Skip to content

news

Three postdoctoral Research Associate posts available in Artificial Intelligence for Multiple Long-Term Conditions Programme

    Applications are invited for 3 Research Associates in Machine Learning for Health, Network Science, Knowledge Representation and AI to work within the Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC) programme in the School of Informatics and Usher Institute, University of Edinburgh.

    Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC) is a 3 year, £3.9 million research programme funded by the National Institute for Health Research (NIHR) Artificial Intelligence for Multiple Long-Term Conditions Programme. AIM-CISC is led by a multidisciplinary team from The University of Edinburgh, University College London and NHS Lothian. This includes clinical and genetic researchers studying complex multimorbidity, public partners, social scientists researching wider social and spatial determinants of health and care, and informatics and data science academics with AI expertise across multiple domains including natural language processing, machine-learning including multilayer network analysis, and applied AI. The research areas are broadly as follows:

    1.Network Science for the analysis and prediction of multimorbidity.

    2. Machine Learning for clustering of complex multimorbidity.

    3. Knowledge Representation for Medical Artificial Intelligence

     

    Our proposal on AI and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC) receives funding from the NIHR!

      The National Institute for Health Research (NIHR) has decided to fund our proposal on Artificial Intelligence and Multimorbidity: Clustering in Individuals, Space and Clinical Context (AIM-CISC). The project, worth £3.9M over 3-years, will employ around 10 postdoctoral researchers across Informatics, the Usher Institute, the Roslin Institute, GeoSciences and SSPS.

      The overall programme will be led by Bruce Guthrie (PI), with Jacques Fleuriot as the AI Lead in Informatics. The other members of the Informatics team are Sohan Seth and Valerio Restocchi.

      Some project details:

      Long-term conditions are health issues which persist over years, with many people having more than one long-term condition (e.g. having both diabetes and asthma). This is known as multimorbidity and often seriously affects how well people feel and what they are able to do. The aim of the project is to use Artificial Intelligence techniques — spanning areas such as machine learning, network science, knowledge graphs and process mining — along with social science and health service research methods, to create a better understanding of common, disabling patterns of multimorbidity and help improve the quality and safety of care.

      Proter open source software released

        Proter is an open-source discrete event simulation library for workflows, written in Scala. It is now available on GitHub and as a library on Maven Central under the Apache 2.0 license.

        Proter was initially developed for the simulation of logic-based workflows in WorkflowFM in the context of the DigiFlow project. It was then gradually separated into an independent project for general purpose process simulation. We are currently extending its capabilities to support BPMN models and other modern features.

        Jorge Gaete passes his second year PhD review

          Jorge Gaete successfully passed his second year PhD review on Explainable AI for healthcare. His panel consisted of Valerio Restocchi, Petros Papapanagiotou and Jacques Fleuriot. Congratulations to Jorge on becoming a senior PhD student.

          Petros Papapanagiotou presents our HICSS-54 paper

            Video presentation of our paper:

            Papapanagiotou P., Vaughan J., Smola F, and Fleuriot J. (2020). A Real-world Case Study of Process and Data Driven Predictive Analytics for Manufacturing Workflows.

            at the 54th Hawaii International Conference on System Sciences (HICSS-54). This discusses real-world results from the DigiFlow project, where WorkflowFM is used in a manufacturing setting.