The early response to concurrent chemoradiotherapy in patients with locally advanced nasopharyngeal carcinoma (LA-NPC) is closely correlated with prognosis. In this study, we aimed to predict early response using a combined model that combines sub-regional radiomics features from multi-sequence MRI with clinically relevant factors. A total of 104 patients with LA-NPC were randomly divided into training and test cohorts at a ratio of 3:1. Radiomic features were extracted from subregions within the tumor area using the K-means clustering method, and feature selection was performed using LASSO regression. Four models were established: a radiomics model, a clinical model, an Intratumor Heterogeneity (ITH) score-based model and a combined model that integrates the ITH score with clinical factors. The predictive performance of these models was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Among the models, the combined model incorporating the ITH score and clinical factors exhibited the highest predictive performance in the test cohort (AUC=0.838). Additionally, the models based on ITH score showed superior prognostic value in both the training cohort (AUC=0.888) and the test cohort (AUC=0.833). The combined model that integrates the ITH score with clinical factors exhibited superior performance in predicting early response following concurrent chemoradiotherapy in patients with LA-NPC.
Objective: The purpose of the study is to develop a prognosis nomogram for esophageal squamous cell carcinoma (ESCC) patients with radical resection and to identify patients who may benefit from postoperative adjuvant radiotherapy/chemoradiotherapy through survival risk stratification. Methods: We retrospectively enrolled patients who underwent esophagectomy in the First Affiliated Hospital of Nanjing Medical University from July 2015 to June 2017. Patients with stage I-III esophageal squamous cell carcinoma who received radical R0 resection with or without postoperative adjuvant radiotherapy/chemoradiotherapy were included. Further, patients were randomly allocated into two groups (training and validation cohorts) with a distribution ratio of 7:3. The prognosis nomogram was constructed based on independent factors determined by univariate and multivariate Cox analyses. The area under the receiver operating characteristic curve (AUC) and calibration curve were adopted to evaluate the discriminative ability and reliability of the nomogram. The accuracy and clinical practicability were respectively assessed by C-index values and decision curve analysis (DCA), and further contrasted the nomogram model and the eighth edition of the American Joint Committee on Cancer (AJCC) TNM staging system. In addition, survival risk stratification was further performed according to the nomogram, and the effect of postoperative adjuvant therapy on each risk group was appraised by the Kaplan-Meier survival analysis. Results: A total of 399 patients with esophageal squamous cell carcinoma were recruited in this study, including the training cohort (n = 280) and the validation cohort (n = 119). The nomogram-related AUC values for 1, 3, and 5-year OS were 0.900, 0.795, and 0.802, respectively, and 0.800, 0.865, 0.829 in the validation cohort, respectively. The slope of the calibration curve for both cohorts was close to 1, indicating good consistency. The C-index value of the nomogram was 0.769, which was higher than that of the AJCC 8th TNM staging system by 0.061 (p < 0.001). Based on the prognosis nomogram, patients were stratified into three risk groups (low, medium, and high), and there were obvious differences in prognosis among the groups (p < 0.001). Furthermore, postoperative adjuvant therapy has been shown to enhance the 5-year survival rate by over 15% among patients classified as medium- and high-risk. Conclusion: The constructed nomogram as developed resulted in accurate and effective prediction performance in survival outcomes for patients with stage I-III esophageal squamous cell carcinoma who underwent radical R0 resection, which is superior to the AJCC 8th TNM staging system. The survival risk stratification had potential clinical application to guide further personalized adjuvant therapy.
Objective: Tumor residue after concurrent chemoradiotherapy (CCRT) in nasopharyngeal carcinoma (NPC) patients often predicts poor prognosis. Thus, the objective of this retrospective study is to develop a nomogram that combines magnetic resonance (MRI) radiomics features and clinical features to predict the early response of locally advanced nasopharyngeal carcinoma (LA-NPC).Methods: A total of 91 patients with LA-NPC were included in this study. Patients were randomly divided into training and validation cohorts at a ratio of 3:1. Univariate and multivariate analyses were performed on the clinical parameters of the patients to select clinical features to build a clinical model. In the training cohort, the Least Absolute Shrinkage and Selection Operator (LASSO) regression model was used to select radiomics features for construction of a radiomics model. The logistic regression algorithm was then used to combine the clinical features with the radiomics features to construct the clinical radiomics nomogram. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were drawn to compare and verify the predictive performances of the clinical model, radiomics model, and clinical radiomics nomogram.Results: Platelet lymphocyte ratio (PLR) and nasopharyngeal tumor volume were identified as independent predictors of early response in patients with locally advanced nasopharyngeal carcinoma. A total of 5502 radiomics features were extracted, from which 25 radiomics features were selected to construct the radiomics model. The clinical radiomics nomogram demonstrated the highest AUC in both the training and validation cohorts (training cohort 0.975 vs 0.973 vs 0.713; validation cohort 0.968 vs 0.952 vs 0.706). The calibration curve and DCA indicated good predictive performance for the nomogram.Conclusion: A clinical radiomics nomogram, which combines clinical features with radiomics features based on MRI, can predict early tumor regression in patients with LA-NPC. The performance of the nomogram is superior to that of either the clinical model or radiomics model alone. Therefore, it can be used to identify patients without CR at an early stage and provide guidance for personalized therapy.
