Prediction of ESRD in IgA Nephropathy Patients from an Asian Cohort: A Random Forest Model

Liu, Yexin; Zhang, Yan; Liu, Di; Tan, Xiao; Tang, Xiaofang; Zhang, Fan; Xia, Ming; Chen, Guochun; He, Liyu; Zhou, Letian; Zhu, Xuejing; Liu, Hong

doi:10.1159/000495818

Cited by 43 publications

(28 citation statements)

References 34 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our previous study, serum D-D was found to serve as a potential predictor for thrombotic events in patients with kidney disease [36]. For IgAN, Scr, eGFR, proteinuria, and pathology characteristics have been identi ed as baseline predictors of progression [8,[37][38][39], which is consistent with our ndings. As coagulation function showed an association with the T score of pathology as described, and could be well monitored in a clinical laboratory, it is of clinical signi cance to explore the relationship between coagulation function and the prognosis of IgAN.…”

Section: Discussionsupporting

confidence: 90%

Coagulation parameters are associated with the prognosis of immunoglobulin A nephropathy: a retrospective study

Xia

Liu

Peng

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Background. Interstitial fibrosis/tubular atrophy (T) score is a known determinant of the progression of immunoglobulin A nephropathy (IgAN). Strong evidence indicates that the components of the coagulation system closely linked with fibrotic events have been highlighted in the kidney. However, whether the coagulation system can affect the renal outcome of IgAN remains unclear. Herein, we investigated the association of coagulation parameters and pathological phenotype of IgAN and their combined effects on the deterioration of renal function.Methods. This retrospective study included N=291 patients with biopsy-proven IgAN from May 2009 to April 2013 in the Second Xiangya Hospital. Clinical data, pathological features were collected, and the associations of coagulation parameters at biopsy, T score, and renal outcome were evaluated. T score indicated the degree of tubular atrophy or interstitial fibrosis. The renal outcome was defined as an end-stage renal disease (ESRD) or an irreversible 50% estimated glomerular filtration rate (eGFR) reduction. Results. Shorter prothrombin time (PT) and the activated partial thromboplastin time (APTT) were significantly associated with T (both p<0.001). PT (<11.15s) or APTT (<29.65s) had worse cumulative survival rate (p=0.008, p=0.027 respectively) and were significantly but not independently associated with a higher risk of renal outcome (p=0.012, p=0.032 respectively). In the combined analyses of PT, APTT, and T lesions, the odd ratios for the outcome were significantly higher in the presence of T with PT (<11.15s) or APTT (<29.65s).Conclusion. Shorter PT and APTT are associated with an increased incidence of the T lesion and are additional factors that portend a poorer prognosis in IgAN. Monitoring coagulation function might be important when assessing the risk of progression. Additional studies exploring the molecular mechanism between coagulation and IgAN pathology are needed.

show abstract

Section: Discussionsupporting

confidence: 90%

Coagulation parameters are associated with the prognosis of immunoglobulin A nephropathy: a retrospective study

Xia

Liu

Peng

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent times, machine learning-based methods have found applications in various fields, including medicine [ 17 – 20 ]. In particular, artificial neural networks have been applied in nephrology for various prediction purposes [ 21 – 24 ]. The ability to automatically identify irregularities in data makes machine learning especially useful for big data comprising a large number of variables, where manual alternatives are not viable.…”

Section: Introductionmentioning

confidence: 99%

Increasing tendency of urine protein is a risk factor for rapid eGFR decline in patients with CKD: A machine learning-based prediction model by using a big database

