Background: The objective of this study was to identify the predictors of in-hospital mortality among patients with diffuse alveolar hemorrhage (DAH).Methods: We conducted a retrospective review of 89 patients hospitalized for DAH at our institution. 49 patients who died during hospitalization and 40 patients who survived were compared. We reviewed their clinical course, radiologic and pathologic findings, along with medical management. We then performed univariate and multivariate analyses to identify the risk factors associated with in-hospital mortality.Results: We identified 12 factors to be associated with mortality when comparing survivor versus non-survivor cohorts: smoking (67 versus 42%, p=0.02), malignancy (17 versus 49%, p=0.002), interstitial lung disease (0 versus 14%, p=0.01), liver failure (2 versus 28%, p=0.001), autoimmune diseases (40 versus 8%, p=0.0006), thrombocytopenia (7 versus 71%, p<0.0001), ICU admission (57 versus 85%, p=0.004), mean ICU stay (p=0.4), steroid use (90 versus 63%, p=0.003), plasma exchange (15 versus 0 %, p=0.005), mechanical ventilation (37 versus 75%, p=0.0007) and acute respiratory distress syndrome (22 versus 77%, p<0.0001). On multivariate analysis, thrombocytopenia (p<0.0001) and ARDS (p=0.0013) were associated with higher odds of mortality in DAH while steroid use (p=0.0004) was associated with a lower risk of in-hospital mortality in patients with DAH.Conclusions: In DAH, thrombocytopenia and ARDS were predictors of in-hospital mortality whereas the use of steroid was associated with a more favorable prognosis.