Being able to accurately predict probability of death is important for the intensivist. Serum cytokine levels parallel physiological derangements observed in critically ill patients and are used in commonly applied scoring systems and prediction models. Thus, serum cytokine based prediction models of outcome seem to be reasonable and of great interest. In this issue of Critical Care, Gauglitz and colleagues present their prediction equation for paediatric burn patients with concomitant inhalation injury. They found that IL-10 on admission, or IL-6 and IL-7 five to seven days later, may predict outcome in an excellent way. Increased mortality is observed as serum IL-6 and IL-10 levels increase and serum IL-7 levels decrease. However, the complexity of cytokine kinetics in critically ill patients and the variety of factors capable to affect circulating cytokines even in a subgroup of critically ill patients may affect the valitidy of the results. Also, serum cytokine based prediction models need to be compared to commonly applied prediction models based on clinical parameters. This will enable identification of the most suitable, accurate, cheapest, and easiest to use model to predict outcome. In this issue of Critical Care, Dr Gauglitz and colleagues  present their prediction equation for outcome of burned children with concomitant inhalation injury based on serum cytokine measurements. Prediction of outcome is very important in the intensive care unit (ICU) and, for this purpose, intensivists have created illness severity scores (Acute Physiology and Chronic Health Evaluation (APACHE), Simplified Acute Physiology Score (SAPS), and Mortality Probability Model (MPM)). These scores are calculated from data collected on the first ICU day and comprise two parts: the score itself, reflecting illness severity; and a probability model, which is an equation giving the probability of hospital death . Accordingly, illness severity scores applicable for paediatric populations are widely used to assess severity and estimate probability of death [3,4]. The probability of death after burns can be easily predicted on the basis of simple, objective clinical criteria: age greater than 60 years; more than 40% of body-surface area burned; and inhalation injury . With regard to burn injury in children, only demographics and injury variables have been used to predict outcome [6,7]. In the later of these studies, an effort to take into account the effects of treatment on several variables to predict outcomes was attempted . The activation of the host immune system and the release of inflammatory mediators have been linked to physiological derangements observed in burn injury and other inflammatory conditions, increasing according to illness severity and the progression of systemic inflammatory response syndrome to multiple organ failure. Thus, it has been assumed that increased physiological responses parallel the intensity of cytokine production and the development of multiple organ failure and death. Since the production or depression of several cytokines is related to physiological derangements commonly used in scoring systems, it seems reasonable to measure these circulating cytokines and use them as an additional tool to predict outcome. In this regard, the article by Gauglitz and colleagues is original and of great interest . The authors present their data on severely burned children with concomitant inhalation injury. They found that children who did not survive had the worst clinical characteristics, including lower PaO2/FiO2 ratios (arterial oxygen partial pressure/fraction of inspired oxygen), higher positive Commentary Circulating cytokines and outcome prediction of burned children with concomitant inhalation injury Pavlos M Myrianthefs and George J Baltopoulos Athens University School of Nursing ICU at “KAT” Hospital, Nikis St, Kifissia, 14561, Greece Corresponding author: Pavlos M Myrianthefs, firstname.lastname@example.org Published: 23 June 2008 Critical Care 2008, 12:155 (doi:10.1186/cc6920) This article is online at http://ccforum.com/content/12/3/155 © 2008 BioMed Central Ltd See related research by Gauglitz et al., http://ccforum.com/content/12/3/R81 ARDS = acute respiratory distress syndrome; FiO2 = fraction of inspired oxygen; ICU = intensive care unit; IL = interleukin; PaO2 = arterial oxygen partial pressure; PIP = positive inspiratory pressure.