Lymph node metastasis is strongly associated with lung metastasis as the first recurrence site in colorectal cancer

Preoperative identification of early extrahepatic recurrence after hepatectomy for colorectal liver metastases: A machine learning approach

BACKGROUND

Machine learning (ML) may provide novel insights into data patterns and improve model prediction accuracy. The current study sought to develop and validate an ML model to predict early extra-hepatic recurrence (EEHR) among patients undergoing resection of colorectal liver metastasis (CRLM).

METHODS

Patients with CRLM who underwent curative-intent resection between 2000 and 2020 were identified from an international multi-institutional database. An eXtreme gradient boosting (XGBoost) model was developed to estimate the risk of EEHR, defined as extrahepatic recurrence within 12 months after hepatectomy, using clinicopathological factors. The relative importance of factors was determined using Shapley additive explanations (SHAP) values.

RESULTS

Among 1410 patients undergoing curative-intent resection, 131 (9.3%) patients experienced EEHR. Median OS among patients with and without EEHR was 35.4 months (interquartile range [IQR] 29.9-46.7) versus 120.5 months (IQR 97.2-134.0), respectively (p < 0.001). The ML predictive model had c-index values of 0.77 (95% CI, 0.72-0.81) and 0.77 (95% CI, 0.73-0.80) in the entire dataset and the validation data set with bootstrapping resamples, respectively. The SHAP algorithm demonstrated that T and N primary tumor categories, as well as tumor burden score were the three most important predictors of EEHR. An easy-to-use risk calculator for EEHR was developed and made available online at: https://junkawashima.shinyapps.io/EEHR/.

CONCLUSIONS

An easy-to-use online calculator was developed using ML to help clinicians predict the chance of EEHR after curative-intent resection for CRLM. This tool may help clinicians in decision-making related to treatment strategies for patients with CRLM.

Machine learning for predicting liver and/or lung metastasis in colorectal cancer: A retrospective study based on the SEER database

OBJECTIVE

This study aims to establish a machine learning (ML) model for predicting the risk of liver and/or lung metastasis in colorectal cancer (CRC).

METHODS

Using the National Institutes of Health (NIH)'s Surveillance, Epidemiology, and End Results (SEER) database, a total of 51265 patients with pathological diagnosis of colorectal cancer from 2010 to 2015 were extracted for model development. On this basis, We have established 7 machine learning algorithm models. Evaluate the model based on accuracy, and AUC of receiver operating characteristics (ROC) and explain the relationship between clinical pathological features and target variables based on the best model. We validated the model among 196 colorectal cancer patients in Beijing Electric Power Hospital of Capital Medical University of China to evaluate its performance and universality. Finally, we have developed a network-based calculator using the best model to predict the risk of liver and/or lung metastasis in colorectal cancer patients.

RESULTS

51265 patients were enrolled in the study, of which 7864 (15.3 %) had distant liver and/or lung metastasis. RF had the best predictive ability, In the internal test set, with an accuracy of 0.895, AUC of 0.956, and AUPR of 0.896. In addition, the RF model was evaluated in the external validation set with an accuracy of 0.913, AUC of 0.912, and AUPR of 0.611.

CONCLUSION

In this study, we constructed an RF algorithm mode to predict the risk of colorectal liver and/or lung metastasis, to assist doctors in making clinical decisions.

Surgical and Interventional Management of Lung Metastasis: Surgical Assessment, Resection, Ablation, Percutaneous Interventions

The lungs are the second most common site of metastases for colorectal cancer after the liver. Pulmonary metastases can be identified at the time of diagnosis of the primary tumor, or metachronously. About 20% of patients with colorectal cancer will develop pulmonary metastases. The best options for treatment include a multidisciplinary treatment approach consisting of surgical resection whenever possible, and chemotherapy. Surgical options most often include minimally invasive segmentectomy or wedge resection, while patients unable to have surgery may benefit from radio frequency ablation or radiation treatment. Prognosis is dependent on preoperative carcinoembryonic antigen level, number, and location of metastatic lesions, and resectability of primary tumor. Overall, pulmonary metastases are best treated by complete resection whenever possible.

Identification of multiple risk factors for colorectal cancer relapse after laparoscopic radical resection

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.

A Machine Learning-Based Predictive Model for Predicting Lymph Node Metastasis in Patients With Ewing's Sarcoma

Objective

In order to provide reference for clinicians and bring convenience to clinical work, we seeked to develop and validate a risk prediction model for lymph node metastasis (LNM) of Ewing’s sarcoma (ES) based on machine learning (ML) algorithms.

Methods

Clinicopathological data of 923 ES patients from the Surveillance, Epidemiology, and End Results (SEER) database and 51 ES patients from multi-center external validation set were retrospectively collected. We applied ML algorithms to establish a risk prediction model. Model performance was checked using 10-fold cross-validation in the training set and receiver operating characteristic (ROC) curve analysis in external validation set. After determining the best model, a web-based calculator was made to promote the clinical application.

Results

LNM was confirmed or unable to evaluate in 13.86% (135 out of 974) ES patients. In multivariate logistic regression, race, T stage, M stage and lung metastases were independent predictors for LNM in ES. Six prediction models were established using random forest (RF), naive Bayes classifier (NBC), decision tree (DT), xgboost (XGB), gradient boosting machine (GBM), logistic regression (LR). In 10-fold cross-validation, the average area under curve (AUC) ranked from 0.705 to 0.764. In ROC curve analysis, AUC ranged from 0.612 to 0.727. The performance of the RF model ranked best. Accordingly, a web-based calculator was developed (https://share.streamlit.io/liuwencai2/es_lnm/main/es_lnm.py).

Conclusion

With the help of clinicopathological data, clinicians can better identify LNM in ES patients. Risk prediction models established in this study performed well, especially the RF model.