Epilepsy is a debilitating group of neurological disorders affecting 1 in 26 people. Despite advances in the field over the last 20 years, more than 30% of patients do not have their seizure controlled. Current clinical practice essentially relies on a trial-and-error approach, whereby the patient is sequentially trialled on different anti-seizure drugs, doses and combinations in the hope of eventually finding an effective regime. For the patient this protracted (often years long) journey results in substantive co-morbidity, loss of productivity and greater risk of sudden unexplained death with epilepsy. For the health system this journey incurs significant cost. There is an urgent need to alter this trajectory and make the journey from diagnosis to effective treatment shorter and cheaper.
To address this major shortcoming we springboard from cohorts of human induced pluripotent stem cell lines (hIPSC) derived from drug-responsive and drug-resistant epilepsy patients established across the two epilepsy research nodes and build on our expertise in generating hIPSC-derived brain organoids and implement artificial intelligence models to further advance drug prediction.
We will use hiPSC-derived brain organoids and screen a library of approved drugs to identify those able to alter neural activity in a patient-specific model, train an artificial intelligence model that leverages both clinical and genomic data to assist drug selection, and validate treatment predictions in real-world clinical settings. Demonstrating the utility of an epilepsy patient-specific in-vitro drug screening platform in combination with decision-making software offers substantive health benefits for patients, provides neurologists with an evidence-based medicine approach, reduces health care costs and has the potential to enable transformative new insights into the genetic drivers of epilepsy and drug-resistance, and informs new therapy development.
Project members
Project lead
Researchers
