Accurate prediction for the prognosis of patients with pancreatic cancer (PC) is a emerge task nowadays. We aimed to develop survival models for postoperative PC patients, based on a novel algorithm, random survival forest (RSF), traditional Cox regression and neural networks (Deepsurv), using the Surveillance, Epidemiology, and End Results Program (SEER) database. A total of 3988 patients were included in this study. Eight clinicopathological features were selected using least absolute shrinkage and selection operator (LASSO) regression analysis and were utilized to develop the RSF model. The model was evaluated based on three dimensions: discrimination, calibration, and clinical benefit. It found that the RSF model predicted the cancer-specific survival (CSS) of the postoperative PC patients with a c-index of 0.723, which was higher than the models built by Cox regression (0.670) and Deepsurv (0.700). The Brier scores at 1, 3, and 5 years (0.188, 0.177, and 0.131) of the RSF model demonstrated the model’s favorable calibration and the decision curve analysis illustrated the model’s value of clinical implement. Moreover, the roles of the key variables were visualized in the Shapley Additive Explanations plotting. Lastly, the prediction model demonstrates value in risk stratification and individual prognosis. In this study, a high-performance prediction model for PC postoperative prognosis was developed, based on RSF The model presented significant strengths in the risk stratification and individual prognosis prediction.

Background: Although nonalcoholic fatty liver disease (NAFLD) is related to obesity, it may also affect lean individuals. Recent data suggest that lean NAFLD patients can develop the whole spectrum of NASH. However, the NAFLD predictive model for lean populations remains lacking. Methods: A total of 5037 lean individuals were included in this study, and the data were separated for training and validation. The logistic regression method was used, and a nomogram, a type of prediction model, was constructed according to the logistic regression analysis and the significant clinical factors. The performance of this model was evaluated based on its discrimination, calibration, and clinical utility. Results: The individuals were divided into the training (n = 4068) or validation (n = 969) cohorts at a ratio of 8 to 2. The overall prevalence of NAFLD in the lean cohort was 6.43%. The nomogram was constructed based on seven predictors: alanine aminotransferase, total cholesterol, triglycerides, low-density lipoprotein cholesterol, creatinine, uric acid, and hemoglobin A1C. The model based on these factors showed good predictive accuracy in the training set and in the internal validation set, with areas under the curve (AUCs) of 0.870 and 0.887, respectively. The calibration curves and decision curve analysis (DCA) displayed good clinical utility. Conclusion: the nomogram model provides a simple and reliable ability to predict the risk of NAFLD in lean subjects. The model can predict lean NAFLD and can help physicians screen and identify lean subjects at a high risk of NAFLD.

Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H₂O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.

Background This study aims to explore a deep learning (DL) algorithm for developing a prognostic model and perform survival analyses in SBT patients. Methods The demographic and clinical features of patients with SBTs were extracted from the Surveillance, Epidemiology and End Results (SEER) database. We randomly split the samples into the training set and the validation set at 7:3. Cox proportional hazards (Cox-PH) analysis and the DeepSurv algorithm were used to develop models. The performance of the Cox-PH and DeepSurv models was evaluated using receiver operating characteristic curves, calibration curves, C-statistics and decision-curve analysis (DCA). A Kaplan–Meier (K–M) survival analysis was performed for further explanation on prognostic effect of the Cox-PH model. Results The multivariate analysis demonstrated that seven variables were associated with cancer-specific survival (CSS) (all p < 0.05). The DeepSurv model showed better performance than the Cox-PH model (C-index: 0.871 vs. 0.866). The calibration curves and DCA revealed that the two models had good discrimination and calibration. Moreover, patients with ileac malignancy and N2 stage disease were not responding to surgery according to the K–M analysis. Conclusions This study reported a DeepSurv model that performed well in CSS in SBT patients. It might offer insights into future research to explore more DL algorithms in cohort studies.

While excessive sodium intake is associated with hepatic steatosis, its precise role in metabolic dysfunction-associated steatotic liver disease (MASLD) remains underexplored. This study investigated the relationship between different measures of sodium intake and the risk of MASLD. The complete data of 286,073 participants on their self-reported frequency of adding salt to food and estimated 24-h urinary sodium excretion from the UK Biobank were analyzed. Cox proportional hazards models quantified hazard ratios (HRs) for incident MASLD, cirrhosis or liver cancer, and liver-related mortality. Mediation analyses evaluated potential mediating between sodium intake and MASLD. Energy-adjusted dietary sodium intake was evaluated in a sub-cohort of 119,073 participants with ≥2 dietary recalls. During a median follow-up of 13.3 years, 3147 MASLD, 1354 cirrhosis or liver cancer, and 523 liver-related mortality cases were identified. After adjusting for confounders, participants who reported "always" adding salt had an increased risk of MASLD (HR=1.36, 95 % CI=1.19-1.56). Higher urinary sodium excretion was also associated with incident MASLD (HR=1.62, 95 % CI=1.53-1.72), displaying a J-shaped nonlinear relationship with the threshold point at 1.93 g/d. Inflammatory dysregulation, insulin resistance and renal function impairment partly mediated this association. In the sub-cohort, every 1 g increase in energy-adjusted dietary sodium intake conferred a 14 % higher risk of MASLD (HR=1.14, 95 % CI=1.01-1.28). The habit of always adding salt to food, a 24-h urinary sodium excretion above 1.93 g/day, and energy-adjusted dietary sodium intake above 1.49g/d increased the risk of MASLD, partly mediated through inflammation, insulin resistance, and renal dysfunction. It is recommended that public health strategies target reducing MASLD risk based on these findings.