AutoScore: An Interpretable Machine Learning-Based Automatic Clinical Score Generator

A novel interpretable machine learning-based framework to automate the development of a clinical scoring model for predefined outcomes. Our novel framework consists of six modules: variable ranking with machine learning, variable transformation, score derivation, model selection, domain knowledge-based score fine-tuning, and performance evaluation.The details are described in our research paper<doi:10.2196/21798>. Users or clinicians could seamlessly generate parsimonious sparse-score risk models (i.e., risk scores), which can be easily implemented and validated in clinical practice. We hope to see its application in various medical case studies.

Version: 0.3.0
Depends: R (≥ 2.10)
Imports: tableone, pROC, randomForest, ggplot2, rpart, knitr
Suggests: rmarkdown
Published: 2022-04-08
Author: Feng Xie ORCID iD [aut, cre], Yilin Ning ORCID iD [aut], Han Yuan ORCID iD [aut], Mingxuan Liu ORCID iD [aut], Ehsan Saffari ORCID iD [aut], Bibhas Chakraborty ORCID iD [aut], Nan Liu ORCID iD [aut]
Maintainer: Feng Xie <xief at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
Citation: AutoScore citation info
CRAN checks: AutoScore results


Reference manual: AutoScore.pdf
Vignettes: Guide_book


Package source: AutoScore_0.3.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): AutoScore_0.3.0.tgz, r-oldrel (arm64): AutoScore_0.3.0.tgz, r-release (x86_64): AutoScore_0.3.0.tgz, r-oldrel (x86_64): AutoScore_0.3.0.tgz
Old sources: AutoScore archive


Please use the canonical form to link to this page.