Automated Prediction of Kidney Failure in IgA Nephropathy with Deep Learning from Biopsy Images

Long-term follow-up of IgA nephropathy: clinicopathological features and predictors of outcomes

Background

The establishment of the Oxford classification and newly developed prediction models have improved the prognostic information for immunoglobulin A nephropathy (IgAN). Considering new treatment options, optimizing prognostic information and improving existing prediction models are favorable.

Methods

We used random forest survival analysis to select possible predictors of end-stage kidney disease among 37 candidate variables in a cohort of 232 patients with biopsy-proven IgAN retrieved from the Norwegian Kidney Biopsy Registry. The predictive value of variables with relative importance >5% was assessed using concordance statistics and the Akaike information criterion. Pearson's correlation coefficient was used to identify correlations between the selected variables.

Results

The median follow-up period was 13.7 years. An isolated analysis of histological variables identified six variables with relative importance >5%: T %, segmental glomerular sclerosis without characteristics associated with other subtypes (not otherwise specified, NOS), normal glomeruli, global sclerotic glomeruli, segmental adherence and perihilar glomerular sclerosis. When histopathological and clinical variables were combined, estimated glomerular filtration rate (eGFR), proteinuria and serum albumin were added to the list. T % showed a better prognostic value than tubular atrophy/interstitial fibrosis (T) lesions with C-indices at 0.74 and 0.67 and was highly correlated with eGFR. Analysis of the subtypes of segmental glomerulosclerosis (S) lesions revealed that NOS and perihilar glomerular sclerosis were associated with adverse outcomes.

Conclusions

Reporting T lesions as a continuous variable, normal glomeruli and subtypes of S lesions could provide clinicians with additional prognostic information and contribute to the improved performance of the Oxford classification and prognostic tools.

Evaluating Progression Risk in Patients With Immunoglobulin A Nephropathy

The highly variable rate of decline in kidney function in patients with immunoglobulin A nephropathy (IgAN) provides a major clinical challenge. Predicting which patients will progress to kidney failure, and how quickly, is difficult. Multiple novel therapies are likely to be approved in the short-term, but clinicians lack the tools to identify patients most likely to benefit from specific treatments at the right time. Noninvasive and validated markers for selecting at-risk patients and longitudinal monitoring are urgently needed. This review summarizes what is known about demographic, clinical, and histopathologic prognostic markers in the clinician's toolkit, including the International IgAN Prediction Tool. We also briefly review what is known on these topics in children and adolescents with IgAN. Although helpful, currently used markers leave clinicians heavily reliant on histologic features from the diagnostic kidney biopsy and standard clinical data to guide treatment choice, and very few noninvasive markers reflect treatment efficacy over time. Novel prognostic and predictive markers are under clinical investigation, with considerable progress being made in markers of complement activation. Other areas of research are the interplay between gut microbiota and galactose-deficient IgA1 expression; microRNAs; imaging; artificial intelligence; and markers of fibrosis. Given the rate of therapeutic advancement, the remaining gaps in biomarker research need to be addressed. We finish by describing our route to clinical utility of predictive and prognostic markers in IgAN. This route will provide us with the chance to improve IgAN prognosis by using robust, clinically practical markers to inform patient care.

Theranostic roles of machine learning in clinical management of kidney stone disease

Kidney stone disease (KSD) is a common illness caused by deposition of solid minerals formed inside the kidney. The disease prevalence varies, based on sociodemographic, lifestyle, dietary, genetic, gender, age, environmental and climatic factors, but has been continuously increasing worldwide. KSD is a highly recurrent disease, and the recurrence rate is about 11% within two years after the stone removal. Recently, machine learning has been widely used for KSD detection, stone type prediction, determination of appropriate treatment modality and prediction of therapeutic outcome. This review provides a brief overview of KSD and discusses how machine learning can be applied to diagnostics, therapeutics and prognostics in clinical management of KSD for better therapeutic outcome.