Predicting metachronous liver metastasis in patients with colorectal cancer: development and assessment of a new nomogram

Predictive modeling algorithms for liver metastasis in colorectal cancer: A systematic review of the current literature

This study aims to assess the quality and performance of predictive models for colorectal cancer liver metastasis (CRCLM). A systematic review was performed to identify relevant studies from various databases. Studies that described or validated predictive models for CRCLM were included. The methodological quality of the predictive models was assessed. Model performance was evaluated by the reported area under the receiver operating characteristic curve (AUC). Of the 117 articles screened, seven studies comprising 14 predictive models were included. The distribution of included predictive models was as follows: radiomics (n = 3), logistic regression (n = 3), Cox regression (n = 2), nomogram (n = 3), support vector machine (SVM, n = 2), random forest (n = 2), and convolutional neural network (CNN, n = 2). Age, sex, carcinoembryonic antigen, and tumor staging (T and N stage) were the most frequently used clinicopathological predictors for CRCLM. The mean AUCs ranged from 0.697 to 0.870, with 86% of the models demonstrating clear discriminative ability (AUC > 0.70). A hybrid approach combining clinical and radiomic features with SVM provided the best performance, achieving an AUC of 0.870. The overall risk of bias was identified as high in 71% of the included studies. This review highlights the potential of predictive modeling to accurately predict the occurrence of CRCLM. Integrating clinicopathological and radiomic features with machine learning algorithms demonstrates superior predictive capabilities.

A nomogram prediction model based on clinicopathological combined radiological features for metachronous liver metastasis of colorectal cancer

Objective: To establish a nomogram prediction model (based on clinicopathological and radiological features) for the development of metachronous liver metastasis (MLM) in patients with colorectal cancer (CRC). Methods: This retrospective study included patients with CRC who underwent surgery at Changshu No.1 People's Hospital and the Second Affiliated Hospital of Soochow University between January 2016 and December 2018. The clinical, pathological, and radiological features of each patient were investigated. Risk factors for MLM were identified by univariable and multivariable analyses. The predictive nomogram for MLM development was constructed. The predictive performance of the nomogram was estimated by the receiver operating characteristics curve, calibration curve, and decision curve analysis. Results: This study included 161 patients with CRC [median age: 66 (range, 33-87) years]. Fifty-nine developed MLM after a median of 12 (range, 2-52) months after surgery. The multivariable logistic regression analysis showed that age >66 years (OR=3.471, 95% CI: 1.272-9.473, P=0.015), N2 stage (OR=6.534, 95% CI: 1.456-29.317, P=0.014), positive vascular invasion (OR=2.995, 95% CI: 1.132-7.926, P=0.027), positive tumor deposit (OR=4.451, 95% CI: 1.153-17.179, P=0.030), and linear (OR=6.774, 95% CI: 1.306-35.135, P=0.023) and nodal pericolic fat infiltration patterns (OR=8.762, 95% CI: 1.521-50.457, P=0.015) were independently associated with MLM. These five factors were used to create a nomogram. The area under the receiver operating characteristics curve of the nomogram was 0.866 (95% CI: 0.803-0.914), indicating favorable prediction performance. The calibration curve of the nomogram showed a satisfactory agreement between the predicted and actual probabilities. Conclusions: A nomogram prediction model based on five clinicopathological and radiological features might have favorable prediction performance for MLM in patients who underwent surgery for CRC. Hence, the present study proposes a nomogram that can easily be used to predict MLM after CRC surgery based on readily available features.

A nomogram was developed using clinicopathological features to predict postoperative liver metastasis in patients with colorectal cancer

PURPOSE

The objective of this study is to examine the risk factors that contribute to the development of liver metastasis (LM) in patients who have suffered radical resection for colorectal cancer (CRC), and to establish a nomogram model that can be used to predict the occurrence of the LM.

METHODS

The present study enrolled 1377 patients diagnosed with CRC between January 2010 and July 2021. The datasets were allocated to training (n = 965) and validation (n = 412) sets in a randomly stratified manner. The study utilized univariate and multivariate logistic regression analyses to establish a nomogram for predicting LM in patients with CRC.

RESULTS

Multivariate analysis revealed that T stage, N stage, number of harvested lymph nodes (LNH), mismatch repair (MMR) status, neutrophil count, monocyte count, postoperative carcinoembryonic antigen (CEA) levels, postoperative cancer antigen 125 (CA125) levels, and postoperative carbohydrate antigen 19-9 (CA19-9) levels were independent predictive factors for LM after radical resection. These factors were then utilized to construct a comprehensive nomogram for predicting LM. The nomogram demonstrated great discrimination, with an area under the curve (AUC) of 0.782 for the training set and 0.768 for the validation set. Additionally, the nomogram exhibited excellent calibration and significant clinical benefit as confirmed by the calibration curves and the decision curve analysis, respectively.

CONCLUSION

This nomogram has the potential to support clinicians in identifying high-risk patients who may develop LM post-surgery. Clinicians can devise personalized treatment and follow-up plans, ultimately leading to an improved prognosis for patients.

