Directed acyclic graphs: a tool for causal studies in paediatrics

Thomas C. Williams; Cathrine C. Bach; Niels B. Matthiesen; Tine B. Henriksen; Luigi Gagliardi

doi:10.1038/s41390-018-0071-3

Directed acyclic graphs: a tool for causal studies in paediatrics

Thomas C. Williams, Cathrine C. Bach, Niels B. Matthiesen, Tine B. Henriksen, Luigi Gagliardi^*

^*Corresponding author af dette arbejde

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Review › Forskning › peer review

3 Citationer (Scopus)

197 Downloads (Pure)

Abstract

Many paediatric clinical research studies, whether observational or interventional, have as an eventual aim the identification or quantification of causal relationships. One might ask: does screen time influence childhood obesity? Could overuse of paracetamol in infancy cause wheeze? How does breastfeeding affect later cognitive outcomes? In this review, we present causal directed acyclic graphs (DAGs) to a paediatric audience. DAGs are a graphical tool which provide a way to visually represent and better understand the key concepts of exposure, outcome, causation, confounding, and bias. We use clinical examples, including those outlined above, framed in the language of DAGs, to demonstrate their potential applications. We show how DAGs can be most useful in identifying confounding and sources of bias, demonstrating inappropriate statistical adjustments for presumed biases, and understanding threats to validity in randomised controlled trials. We believe that a familiarity with DAGs, and the concepts underlying them, will be of benefit both to the researchers planning studies, and practising clinicians interpreting them.

Originalsprog	Engelsk
Tidsskrift	Pediatric Research
Vol/bind	84
Nummer	4
Sider (fra-til)	487-493
Antal sider	7
ISSN	0031-3998
DOI	https://doi.org/10.1038/s41390-018-0071-3
Status	Udgivet - okt. 2018

Adgang til dokumentet

10.1038/s41390-018-0071-3

s41390-018-0071-3Forlagets udgivne version, 670 KBLicens: CC BY

Andre filer og links

http://www.scopus.com/inward/record.url?scp=85049529863&partnerID=8YFLogxK

Citationsformater

@article{66d52e1bd8eb40a8a932f55d8e996b1f,

title = "Directed acyclic graphs: a tool for causal studies in paediatrics",

abstract = "Many paediatric clinical research studies, whether observational or interventional, have as an eventual aim the identification or quantification of causal relationships. One might ask: does screen time influence childhood obesity? Could overuse of paracetamol in infancy cause wheeze? How does breastfeeding affect later cognitive outcomes? In this review, we present causal directed acyclic graphs (DAGs) to a paediatric audience. DAGs are a graphical tool which provide a way to visually represent and better understand the key concepts of exposure, outcome, causation, confounding, and bias. We use clinical examples, including those outlined above, framed in the language of DAGs, to demonstrate their potential applications. We show how DAGs can be most useful in identifying confounding and sources of bias, demonstrating inappropriate statistical adjustments for presumed biases, and understanding threats to validity in randomised controlled trials. We believe that a familiarity with DAGs, and the concepts underlying them, will be of benefit both to the researchers planning studies, and practising clinicians interpreting them.",

author = "Williams, {Thomas C.} and Bach, {Cathrine C.} and Matthiesen, {Niels B.} and Henriksen, {Tine B.} and Luigi Gagliardi",

year = "2018",

month = oct,

doi = "10.1038/s41390-018-0071-3",

language = "English",

volume = "84",

pages = "487--493",

journal = "Pediatric Research",

issn = "0031-3998",

publisher = "Nature Publishing Group",

number = "4",

}

TY - JOUR

T1 - Directed acyclic graphs

T2 - a tool for causal studies in paediatrics

AU - Williams, Thomas C.

AU - Bach, Cathrine C.

AU - Matthiesen, Niels B.

AU - Henriksen, Tine B.

AU - Gagliardi, Luigi

PY - 2018/10

Y1 - 2018/10

N2 - Many paediatric clinical research studies, whether observational or interventional, have as an eventual aim the identification or quantification of causal relationships. One might ask: does screen time influence childhood obesity? Could overuse of paracetamol in infancy cause wheeze? How does breastfeeding affect later cognitive outcomes? In this review, we present causal directed acyclic graphs (DAGs) to a paediatric audience. DAGs are a graphical tool which provide a way to visually represent and better understand the key concepts of exposure, outcome, causation, confounding, and bias. We use clinical examples, including those outlined above, framed in the language of DAGs, to demonstrate their potential applications. We show how DAGs can be most useful in identifying confounding and sources of bias, demonstrating inappropriate statistical adjustments for presumed biases, and understanding threats to validity in randomised controlled trials. We believe that a familiarity with DAGs, and the concepts underlying them, will be of benefit both to the researchers planning studies, and practising clinicians interpreting them.

AB - Many paediatric clinical research studies, whether observational or interventional, have as an eventual aim the identification or quantification of causal relationships. One might ask: does screen time influence childhood obesity? Could overuse of paracetamol in infancy cause wheeze? How does breastfeeding affect later cognitive outcomes? In this review, we present causal directed acyclic graphs (DAGs) to a paediatric audience. DAGs are a graphical tool which provide a way to visually represent and better understand the key concepts of exposure, outcome, causation, confounding, and bias. We use clinical examples, including those outlined above, framed in the language of DAGs, to demonstrate their potential applications. We show how DAGs can be most useful in identifying confounding and sources of bias, demonstrating inappropriate statistical adjustments for presumed biases, and understanding threats to validity in randomised controlled trials. We believe that a familiarity with DAGs, and the concepts underlying them, will be of benefit both to the researchers planning studies, and practising clinicians interpreting them.

UR - http://www.scopus.com/inward/record.url?scp=85049529863&partnerID=8YFLogxK

U2 - 10.1038/s41390-018-0071-3

DO - 10.1038/s41390-018-0071-3

M3 - Review

C2 - 29967527

AN - SCOPUS:85049529863

SN - 0031-3998

VL - 84

SP - 487

EP - 493

JO - Pediatric Research

JF - Pediatric Research

IS - 4

ER -

Directed acyclic graphs: a tool for causal studies in paediatrics

Abstract

Adgang til dokumentet

Andre filer og links

Fingeraftryk

Citationsformater