Why the study?
Existing polygenic risk scoring models for SLE assume independent and additive contributions of genetic variants, leaving room to improve prediction accuracy using machine-learning algorithms.
Does a random forest algorithm improve the accuracy of genetic risk prediction for systemic lupus erythematosus compared to polygenic risk scoring?
Population
19,208 participants from previous Chinese or European GWAS
Comparison
RF vs SVM, ANN, and PRS models
Design
Machine-learning prediction model development and validation study
Authors
Loading...
RF models may aid SLE genetic risk stratification in Chinese cohorts; hypothesis-generating and requires prospective validation before clinical use.
Does a random forest algorithm improve the accuracy of genetic risk prediction for systemic lupus erythematosus compared to polygenic risk scoring?
A random forest machine-learning algorithm significantly improves the accuracy of genetic risk prediction for systemic lupus erythematosus compared to traditional polygenic risk scoring.
Ma et al. (2022) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: