Conferences
6–9 October 2021, Porto, Portugal
Data Science in Health - IEEE DSAA'2021
AI affects every aspect of human lives with a especial impact on healthcare. Healthcare can benefit broadly from the advances in AI, going beyond the commonly known classical data intensive clinical health domains like medical imaging and electronic health records. The amount of health-related data generated spans the whole life span, covering besides clinical health data increasingly also self-monitoring data from wearables and non-medical sources. Researchers recognize that most of the technical and research challenges that AI experts face when dealing with the healthcare resources are data related. Dealing with the complexity of storing and accessing heterogeneous data is one of the main research areas when using AI models in the medical domain. Unstructured data represents a powerful resource that can help drive competitive advantage but also it challenges researchers on extracting patterns from them.
Another challenge in medical data processing is the uncertainty of machine learning models. Despite the continuing progress of machine learning accuracy in the medical domain, trust in these models remains an issue. This is especially true with the significant leaps of progress in adopting deep learning in the medical domain, because of the black-box nature of the produced models.
This special session invites contributors form both academia and the industry to submit research achieved results on different machine learning and information theoretic methods applied in the medical domain. Topics addressing uncertainty of machine learning methods, and explainability of back-box models, interoperability, federated databases and integration of sources spanning the life of the patient are especially welcome, but we also we welcome contributions from the wider domain of medical information processing. The goal of this session is to make the health sector familiar with the ways in which AI can help the health sector, and to frame data mining research in the context of what medical researchers can expect from their data.
