Personalising the pharmacological treatment of bipolar disorder

Bipolar disorder is a life-long illness that causes major disability worldwide. Medication is the mainstay of treatment, and it is often required for long periods. Lithium remains the most effective medication to treat bipolar disorder. However, only 30% of people have a good therapeutic response and concerns about adverse effects, especially kidney failure, have reduced its use. There is no reliable way to predict responses to lithium, or who will require an alternative drug. Furthermore, it is not currently possible to predict who will develop kidney failure with lithium or will experience adverse effects while taking alternatives. 

I will combine my expertise in using large datasets with novel artificial intelligence techniques to identify patient characteristics that predict response to lithium and adverse events.

The identified characteristics will be combined into online tools to inform treatment decisions, ultimately personalising treatment choices and improving medication effectiveness with reduced side effects.