Dr Goran Nenadic has been working in the area of natural language processing and text mining since 1993. His research interests include automatic terminology extraction, classification and management, compound word recognition and digital corpora encoding. He also investigates terminology-driven mining of scientific literature (in particular for life sciences) by extracting terms and establishing associations and links among them. He is interested in text analytics and sentiment analysis from online resources, in particular in the healthcare domain. He leads the UK healthcare text analytics network (http://www.healtex.org) and his team is part of The Farr Institute’s Health eResearch Centre (HeRC), where he co-ordinates healthcare text analytics efforts in collaboration with a number of local hospitals and charities.
His current research focus is on large-scale extraction and linking of clinical/epidemiological findings from electronic health records (EHRs), healthcare social media and biomedical literature. His team has worked on mining narratives from EHRs (e.g. for clinical outcomes in cancer patients, or medication prescription extraction), making sense of patient-generated data from social media (e.g. benefits and harms of medical treatments) and providing context to clinical decision support systems (e.g. for treatment planning in brain injuries). He has led a number of joint projects with healthcare service providers (e.g. semi-automated large-scale anonymisation of clinical narratives; identification of mental health symptoms in social media; process mapping of occupational therapy reports), as well as with industrial partners (e.g. dynamic clinical documentation management, information extraction from clinical trial reports). Since 2008, his team has been actively involved in international challenges in clinical text mining.