A decision tree model based on clinical and laboratory manifestations as predictor of kidney biopsy findings in patients with lupus nephritis (original) (raw)
Related papers
Early Prediction of Lupus Disease: A Study on the Variations of Decision Tree Models
Research Square (Research Square), 2022
Systematic Lupus Erythematosus (SLE) is an irreversible autoimmune disease that has seen to bring a lot of negative effect on the human body. It has become a very challenging task in predicting the prevalence of Lupus in patients. It has slowly gained popularity among many researchers to study the prevalence of this disease and developing prediction models that not only study the prevalence of the disease but is also able to predict suitable dosage requirements, treatment effectiveness and the severity of the disease in patients. All of these is usually done with medical records or clinical data that has different attributes related and signi cant to the analysis done. With the advancement in machine learning models and ensemble techniques, accurate prediction models have been developed. However, these models are not able to explain the signi cant contributing factors as well as correctly classify the severity of the disease. Decision Tree Classi er, Random Forest Classi er and Extreme Gradient Boosting (XGBoost) are the models that will be used in this paper to predict the early prevalence to Lupus Disease in patients using clinical records. The most signi cant factors affecting Systematic Lupus Erythematosus (SLE) will then be identi ed to aid medical practitioners to take suitable preventive measures that can manage the complications that arise from the disease. Hence, this paper aims to assess the performance of tree models by performing several experiments on the hyper parameters to develop a more accurate model that is able to classify Lupus Disease in patients in the early stages. Findings revealed that the best model was the Random Forest Classi er with parameter tuning. The most signi cant factor that affected the presence of Lupus Disease in patients was identi ed as the Ethnicity and the Renal Outcome or the kidney function of the patients.
2021
Objective Lupus nephritis (LN) is an immune complex-mediated glomerular and tubulointerstitial disease in patients with SLE. Prediction of outcomes at the onset of LN diagnosis can guide decisions regarding intensity of monitoring and therapy for treatment success. Currently, no machine learning model of outcomes exists. Several outcomes modelling works have used univariate or linear modelling but were limited by the disease heterogeneity. We hypothesised that a combination of renal pathology results and routine clinical laboratory data could be used to develop and to cross-validate a clinically meaningful machine learning early decision support tool that predicts LN outcomes at approximately 1 year. Methods To address this hypothesis, patients with LN from a prospective longitudinal registry at the Medical University of South Carolina enrolled between 2003 and 2017 were identified if they had renal biopsies with International Society of Nephrology/Renal Pathology Society pathologic...
Journal of Population Therapeutics & Clinical Pharmacology
Background: The most common symptom of systematic lupus erythematosus (SLE) is lupus nephritis (LN), with an incidence of 50-70%. Kidney biopsy, which enables histology-based classification in accordance with World Health Organization (WHO) standards declared in 1982, is the main method used to examine LN. This study aimed to classify LN according to the International Society of Nephrology/Renal Pathology Society (ISN/RPS) 2003 classification system and determine the prevalence of different classes. Methods: The Nephrology Department at a tertiary care hospital in Islamabad, Pakistan, conducted a retrospective observational study between February 2012 and April 2018. The study included adult
Acta medica Indonesiana, 2018
BACKGROUND proliferative lupus nephritis (LN) has higher prevalence and worse prognosis than non-proliferative LN. Renal biopsy plays an important role in diagnosis and therapy of LN, but there are some obstacles in its implementation. A diagnostic scoring system for proliferative LN is necessary, especially for cases in which renal biopsy cannot be performed. This study aimed to develop a diagnostic scoring system of proliferative LN based on its diagnostic determinants including hypertension, proteinuria, hematuria, eGFR, anti-dsDNA antibody, and C3 levels. METHODS a cross-sectional study with total sampling method was conducted. Our subjects were adult LN patients who underwent renal biopsy in Cipto Mangunkusumo Hospital between January 2007 and June 2017. RESULTS from a total of 191 subjects with biopsy-proven LN in this study, we found a proportion of proliferative LN of 74.8%. There were 113 subjects included for analysis of proliferative LN determinants. The multivariate anal...
Journal of laboratory physicians
Lupus nephritis (LN) is a major complication of systemic lupus erythematosus (SLE). Renal involvement is a major determinant of the prognosis of SLE. The histological classification of LN is a key factor in determining the renal survival of patients with LN. Prompt recognition and treatment of renal disease are important, as early response to therapy is correlated with better outcome and renal biopsy plays an important role in achieving this. The objective of this study was to correlate the clinical and laboratory findings with histopathological classes of LN as per the 2003 International Society of Nephrology-Renal Pathology Society (ISN/RPS) classification system. Fifty-six patients with SLE, undergoing a renal biopsy for renal dysfunction were studied. The comparison of data from multiple groups was made by Pearson's Chi-square test and between two groups by independent samples t-test. The values of P < 0.05 were considered statistically significant. Of the 56 cases studie...
