Background: Although several studies have performed tyrosine kinase inhibitor (TKI)-induced hepatotoxicity, the relationship and risk factors between TKI and the incidence of hepatotoxicity are still unclear. Methods: This cohort study used population-based representative claims data from the National Health Insurance Service in Korea from 2002-2021. Cancer and hepatotoxicity were defined using the ICD-10 code. Outcome was defined as patients taking a TKI within 1 year of cancer diagnosis when hepatotoxicity occurred. The controls were randomly 1:1 matched to cases by age, sex, and the first exposure date. Proportional hazard analysis, Kaplan meier curve and log lank test were used to determine the difference in risk between TKI exposed and non-exposed groups. Random Survival Forest was used to determine Brier scores and variable importance. Results: A total of 21,462 cancer patients were included in the analysis. The patient with TKIs had an increased risk of hepatotoxicity compared with the patients without TKIs (Adjusted HR 1.19, 95% CI 1.11-1.30). Among comorbidities, including diabetes, chronic liver disease, hepatitis B, liver cancer, and pancreatitis, increased the incidence of hepatotoxicity approximately 1.1-2.3 times. The concomitant use of medications, including Anthracycline agents, Arrhythmia agents, Diuretic agents, were associated with the increased risk of hepatotoxicity by 1.1-1.2 folds. The difference between the Brier scores of the Kaplan-Meier (KM) censored distribution estimator and the Random Survival Forest (RSF) censored distribution estimator was checked at 1000 days and was finally found to be around 0.22 for the RSF model and 0.27 for the KM model. When checking the variable importance based on RSF, a total of five variables were identified as important factors in predicting hepatotoxicity: Diuretic agent, Pancreatitis, TKI, Sex, and Liver cancer. Conclusion: This study confirms that the use of TKIs in cancer patients is associated with an increased risk of developing hepatotoxicity. The five factors identified in the variable importance may be helpful in for clinical decision-making with the administration of TKIs in cancer patients.