BACKGROUND Colorectal cancer(CRC)is a significant global health issue,and lymph node metastasis(LNM)is a crucial prognostic factor.Accurate prediction of LNM is essential for developing individualized treatment strate...BACKGROUND Colorectal cancer(CRC)is a significant global health issue,and lymph node metastasis(LNM)is a crucial prognostic factor.Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC.However,the prediction of LNM is challenging and depends on various factors such as tumor histology,clinicopathological features,and molecular characteristics.The most reliable method to detect LNM is the histopathological examination of surgically resected specimens;however,this method is invasive,time-consuming,and subject to sampling errors and interobserver variability.AIM To analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue.METHODS This study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021.A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors.RESULTS The prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables.The model achieved high accuracy(0.86),sensitivity(0.81),specificity(0.87),positive predictive value(0.66),negative predictive value(0.94),area under the curve for the receiver operating characteristic(0.91),and a low Brier score(0.10).The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds,indicating good calibration and clinical utility.CONCLUSION The present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC.This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables,demonstrating superior performance and clinical applicability compared to existing models.The study provides new insights into the potential of deep learning to extract valuable information from tumor histology,in turn,improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.展开更多
BACKGROUND Colorectal cancer(CRC)is a common life-threatening disease that often requires surgical intervention,such as laparoscopic radical resection.However,despite successful surgeries,some patients experience dise...BACKGROUND Colorectal cancer(CRC)is a common life-threatening disease that often requires surgical intervention,such as laparoscopic radical resection.However,despite successful surgeries,some patients experience disease relapse.Identifying the risk factors for CRC relapse can help guide clinical interventions and improve patient outcomes.AIM To determine the risk factors that may lead to CRC relapse after laparoscopic radical resection.METHODS We performed a retrospective analysis using the baseline data of 140 patients with CRC admitted to our hospital between January 2018 and January 2020.All included participants were followed up until death or for 3 years.The baseline data and laboratory indicators were compared between the patients who experienced relapse and those who did not experienced relapse.RESULTS Among the 140 patients with CRC,30 experienced relapse within 3 years after laparoscopic radical resection and 110 did not experience relapse.The relapse group had a higher frequency of rectal tumors with low differentiation and lymphatic vessel invasion than that of the non-relapse group.The expression of serum markers and the prognostic nutritional index were lower,whereas the neutrophil-to-lymphocyte ratio,expression of cytokeratin 19 fragment antigen 21-1,vascular endothelial growth factor,and Chitinase-3-like protein 1 were significantly higher in the relapse group than those in the non-relapse group.The groups did not differ significantly based on other parameters.Logistic regression analysis revealed that all the above significantly altered factors were independent risk factors for CRC relapse.CONCLUSION We identified multiple risk factors for CRC relapse following surgery,which can be considered for the clinical monitoring of patients to reduce disease recurrence and improve patient survival.展开更多
文摘BACKGROUND Colorectal cancer(CRC)is a significant global health issue,and lymph node metastasis(LNM)is a crucial prognostic factor.Accurate prediction of LNM is essential for developing individualized treatment strategies for patients with CRC.However,the prediction of LNM is challenging and depends on various factors such as tumor histology,clinicopathological features,and molecular characteristics.The most reliable method to detect LNM is the histopathological examination of surgically resected specimens;however,this method is invasive,time-consuming,and subject to sampling errors and interobserver variability.AIM To analyze influencing factors and develop and validate a risk prediction model for LNM in CRC based on a large patient queue.METHODS This study retrospectively analyzed 300 patients who underwent CRC surgery at two Peking University Shenzhen hospitals between January and December 2021.A deep learning approach was used to extract features potentially associated with LNM from primary tumor histological images while a logistic regression model was employed to predict LNM in CRC using machine-learning-derived features and clinicopathological variables as predictors.RESULTS The prediction model constructed for LNM in CRC was based on a logistic regression framework that incorporated machine learning-extracted features and clinicopathological variables.The model achieved high accuracy(0.86),sensitivity(0.81),specificity(0.87),positive predictive value(0.66),negative predictive value(0.94),area under the curve for the receiver operating characteristic(0.91),and a low Brier score(0.10).The model showed good agreement between the observed and predicted probabilities of LNM across a range of risk thresholds,indicating good calibration and clinical utility.CONCLUSION The present study successfully developed and validated a potent and effective risk-prediction model for LNM in patients with CRC.This model utilizes machine-learning-derived features extracted from primary tumor histology and clinicopathological variables,demonstrating superior performance and clinical applicability compared to existing models.The study provides new insights into the potential of deep learning to extract valuable information from tumor histology,in turn,improving the prediction of LNM in CRC and facilitate risk stratification and decision-making in clinical practice.
文摘BACKGROUND Colorectal cancer(CRC)is a common life-threatening disease that often requires surgical intervention,such as laparoscopic radical resection.However,despite successful surgeries,some patients experience disease relapse.Identifying the risk factors for CRC relapse can help guide clinical interventions and improve patient outcomes.AIM To determine the risk factors that may lead to CRC relapse after laparoscopic radical resection.METHODS We performed a retrospective analysis using the baseline data of 140 patients with CRC admitted to our hospital between January 2018 and January 2020.All included participants were followed up until death or for 3 years.The baseline data and laboratory indicators were compared between the patients who experienced relapse and those who did not experienced relapse.RESULTS Among the 140 patients with CRC,30 experienced relapse within 3 years after laparoscopic radical resection and 110 did not experience relapse.The relapse group had a higher frequency of rectal tumors with low differentiation and lymphatic vessel invasion than that of the non-relapse group.The expression of serum markers and the prognostic nutritional index were lower,whereas the neutrophil-to-lymphocyte ratio,expression of cytokeratin 19 fragment antigen 21-1,vascular endothelial growth factor,and Chitinase-3-like protein 1 were significantly higher in the relapse group than those in the non-relapse group.The groups did not differ significantly based on other parameters.Logistic regression analysis revealed that all the above significantly altered factors were independent risk factors for CRC relapse.CONCLUSION We identified multiple risk factors for CRC relapse following surgery,which can be considered for the clinical monitoring of patients to reduce disease recurrence and improve patient survival.
