Background Kidney disease progression rates vary among patients. Rapid and accurate prediction of kidney disease outcomes is crucial for disease management. In recent years, various prediction models using Machine Learning (ML) algorithms have been established in nephrology. However, their accuracy have been inconsistent. Therefore, we conducted a systematic review and meta-analysis to investigate the diagnostic accuracy of ML algorithms for kidney disease progression. Methods We searched PubMed, EMBASE, Cochrane Central Register of Controlled Trials, the Chinese Biomedicine Literature Database, Chinese National Knowledge Infrastructure, Wanfang Database, and the VIP Database for diagnostic studies on ML algorithms’ accuracy in predicting kidney disease prognosis, from the establishment of these databases until October 2020. Two investigators independently evaluate study quality by QUADAS-2 tool and extracted data from single ML algorithm for data synthesis using the bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model. Results Fifteen studies were left after screening, only 6 studies were eligible for data synthesis. The sample size of these 6 studies was 12,534, and the kidney disease types could be divided into chronic kidney disease (CKD) and Immunoglobulin A Nephropathy, with 5 articles using end-stage renal diseases occurrence as the primary outcome. The main results indicated that the area under curve (AUC) of the HSROC was 0.87 (0.84–0.90) and ML algorithm exhibited a strong specificity, 95% confidence interval and heterogeneity (I2) of (0.87, 0.84–0.90, [I2 99.0%]) and a weak sensitivity of (0.68, 0.58–0.77, [I2 99.7%]) in predicting kidney disease deterioration. And the the results of subgroup analysis indicated that ML algorithm’s AUC for predicting CKD prognosis was 0.82 (0.79–0.85), with the pool sensitivity of (0.64, 0.49–0.77, [I2 99.20%]) and pool specificity of (0.84, 0.74–0.91, [I2 99.84%]). The ML algorithm’s AUC for predicting IgA nephropathy prognosis was 0.78 (0.74–0.81), with the pool sensitivity of (0.74, 0.71–0.77, [I2 7.10%]) and pool specificity of (0.93, 0.91–0.95, [I2 83.92%]). Conclusion Taking advantage of big data, ML algorithm-based prediction models have high accuracy in predicting kidney disease progression, we recommend ML algorithms as an auxiliary tool for clinicians to determine proper treatment and disease management strategies.
ObjectivesTo develop and validate a nomogram model to predict chronic kidney disease (CKD) stages 3–5 prognosis.DesignA retrospective cohort study. We used univariate and multivariate Cox regression analysis to select the relevant predictors. To select the best model, we evaluated the prediction models’ accuracy by concordance index (C-index), calibration curve, net reclassification index (NRI) and integrated discrimination improvement (IDI). We evaluated the clinical utility by decision curve analysis.SettingChronic Disease Management (CDM) Clinic in the Nephrology Department at the Guangdong Provincial Hospital of Chinese Medicine.ParticipantsPatients with CKD stages 3–5 in the derivation and validation cohorts were 459 and 326, respectively.Primary outcome measureRenal replacement therapy (haemodialysis, peritoneal dialysis, renal transplantation) or death.ResultsWe built four models. Age, estimated glomerular filtration rate and urine protein constituted the most basic model A. Haemoglobin, serum uric acid, cardiovascular disease, primary disease, CDM adherence and predictors in model A constituted model B. Oral medications and predictors in model A constituted model C. All the predictors constituted model D. Model B performed well in both discrimination and calibration (C-index: derivation cohort: 0.881, validation cohort: 0.886). Compared with model A, model B showed significant improvement in the net reclassification and integrated discrimination (model A vs model B: NRI: 1 year: 0.339 (−0.011 to 0.672) and 2 years: 0.314 (0.079 to 0.574); IDI: 1 year: 0.066 (0.010 to 0.127), p<0.001 and 2 years: 0.063 (0.008 to 0.106), p<0.001). There was no significant improvement between NRI and IDI among models B, C and D. Therefore, we selected model B as the optimal model.ConclusionsWe constructed a prediction model to predict the prognosis of patients with CKD stages 3–5 in the first and second year. Applying this model to clinical practice may guide clinical decision-making. Also, this model needs to be externally validated in the future.Trial registration numberChiCTR1900024633 (http://www.chictr.org.cn).
