Application Value of Combined Detection of NLR, PNI, D-Dimer, CD3+ T Lymphocytes, and CEA in Colorectal Cancer Screening

Risk factors analysis and the establishment of nomogram prediction model for PICC-related venous thrombosis in patients with lymphoma: a double-center cohort-based case-control study

Objective

The objective of this study is to examine the risk factors associated with the occurrence of PICC-Related Venous Thrombosis (PICC-RVTE) in individuals diagnosed with lymphoma, as well as to develop a predictive risk nomogram model.

Methods

A total of 215 patients with lymphoma treated at Yunnan Provincial Tumor Hospital from January 2017 to December 2020 were retrospectively evaluated as the training cohort; 90 patients with lymphoma treated at the Department of Oncology of the First People's Hospital of Anning, Affiliated to Kunming University of Science and Technology during the January 2021 to September 2023 were evaluated as the validation cohort. Independent influencing factors were analyzed by logistic regression, a nomogram was developed and validated, and the model was evaluated using internal and external data cohorts for validation.

Results

A total of 305 lymphoma patients were selected and 35 (11.48%) PICC-RVTE occurred, the median time was 13 days. The incidence within 1-2week was 65.71%. Multivariate analysis suggested that the activity amount, thrombosis history(within the last 12 months), ATIII, Total cholesterol and D-dimer levels were independently associated with PICC-RVTE, and a nomogram was constructed based on the multivariate analysis. ROC analysis indicated good discrimination in the training set (area under the curve [AUC] = 0.907, 95%CI:0.850-0.964) and the testing set (AUC = 0.896, 95%CI: 0.782-1.000) for the PICC-RVTE nomogram. The calibration curves showed good calibration abilities, and the decision curves indicated the clinical usefulness of the prediction nomograms.

Conclusions

Patients should be advised to undergo color Doppler ultrasound system testing within two week after the implantation of a PICC catheter to detect PICC-RVTE at an early stage. The validated nomogram can be used to predict the risk of catheter-related thrombosis (CRT) in patients with lymphoma who received at least one chemotherapy after PICC catheterization, no bleeding tendency, no recent history of anticoagulant exposure and no severe heart, lung, renal insufficiency. This model has the potential to assist clinicians in formulating individualized treatment strategies for each patient.

Machine learning algorithms to predict atypical metastasis of colorectal cancer patients after surgical resection

Background

The prognosis of colorectal cancer with atypical metastasis is poor. However, atypical metastasis was less common and under-appreciated.

Methods

In this study we attempted to present the first machine learning models to predict the risk of atypical metastasis in colorectal cancer patients. We evaluated the differences between metastasis and non-metastasis groups, assessed factors associated with atypical metastasis using univariate and multivariate logistic regression analyses, and preliminarily developed the multiple machine learning models to predict atypical metastasis.

Results

168 patients were included. Prognostic Nutritional Index (PNI) [OR =  0.998; P = 0.030], Cancer antigen 19-9 (CA19-9) [OR = 1.011; P = 0.043] and MR-Distance [-mid OR = 0.289; P = 0.009] [-high OR = 0.248; P = 0.021] were shown to be independent risk factors for the atypical metastasis via multivariate analysis. Furthermore, the machine learning model based on AdaBoost algorithm (AUC: 0736) has better predictive performance comparing to Logistic Regression (AUC: 0.671) and KNeighbors Classifier (AUC: 0.618) by area under the curve (AUC) in the validation cohorts. The accuracy, sensitivity, and specificity of the model trained using the Adaboost method in the validation set are 0.786, 0.776 and 0.700, while 0.601, 0.933, 0.508 using Logistic Regression and 0.743, 0.390, 0.831 using KNeighbors Classifier.

Conclusion

Machine-learning approaches containing PNI, CA19-9 and MR-Distance show great potentials in atypical metastasis prediction.

A Nomogram Combining Neutrophil-to-Lymphocyte Ratio and D-Dimer Predicts Chemosensitivity of Oxaliplatin-Based First-Line Chemotherapy in Patients with Unresectable Advanced Gastric Cancer

Introduction: No effective peripheral blood predictors have been establoshed for first-line chemotherapy in patients with advanced gastric cancer. In this study, a nomogram combining the neutrophil-to-lymphocyte ratio/D-dimer with gender, number of metastases, and histological grade was established to predict progression-free survival in patients with unresectable advanced gastric cancer. Methods: We retrospectively collected baseline clinical characteristics and blood parameters from 153 patients diagnosed with advanced gastric cancer that underwent oxaliplatin-based first-line chemotherapy. Kaplan–Meier analysis and Cox regression analysis were used to determine the factors associated with progression-free survival. The concordance index (C-index) and calibration curve were used to determine the prediction accuracy and discriminative ability of the nomogram as a visual complement to the prognostic score system. Results: Determined by the X-tile software, the optimal cut-off points for the neutrophil-to-lymphocyte ratio and D-dimer were 3.18 and 0.56 mg/L, respectively. Multivariate analysis identified four independent prognostic factors: two or more metastatic organs (HR: 1.562, 95% CI: 1.009-2.418, P = .046), poor differentiation (HR: 0.308, 95% CI: 0.194-0.487, P < .001), neutrophil-to-lymphocyte ratio >3.18 (HR: 1.427, 95% CI: 1.024-1.989, P = .036), and D-dimer >0.56 mg/L (HR: 1.811, 95% CI: 1.183-2.773, P = .006). Receiver operating characteristic curves showed that the combination of the neutrophil-to-lymphocyte ratio and D-dimer in the prediction model exhibited the highest predictive performance (area under the curve, 0.800). The prognostic nomogram yielded a C-index of 0.800. Decision curve analysis demonstrated that the prognostic nomogram was clinically useful. A nomogram-based risk classification system was also constructed to facilitate risk stratification of advanced gastric cancer for optimal clinical management. Conclusion: We identified the neutrophil-to-lymphocyte ratio and D-dimer level as independent prognostic factors for advanced gastric cancer. The prognostic nomogram combining the neutrophil-to-lymphocyte ratio and D-dimer level can be applied in the individualized prediction of treatment outcome in patients with advanced gastric cancer.