Diagnostics
Objectives: To assess the performance of clinical and biochemical parameters in identifying renal histopathology. To assess the performance of a combination of demographic, clinical, serological and histopathological parameters in determining renal response at one year. Methods: Data of biopsy-proven (ISN/RPS—2003 criteria) Lupus Nephritis (LN) were extracted from the institute database. Demographic, clinical and biochemical parameters at the time of biopsy were noted, and their associations with histopathological class, activity and chronicity scores were evaluated. Follow-up data at one year were collected. Complete, partial or no response (CR, PR, NR) for renal outcomes at one year and the predictors of NR were assessed. Results: Out of the 333 renal biopsies, 240 (71.8%) were Class III/IV. More patients with Class III/IV LN had hypertension (52.1%) and low eGFR (p < 0.001). Among Class III/IV, AS correlated weakly with UPCR (r = 0.31, p < 0.01), eGFR (r = −0.172; p < 0....
Lupus, 2002
Arti cial neural networks are intelligent systems that have been successfully used for prediction in different medical elds. In this study, ef ciency of neural networks for prediction of lupus nephritis in patients with systemic lupus erythematosus (SLE) was compared with a logistic regression model and clinicians' diagnosis. Overall accuracy, sensitivity and speci city of the optimal neural network were 68.69, 73.77 and 62.96%, respectively. Overall accuracy of neural network was greater than the other two methods (P-value < 0.05). The neural network was more speci c in predicting lupus nephritis (P-value < 0.01), but there was no signi cant difference between sensitivities of the three methods. Sensitivities of all three methods were greater than their speci cities. We concluded that neural networks are ef cient in predicting lupus nephritis in SLE patients. Lupus (2002) 11, 485-492.
Zahedan Journal of Research in Medical Sciences
Background: There are controversies regarding the diagnosis of lupus nephritis. Also, its clinical manifestations and severity are different from one patient to another. Objectives: The current study aimed to interpret clinical and laboratory features of lupus nephritis according to the results of the biopsy. Methods: Following a retrospective design, 30 patients with lupus, who were candidates for renal biopsy and undergoing kidney biopsy, were studied. Clinical findings (blood pressure and limb edema) and laboratory findings (Cr, ESR, CRP, BUN, C3, C4, CH50, Anti-ds DNA, and hematuria) were gathered. Finally, the diagnostic value of clinical and laboratory findings was interpreted according to the biopsies and the staging of samples in the pathology. Data were analyzed using SPSS. Quantitative variables are displayed using mean and quartiles. Fisher’s exact test was used to compare study groups. Also, independent samples t-test and Levene’s test were used to evaluate variances of ...
Clinicopathological correlations in lupus nephritis; a single center experience
Journal of nephropathology, 2014
Renal biopsies play an important role in the diagnosis, management and prognosis of patients with lupus nephritis (LN). To determine the correlation between the pathological features of LN and the demographic, clinical and laboratory parameters. This retrospective study was conducted from 2008 to 2014 on all consecutive cases of biopsy-proven LN at a nephropathology laboratory in Iran. The demographic, clinical and laboratory data were obtained from patients(') files and the biopsy findings from the original biopsy request forms. Of the 84 patients enrolled, 69 (82.2%) were females and 15 (17.8%) males. The mean age was 32.7±12 years. The mean serum creatinine was 1.5±0.94 mg/dl and the mean 24-h proteinuria, 1.6±1.9 grams. The majority of cases belonged to classes III and IV. The extracapillary proliferation was found in 42.86% of biopsies and endocapillary proliferation in 66.67% of biopsies. Patients of class IV-LN had a higher mean serum value of creatinine in comparison to ...
Morphological Indexes: Can They Predict Lupus Nephritis Outcomes? A Retrospective Study
Acta Médica Portuguesa, 2019
Introduction: Lupus nephritis is a serious complication of systemic lupus erythematosus. Currently, therapy is guided by findings in the renal biopsy, following the International Society of Nephrology / Renal Pathology Society classification. Austin and Hill’s histomorphological indexes are not routinely obtained. In this retrospective single-centre study, we aimed to analyze the importance and applicability of the different morphological indexes in predicting response to treatment and prognosis.Material and Methods: Patients with kidney biopsy demonstrating lupus nephritis from the 2010 – 2016 period were included. We analyzed their demographic data, comorbidities, clinical presentation and laboratorial evaluation at the time of renal biopsy. We evaluated the following outcomes: clinical remission, renal function and proteinuria at end of follow-up. Histologic analysis was performed using the International Society of Nephrology / Renal Pathology Society classification and the morph...