The Knowledge Discovery in Healthcare Data (KDH) workshop series was established in 2016 to present AI research efforts to solve pressing problems in healthcare. The workshop series aims to bring together clinical and AI researchers to foster collaborative discussions. This year, the workshop will be co-located with IJCAI 2019 in Macao, China and the focus is on learning healthcare systems.
The healthcare industry is undergoing significant transformation as organisations increasingly incorporate AI into important areas of healthcare delivery and management. The global market for AI in healthcare is estimated at 2.1bn USD in 2018, and is expected to be worth over 36bn USD by 2025. This success of AI is driven by the development of systems that are able to translate routinely collected data into knowledge that drives the continual improvement of medical care. Such systems have varying descriptions but each perform (a) data assembly, analysis and interpretation from multiple sources (clinical records, guidelines, patient-provided data including wearables, omic data, etc..); and improve clinical practice by automatically feeding acquired knowledge to clinician or patient-facing decision support systems to provide personalised recommendations , in the ultimate aims of improving outcomes and personalising care.
In this workshop we wish to address the challenge of leveraging knowledge-based models that can utilise patient-focused data to improve care delivery to bring about "learning healthcare systems". This calls for methods that can: 1) extract, organise and assemble from large amounts of structured and unstructured data silos, 2) analyse and discover actionable knowledge from the large, temporal and uncertainty-ridden healthcare data and 3) design tools to support clinical decision making and self-management by patients in an autonomous and efficient manner, and without jeopardising existing clinical workflows or the privacy of patient data. Therefore, the notion of the learning healthcare system encompasses research in prominent areas of Artificial Intelligence including language engineering, data mining, knowledge representation & reasoning, learning and autonomous systems.
This year we feature the KDH challenge, Multi-modal Low-back Pain Exercise Recognition:
- to provide AI researchers with an impactful case study and data with the potential to improve the health and wellbeing of people with low-back pain.
- to create a platform for AI researchers to compare the efficacy of different machine learning prediction approaches on a standard set of multi-modal sensor data.
Links to previous workshops:
- March 14th, 2019 : Multi-modal Low-back Pain Exercise Recognition Challenge Dataset is available for download
- Mar 1st, 2019 : CFP distributed
- Feb 28th, 2019: web site live
- Feb 20th, 2019: 4th KDH workshop accepted