Risk scores in anaesthesia: the future is hard to predict

Daniel James Drayton; Michael Ayres; Samuel D Relton; Matthew Sperrin; Marlous Hall

doi:10.1016/j.bjao.2022.100027

Risk scores in anaesthesia: the future is hard to predict

BJA Open. 2022 Aug 17:3:100027. doi: 10.1016/j.bjao.2022.100027. eCollection 2022 Sep.

Authors

Daniel James Drayton¹, Michael Ayres², Samuel D Relton³, Matthew Sperrin⁴, Marlous Hall¹

Affiliations

¹ Leeds Institute for Data Analytics, Leeds, UK.
² Leeds Institute of Medical Research, Leeds, UK.
³ Leeds Institute of Health Science, University of Leeds, Leeds, UK.
⁴ Division of Informatics, Imaging & Data Sciences, University of Manchester, Manchester, UK.

Abstract

External validation helps to assess whether a given risk prediction model will perform well in a target population. Validation is an important step in maintaining the utility of risk prediction models, as their ability to provide reliable risk estimates will deteriorate over time (calibration drift).

Keywords: anaesthesia; modelling; perioperative medicine; perioperative risk; risk prediction.

Publication types

Editorial