The advent of tyrosine kinase inhibitors (TKIs) has dramatically improved the outcome of patients with chronic myeloid leukemia (CML). Currently, four TKIs are available for the frontline treatment, including the first-generation TKI (imatinib) and the second-generation TKIs (dasatinib, nilotinib, and bosutinib). The second-generation TKIs lead to a faster and deeper molecular response without a survival benefit compared with imatinib. However, the opportunity for the treatment discontinuation and functional cure requires the achievement of durable deep molecular remission. Therefore, the second-generation TKIs should be considered as initial therapy for chronic-phase CML. Switch of therapy is warranted in case of treatment failure, including resistance and/or intolerance. The life expectancy of patients with CML is approaching that of the general population. Given an expected lifespan, future perspectives should consider the strategy for the optimal choice of TKIs, allowing for long-duration of effective TKI therapy with less toxicity to aim for a functional cure. A novel prediction approach such as artificial intelligence-driven analysis on the accumulated data from clinical trials paves a promising path for the personalized recommendation on frontline TKIs and precise survival prediction.
Keywords: Artificial intelligence; Chronic myeloid leukemia; Tyrosine kinase inhibitor.