Depth of anesthesia, temperature, and postoperative delirium in children and adolescents undergoing cardiac surgery

Abstract

Background: After pediatric cardiosurgical interventions, postoperative delirium can occur, which can be associated with undesirable consequences during and after the hospital stay. It is therefore important to avoid any factors causing delirium as far as possible. Electroencephalogram (EEG) monitoring can be used during anesthesia to individually adjust dosages of hypnotically acting drugs. It is necessary to gain knowledge about the relationship between intraoperative EEG and postoperative delirium in children.

Methods: In a dataset comprising 89 children (53 male, 36 female; median age: 0.99 (interquartile range: 0.51, 4.89) years) undergoing cardiac surgery involving use of a heart-lung machine, relationships between depth of anesthesia as measured by EEG (EEG index: Narcotrend Index (NI)), sevoflurane dosage, and body temperature were analyzed. A Cornell Assessment of Pediatric Delirium (CAP-D) score ≥ 9 indicated delirium.

Results: The EEG could be used in patients of all age groups for patient monitoring during anesthesia. In the context of induced hypothermia, EEG monitoring supported individually adjusted sevoflurane dosing. The NI was significantly correlated with the body temperature; decreasing temperature was accompanied by a decreasing NI. A CAP-D score ≥ 9 was documented in 61 patients (68.5%); 28 patients (31.5%) had a CAP-D < 9. Delirious patients with an intubation time ≤ 24 h showed a moderate negative correlation between minimum NI (NI_min) and CAP-D (rho = -0.41, 95% CI: -0.70 - -0.01, p = 0.046), i.e., CAP-D decreased with increasing NI_min. In the analysis of all patients' data, NI_min and CAP-D showed a weak negative correlation (rho = -0.21, 95% CI: -0.40 - 0.01, p = 0.064). On average, the youngest patients had the highest CAP-D scores (p = 0.002). Patients with burst suppression / suppression EEG had a longer median intubation time in the intensive care unit than patients without such EEG (p = 0.023). There was no relationship between minimum temperature and CAP-D score.

Conclusions: The EEG can be used to individually adjust sevoflurane dosing during hypothermia. Of the patients extubated within 24 h and classified as delirious, patients with deeper levels of anesthesia had more severe delirium symptoms than patients with lighter levels of anesthesia.

Keywords: Body temperature; Cardiac surgery; Delirium; Depth of anesthesia; EEG; Heart–lung machine.

Fig. 1

Course of anesthesia in an 11-month-old child. a) Cerebrogram b) Density spectral array (DSA) c) Amplitude-integrated EEG (aEEG) and burst suppression ratio (BSR) d) Temperature and sevoflurane concentration

Fig. 2

Relation between a) Narcotrend Index and temperature b) Narcotrend Index and sevoflurane concentration for the time point with the lowest temperature during the HLM period

Fig. 3

a) Temperature and b) sevoflurane concentration before cooling and in EEG stage F₁ (suppression) during cooling

Fig. 4

Minimum Narcotrend Index (NI_min) and CAP-D score in patients who had a CAP-D ≥ 9 and an intubation time ≤ 24 h

Fig. 5

CAP-D score across four age groups. Dark blue bars: 50^th percentile (median), lower and upper margin of light blue boxes: 25^th and 75^th percentile