Predictability of drug-induced liver injury by machine learning

摘要

Adverse drug reactions (ADRs) are a major threat to the development of novel drugs and their therapeutic use [ , ]. A particular class of ADRs is drug induced liver injury (DILI), encompassing ADRs that cause liver damage. The liver is the most common target of ADRs, because of its crucial role in the metabolism of endogenous and exogenous compounds [ ]. Predictive markers of DILI able to identify susceptible patients would give an enormous advantage to accelerate safe drug development and to prevent severe reactions after approval [ , ]. DILI poses particular challenges, as pre-clinical testing for side effects in animals does not automatically transfer to clinical trials and then to post-marketing treatment in the population. Indeed, individual susceptibility may arise in patients different from those enrolled in trials, or range from clinically serious to worse as a function of interaction with other factors [ ].