Repository files navigation

AutoScore is a novel machine learning framework to automate the development of interpretable clinical scoring models. AutoScore consists of six modules: 1) variable ranking with machine learning, 2) variable transformation, 3) score derivation, 4) model selection, 5) domain knowledge-based score fine-tuning, and 6) performance evaluation. The original AutoScore structure is elaborated inthis article and its flowchart is shown in the following figure. AutoScore was originally designed for binary outcomes and later extended tosurvival outcomes andordinal outcomes. AutoScore could seamlessly generate risk scores using a parsimonious set of variables for different types of clinical outcomes, which can be easily implemented and validated in clinical practice. Moreover, it enables users to build transparent and interpretable clinical scores quickly in a straightforward manner.

Please visit ourbookdown page for a full tutorial on AutoScore usage.

The five pipeline functions constitute the 5-step AutoScore-basedprocess for generating point-based clinical scores for binary, survivaland ordinal outcomes.

This 5-step process gives users the flexibility of customization (e.g.,determining the final list of variables according to the parsimony plot, andfine-tuning the cutoffs in variable transformation):

• STEP(i):AutoScore_rank()orAutoScore_rank_Survival() orAutoScore_rank_Ordinal() - Rank variables with machine learning(AutoScore Module 1)
• STEP(ii):AutoScore_parsimony() orAutoScore_parsimony_Survival() orAutoScore_parsimony_Ordinal() - Select the best model withparsimony plot (AutoScore Modules 2+3+4)
• STEP(iii):AutoScore_weighting() orAutoScore_weighting_Survival() orAutoScore_weighting_Ordinal() - Generate the initial score withthe final list of variables (Re-run AutoScore Modules 2+3)
• STEP(iv):AutoScore_fine_tuning() orAutoScore_fine_tuning_Survival() orAutoScore_fine_tuning_Ordinal() - Fine-tune the score by revisingcut_vec with domain knowledge (AutoScore Module 5)
• STEP(v):AutoScore_testing() orAutoScore_testing_Survival() orAutoScore_testing_Ordinal() - Evaluate the final score with ROCanalysis (AutoScore Module 6)

We also include several optional functions in the package, which could help with data analysis and result reporting.

• Xie F, Chakraborty B, Ong MEH, Goldstein BA, Liu N.AutoScore: A machine learning-based automatic clinical score generator and its application to mortality prediction using electronic health records. JMIR Medical Informatics 2020; 8(10): e21798.
• Xie F, Ning Y, Liu M, Li S, Saffari SE, Yuan H, Volovici V, Ting DSW, Goldstein BA, Ong MEH, Vaughan R, Chakraborty B, Liu N.A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes. STAR Protocols 2023 Jun; 4(2): 102302.

• Xie F, Ning Y, Yuan H, Goldstein BA, Ong MEH, Liu N, Chakraborty B.AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data. Journal of Biomedical Informatics 2022; 125: 103959.

• Saffari SE, Ning Y, Xie F, Chakraborty B, Volovici V, Vaughan R, Ong MEH, Liu N,AutoScore-Ordinal: An interpretable machine learning framework for generating scoring models for ordinal outcomes, BMC Medical Research Methodology 2022; 22: 286.

• Ning Y, Li S, Ong ME, Xie F, Chakraborty B, Ting DS, Liu N.A novel interpretable machine learning system to generate clinical risk scores: An application for predicting early mortality or unplanned readmission in a retrospective cohort study. PLOS Digital Health 2022; 1(6): e0000062.

This page provides a collection of clinical applications using AutoScore and its extensions. The application list is categorized according to medical specialties and is updated regularly. However, due to the manual process of updating, we are unable to keep track of all publications.

• Feng Xie (Email:xief@u.duke.nus.edu)
• Yilin Ning (Email:yilin.ning@duke-nus.edu.sg)
• Nan Liu (Email:liu.nan@duke-nus.edu.sg)

Install from GitHub or CRAN:

# From Githubinstall.packages("devtools")library(devtools)install_github(repo="nliulab/AutoScore",build_vignettes=TRUE)# From CRAN (recommended)install.packages("AutoScore")

Load AutoScore package:

library(AutoScore)