Troglitazone (TGZ) causes delayed, life-threatening drug-induced liver injury in some patients but was not hepatotoxic in rats. This study investigated altered bile acid homeostasis as a mechanism of TGZ hepatotoxicity using a systems pharmacology model incorporating drug/metabolite disposition, bile acid physiology/pathophysiology, hepatocyte life cycle, and liver injury biomarkers. In the simulated human population, TGZ (200-600 mg/day × 6 months) resulted in delayed increases in serum alanine transaminase >3× the upper limit of normal in 0.3-5.1%, with concomitant bilirubin elevations >2× the upper limit of normal in 0.3-3.6%, of the population. By contrast, pioglitazone (15-45 mg/day × 6 months) did not elicit hepatotoxicity, consistent with clinical data. TGZ was not hepatotoxic in the simulated rat population. In summary, mechanistic modeling based only on bile acid effects accurately predicted the incidence, delayed presentation, and species differences in TGZ hepatotoxicity, in addition to predicting the relative liver safety of pioglitazone. Systems pharmacology models integrating physiology and experimental data can evaluate drug-induced liver injury mechanisms and may be useful to predict the hepatotoxic potential of drug candidates.