for rectal cancer, with 552 patients from one medical center and 103 from another. Through machine learning algorithms, five predictive models were developed, and each was thoroughly evaluated for predictive performance. The model with superior predictive accuracy underwent additional validation using both an independent testing cohort and the external validation cohort. The Shapley Additive exPlanations (SHAP) approach was employed to elucidate the predictive factors influencing the model, providing an in-depth visual analysis of its decision-making process. RESULTS: Eight variables were selected for the construction of the model. The support vector machine (SVM) model exhibited superior predictive performance in the training set, evidenced by an AUC of 0.854 (95 % CI:0.803-0.904). This performance was corroborated in both the testing set and external validation set, where the model demonstrated an AUC of 0.851 (95%CI:0.748-0.954) and 0.815 (95%CI:0.710-0.919), respectively, indicating its efficacy in identifying the PS. CONCLUSIONS: The model(https://yangsu2023.shinyapps.io/psrisk/) indicated robust predictive performance in identifying PS after anterior resection for rectal cancer, potentially guiding surgeons in the preoperative stratification of patients, thus informing individualized treatment plans and improving patient outcomes.

Automated machine learning-based model for predicting benign anastomotic strictures in patients with rectal cancer who have received anterior resection.

BACKGROUND: Benign anastomotic strictures (BAS) significantly impact patients' quality of life and long-term prognosis. However, the current clinical practice lacks accurate tools for predicting BAS. This study aimed to develop a machine-learning model to predict BAS in patients with rectal cancer who have undergone anterior resection. METHODS: Data from 1973 patients who underwent anterior resection for rectal cancer were collected. Multiple machine learning classification models were integrated to analyze the data and identify the optimal model. Model performance was evaluated using receiver operator characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves. The Shapley Additive exPlanation (SHAP) algorithm was utilized to assess the impact of various clinical characteristics on the optimal model to enhance the interpretability of the model results. RESULTS: A total of 10 clinical features were considered in constructing the machine learning model. The model evaluation results indicated that the random forest (RF)model was optimal, with the area under the test set curve (AUC: 0.888, 95% CI: 0.810-0.965), accuracy: 0.792, sensitivity: 0.846, specificity: 0.791. The SHAP algorithm analysis identified prophylactic ileostomy, operative time, and anastomotic leakage as significant contributing factors influencing the predictions of the RF model. CONCLUSION: We developed a robust machine-learning model and user-friendly online prediction tool for predicting BAS following anterior resection of rectal cancer. This tool offers a potential foundation for BAS prevention and aids clinical practice by enabling more efficient disease management and precise medical interventions.

Over-expression of SOX8 predicts poor prognosis in colorectal cancer: A retrospective study.

Aberrant expression of SRY-box 8 (SOX8) is closely correlated with the development and progression of many types of cancers in human. Limited studies report the relationship between SOX8 expression and overall survival in colorectal cancer (CRC). This study aimed to collect the pathological tissues and clinical data in order to analyze the relationship between SOX8 expression and clinicopathological parameters and prognosis of CRC patients. Tissue microarrays were constructed from 424 primary CRC patients with clinicopathological information and follow-up data. Immunohistochemistry (IHC) was performed on tissue microarrays to explore the relationship between SOX8 expression and clinicopathological information and patient's prognosis. The expression of SOX8 was higher in CRC tissues than that in non-tumor adjacent tissues (NATs, P <.001). High expression of SOX8 was associated with tumor stage (P = .04) and shorter overall survival (OS) after operation of patients (P = .004). Subsequently, univariate COX analysis identified that high expression of SOX8 (P = .004), differentiation (P = .006), distant metastasis (P <.001), tumor stage (P = .003), and higher rate of lymph node metastasis (P <.001), all significantly predicted decrease in OS. Multivariate analysis demonstrated that distant metastasis (P <.001), high SOX8 expression, (P = .013) and lymph node metastasis (P <.001) were independent poor prognostic factors in CRC patients. This study showed that SOX8 is over-expressed in patients with high T stage, which affects the outcome of prognosis in CRC patients. High expression of SOX8 usually has a poor independent prognostic factor for CRC.

Expression of Aldehyde Dehydrogenase 1A1 (ALDH1A1) as a Prognostic Biomarker in Colorectal Cancer Using Immunohistochemistry.

BACKGROUND The expression of aldehyde dehydrogenase 1A1 (ALDH1A1) is increased in several human tumors, including colorectal carcinoma (CRC). The aim of this study was to compare the expression ALDH1A1 in CRC tumor tissue compared with non-tumor adjacent tissue (NAT), using immunohistochemistry (IHC), and to determine whether the expression of the ALDH1A1 protein was associated with prognostic factors in CRC. MATERIAL AND METHODS Formalin-fixed paraffin-embedded (FFPE) tissue from 424 patients diagnosed with CRC, and 196 matched NATs were used to prepare tissue microarrays (TMAs). IHC was performed using an immunoperoxidase method with a primary polyclonal rabbit anti-ALDH1A1 antibody. The IHC scores by light microscopy were the staining intensity (scored from 0-3) multiplied by the percentage area of positive immunostaining within the visual field (scored from 0-4). Associations between tumor expression levels of ALDH1A1 and patient clinicopathological characteristics, including tumor grade, size, and TNM stage at surgery were analyzed. RESULTS ALDH1A1 protein expression was significantly increased in CRC tissues compared with matched NATs. In patients with CRC, increased expression of the ALDH1A1 protein was significantly associated with the presence of lymph node metastasis: 64.28% in N0 cases; 75.49% in N1 cases; and 82.14% in N2 cases, (P=0.002). Univariate and multivariate analysis showed that ALDH1A1 expression was an independent prognostic marker for CRC (P<0.001). CONCLUSIONS Using IHC, the expression of the ALDH1A1 protein in CRC tissues was significantly associated with the presence of lymph node metastases and might be a potential prognostic marker in patients with CRC.