Background The feasibility and efficacy of low-protein diets (LPD) treatment in chronic kidney disease (CKD) is controversial. Based on the characteristics of the Chinese diet, we observe the qualification rates and short-term clinical effects of LPD for CKD patients in our center. Methods This is a retrospective cohort study. CKD stages 3–5 patients who were regularly followed up 5 times (over 2 years) and treated with LPD were included. We collected clinical data to observe the changes in LPD qualification rates and divided patients into LPD and non-LPD group according to the average dietary protein intake (DPI) of 5 follow-up time points and compared the changes in primary and secondary outcome measures between the two groups. Results We analyzed data from 161 eligible CKD stages 3–5 patients. From baseline to the 5th follow-up time point, the LPD qualification rates of all patients were 11.80%, 35.40%, 47.82%, 53.43% and 54.04%, respectively. For primary outcome measures, the urine protein/creatinine ratio (UPCR) decreased more in the LPD group than in the non-LPD group [Median (interquartile range, IQR) of the difference between the 5th follow-up time point and baseline: 0.19 (− 0.01–0.73) vs. 0.10 (− 0.08–0.27), P < 0.001]. We constructed three classes of mixed linear models (model I, II, III). The UPCR slopes were all negative in the LPD group and positive in the non-LPD group (P < 0.001). Meanwhile, in model I, the estimate glomerular filtration rate(eGFR) decline slope in the LPD group was lower than that in the non-LPD group [slope (standard error): − 1.32 (0.37) vs. − 2.35 (0.33), P = 0.036]. For secondary outcome measures, body mass index (BMI) triglycerides (TG), body weight, and fat free mass (FFM) showed stable statistical differences in the comparison of LPD and non-LPD groups, with greater declines in the former. Conclusion The results of this study suggest that LPD treatment can reduce UPCR in patients with CKD stages 3–5, and may also delay the decline in eGFR. Meanwhile, it also reduces BMI, TG, body weight, and FFM, thus the need to prevent malnutrition in clinical implementation.
Background: To transfer a paper-version Chinese and Western medication adherence scale for CKD into an electronic scale, and evaluate its validity, internal consistency and clinical implementation, and assess whether the transition is feasible in clinic. Methods: We built an e-version Chinese and Western medication adherence scale based on the Wen-JuanXing platform. CKD subjects' responses were applied to test the scale's validity and internal consistency. We retested some of the participants two weeks later randomly. We also tested the clinical application. Results: Of the 434 recruited patients, 228 responded. In exploratory factor analysis (EFA), the Kaiser-Meyer-Olkin (KMO) measure of sampling adequacy = 0.8 and Bartlett's approx. Chi-Square = 1340.0 (df = 105, p < 0.001). We extracted four common factors which could explain 61.47% of the variance. However, Item 15 "Have you changed a traditional Chinese medicine prescription yourself within the past month?" had factor loading = 0.3 and measure of sampling adequacy (MSA) = 0.5, meaning we could not enter it into the factor analysis. The internal consistency reliability for medication adherence was 0.9, with a Guttman splithalf coefficient = 0.5 and a Spearman-Brown coefficient = 0.6. Cronbach's α was 0.9, 0.4 and 0.5 for the knowledge, belief and behavior domains, respectively. The correlation coefficient r of the test-retest reliability was −0.8 and was −0.8, 0.4, −0.3 in the knowledge, belief and behavior domains, respectively. Patients with comorbidities were more likely to respond. We detected no other significant differences in the clinical profiles between respondents and non-respondents. Conclusion:The e-version Chinese and Western medication adherence scales have undesirable construct validity and internal consistency. Thus, caution is needed in transitioning the paper-version scale into an e-version.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.