Machine learning for risk stratification in kidney disease

Abstract

Purpose of reviewRisk stratification for chronic kidney is becoming increasingly important as a clinical tool for both treatment and prevention measures. The goal of this review is to identify how machine learning tools contribute and facilitate risk stratification in the clinical setting.Recent findingsThe two key machine learning paradigms to predictively stratify kidney disease risk are genomics-based and electronic health record based approaches. These methods can provide both quantitative information such as relative risk and qualitative information such as characterizing risk by subphenotype.SummaryThe four key methods to stratify chronic kidney disease risk are genomics, multiomics, supervised and unsupervised machine learning methods. Polygenic risk scores utilize whole genome sequencing data to generate an individual's relative risk compared with the population. Multiomic methods integrate information from multiple biomarkers to generate trajectories and prognostic different outcomes. Supervised machine learning methods can directly utilize the growing compendia of electronic health records such as laboratory results and notes to generate direct risk predictions, while unsupervised machine learning methods can cluster individuals with chronic kidney disease into subphenotypes with differing approaches to care.

Derivation and Validation of a Machine Learning Approach to Detect and Mitigate Biases in Healthcare Data

“…The minimum number of samples n such that E[g n (X train , X train )] < 1.0 is the minimum convergence sample estimate. Above the minimum convergence sample, our previous work has shown that the decrease in autoencoder loss is proportional to the gain in generalizability as measured by area-under-the-curve metric 4 . We have previously shown that the minimum convergence sample estimate remains a valid approximation of generalizability across model architecture, hyperparameter selections, dataset dimensions and dataset complexity.…”

Integration of Federated Learning and Blockchain in Healthcare: A Tutorial

“…• Disease prediction and Risk Stratification: ML algorithms scrutinize genomic data to discern patterns and variations linked to specific diseases. This analytical approach allows for the assessment of the risk associated with certain health conditions [144]- [148].…”

Designing a Smart IoT Environment by Predicting Chronic Kidney Disease Using Kernel Based Xception Deep Learning Model

“…The medical term for the slow, progressive loss of kidney function that occurs over time is "chronic." CKD is a leading cause of death in countries owing to a lack of access to quality, cost-effective healthcare [14]. CKD may lead to cardiovascular disease and is permanent in its progression.…”