RESUMO
BACKGROUND: Gastric cancer (GC) is prevalent and aggressive, especially when patients have distant lung metastases, which often places patients into advanced stages. By identifying prognostic variables for lung metastasis in GC patients, it may be possible to construct a good prediction model for both overall survival (OS) and the cumulative incidence prediction (CIP) plot of the tumour. AIM: To investigate the predictors of GC with lung metastasis (GCLM) to produce nomograms for OS and generate CIP by using cancer-specific survival (CSS) data. METHODS: Data from January 2000 to December 2020 involving 1652 patients with GCLM were obtained from the Surveillance, epidemiology, and end results program database. The major observational endpoint was OS; hence, patients were separated into training and validation groups. Correlation analysis determined various connections. Univariate and multivariate Cox analyses validated the independent predictive factors. Nomogram distinction and calibration were performed with the time-dependent area under the curve (AUC) and calibration curves. To evaluate the accuracy and clinical usefulness of the nomograms, decision curve analysis (DCA) was performed. The clinical utility of the novel prognostic model was compared to that of the 7th edition of the American Joint Committee on Cancer (AJCC) staging system by utilizing Net Reclassification Improvement (NRI) and Integrated Discrimination Improvement (IDI). Finally, the OS prognostic model and Cox-AJCC risk stratification model modified for the AJCC system were compared. RESULTS: For the purpose of creating the OS nomogram, a CIP plot based on CSS was generated. Cox multivariate regression analysis identified eleven significant prognostic factors (P < 0.05) related to liver metastasis, bone metastasis, primary site, surgery, regional surgery, treatment sequence, chemotherapy, radiotherapy, positive lymph node count, N staging, and time from diagnosis to treatment. It was clear from the DCA (net benefit > 0), time-dependent ROC curve (training/validation set AUC > 0.7), and calibration curve (reliability slope closer to 45 degrees) results that the OS nomogram demonstrated a high level of predictive efficiency. The OS prediction model (New Model AUC = 0.83) also performed much better than the old Cox-AJCC model (AUC difference between the new model and the old model greater than 0) in terms of risk stratification (P < 0.0001) and verification using the IDI and NRI. CONCLUSION: The OS nomogram for GCLM successfully predicts 1- and 3-year OS. Moreover, this approach can help to appropriately classify patients into high-risk and low-risk groups, thereby guiding treatment.
RESUMO
BACKGROUND: Cervical cancer (CC) is a common malignancy of the female reproductive tract, and preoperative prediction of lymph node metastasis (LNM) is essential. This study aims to design and validate a magnetic resonance imaging (MRI) radiomics-based predictive model capable of detecting LNM in patients diagnosed with CC. METHODS: This retrospective analysis incorporated 86 and 38 CC patients into the training and testing groups, respectively. Radiomics features were extracted from MRI T2WI, T2WI-SPAIR, and axial apparent diffusion coefficient (ADC) sequences. Selected features identified in the training group were then used to construct a radiomics scoring model, with relevant LNM-related risk factors having been identified through univariate and multivariate logistic regression analyses. The resultant predictive model was then validated in the testing cohort. RESULTS: In total, 16 features were selected for the construction of a radiomics scoring model. LNM-related risk factors included worse differentiation (P < 0.001), more advanced International Federation of Gynecology and Obstetrics (FIGO) stages (P = 0.03), and a higher radiomics score from the combined MRI sequences (P = 0.01). The equation for the predictive model was as follows: -0.0493-2.1410 × differentiation level + 7.7203 × radiomics score of combined sequences + 1.6752 × FIGO stage. The respective area under the curve (AUC) values for the T2WI radiomics score, T2WI-SPAIR radiomics score, ADC radiomics score, combined sequence radiomics score, and predictive model were 0.656, 0.664, 0.658, 0.835, and 0.923 in the training cohort, while these corresponding AUC values were 0.643, 0.525, 0.513, 0.826, and 0.82 in the testing cohort. CONCLUSIONS: This MRI radiomics-based model exhibited favorable accuracy when used to predict LNM in patients with CC. Relative to the use of any individual MRI sequence-based radiomics score, this predictive model yielded superior diagnostic accuracy.