Complete Blood Count Alterations Prior to the Diagnosis of Colorectal Cancer May Help in the Detection of Synchronous Liver Metastases

Background and Aims: Colorectal cancer (CRC) represents 10% of all cancers worldwide with the highest incidence in developed countries; its incidence is also increasing in middle- and low-income countries. Population screening programs facilitate early diagnosis of the disease. When the diagnosis is carried out in advanced stages, approximately 80% of patients with liver metastases (LM) are considered unresectable at the time of diagnosis. In our study, variations in blood counts prior to CRC diagnosis were analyzed to assess whether they could be useful in identifying smaller, more manageable metastases at earlier stages for more effective treatment. Methods: A study was carried out using complete blood counts (CBCs) from CRC patients, obtained from primary health centers and the La Ribera University Hospital within La Ribera Health Department, Valencian Community, Spain, between July 2012 and September 2020. Data from CRC patients who presented synchronous liver metastasis (CRLM) were compared with those with CRC without LM at diagnosis (CRC patients). Results: Our analysis shows that at least 15 months before CRC diagnosis, a progressive alteration was observed in CBC parameters in both groups. A higher incidence of anemia (p < 0.001) was observed among CRLM patients in the three months prior to CRC diagnosis than in CRC patients showing no LM. Conclusions: A statistically significant deterioration of CBC was observed in patients with advanced-stage CRC and synchronous or early LM (CRLM) in the three months prior to diagnosis. The primary goal of incorporating CBC variations into predictive models is to identify individuals who are at a greater risk of developing metastatic colon cancer, leading to early diagnosis. Our research improves these models by highlighting a more pronounced and rapid decline in hemoglobin levels among CRLM patients. Identification of metastases at an earlier stage when they are smaller, more manageable, and more amenable to treatment may be a valuable tool to prevent their further progression.

Establishment and validation of a predictive model of recurrence in primary hepatocellular carcinoma after resection

Background

In recent years, nomogram prediction models have been widely used to evaluate the prognosis of various diseases. However, studies in primary hepatocellular carcinoma (HCC) are limited. This study sought to explore the risk factors of recurrence of patients with primary HCC after surgical resection and establish a nomogram prediction model.

Methods

The data of 424 patients with primary HCC who had been admitted to the Wuhan Third Hospital were retrospectively collected. The patients were followed-up for 5 years after surgery. The patients were divided into the recurrence group (n=189) and control group (n=235) according to whether the cancer recurred after surgery. The differences in the clinical characteristics between the two groups were analyzed. The risk factors of recurrence after surgical resection of primary HCC were also analyzed, and a prediction model was then established using R4.0.3 statistical software.

Results

There were significant statistical differences between the two groups in terms of the tumor size, systemic immune-inflammation (SII) index, the number of lesions, tumor differentiation degree, ascites, vascular invasion, and portal vein tumor thrombus (P<0.05). The multivariate regression analysis showed that multiple foci, poorly differentiated tumors, ascites, vascular invasion, and portal vein tumor thrombus were risk factors for the recurrence of primary HCC in patients after surgical resection (P<0.05). The data set was randomly divided into a training set and verification set. The sample size of the training set was 297, and the sample size of the verification set was 127. The area under the receiver operating characteristic (ROC) curve of the training set was 0.866 [95% confidence interval (CI): 0.824-0.907], and the area under the ROC curve of the validation set was 0.812 (95% CI: 0.734-0.890). The Hosmer-Lemeshow Goodness-of-Fit Test was used to test the model with the validation set (χ2=11.243, P=0.188), which indicated that the model had high value in predicting the recurrence of primary HCC after surgical resection.

Conclusions

This model had high value in predicting the recurrence of primary HCC in patients after surgical resection. This model could assist clinicians to assess the prognosis of patients. Intensive treatment for high-risk patients might improve the prognosis of patients.

Effect of abdominal aortic calcification on the prognosis and recurrence of colorectal cancer stages II-III: A retrospective cohort study

PURPOSE

Abdominal aortic calcification (AAC) is a well-known risk marker for cardiovascular disease. However, its clinical effect on patients who underwent radical surgery for colorectal cancer (CRC) stages II-III is unclear. This study aimed to analyze the associations between AAC and prognosis of patients with stage II-III CRC.

METHODS

To evaluate the effect of AAC on clinical outcomes, prognosis, and metastatic patterns of CRC, we analyzed 362 patients who underwent radical surgery for stage II-III CRC between 2010 and 2018.

RESULTS

The high AAC group had significantly worse overall survival (OS), cancer-specific survival (CSS), and recurrence-free survival (RFS) after propensity score matching to adjust for differences in baseline characteristics of patients and tumors. In the multivariate Cox regression analyses, a high AAC was an independent risk factor for poor OS (hazard ratio [HR], 2.38; 95% confidence interval [CI], 1.23-4.59; p = 0.01), poor CSS (HR, 5.22; 95% CI, 1.74-15.6; p < 0.01), and poor RFS (HR, 1.83; 95% CI, 1.19-2.83; p < 0.01). A high AAC was not associated with a risk of lung metastasis or local or peritoneal recurrence, but a risk for liver metastasis of CRC.