The aim of this study is to evaluate the efficacy and cost-effectiveness of various induction chemotherapy (IC) regimens as first-line treatment for Locoregionally advanced nasopharyngeal carcinoma (LA-NPC), aiming to provide clinicians and patients with informed insights to aid in treatment decision-making. We conducted a network meta-analysis (NMA) and cost-effectiveness analysis (CEA) based on data from 10 clinical trials investigating IC regimens for the treatment of LA-NPC. A Bayesian NMA was performed, with the primary outcomes being hazard ratios (HRs) for disease-free survival (DFS) and overall survival (OS). To model the disease progression of LA-NPC, we developed a dynamic partitioned survival model consisting of three disease states: progression-free survival (PFS), progression disease (PD), and death. The model was run on a 3-week cycle for a research period of 10 years, with quality-adjusted life-years (QALYs) and incremental cost-effectiveness ratios (ICERs) serving as outcome measures. According to the surface under the cumulative ranking curve (SUCRA) estimates derived from the NMA, TPC and TP, as IC regimens, appear to exhibit superior efficacy compared to other treatment modalities. In terms of CEA, concurrent chemoradiotherapy (CCRT), TPF + CCRT, and GP + CCRT were found to be dominated (more costs and less QALYs). Comparatively, TPC + CCRT emerged as a cost-effective option with an ICER of $1260.57/QALY when compared to PF + CCRT. However, TP + CCRT demonstrated even greater cost-effectiveness than TPC + CCRT, with an associated increase in costs of $3300.83 and an increment of 0.1578 QALYs per patient compared to TPC + CCRT, resulting in an ICER of $20917.62/QALY. Based on considerations of efficacy and cost-effectiveness, the TP + CCRT treatment regimen may emerge as the most favorable first-line therapeutic approach for patients with LA-NPC.
Objective: Anlotinib is a multitarget anti-angiogenic drug that combined with temozolomide (TMZ) can effectively prolongs the overall survival (OS) of recurrent malignant glioma(rMG),but some patients do not respond to anlotinib combined with TMZ. These patients were associated with a worse prognosis and lack effective identification methods. Therefore, it is necessary to differentiate patients who may have good response to anlotinb in combination with TMZ from those who are not, in order to provide personalized targeted therapies. Methods: Fifty three rMG patients (42 in training cohort and 11 in testing cohort) receiving anlotinib combined with TMZ were enrolled. A total of 3668 radiomics features were extracted from the recurrent MRI images. Radiomics features are reduced and filtered by hypothesis testing and Least Absolute Shrinkage And Selection (LASSO) regression. Eight machine learning models construct the radiomics model, and then screen out the optimal model. The performance of the model was assessed by its discrimination, calibration, and clinical usefulness with validation. Results: Fifty three patients with rMG were enrolled in our study. Thirty four patients displayed effective treatment response, showed a higher survival benefits than non-response group, the median progression-free survival(PFS) was 8.53 months versus 5.33 months (p = 0.06) and the median OS was 19.9 months and 7.33 months (p = 0.029), respectively. Three radiomics features were incorporated into the model construction as final variables after LASSO regression analysis. In testing cohort, Logistic Regression (LR) model has the best performance with an Area Under the Curve (AUC) of 0.93 compared with other models, which can effectively predict the response of rMG patients to anlotinib in combination with TMZ. The calibration curve confirmed the agreement between the observed actual and prediction probability. Within the reasonable threshold probability range (0.38–0.88), the radiomics model shows good clinical utility. Conclusions: The above-described radiomics model performed well, which can serve as a clinical tool for individualized prediction of the response to anlotinb combined with TMZ in rMG patients.
Objective: The prediction of early response in locally advanced nasopharyngeal carcinoma (LA-NPC) after concurrent chemoradiotherapy (CCRT) is important for determining the need for timely consolidation therapy. We developed a radiomic analysis of multi-sequences MR based on machine learning (ML) to assess early response in LA-NPC after CCRT. Methods: This study retrospectively enrolled 104 LA-NPC patients, randomly divided into training (70%) and test (30%) cohorts. Radiomic features were extracted from five MR sequences (T1, T1C, T2, DWI, and ADC). Feature selection was performed using Pearson's correlation coefficient and LASSO regression to reduce redundancy. ML algorithms were compared to develop models, with suboptimal sequences excluded from the multi-sequence MR fusion model. A combined model integrating the fusion and clinical model was developed using logistic regression, and its diagnostic effectiveness was evaluated using receiver operating characteristic (ROC) analysis. Results: In the mono-sequence MR analysis, T1 demonstrated the lowest discriminative capacity (AUC = 0.505), followed by T2 (AUC = 0.738). Consequently, we developed a fusion model incorporating ADC, DWI, and T1C features while excluding T1 and T2. In the test cohort, the combined model outperformed both the clinical (AUC = 0.852) and fusion (AUC = 0.886) models, achieving superior effectiveness (AUC = 0.900). Shapley Additive Explanations (SHAP) analysis identified lbp_GrayLevelVariance_ADC as the most influential predictive feature. Conclusions: A combined model, which merges clinical and multi-sequences MR radiomics model, showed good performance for predicting early response of LA-NPC after CCRT.