Lupus nephritis (LN) is a major organ complication and cause of morbidity and mortality in patients with systemic lupus erythematosus. This study aims to provide the clinician with a quantitative tool for the prediction of the individual remission probability of LN and obtain new insights for improved clinical management in LN treatment.Lupus nephritis (LN) is a frequent and severe manifestation of systemic lupus erythematosus (SLE). The impairment of renal function results from glomerular, tubulointerstitial and vascular lesions. LN occurs mostly within five years from the diagnosis in about 40% of patients with SLE. LN develops into end-stage renal disease (ESRD) at a rate of 4.3%–10.1% within overall 10 years. Renal failure is one of the most common causes of death in patients with SLE and is linked to low health-related quality of life. The probability of remission in LN remains low in the past few years. Different investigations examined clinical and serological markers, including serum creatinine, proteinuria levels and haematuria, as predictors of renal prognosis. However, these markers have not shown the ability to predict the long-term kidney outcome adequately. Despite a substantial improvement in SLE diagnosis and treatment over the years, the prognosis of patients with LN is difficult to predict. Given its development, machine learning is gradually applied to predictive models and can assist clinicians in defining treatment responses.

The nomogram, which is widely used for disease prognosis at present, is tailored to the profile of an individual patient and facilitates clinical decision-making. For example, the nomogram is widely used in the prognosis of cancer and nerve- and infection-related diseases. However, no clinically existing individual tool is available to predict remission by using baseline data in SLE even in patients with LN. Despite the development of machine learning models, currently used clinical biomarkers provide only 69% accuracy for predicting LN prognosis. Thus, a noninvasive and powerful predictive model of LN that uses clinical registries with an optimal collection of patients’ data and biospecimens should be developed. This study intends to analyse the factors affecting the remission probability of patients with LN and develop a novel clinical model to predict the probability of remission in patients with LN.

visit for more articles at  Journal of Clinical & Experimental Nephrology

Kindly submit your article at https://www.imedpub.com/submissions/clinical-experimental-nephrology.html or nephrology@eclinicalsci.com 

Regards
Mishita
Jornal co-ordinator
Journal of Clinical & Experimental Nephrology