A nomogram for predicting survival and retroperitoneal lymph node dissection treatment in patients with resected testicular germ cell tumors

Using machine learning for mortality prediction and risk stratification in atezolizumab-treated cancer patients: Integrative analysis of eight clinical trials

BACKGROUND

Few models exist to predict mortality in cancer patients receiving immunotherapy. Our aim was to build a machine learning-based risk stratification model for predicting mortality in atezolizumab-treated cancer patients.

METHODS

Data from 2538 patients in eight atezolizumab-treated cancer clinical trials across three cancer types (non-small-cell lung cancer, bladder transitional cell carcinoma, and renal cell carcinoma) were included. The whole cohort was randomly split into development and validation cohorts in a 7:3 ratio. Machine-learning algorithms (extreme gradient boosting, random forest, logistic regression with lasso regularization, support vector machine, and K-nearest neighbor) were applied to develop prediction models. Model performance was mainly assessed by area under the receiver operating characteristic curve (AUC) value, calibration plot, and decision curve analysis. The probability of death risk was then stratified.

RESULTS

One thousand and three hundred and seventy-nine (54.33%) patients died. The random forest (RF) model was overall the best in terms of predictive performance, with the AUC of 0.844 (95% confidence interval [CI]: 0.826-0.862) in the development cohort and 0.786 (95% CI: 0.754-0.818) in the validation cohort for predicting mortality. Twelve baseline variables contributing to mortality prediction in the RF model were C-reactive protein, PD-L1 level, cancer type, prior liver metastasis, derived neutrophil-to-lymphocyte ratio, alkaline phosphatase, albumin, hemoglobin, white blood cell count, number of metastatic sites, pulse rate, and Eastern Cooperative Oncology Group (ECOG) performance status. A total of 1782 (70.2%) patients were separated into the high-risk and 756 (29.8%) low-risk groups. Patients in the high-risk group were significantly more likely to die, experience disease progression, discontinue study, and discontinue treatment than patients in the low-risk group (all p values < 0.001). Risk groups were not associated with immune-related adverse events and grades 3-5 treatment-related adverse events (all p values > 0.05).

CONCLUSION

RF model has good performance in mortality prediction and risk stratification for cancer patients receiving atezolizumab monotherapy.

Development and validation of a preoperative nomogram for predicting survival of patients with locally advanced prostate cancer after radical prostatectomy

Background

For selected locally advanced prostate cancer (PCa) patients, radical prostatectomy (RP) is one of the first-line treatments. We aimed to develop a preoperative nomogram to identify what kinds of patients can get the most survival benefits after RP.

Methods

We conducted analyses with data from the Surveillance, Epidemiology, and End Results (SEER) database. Covariates used for analyses included age at diagnosis, marital status, race, American Joint Committee on Cancer (AJCC) 7th TNM stage, Prostate specific antigen, Gleason biopsy score (GS), percent of positive cores. We estimated the cumulative incidence function for cause-specific death. The Fine and Gray’s proportional subdistribution hazard approach was used to perform multivariable competing risk analyses and reveal prognostic factors. A nomogram was built by these factors (including GS, percent of positive cores and N stage) and validated by concordance index and calibration curves. Risk stratification was established based on the nomogram.

Results

We studied 14,185 patients. N stage, GS, and percent of positive cores were the independent prognostic factors used to construct the nomogram. For validating, in the training cohort, the C-index was 0.779 (95% CI 0.736–0.822), and in the validation cohort, the C-index was 0.773 (95% CI 0.710–0.836). Calibration curves showed that the predicted survival and actual survival were very close. The nomogram performed better over the AJCC staging system (C-index 0.779 versus 0.764 for training cohort, and 0.773 versus 0.744 for validation cohort). The new stratification of risk groups based on the nomogram also showed better discrimination than the AJCC staging system.

Conclusions

The preoperative nomogram can provide favorable prognosis stratification ability to help clinicians identify patients who are suitable for surgery.