AutoScore: An Interpretable Machine Learning-Based Automatic Clinical Score
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 The original AutoScore structure is described in the research paper<doi:10.2196/21798>. A full tutorial can be found here<https://nliulab.github.io/AutoScore/>. 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.
||R (≥ 3.5.0)
||tableone, pROC, randomForest, ggplot2, knitr, Hmisc, car, coxed, dplyr, ordinal, survival, tidyr, plotly, magrittr, randomForestSRC, rlang, survAUC, survminer
||Feng Xie [aut,
Yilin Ning [aut],
Han Yuan [aut],
Seyed Ehsan Saffari
Siqi Li [aut],
Nan Liu [aut]
||Feng Xie <xief at u.duke.nus.edu>
||GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
||AutoScore citation info
Please use the canonical form
to link to this page.