Abstract
Abstract only
7563
Background: Hemophagocytic lymphohistiocytosis (HLH) is a life-threatening inflammatory syndrome that may accompany hematologic malignancies (HM). The diagnosis of HLH in patients with HM (HM-HLH) is confounded by a number of factors: the most commonly used HLH-2004 diagnostic criteria are derived from studies in infants while the Hscore used in adults is not specific for HMs; moreover, most parameters in these scoring systems may reflect features of the underlying HM rather than HLH associated inflammation; and finally specific diagnostic cutoff values for laboratory abnormalities in HM-HLH have not been defined. We therefore conducted a study to optimize the HLH-2004 laboratory thresholds for the diagnosis of HM-HLH. Methods: A multi-center retrospective study in adult patients with HM in whom testing for HLH was performed. HM-HLH was defined as fulfillment of 5/8 HLH-2004 diagnostic criteria. We established the optimal diagnostic cutoff levels for HLH-2004 laboratory parameters using receiver operating curves (ROC) and combined the best performing parameters into a combined index, using binary logistic regression. We then created a clinical decision tree using a Classification and Regression Tree (CART) analysis with all available parameters, using cross validation. We also determined the prognostic value of our combined diagnostic tool. Results: 225 adults were analyzed (112 with HM-HLH per HLH-2004 and 113 with HM only). 35% of patients were evaluated for HLH routinely upon HM diagnosis. Soluble CD25 (sCD25) and ferritin best discriminated HM-HLH from HM, with an area under the curve (AUC) of 0.83 for each. ROC analysis demonstrated an optimal cutoff of > 4190 U/mL for sCD25 (sensitivity/specificity 91%/69%) and an optimal cutoff of > 2636 ng/ml for ferritin (sensitivity/specificity 64%/86%) for HM-HLH. We term the combination of elevated sCD25 and ferritin using optimized cutoff levels the ‘optimized HLH inflammatory’ (OHI) index. This OHI index was highly specific for the diagnosis of HM-HLH (specificity of 92%, sensitivity 79%). CART analysis demonstrated that OHI index positivity was sufficient to diagnose HM-HLH. In patients without a positive OHI index an Hscore > 168 and either splenomegaly or triglycerides > 279 ng/dL can still diagnose HM-HLH. By following this decision pathway, approximately 92% of patients were accurately classified based on HLH-2004. Furthermore, the OHI was better (odds ratio (OR) 7.9; 95% confidence interval (CI) 4.2-14.6) than Hscore >169 (OR 5.5; CI 3.9-9.6) and > 5/8 HLH-2004 (OR 5.3; CI 3-9.3) at predicting mortality at 1 year. Conclusions: The OHI index derived here is a simple tool that can accurately diagnose HLH and predict mortality in patients with hematologic malignancies. Some patients may not need full HLH workup before intervening with therapy that is HLH directed and not only malignancy directed.