This repository contains code to reproduce the results presented in the paper
Charu V, Liang JW, Mannalithara A, Kwong A, Tian, Lu, and Kim, RW. Benchmarking clinical risk prediction algorithms with ensemble machine learning: An illustration of the superlearner algorithm for the non-invasive diagnosis of liver fibrosis in non-alcoholic fatty liver disease. 2024.
- Data wrangling and visualization:
tidyverse
,gridExtra
,gtable
,reshape2
,forcats
, andcowplot
- Superlearners:
Superlearner
- Performance metrics and survey weighting:
cvAUC
,pROC
,survey
,DescTools
, andWeightedROC
- Nonalcoholic Steatohepatitis Clinical Research Network Cohort1 (NASH-CRN; training set)
- Farnesoid X Receptor (FXR) Ligand Obeticholic Acid in NASH Treatment trial2 (FLINT; testing set 1)
- National Health and Nutrition Examination Survey NAFLD Cohort3 (NHANES-NAFLD; testing set 2)
1. Harrison SA, Oliver D, Arnold HL, Gogia S, Neuschwander-Tetri BA. Development and validation of a simple NAFLD clinical scoring system for identifying patients without advanced disease. Gut. 2008;57(10):1441-1447. doi:10.1136/gut.2007.146019
2. Neuschwander-Tetri BA, Loomba R, Sanyal AJ, et al. Farnesoid X nuclear receptor ligand obeticholic acid for non-cirrhotic, non-alcoholic steatohepatitis (FLINT): a multicentre, randomised, placebo-controlled trial. Lancet. 2015;385(9972):956-965.
3. National Center for Health Statistics. About the National Health and Nutrition Examination Survey. Accessed October 17, 2021. https://www.cdc.gov/nchs/nhanes/about_nhanes.htm