Propensity weighting: how to minimise comparative bias in non-randomised studies?

Non-randomised study designs are frequently used by researchers in cardiovascular nursing and allied professions. Baseline differences between the groups to be compared may introduce bias in the results. Methods for causal inference address this issue. One such method is propensity weighting, in which two or more treatments/exposure groups are weighted to make the groups as comparable as possible. As such, it mimics a randomised controlled trial design. In this article, the Twang package is presented for propensity weighting, and its use is exemplified in a study on smoking and cannabis consumption in adults with congenital heart disease.

Download Full-text

CHIP-Family intervention to improve the psychosocial well-being of young children with congenital heart disease and their families: results of a randomised controlled trial

Cardiology in the Young ◽

10.1017/s1047951119001732 ◽

2019 ◽

Vol 29 (09) ◽

pp. 1172-1182 ◽

Cited By ~ 6

Author(s):

Malindi van der Mheen ◽

Maya G. Meentken ◽

Ingrid M. van Beynum ◽

Jan van der Ende ◽

Eugène van Galen ◽

...

Keyword(s):

Congenital Heart Disease ◽

Heart Disease ◽

Randomised Controlled Trial ◽

Congenital Heart ◽

Controlled Trial ◽

Psychosocial Problems ◽

School Functioning ◽

Trial Registry ◽

Randomised Controlled

AbstractObjective:Children with congenital heart disease and their families are at risk of psychosocial problems. Emotional and behavioural problems, impaired school functioning, and reduced exercise capacity often occur. To prevent and decrease these problems, we modified and extended the previously established Congenital Heart Disease Intervention Program (CHIP)–School, thereby creating CHIP-Family. CHIP-Family is the first psychosocial intervention with a module for children with congenital heart disease. Through a randomised controlled trial, we examined the effectiveness of CHIP-Family.Methods:Ninety-three children with congenital heart disease (age M = 5.34 years, SD = 1.27) were randomised to CHIP-Family (n = 49) or care as usual (no psychosocial care; n = 44). CHIP-Family consisted of a 1-day group workshop for parents, children, and siblings and an individual follow-up session for parents. CHIP-Family was delivered by psychologists, paediatric cardiologists, and physiotherapists. At baseline and 6-month follow-up, mothers, fathers, teachers, and the child completed questionnaires to assess psychosocial problems, school functioning, and sports enjoyment. Moreover, at 6-month follow-up, parents completed program satisfaction assessments.Results:Although small improvements in child outcomes were observed in the CHIP-Family group, no statistically significant differences were found between outcomes of the CHIP-Family and care-as-usual group. Mean parent satisfaction ratings ranged from 7.4 to 8.1 (range 0–10).Conclusions:CHIP-Family yielded high program acceptability ratings. However, compared to care as usual, CHIP-Family did not find the same extent of statistically significant outcomes as CHIP-School. Replication of promising psychological interventions, and examination of when different outcomes are found, is recommended for refining interventions in the future.Trial registryDutch Trial Registry number NTR6063, https://www.trialregister.nl/trial/5780.

Download Full-text