CONCLUSION

A high AAC showed a strong relationship with poor OS, CSS, and RFS after curative resection for stage II-III CRC. A high AAC was also associated with a risk for liver metastasis, which may worsen the prognosis in stage II-III CRC. AAC could be a new clinical tool for predicting the prognosis for patients in stage II-III CRC.

Development and validation of a nomogram for predicting metachronous peritoneal metastasis in colorectal cancer: A retrospective study

BACKGROUND

Peritoneal metastasis (PM) after primary surgery for colorectal cancer (CRC) has the worst prognosis. Prediction and early detection of metachronous PM (m-PM) have an important role in improving postoperative prognosis of CRC. However, commonly used imaging methods have limited sensitivity to detect PM early. We aimed to establish a nomogram model to evaluate the individual probability of m-PM to facilitate early interventions for high-risk patients.

AIM

To establish and validate a nomogram model for predicting the occurrence of m-PM in CRC within 3 years after surgery.

METHODS

We used the clinical data of 878 patients at the Second Hospital of Jilin University, between January 1, 2014 and January 31, 2019. The patients were randomly divided into training and validation cohorts at a ratio of 2:1. The least absolute shrinkage and selection operator (LASSO) regression was performed to identify the variables with nonzero coefficients to predict the risk of m-PM. Multivariate logistic regression was used to verify the selected variables and to develop the predictive nomogram model. Harrell’s concordance index, receiver operating characteristic curve, Brier score, and decision curve analysis (DCA) were used to evaluate discrimination, distinctiveness, validity, and clinical utility of this nomogram model. The model was verified internally using bootstrapping method and verified externally using validation cohort.

RESULTS

LASSO regression analysis identified six potential risk factors with nonzero coefficients. Multivariate logistic regression confirmed the risk factors to be independent. Based on the results of two regression analyses, a nomogram model was established. The nomogram included six predictors: Tumor site, histological type, pathological T stage, carbohydrate antigen 125, v-raf murine sarcoma viral oncogene homolog B mutation and microsatellite instability status. The model achieved good predictive accuracy on both the training and validation datasets. The C-index, area under the curve, and Brier scores were 0.796, 0.796 [95% confidence interval (CI) 0.735-0.856], and 0.081 for the training cohort and 0.782, 0.782 (95%CI 0.690-0.874), and 0.089 for the validation cohort, respectively. DCA showed that when the threshold probability was between 0.01 and 0.90, using this model to predict m-PM achieved a net clinical benefit.

CONCLUSION

We have established and validated a nomogram model to predict m-PM in patients undergoing curative surgery, which shows good discrimination and high accuracy.

Whole-liver enhanced CT radiomics analysis to predict metachronous liver metastases after rectal cancer surgery

Background

To develop a radiomics model based on pretreatment whole-liver portal venous phase (PVP) contrast-enhanced CT (CE-CT) images for predicting metachronous liver metastases (MLM) within 24 months after rectal cancer (RC) surgery.

Methods

This study retrospectively analyzed 112 RC patients without preoperative liver metastases who underwent rectal surgery between January 2015 and December 2017 at our institution. Volume of interest (VOI) segmentation of the whole-liver was performed on the PVP CE-CT images. All 1316 radiomics features were extracted automatically. The maximum-relevance and minimum-redundancy and least absolute shrinkage and selection operator methods were used for features selection and radiomics signature constructing. Three models based on radiomics features (radiomics model), clinical features (clinical model), and radiomics combined with clinical features (combined model) were built by multivariable logistic regression analysis. Receiver operating characteristic (ROC) curves were used to assess the diagnostic performance of models, and calibration curve and the decision curve analysis were performed to evaluate the clinical application value.

Results

In total, 52 patients in the MLM group and 60 patients in the non-MLM group were enrolled in this study. The radscore was built using 16 selected features and the corresponding coefficients. Both the radiomics model and the combined model showed higher diagnostic performance than clinical model (AUCs of training set: radiomics model 0.84 (95% CI, 0.76–0.93), clinical model 0.65 (95% CI, 0.55–0.75), combined model 0.85 (95% CI, 0.77–0.94); AUCs of validation set: radiomics model 0.84 (95% CI, 0.70–0.98), clinical model 0.58 (95% CI, 0.40–0.76), combined model 0.85 (95% CI, 0.71–0.99)). The calibration curves showed great consistency between the predicted value and actual event probability. The DCA showed that both the radiomics and combined models could add a net benefit on a large scale.

Conclusions

The radiomics model based on preoperative whole-liver PVP CE-CT could predict MLM within 24 months after RC surgery. Clinical features could not significantly improve the prediction efficiency of the radiomics model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40644-022-00485-z.