Stepwise logistic regression

Nomogram for predicting the preoperative lymph node metastasis in resectable pancreatic cancer

BACKGROUND

Lymph node metastasis (LNM) is a critical prognostic factor in resectable pancreatic cancer (PC) patients, determining treatment strategies. This study aimed to develop a clinical model to adequately and accurately predict the risk of LNM in PC patients.

METHODS

13,200 resectable PC patients were enrolled from the SEER (Surveillance, Epidemiology, and End Results) database, and randomly divided into a training group and an internal validation group at a ratio of 7:3. An independent group (n = 62) obtained from The First Affiliated Hospital of Xinxiang Medical University was enrolled as the external validation group. The univariate and multivariate logistic regression analyses were used to screen independent risk factors for LNM. The minimum Akaike's information criterion (AIC) was performed to select the optimal model parameters and construct a nomogram for assessing the risk of LNM. The performance of the nomogram was assessed by the receiver operating characteristics (ROC) curve, calibration plot, and decision curve analysis (DCA). In addition, an online web calculator was designed to assess the risk of LNM.

RESULT

A total of six risk predictors (including age at diagnosis, race, primary site, grade, histology, and T-stage) were identified and included in the nomogram. The areas under the curves (AUCs) [95% confidential interval (CI)] were 0.711 (95%CI: 0.700-0.722), 0.700 (95%CI: 0.683-0.717), and 0.845 (95%CI: 0.749-0.942) in the training, internal validation and external validation groups, respectively. The calibration curves showed satisfied consistency between nomogram-predicted LNM and actual observed LNM. The concordance indexes (C-indexes) in the training, internal, and external validation sets were 0.689, 0.686, and 0.752, respectively. The DCA curves of the nomogram demonstrated good clinical utility.

CONCLUSION

We constructed a nomogram model for predicting LNM in pancreatic cancer patients, which may help oncologists and surgeons to choose more individualized clinical treatment strategies and make better clinical decisions.

Predicting mortality risk in dialysis: Assessment of risk factors using traditional and advanced modeling techniques within the Monitoring Dialysis Outcomes initiative

INTRODUCTION

Several factors affect the survival of End Stage Kidney Disease (ESKD) patients on dialysis. Machine learning (ML) models may help tackle multivariable and complex, often non-linear predictors of adverse clinical events in ESKD patients. In this study, we used advanced ML method as well as a traditional statistical method to develop and compare the risk factors for mortality prediction model in hemodialysis (HD) patients.

MATERIALS AND METHODS

We included data HD patients who had data across a baseline period of at least 1 year and 1 day in the internationally representative Monitoring Dialysis Outcomes (MONDO) Initiative dataset. Twenty-three input parameters considered in the model were chosen in an a priori manner. The prediction model used 1 year baseline data to predict death in the following 3 years. The dataset was randomly split into 80% training data and 20% testing data for model development. Two different modeling techniques were used to build the mortality prediction model.

FINDINGS

A total of 95,142 patients were included in the analysis sample. The area under the receiver operating curve (AUROC) of the model on the test data with XGBoost ML model was 0.84 on the training data and 0.80 on the test data. AUROC of the logistic regression model was 0.73 on training data and 0.75 on test data. Four out of the top five predictors were common to both modeling strategies.

DISCUSSION

In the internationally representative MONDO data for HD patients, we describe the development of a ML model and a traditional statistical model that was suitable for classification of a prevalent HD patient's 3-year risk of death. While both models had a reasonably high AUROC, the ML model was able to identify levels of hematocrit (HCT) as an important risk factor in mortality. If implemented in clinical practice, such proof-of-concept models could be used to provide pre-emptive care for HD patients.