Scientific, ethical, and logistical considerations in introducing a new operation: a retrospective cohort study from paediatric cardiac surgery

Abstract

Objective: To review the initial impact on mortality of infants with congenital heart disease of a new surgical technique that is now taken for granted.

Design: Retrospective cohort study.

Setting: A tertiary paediatric cardiology centre.

Subjects: 325 consecutive neonates with simple transposition of the great arteries admitted before, during, and after the preferred management changed from the Senning operation to the arterial switch (1978-98); and 100 consecutive neonates requiring a different neonatal open heart operation that did not change in that period.

Main outcome measures: Mortality before and early after operation reconstructed sequentially as the series evolved and retrospectively once the series was complete; actuarial survival associated with the different treatment strategies.

Results: For both the transposition and the comparison group, early mortality in 1998 was lower than in 1978. During that period, however, there was a phase temporally related to the adoption of the switch operation in which early mortality for transposition increased. Actuarial survival of recent patients with "intention to treat" with arterial switch is superior to those with intention to treat with the Senning operation, as predicted when the switch operation was first adopted.

Conclusions: A period of increased hazard for individual patients may occur when a specialist community, a particular unit, and an individual surgeon are all learning a new technique concurrently. Obtaining informed consent during this time of uncertainty is helped by clarity about the objectives of treatment and availability of relevant local and international data.

Figure 1

Cumulative mortality along the series (1978-98) for infants who had a Senning operation, a switch operation, all infants with simple transpositions including preoperative death, and all infants with total anomalous pulmonary venous drainage (see methods section for explanations of eras)

Figure 2

Logistic regression models. Senning and switch model the mortality of infants who had these operations. Transposition of the great arteries and total anomalous pulmonary venous drainage show mortality for the whole series by diagnosis (see methods section for explanations of eras)

Figure 3

Actuarial survival of patients with intention to treat with the Senning procedure and the switch. The switch data are stratified by era. Switch survival in era 3 is superior to Senning survival (P=0.04). The values in parentheses show the numbers of patients alive at time of procedure and at 5 year intervals (see methods section for explanations of eras)

Figure 4

Top: Model published in 1985 contrasting estimates of the survival curves for the normal population with patients committed to a Senning operation at age 1 month with a 2% operative mortality and an annual late hazard of 2% and for patients committed to a switch operation at birth with a 40% early mortality and a 0.3% annual late hazard. Bottom: Current model, with normal survival as above. The Senning operation is assumed to take place at age 4 months and be associated with a hazard of 16% (including preoperative deaths) and an annual late hazard of 0.7%. The switch is assumed to be done at age 2 weeks and be associated with a 6.2% mortality (including preoperative deaths) and a 0.16% annual late hazard