Machine learning in predicting T-score in the Oxford classification system of IgA nephropathy

BackgroundImmunoglobulin A nephropathy (IgAN) is one of the leading causes of end-stage kidney disease (ESKD). Many studies have shown the significance of pathological manifestations in predicting the outcome of patients with IgAN, especially T-score of Oxford classification. Evaluating prognosis may be hampered in patients without renal biopsy.MethodsA baseline dataset of 690 patients with IgAN and an independent follow-up dataset of 1,168 patients were used as training and testing sets to develop the pathology T-score prediction (Tpre) model based on the stacking algorithm, respectively. The 5-year ESKD prediction models using clinical variables (base model), clinical variables and real pathological T-score (base model plus Tbio), and clinical variables and Tpre (base model plus Tpre) were developed separately in 1,168 patients with regular follow-up to evaluate whether Tpre could assist in predicting ESKD. In addition, an external validation set consisting of 355 patients was used to evaluate the performance of the 5-year ESKD prediction model using Tpre.ResultsThe features selected by AUCRF for the Tpre model included age, systolic arterial pressure, diastolic arterial pressure, proteinuria, eGFR, serum IgA, and uric acid. The AUC of the Tpre was 0.82 (95% CI: 0.80–0.85) in an independent testing set. For the 5-year ESKD prediction model, the AUC of the base model was 0.86 (95% CI: 0.75–0.97). When the Tbio was added to the base model, there was an increase in AUC [from 0.86 (95% CI: 0.75–0.97) to 0.92 (95% CI: 0.85–0.98); P = 0.03]. There was no difference in AUC between the base model plus Tpre and the base model plus Tbio [0.90 (95% CI: 0.82–0.99) vs. 0.92 (95% CI: 0.85–0.98), P = 0.52]. The AUC of the 5-year ESKD prediction model using Tpre was 0.93 (95% CI: 0.87–0.99) in the external validation set.ConclusionA pathology T-score prediction (Tpre) model using routine clinical characteristics was constructed, which could predict the pathological severity and assist clinicians to predict the prognosis of IgAN patients lacking kidney pathology scores.