ObjectiveThis study aimed to develop early mortality risk prediction models for patients with severe acute pancreatitis (SAP) based on eight machine learning algorithms, and to identify the major risk factors. MethodsClinical data of SAP patients diagnosed at West China Hospital of Sichuan University between January 2020 and August 2023, were retrospectively collected and randomly divided into a training set (n=878) and a validation set (n=376) in a 7∶3 ratio. Eight machine learning algorithms, including random forest, logistic regression, support vector machine, multilayer perceptron, XGBoost, Gaussian naive Bayes, CatBoost, and AdaBoost, were applied to construct early mortality prediction models for SAP. The models were evaluated using the area under curve (AUC), decision curve analysis (DCA), and Shapley additive explanations (SHAP). ResultsA total of 1 254 SAP patients were finally included in this study, with an early mortality rate of 15.79% (198/1 254). The random forest algorithm demonstrated the best predictive performance in both the training and validation sets, with AUCs of 0.913 and 0.844, respectively. In the DCA, random forest also yielded the greatest net benefit. SHAP analysis ranked seven key predictors of early mortality in SAP by importance: age, body mass index, heart rate, need for assisted ventilation, hemoglobin, interleukin-6, and lactate dehydrogenase, with the need for assisted ventilation being the most critical predictor. ConclusionThe random forest model developed in this study can assist clinicians in more accurately identifying high-risk SAP patients at an early stage, thereby enabling timely interventions to reduce early mortality.
Objective To study the effect of alpha fetoprotein-tumor burden score (ATS) on the long-term prognosis of hepatocellular carcinoma (HCC) after resection. MethodsThe data of 2 907 patients with HCC who underwent first hepatectomy from West China Hospital of Sichuan University, West China Ziyang Hospital/Ziyang Central Hospital, The First People’s Hospital of Neijiang, West China Yibin Hospital/the Second People’s Hospital of Yibin, and the Affiliated Hospital of Chengdu University between 2015 and 2022, were retrospectively analyzed. The X-tile software was used to calculate the optimal truncation of the ATS score. Cox proportional hazard regression model was used to explore risk factors affecting postoperative recurrence-free survival (RFS) and overall survival (OS) in HCC patients, respectively. ResultsAll patients were followed-up with a median of 37 months (1–90 months), 1 364 cases (46.9%, the recurrence time was 1–89 months after surgery) of them experienced recurrence and 847 cases (29.1%) died (the death time was 1–88 months after surgery). The 1-, 2- and 3-year OS rates were 89.3%, 81.4% and 75.9%, respectively. The 1-, 2- and 3-year RFS rates were 76.0%, 64.3% and 57.2%, respectively. The 5-year RFS rate of HCC patients with low-, medium-, and high-ATS scores were 56.4%, 45.0% and 27.2%, respectively, and patients with low ATS score had better RFS (χ2=264.747, P<0.001). The 5-year OS rates of HCC patients with low-, medium-, and high-ATS scores were 78.0%, 59.8% and 38.8%, respectively, and patients with low-ATS score had better OS (χ2=372.685, P<0.001). Multivariate Cox proportional hazard regression model suggested that, in condition of adjusting other factors, medium-ATS score [RR=1.375, 95%CI (1.209, 1.564), P<0.001] and high-ATS score [RR=2.048, 95%CI (1.764, 2.377), P<0.001] were risk factors for postoperative RFS; the medium-ATS score [RR=1.779, 95%CI (1.499, 2.112), P<0.001] and high ATS score [RR=2.676, 95%CI (2.211, 3.239), P<0.001] were also risk factors affecting postoperative OS. ConclusionATS score can predict the prognosis of HCC patients after resection, patients with high ATS score had a higher incidence of postoperative recurrence and mortality.