A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

Feng Xie; Yilin Ning; Mingxuan Liu; Siqi Li; Seyed Ehsan Saffari; Han Yuan; Victor Volovici; Daniel Shu Wei Ting; Benjamin Alan Goldstein; Marcus Eng Hock Ong; Roger Vaughan; Bibhas Chakraborty; Nan Liu

doi:10.1016/j.xpro.2023.102302

A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

Feng Xie, Yilin Ning, Mingxuan Liu, Siqi Li, Seyed Ehsan Saffari, Han Yuan, Victor Volovici, Daniel Shu Wei Ting, Benjamin Alan Goldstein, Marcus Eng Hock Ong, Roger Vaughan, Bibhas Chakraborty, Nan Liu^*

^*Corresponding author for this work

Neurosurgery

Research output: Contribution to journal › Article › Academic › peer-review

6 Citations (Scopus)

35 Downloads (Pure)

Abstract

The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),¹ Xie et al. (2022)², Saffari et al. (2022)³ and the online tutorial https://nliulab.github.io/AutoScore/.

Original language	English
Article number	102302
Journal	STAR Protocols
Volume	4
Issue number	2
DOIs	https://doi.org/10.1016/j.xpro.2023.102302
Publication status	Published - 16 Jun 2023

Bibliographical note

Acknowledgments:
This study was supported by Duke-NUS Medical School , Singapore. Y.N. is supported by the Khoo Postdoctoral Fellowship Award (project no. Duke-NUS- KPFA/2021/0051 ) from the Estate of Tan Sri Khoo Teck Puat. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Publisher Copyright: © 2023 The Authors

Access to Document

10.1016/j.xpro.2023.102302Licence: CC BY

1-s2.0-S2666166723002691-mainFinal published version, 5.87 MBLicence: CC BY

Cite this

Xie, F., Ning, Y., Liu, M., Li, S., Saffari, S. E., Yuan, H., Volovici, V., Ting, D. S. W., Goldstein, B. A., Ong, M. E. H., Vaughan, R., Chakraborty, B., & Liu, N. (2023). A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes. STAR Protocols, 4(2), Article 102302. https://doi.org/10.1016/j.xpro.2023.102302

@article{11e88d9972f4435ead4407b3313727d1,

title = "A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes",

abstract = "The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),1 Xie et al. (2022)2, Saffari et al. (2022)3 and the online tutorial https://nliulab.github.io/AutoScore/.",

author = "Feng Xie and Yilin Ning and Mingxuan Liu and Siqi Li and Saffari, {Seyed Ehsan} and Han Yuan and Victor Volovici and Ting, {Daniel Shu Wei} and Goldstein, {Benjamin Alan} and Ong, {Marcus Eng Hock} and Roger Vaughan and Bibhas Chakraborty and Nan Liu",

note = "Acknowledgments: This study was supported by Duke-NUS Medical School , Singapore. Y.N. is supported by the Khoo Postdoctoral Fellowship Award (project no. Duke-NUS- KPFA/2021/0051 ) from the Estate of Tan Sri Khoo Teck Puat. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: {\textcopyright} 2023 The Authors",

year = "2023",

month = jun,

day = "16",

doi = "10.1016/j.xpro.2023.102302",

language = "English",

volume = "4",

journal = "STAR Protocols",

issn = "2666-1667",

publisher = "Cell Press",

number = "2",

}

TY - JOUR

T1 - A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

AU - Xie, Feng

AU - Ning, Yilin

AU - Liu, Mingxuan

AU - Li, Siqi

AU - Saffari, Seyed Ehsan

AU - Yuan, Han

AU - Volovici, Victor

AU - Ting, Daniel Shu Wei

AU - Goldstein, Benjamin Alan

AU - Ong, Marcus Eng Hock

AU - Vaughan, Roger

AU - Chakraborty, Bibhas

AU - Liu, Nan

N1 - Acknowledgments: This study was supported by Duke-NUS Medical School , Singapore. Y.N. is supported by the Khoo Postdoctoral Fellowship Award (project no. Duke-NUS- KPFA/2021/0051 ) from the Estate of Tan Sri Khoo Teck Puat. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Publisher Copyright: © 2023 The Authors

PY - 2023/6/16

Y1 - 2023/6/16

N2 - The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),1 Xie et al. (2022)2, Saffari et al. (2022)3 and the online tutorial https://nliulab.github.io/AutoScore/.

AB - The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),1 Xie et al. (2022)2, Saffari et al. (2022)3 and the online tutorial https://nliulab.github.io/AutoScore/.

UR - http://www.scopus.com/inward/record.url?scp=85159322832&partnerID=8YFLogxK

U2 - 10.1016/j.xpro.2023.102302

DO - 10.1016/j.xpro.2023.102302

M3 - Article

C2 - 37178115

AN - SCOPUS:85159322832

SN - 2666-1667

VL - 4

JO - STAR Protocols

JF - STAR Protocols

IS - 2

M1 - 102302

ER -

A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this