The future of artificial intelligence in intensive care: moving from predictive to actionable AI

the Causal Inference for ICU Collaborators; Jim M. Smit; Jesse H. Krijthe; Jasper van Bommel; M. E. van Genderen; J. A. Labrecque; M. Komorowski; D. A.M.P.J. Gommers; M. J.T. Reinders

doi:10.1007/s00134-023-07102-y

The future of artificial intelligence in intensive care: moving from predictive to actionable AI

the Causal Inference for ICU Collaborators, Jim M. Smit^*, Jesse H. Krijthe, Jasper van Bommel, M. E. van Genderen, J. A. Labrecque, M. Komorowski, D. A.M.P.J. Gommers, M. J.T. Reinders

^*Corresponding author for this work

Research output: Contribution to journal › Comment/Letter to the editor › Scientific › peer-review

6 Citations (Scopus)

42 Downloads (Pure)

Abstract

Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict out-
comes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the impor- tance of causal inference, we propose to refer to any data- driven model used for causal inference tasks as ‘action- able AI’, as opposed to ‘predictive AI’, and discuss how these models could provide meaningful decision support in the ICU.

Original language	English
Pages (from-to)	1114-1116
Number of pages	3
Journal	Intensive Care Medicine
Volume	49
Issue number	9
DOIs	https://doi.org/10.1007/s00134-023-07102-y
Publication status	Published - 2023

Access to Document

10.1007/s00134-023-07102-y

s00134-023-07102-yFinal published version, 1.25 MBLicence: CC BY-NC

Cite this

the Causal Inference for ICU Collaborators, Smit, J. M., Krijthe, J. H., van Bommel, J., van Genderen, M. E., Labrecque, J. A., Komorowski, M., Gommers, D. A. M. P. J., & Reinders, M. J. T. (2023). The future of artificial intelligence in intensive care: moving from predictive to actionable AI. Intensive Care Medicine, 49(9), 1114-1116. https://doi.org/10.1007/s00134-023-07102-y

@article{38dd500a7e714ae19b383d8c756c2637,

title = "The future of artificial intelligence in intensive care: moving from predictive to actionable AI",

abstract = "Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict out-comes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the impor- tance of causal inference, we propose to refer to any data- driven model used for causal inference tasks as {\textquoteleft}action- able AI{\textquoteright}, as opposed to {\textquoteleft}predictive AI{\textquoteright}, and discuss how these models could provide meaningful decision support in the ICU.",

author = "{the Causal Inference for ICU Collaborators} and Smit, {Jim M.} and Krijthe, {Jesse H.} and {van Bommel}, Jasper and {van Genderen}, {M. E.} and Labrecque, {J. A.} and M. Komorowski and Gommers, {D. A.M.P.J.} and Reinders, {M. J.T.}",

year = "2023",

doi = "10.1007/s00134-023-07102-y",

language = "English",

volume = "49",

pages = "1114--1116",

journal = "Intensive Care Medicine",

issn = "0342-4642",

publisher = "Springer",

number = "9",

}

TY - JOUR

T1 - The future of artificial intelligence in intensive care

T2 - moving from predictive to actionable AI

AU - the Causal Inference for ICU Collaborators

AU - Smit, Jim M.

AU - Krijthe, Jesse H.

AU - van Bommel, Jasper

AU - van Genderen, M. E.

AU - Labrecque, J. A.

AU - Komorowski, M.

AU - Gommers, D. A.M.P.J.

AU - Reinders, M. J.T.

PY - 2023

Y1 - 2023

N2 - Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict out-comes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the impor- tance of causal inference, we propose to refer to any data- driven model used for causal inference tasks as ‘action- able AI’, as opposed to ‘predictive AI’, and discuss how these models could provide meaningful decision support in the ICU.

AB - Artificial intelligence (AI) research in the intensive care unit (ICU) mainly focuses on developing models (from linear regression to deep learning) to predict out-comes, such as mortality or sepsis [1, 2]. However, there is another important aspect of AI that is typically not framed as AI (although it may be more worthy of the name), which is the prediction of patient outcomes or events that would result from different actions, known as causal inference [3, 4]. This aspect of AI is crucial for decision-making in the ICU. To emphasize the impor- tance of causal inference, we propose to refer to any data- driven model used for causal inference tasks as ‘action- able AI’, as opposed to ‘predictive AI’, and discuss how these models could provide meaningful decision support in the ICU.

UR - http://www.scopus.com/inward/record.url?scp=85161090364&partnerID=8YFLogxK

U2 - 10.1007/s00134-023-07102-y

DO - 10.1007/s00134-023-07102-y

M3 - Comment/Letter to the editor

C2 - 37278758

AN - SCOPUS:85161090364

SN - 0342-4642

VL - 49

SP - 1114

EP - 1116

JO - Intensive Care Medicine

JF - Intensive Care Medicine

IS - 9

ER -

The future of artificial intelligence in intensive care: moving from predictive to actionable AI

Abstract

Access to Document

Other files and links

Fingerprint

Cite this