Development and Validation of Prognostic Nomogram for Young Patients with Kidney Cancer

Development and validation of a novel combinatorial nomogram model to predict in-hospital deaths in heart failure patients

BACKGROUND

The purpose of this study was to develop a Nomogram model to identify the risk of all-cause mortality during hospitalization in patients with heart failure (HF).

METHODS

HF patients who had been registered in the Medical Information Mart for Intensive Care (MIMIC) III and IV databases were included. The primary outcome was the occurrence of all-cause mortality during hospitalization. Two Logistic Regression models (LR1 and LR2) were developed to predict in-hospital death for HF patients from the MIMIC-IV database. The MIMIC-III database were used for model validation. The area under the receiver operating characteristic curve (AUC) was used to compare the discrimination of each model. Calibration curve was used to assess the fit of each developed models. Decision curve analysis (DCA) was used to estimate the net benefit of the predictive model.

RESULTS

A total of 16,908 HF patients were finally enrolled through screening, of whom 2,283 (13.5%) presented with in-hospital death. Totally, 48 variables were included and analyzed in the univariate and multifactorial regression analysis. The AUCs for the LR1 and LR2 models in the test cohort were 0.751 (95% CI: 0.735∼0.767) and 0.766 (95% CI: 0.751-0.781), respectively. Both LR models performed well in the calibration curve and DCA process. Nomogram and online risk assessment system were used as visualization of predictive models.

CONCLUSION

A new risk prediction tool and an online risk assessment system were developed to predict mortality in HF patients, which performed well and might be used to guide clinical practice.

Development and validation of prognostic nomogram for elderly patients with clear cell renal cell carcinoma based on the SEER database

This study sought to establish nomogram models of overall survival (OS) in patients with elderly clear cell renal cell carcinoma (ECCRCC). The Surveillance, Epidemiology, and End Results database provided data of the ECCRCC-afflicted patients diagnosed during the period from 2010 to 2015. This data was subsequently segregated into the training and validation sets randomly in a 7:3 ratio. The calibration curves, the receiver operating characteristic curves, the decision curve analysis and the Concordance index (C-index) were applied for the model evaluation. 9201 eligible cases from 2010 to 2015 were extracted; 6441 were included in the training cohort and 2760 in the validation cohort. The C-index for the training and validation sets were 0.710 and 0.709, respectively. The receiver operating characteristic and decision curve analysis curves demonstrated that nomograms outperformed the AJCC stage in predictive performance. Moreover, the nomogram was found to match closely with the actual observation, as indicated by the calibration plots. To make predictions with regard to the survival of the ECCRCC-afflicted individuals, and as a guide for treatment, the new nomogram could be used.

Web-based nomogram and risk stratification system constructed for predicting the overall survival of older adults with primary kidney cancer after surgical resection

BACKGROUND

Kidney cancer (KC) is one of the most common malignant tumors in adults which particularly affects the survival of elderly patients. We aimed to construct a nomogram to predict overall survival (OS) in elderly KC patients after surgery.

METHODS

Information on all primary KC patients aged more than 65 years and treated with surgery between 2010 and 2015 was downloaded from the Surveillance, Epidemiology, and End Results (SEER) database. Univariate and multivariate Cox regression analysis was used to identify the independent prognostic factors. Consistency index (C-index), receiver operating characteristic curve (ROC), the area under curve (AUC), and calibration curve were used to assess the accuracy and validity of the nomogram. Comparison of the clinical benefits of nomogram and the TNM staging system is done by decision curve analysis (DCA) and time-dependent ROC.

RESULTS

A total of 15,989 elderly KC patients undergoing surgery were included. All patients were randomly divided into training set (N = 11,193, 70%) and validation set (N = 4796, 30%). The nomogram produced C-indexes of 0.771 (95% CI 0.751-0.791) and 0.792 (95% CI 0.763-0.821) in the training and validation sets, respectively, indicating that the nomogram has excellent predictive accuracy. The ROC, AUC, and calibration curves also showed the same excellent results. In addition, DCA and time-dependent ROC showed that the nomogram outperformed the TNM staging system with better net clinical benefits and predictive efficacy.

CONCLUSIONS

Independent influencing factors for postoperative OS in elderly KC patients were sex, age, histological type, tumor size, grade, surgery, marriage, radiotherapy, and T-, N-, and M-stage. The web-based nomogram and risk stratification system could assist surgeons and patients in clinical decision-making.