Skip to main content
Journal cover image

AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data.

Publication ,  Journal Article
Xie, F; Ning, Y; Yuan, H; Goldstein, BA; Ong, MEH; Liu, N; Chakraborty, B
Published in: J Biomed Inform
January 2022

BACKGROUND: Scoring systems are highly interpretable and widely used to evaluate time-to-event outcomes in healthcare research. However, existing time-to-event scores are predominantly created ad-hoc using a few manually selected variables based on clinician's knowledge, suggesting an unmet need for a robust and efficient generic score-generating method. METHODS: AutoScore was previously developed as an interpretable machine learning score generator, integrating both machine learning and point-based scores in the strong discriminability and accessibility. We have further extended it to the time-to-event outcomes and developed AutoScore-Survival, for generating time-to-event scores with right-censored survival data. Random survival forest provided an efficient solution for selecting variables, and Cox regression was used for score weighting. We implemented our proposed method as an R package. We illustrated our method in a study of 90-day survival prediction for patients in intensive care units and compared its performance with other survival models, the random survival forest, and two traditional clinical scores. RESULTS: The AutoScore-Survival-derived scoring system was more parsimonious than survival models built using traditional variable selection methods (e.g., penalized likelihood approach and stepwise variable selection), and its performance was comparable to survival models using the same set of variables. Although AutoScore-Survival achieved a comparable integrated area under the curve of 0.782 (95% CI: 0.767-0.794), the integer-valued time-to-event scores generated are favorable in clinical applications because they are easier to compute and interpret. CONCLUSIONS: Our proposed AutoScore-Survival provides a robust and easy-to-use machine learning-based clinical score generator to studies of time-to-event outcomes. It gives a systematic guideline to facilitate the future development of time-to-event scores for clinical applications.

Duke Scholars

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

January 2022

Volume

125

Start / End Page

103959

Location

United States

Related Subject Headings

  • Medical Informatics
  • Machine Learning
  • Likelihood Functions
  • Humans
  • Biomedical Engineering
  • 4601 Applied computing
  • 4203 Health services and systems
  • 11 Medical and Health Sciences
  • 08 Information and Computing Sciences
  • 06 Biological Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Xie, F., Ning, Y., Yuan, H., Goldstein, B. A., Ong, M. E. H., Liu, N., & Chakraborty, B. (2022). AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data. J Biomed Inform, 125, 103959. https://doi.org/10.1016/j.jbi.2021.103959
Xie, Feng, Yilin Ning, Han Yuan, Benjamin Alan Goldstein, Marcus Eng Hock Ong, Nan Liu, and Bibhas Chakraborty. “AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data.J Biomed Inform 125 (January 2022): 103959. https://doi.org/10.1016/j.jbi.2021.103959.
Xie F, Ning Y, Yuan H, Goldstein BA, Ong MEH, Liu N, et al. AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data. J Biomed Inform. 2022 Jan;125:103959.
Xie, Feng, et al. “AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data.J Biomed Inform, vol. 125, Jan. 2022, p. 103959. Pubmed, doi:10.1016/j.jbi.2021.103959.
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. J Biomed Inform. 2022 Jan;125:103959.
Journal cover image

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

January 2022

Volume

125

Start / End Page

103959

Location

United States

Related Subject Headings

  • Medical Informatics
  • Machine Learning
  • Likelihood Functions
  • Humans
  • Biomedical Engineering
  • 4601 Applied computing
  • 4203 Health services and systems
  • 11 Medical and Health Sciences
  • 08 Information and Computing Sciences
  • 06 Biological Sciences