Treatment with sorafenib of patients with advanced hepatocellular carcinoma is challenged by anticipated discontinuation due to tumor progression, liver decompensation, or adverse effects. While postprogression survival is clearly determined by the pattern of tumor progression, understanding the factors that drive prognosis in patients who discontinued sorafenib for any reason may help to improve patient management and second-line trial design. Patients consecutively admitted to three referral centers who were receiving best supportive care following permanent discontinuation of sorafenib for any reason were included. Postsorafenib survival (PSS) was calculated from the last day of treatment to death or last visit available. Two hundred and sixty patients were included in this prospective study, aged 67 years, 60% with hepatitis C, 51% Child-Pugh A, 83% performance status (PS) 1, 41% with macroscopic vascular invasion, and 38% with extrahepatic tumor spread. Overall, median PSS was 4.1 (3.3-4.9) months, resulting from 4.6 (3.3-5.7) months for 123 progressors, 7.3 (6.0-10.0) months in 77 with adverse effects, and 1.8 (1.6-2.4) months in 60 decompensated patients (P<0.001). Postsorafenib survival was independently predicted by PS, prothrombin time, extrahepatic tumor spread, macrovascular invasion, and reason for discontinuation. Two hundred patients potentially eligible for second-line therapy had a PSS of 5.3 (4.6-7.1) months, which was dependent on reasons of discontinuation (P=0.004), PS (P<0.001), macrovascular invasion (P<0.001), and extrahepatic metastases (P<0.002). Conclusion: Discontinuation due to adverse effects in the absence of macrovascular invasion, extrahepatic metastases, and deteriorated PS predicts the best PSS in compensated patients, thereby setting the stage for both improved patient counseling and selection for second-line therapy. (Hepatology 2015;62:784-791)
