Urinary protein quantification is critical for assessing the severity of chronic kidney disease (CKD). However, the current procedure for determining the severity of CKD is completed through evaluating 24-h urinary protein, which is inconvenient during follow-up. To quickly predict the severity of CKD using more easily available demographic and blood biochemical features during follow-up, we developed and compared several predictive models using statistical, machine learning and neural network approaches. The clinical and blood biochemical results from 551 patients with proteinuria were collected. Thirteen blood-derived tests and 5 demographic features were used as non-urinary clinical variables to predict the 24-h urinary protein outcome response. Nine predictive models were established and compared, including logistic regression, Elastic Net, lasso regression, ridge regression, support vector machine, random forest, XGBoost, neural network and k-nearest neighbor. The AU-ROC, sensitivity (recall), specificity, accuracy, log-loss and precision of each of the models were evaluated. The effect sizes of each variable were analysed and ranked. The linear models including Elastic Net, lasso regression, ridge regression and logistic regression showed the highest overall predictive power, with an average AUC and a precision above 0.87 and 0.8, respectively. Logistic regression ranked first, reaching an AUC of 0.873, with a sensitivity and specificity of 0.83 and 0.82, respectively. The model with the highest sensitivity was Elastic Net (0.85), while XGBoost showed the highest specificity (0.83). In the effect size analyses, we identified that ALB, Scr, TG, LDL and EGFR had important impacts on the predictability of the models, while other predictors such as CRP, HDL and SNA were less important. Blood-derived tests could be applied as non-urinary predictors during outpatient follow-up. Features in routine blood tests, including ALB, Scr, TG, LDL and EGFR levels, showed predictive ability for CKD severity. The developed online tool can facilitate the prediction of proteinuria progress during follow-up in clinical practice.

Quantitative evaluation of position control ability in stroke patients is needed. Here we report a demonstration of position control ability assessment and test-retest reliability during squat-stand activity on a new system in hemiparetic patients and controls. Sixty-two healthy adults and thirty-four hemiparetics were enrolled. All of the participants were required to complete five repeated squat-stand activities under three different conditions: partial weight support, standard weight bearing, and resistance. The healthy adults’ test was repeated twice to assess the reliability, while the hemiparetics were tested one time to assess impairments in their position control ability. The healthy participants completed their second test 1 wk after the first. Intraclass correlation coefficients (ICCs) were used to assess test-retest reliability. During partial weight support, the ICCs ranged from 0.77 to 0.91, which indicated a good reliability. During standard weight bearing and resistance, the ICCs varied from 0.64 to 0.86 and 0.54 to 0.84, respectively, indicating a fair reliability. Compared with the healthy adults, the stroke patients demonstrated poorer position control ability. The posturography of the squat-stand activity is a new and reliable measurement tool for position control. According to the methods proposed here, hemiparetics can be differentiated from healthy adults using the squat-stand activity. This activity will provide a new evaluation tool and therapy with visual feedback for the stroke patients. Chinese clinical trial registry, ChiCTR-TRC-10000863