A model for predicting overall survival in bladder cancer patients with signet ring cell carcinoma: a population-based study

A predictive and prognostic model for metastasis risk and prognostic factors in gastrointestinal signet ring cell carcinoma

BACKGROUND

This study aimed to predict metastasis risk and identify prognostic factors of gastrointestinal signet ring cell carcinoma (SRCC) using data from the SEER database, the largest cancer dataset in North America.

METHODS

Data were obtained from the SEER database, covering 17 cancer registries from 2004 to 2020. Demographic and clinical data included sex, age, race, tumor location, size, pathological grade, stage, overall survival time, and treatment modalities. Statistical analyses were conducted using SPSS and R software. Propensity Score Matching (PSM) ensured comparable baseline characteristics between gastric cancer (GC) and colorectal cancer (CRC) groups. LASSO regression analysis identified predictors of metastasis, leading to the construction of predictive models using the lrm function in R. Nomograms were visualized with the "rms" package and assessed via ROC curves, calibration curves, and decision curve analysis (DCA). Cox regression analyses identified prognostic indicators for overall survival (OS), and Kaplan-Meier curves compared OS between high-risk and low-risk groups.

RESULTS

From 2004 to 2020, 7680 SRCC patients were identified, including 4980 GC and 2700 CRC patients. CRC patients were older and had larger tumors, higher staging, and worse differentiation. Nomograms demonstrated good discriminative ability, with AUCs of 0.704 and 0.694 for GC, and 0.694 and 0.701 for CRC in training and validation cohorts, respectively. The DCA curve indicates that this predictive model has a high gain in predicting metastasis and OS.

CONCLUSIONS

The nomograms effectively predicted metastasis risk and OS in metastatic SRCC patients, offering clinical utility in stratifying patients and guiding treatment decisions, thereby enhancing personalized treatment approaches.

Comparison of deep learning models to traditional Cox regression in predicting survival of colon cancer: Based on the SEER database

BACKGROUND AND AIM

In this study, a deep learning algorithm was used to predict the survival rate of colon cancer (CC) patients, and compared its performance with traditional Cox regression.

METHODS

In this population-based cohort study, we used the characteristics of patients diagnosed with CC between 2010 and 2015 from the Surveillance, Epidemiology and End Results (SEER) database. The population was randomized into a training set (n = 10 596, 70%) and a test set (n = 4536, 30%). Brier scores, area under the (AUC) receiver operating characteristic curve and calibration curves were used to compare the performance of the three most popular deep learning models, namely, artificial neural networks (ANN), deep neural networks (DNN), and long-short term memory (LSTM) neural networks with Cox proportional hazard (CPH) model.

RESULTS

In the independent test set, the Brier values of ANN, DNN, LSTM and CPH were 0.155, 0.149, 0.148, and 0.170, respectively. The AUC values were 0.906 (95% confidence interval [CI] 0.897-0.916), 0.908 (95% CI 0.899-0.918), 0.910 (95% CI 0.901-0.919), and 0.793 (95% CI 0.769-0.816), respectively. Deep learning showed superior promising results than CPH in predicting CC specific survival.

CONCLUSIONS

Deep learning showed potential advantages over traditional CPH models in terms of prognostic assessment and treatment recommendations. LSTM exhibited optimal predictive accuracy and has the ability to provide reliable information on individual survival and treatment recommendations for CC patients.

Treatment Options for Signet Ring Cell Carcinoma of the Urinary Bladder: A Population-Based Study

OBJECTIVES

Signet ring cell carcinoma (SRCC) of the urinary bladder is a rare and highly aggressive form of bladder cancer, with no widely agreed-upon treatment strategy. The aim of this study was to identify important factors influencing patient prognosis and to assess how various treatment approaches affect survival outcomes.

METHODS

A retrospective study was conducted using data from the Surveillance, Epidemiology, and End Results (SEER) Program, including patients with bladder primary SRCC who were presented between 2000 and 2017. Univariate and multivariate Cox regression models were used to examine the impact of various factors on cancer-specific survival (CSS) and overall survival (OS). Propensity score matching (PSM) and inverse probability of treatment weighting (IPTW) were applied to homogenize both groups. The impact of different treatment regimens on patient CSS and OS was analyzed using the Kaplan-Meier method.

RESULTS

A total of 33 cases of non-muscular invasive SRCC and 210 cases of muscular invasive SRCC were included in this study. Multivariate analysis identified race, TNM stage, and surgical method as independent variables influencing both OS and CSS. In non-muscle invasive bladder SRCC patients, radical cystectomy showed no CSS benefit compared to transurethral resection of bladder tumors (P = 0.304). For muscle invasive SRCC, patients who underwent partial cystectomy had better OS and CSS compared to those who underwent radical cystectomy (P = 0.019, P = 0.024). However, after conducting a PSM analysis, the differences between the two surgical outcomes were not statistically significant (P = 0.504, P = 0.335). Lymphadenectomy, chemotherapy, and radiation did not show any benefit to the prognosis of patients.

CONCLUSION

This study identified race, TNM stage, and surgical approach as significant independent predictors for SRCC outcomes. Simple radical cystectomy and partial cystectomy proved to be effective treatments for SRCC. The optimal treatment option still needs to be supported by a number of prospective research trials.

Development and validation of a novel nomogram model for predicting the survival of patients with T2-4a, N0-x, M0 bladder cancer: a retrospective cohort study

OBJECTIVE

Recent developments in bladder cancer treatment strategies have significantly improved the prognosis of clinically curable muscle invasive bladder cancer (MIBC) patients. Here, the prognostic factors of T2-4a, N0-x, M0 MIBC patients were investigated using the Surveillance, Epidemiology, and End Results (SEER) database and a novel nomogram model was established for prognosis prediction.

METHODS

The data of 7,292 patients with T2-4a, N0-x, M0 MIBC were retrieved from the SEER database (2000-2020) and randomly classified into a training set (n = 5,106) and validation set (n = 2,188). Kaplan-Meier analysis was used to calculate cancer-specific survival (CSS) and overall survival (OS) rates of patients, and differences between survival curves were analyzed using the log-rank test. Cox regression analysis was used to screen and incorporate patient prognosis-affecting independent risk factors into the nomogram model. Consistency index (C-index) values and areas under the time-dependent receiver operating characteristic curve (AUC) were used to evaluate the discriminatory ability, and the calibration curve was used to assess the calibration of the model. Its predictive performance and American Joint Committee on Cancer (AJCC) stage were compared using decision curve analysis (DCA).

RESULTS

The 1-, 3-, and 5-year CSS and OS rates of patients with T2-4a, N0-x, M0 MIBC were 76.9%, 56.0%, and 49.9%, respectively, and 71.3%, 47.9%, and 39.5%, respectively. Cox regression analysis showed that age, marital status, race, pathological type, tumor size, AJCC stage, T stage, N stage, surgery of primary tumor, regional lymph node dissection, radiation, and chemotherapy were independent prognostic risk factors of both CSS and OS (P < 0.05). The C-index and AUC of the nomogram model constructed based on the training and validation sets were both > 0.7, and calibration curves for predicting the 1-, 3-, and 5-year survival were consistent with the ideal curve. The nomogram model showed a higher net benefit with DCA than AJCC stage analysis.

CONCLUSION

The nomogram model could accurately predict the prognosis of patients with T2-4a, N0-x, M0 MIBC. It may help clinicians perform personalized prognosis evaluations and formulate treatment plans.