Transfusion practice in the non-bleeding critically ill: an international online survey-the TRACE survey

Abstract

Background: Over the last decade, multiple large randomized controlled trials have studied alternative transfusion strategies in critically ill patients, demonstrating the safety of restrictive transfusion strategies. Due to the lack of international guidelines specific for the intensive care unit (ICU), we hypothesized that a large heterogeneity in transfusion practice in this patient population exists. The aims of this study were to describe the current transfusion practices and identify the knowledge gaps.

Methods: An online, anonymous, worldwide survey among ICU physicians was performed evaluating red blood cell, platelet and plasma transfusion practices. Furthermore, the presence of a hospital- or ICU-specific transfusion guideline was asked. Only completed surveys were analysed.

Results: Nine hundred forty-seven respondents filled in the survey of which 725 could be analysed. Hospital transfusion protocol available in their ICU was reported by 53% of the respondents. Only 29% of respondents used an ICU-specific transfusion guideline. The reported haemoglobin (Hb) threshold for the general ICU population was 7 g/dL (7-7). The highest reported variation in transfusion threshold was in patients on extracorporeal membrane oxygenation or with brain injury (8 g/dL (7.0-9.0)). Platelets were transfused at a median count of 20 × 10⁹ cells/L IQR (10-25) in asymptomatic patients, but at a higher count prior to invasive procedures (p < 0.001). In patients with an international normalized ratio (INR) > 3, 43% and 57% of the respondents would consider plasma transfusion without any upcoming procedures or prior to a planned invasive procedure, respectively. Finally, doctors with base specialty in anaesthesiology transfused critically ill patients more liberally compared to internal medicine physicians.

Conclusion: Red blood cell transfusion practice for the general ICU population is restrictive, while for different subpopulations, higher Hb thresholds are applied. Furthermore, practice in plasma and platelet transfusion is heterogeneous, and local transfusion guidelines are lacking in the majority of the ICUs.

Keywords: Critically ill; Plasma; Platelets; Red blood cells; Transfusion practice.

Fig. 1

Respondents were asked which Hb threshold they used for RCC transfusion in the general ICU population and different subpopulations. Respondents used in the general population a Hb threshold of 7.0 g/dL (7.0–7.5). This is significantly lower (p < 0.001) compared to patients with acute coronary syndrome (9.0 g/dL (8–9.7)), septic shock (7.5 g/dL (7.0–8.0)), acute brain injury (8.0 g/dL (7.0–9.0)), patients undergoing ECMO (8.0 (7.0–9.0) g/dL), issues of prolonged weaning (7.5 g/dL (7.0–8.0)), or patients with ARDS (7.5 g/dL (7.0–8.0)). No statistical differences were observed between the general ICU population and patients older than 65 years and patients with (haematological) oncology (all three groups were transfused at a Hb threshold of 7.0 g/dL (7.0–7.5))

Fig. 2

a, b The use of transfusion triggers in addition to a haemoglobin threshold

Fig. 3

Prophylactic platelet thresholds without any planned invasive procedure and  prior to different procedures

Fig. 4

More respondents would correct a vitamin K-induced INR > 3 prior to an invasive procedure than in the absence of a procedure (a). Both in the absence of an invasive procedure (b) and prior to an invasive procedure (c), the majority would correct this with vitamin K