et al. 2020

View full text Add to dashboard Cite

Artificial intelligence is increasingly being adopted in medical fields to predict various outcomes. In particular, chronic kidney disease (CKD) is problematic because it often progresses to end-stage kidney disease. However, the trajectories of kidney function depend on individual patients. In this study, we propose a machine learning-based model to predict the rapid decline in kidney function among CKD patients by using a big hospital database constructed from the information of 118,584 patients derived from the electronic medical records system. The database included the estimated glomerular filtration rate (eGFR) of each patient, recorded at least twice over a period of 90 days. The data of 19,894 patients (16.8%) were observed to satisfy the CKD criteria. We characterized the rapid decline of kidney function by a decline of 30% or more in the eGFR within a period of two years and classified the available patients into two groups—those exhibiting rapid eGFR decline and those exhibiting non-rapid eGFR decline. Following this, we constructed predictive models based on two machine learning algorithms. Longitudinal laboratory data including urine protein, blood pressure, and hemoglobin were used as covariates. We used longitudinal statistics with a baseline corresponding to 90-, 180-, and 360-day windows prior to the baseline point. The longitudinal statistics included the exponentially smoothed average (ESA), where the weight was defined to be 0.9*(t/b), where t denotes the number of days prior to the baseline point and b denotes the decay parameter. In this study, b was taken to be 7 (7-day ESA). We used logistic regression (LR) and random forest (RF) algorithms based on Python code with scikit-learn library ( https://scikit-learn.org/ ) for model creation. The areas under the curve for LR and RF were 0.71 and 0.73, respectively. The 7-day ESA of urine protein ranked within the first two places in terms of importance according to both models. Further, other features related to urine protein were likely to rank higher than the rest. The LR and RF models revealed that the degree of urine protein, especially if it exhibited an increasing tendency, served as a prominent risk factor associated with rapid eGFR decline.

show abstract

“…Similarly, Clinical Decision Support System for IgAN also suggested that age, gender, hypertension, serum creatinine, proteinuria, and histological grade were predictors for renal outcomes. Liu et al [28] fitted a random forest model to predict ESRD for IgAN patients and found that C3 staining, MEST-C scores, and eGFR could convey additional information, and a better interpretative model could provide greater insights into prediction regarding ESRD in IgAN patients.…”

Section: Discussionmentioning

confidence: 99%

Glomerular C4 deposition and glomerulosclerosis predict worse renal outcomes in Chinese patients with IgA nephropathy

et al. 2020

View full text Add to dashboard Cite

Background: Immunoglobulin A nephropathy (IgAN) is a clinical and pathological syndrome with heterogenous manifestation and progression. Complement activation is involved in the disease. However, the clinical significance of C4 deposition in IgAN is obscure. Methods: A multicenter retrospective study was conducted in biopsy-proven IgAN patients. Based on mesangial C4 deposition, patients were divided into two groups. The baseline clinical data and immunopathological phenotypes were compared. The composite endpoint was defined as eGFR decline greater than 50%, doubling of baseline serum creatinine, the occurrence of endstage renal disease (ESRD). Results: A total of 642 IgAN patients were recruited, with 41 patients showing mesangial C4 deposition. The mesangial C4 positive group showed lower serum albumin, higher proteinuria, and a higher rate of IgG, IgM, and C1q mesangial deposition. After a median follow-up of 43.18 months, 81 (12.62%) patients achieved the composite endpoint. The multivariate Cox regression models identified glomerular C4 deposition (hazard ratios [HR] ¼ 3.22, 95% confidence intervals [CI] ¼ 1.51-6.87, p < 0.01), global sclerosis (G1 vs. G0, HR ¼ 1.90, 95%CI ¼ 1.02-3.52, p ¼ 0.04; G2 vs. G0, HR ¼ 3.72, 95%CI ¼ 1.98-7.00, p < 0.01), male (HR ¼ 1.80, 95%CI ¼ 1.10-2.97, p ¼ 0.02), serum creatinine (HR ¼ 1.01, 95%CI ¼ 1.00-1.01, p < 0.01), triglyceride (HR ¼ 1.17, 95%CI ¼ 1.01-1.35, p ¼ 0.04), proteinuria (HR ¼ 1.07, 95%CI ¼ 1.01-1.13, p ¼ 0.02), serum C3 level (HR ¼ 0.05, 95%CI ¼ 0.01-0.25, p < 0.01), and serum C4 level (HR ¼ 99.59, 95%CI ¼ 8.69-1140.89, p < 0.01) as independent risk factors for poor renal outcomes. Conclusions: Glomerular mesangial C4 deposition and global sclerosis are independent predictors for poor prognosis in IgAN patients.

show abstract

Prediction of ESRD in IgA Nephropathy Patients from an Asian Cohort: A Random Forest Model

Cited by 43 publications

References 34 publications

Coagulation parameters are associated with the prognosis of immunoglobulin A nephropathy: a retrospective study

Coagulation parameters are associated with the prognosis of immunoglobulin A nephropathy: a retrospective study

Increasing tendency of urine protein is a risk factor for rapid eGFR decline in patients with CKD: A machine learning-based prediction model by using a big database

Glomerular C4 deposition and glomerulosclerosis predict worse renal outcomes in Chinese patients with IgA nephropathy

Contact Info

Product

Resources

About