Three Biomarker Panel at Day 7 and 14 Can Predict Development of Grade II-IV Acute Graft-Versus-Host Disease

We have previously identified five biomarker proteins that have diagnostic and prognostic value for acute graft-versus-host disease (GVHD) (Blood 113:273-278, Sci Transl Med 2:50-57). In order to determine whether biomarkers can predict GVHD before the appearance of clinical symptoms, we evaluated the three most informative biomarkers of the five (IL2-Receptor-α, TNFR1, elafin) in patient samples prospectively collected between 2000 and 2010 from 513 unrelated (URD) hematopoietic cell transplant (HCT) patients. We focused on URD HCT recipients because they are most likely to develop acute GVHD and could potentially benefit from a predictive laboratory assay and subsequent preemptive intervention. We measured biomarker plasma levels by sequential enzyme-linked immunosorbent assay on samples obtained prior to conditioning (pre-HCT), and at day +7 and day +14 after HCT. In designing the analytical approach, we took into consideration that median time to GVHD onset is delayed after reduced intensity conditioning, that there may be limited opportunity to preemptively intervene in patients on the verge of developing GVHD, and that there have been changes in GVHD prophylaxis agents over the past decade. Therefore, we randomly divided the patients into training (N=342) and validation (N=171) data sets that were balanced for (i) full intensity conditioning, (ii) onset of grade II-IV GVHD earlier than day +21 and (iii) HCT performed after 2005.

In order to create a prediction model for acute GVHD, we used the biomarker levels in the training data set to simulate biomarker values for a hypothetical 50,000 patients using the following assumptions: (1) the incidence of GVHD by day 100 is 55%, (2) the median day of GVHD onset after full intensity URD HCT is day 21, with 10% of patients developing GVHD prior to day +7, and 3% developing GVHD after day +56. These assumptions were based on historical URD HCT data at our center. We used logistic regression to compute a predicted probability, p_7, of developing grade II-IV GVHD for each of the 50,000 patients based upon the biomarker levels pre-HCT and at day +7. Any patient with p₇≥0.64 was categorized as high risk for development of GVHD. For all low risk patients (p₇<0.64), who had not developed GVHD between day +7 and +14, we measured the biomarkers at day +14 and created another logistic regression model to compute an additional predicted probability, p₁₄, of development of grade II-IV GVHD after day +14. Any patient in the initial low risk group with p14≥0.41 was now categorized as high risk. For the training data set, the combination of these two tests correctly predicted the absence of grade II-IV GVHD by day 56 in 77% (95% CI: 71%-83%) of patients without GVHD (i.e. specificity), and correctly predicted the development of grade II-IV GVHD by day 56 in 50% (95% CI: 42%-58%) of patients who had not already developed GVHD by the time of the test sample (i.e. sensitivity). Applying these two diagnostic tests to the validation data set gave a specificity of 75% (95% CI: 67%-83%) and a sensitivity of 57% (95% CI: 44%-69%), similar to the values found in the training data set. Table 1 shows the specificity and sensitivity of the two combined tests for different values of p₇ and p₁₄. The table is ordered by descending combined specificity. The bolded numbers, which we propose could be used for designing a GVHD preemptive clinical trial, correspond to the values of combined specificity and sensitivity, which lead to the greatest percentage of patients correctly predicted for GVHD occurrence among those listed. In conclusion, measurement of a three-biomarker panel pre-HCT, at day +7, and day +14 predicts grade II-IV GVHD with a specificity of 75% and sensitivity of 57%, with the median time between a high risk test result and onset of grade II-IV GVHD by day 56 equal to 14 days, with a range of (2-41) days. If these results are confirmed in multicenter samples, we could propose to preemptively treat acute grade II-IV GVHD in the unrelated HCT population.

No relevant conflicts of interest to declare.