RESUMEN
Objective: This study aimed to explore specific biochemical indicators and construct a risk prediction model for diabetic kidney disease (DKD) in patients with type 2 diabetes (T2D). Methods: This study included 234 T2D patients, of whom 166 had DKD, at the First Hospital of Jilin University from January 2021 to July 2022. Clinical characteristics, such as age, gender, and typical hematological parameters, were collected and used for modeling. Five machine learning algorithms [Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF)] were used to identify critical clinical and pathological features and to build a risk prediction model for DKD. Additionally, clinical data from 70 patients (nT2D = 20, nDKD = 50) were collected for external validation from the Third Hospital of Jilin University. Results: The RF algorithm demonstrated the best performance in predicting progression to DKD, identifying five major indicators: estimated glomerular filtration rate (eGFR), glycated albumin (GA), Uric acid, HbA1c, and Zinc (Zn). The prediction model showed sufficient predictive accuracy with area under the curve (AUC) values of 0.960 (95% CI: 0.936-0.984) and 0.9326 (95% CI: 0.8747-0.9885) in the internal validation set and external validation set, respectively. The diagnostic efficacy of the RF model (AUC = 0.960) was significantly higher than each of the five features screened with the highest feature importance in the RF model. Conclusion: The online DKD risk prediction model constructed using the RF algorithm was selected based on its strong performance in the internal validation.
RESUMEN
BACKGROUND AND OBJECTIVE: Noninvasive prognostic tools for colorectal cancer (CRC) are urgently needed. This study was designed to investigate the prognostic value of preoperative serum lipid and lipoprotein concentrations (including ApoA-I, Apo-B, HDL-C, LDL-C, TC and TG) and CRP levels retrospectively in CRC patients. METHODS: Preoperative serum lipid and lipoprotein concentrations (including ApoA-I, Apo-B, HDL-C, LDL-C, TC and TG) and CRP levels were analyzed retrospectively in 250 patients with CRC. The prognostic significance of these indexes was determined by univariate and multivariate Cox hazard models. RESULTS: CRC patients with higher levels of ApoA-I and HDL-C and lower levels of CRP had significantly longer overall survival (OS, log rank test, p<0.05). Based on univariate analysis, ApoA-I levels (p=0.002), CRP levels (p=0.007), HDL-C levels (p=0.005), pT classification (p=0.005), pN classification (p<0.001), pM classification (p<0.001) and pTNM stage (p<0.001) were significantly associated with OS. Multivariate Cox proportional hazards regression analysis indicated that ApoA-I levels (HR: 1.52, p=0.023), CRP levels (HR: 1.85, p=0.035) and pTNM stage (HR: 2.53, p< 0.001) were independent predictors of CRC survival. The included patients were then stratified into three tiers based on the ApoA-I and CRP levels. In the whole cohort, the OS and disease-free survival differed significantly between the low-risk (ApoA-I≥1.08 mg/dL and CRP<3.04 mg/dL), medium-risk (ApoA-I≥1.08 mg/dL or CRP<3.04 mg/dL), and high-risk (ApoA-I<1.08 mg/dL and CRP ≥3.04 mg/dL) groups (p=0.001 and p=0.004). CONCLUSION: Decreased levels of ApoA-I and HDL-C and increased levels of CRP were predictive of poor prognosis among patients with CRC. In addition, the combination of ApoA-I and CRP can serve as a novel prognostic stratification system for more accurate clinical staging of CRC.
