Research Associate in Care Technologies in Context
Salary: £37,099 – £44,263 per annum. (£39,347 – £46,974 from Spring 2024)
Closing date: 29th February 2024 (23:59)
The Opportunity:
This post will contribute to the joint research goals of the “Understanding the Person in Context” (WP4) and “Integrated Technologies of Care” (WP6) Work Packages within the Advanced Care Research Centre (ACRC) at the University of Edinburgh. The post-holder will work across the School of Informatics and the Advanced Care Research Centre, with a base in both spaces.
The ACRC programme led by the University of Edinburgh has been established to research and develop innovative solutions for the care of people in later life that can promote and maintain healthy ageing. Central to the ACRC interdisciplinary approach is a commitment to working in partnership with people in later life, their families and communities, and to creating a sustainable UK-wide collaboration to ensure excellence and impact.
Informal enquiries can be addressed to: Informal enquiries to be directed to Prof. Jacques Fleuriot (jdf@ed.ac.uk), Prof. Jane Hillston (jane.hillston@ed.ac.uk), Prof. John Vines (john.vines@ed.ac.uk) or Prof. Heather Wilkinson (h.wilkinson@ed.ac.uk).
More details and the application procedure are available here.
Past opportunities
Fully Funded PhD in
Predicting harm from prescribed drugs in people with polypharmacy, multimorbidity and frailty
Supervisors: Prof Bruce Guthrie and Prof Jacques Fleuriot
Deadline: Tuesday, January 30, 2024
The aim of this project is to develop and validate new models to predict who is at risk of being harmed by prescribed drugs, focusing on the outcome of acute kidney injury.
Objectives
- To systematically review the literature examining medication and other causes of acute kidney injury (AKI)
- To apply and compare epidemiological and machine learning approaches to predicting AKI risk associated with medication and other patient characteristics
Description
Acute kidney injury is common and associated with multiple longer-term adverse outcomes. Medication is an important preventable cause of AKI, but our understanding of how prescribing interacts with underlying conditions and other patient characteristics like frailty is poor. This project will use large-scale routine healthcare data to develop and validate prediction models for AKI, and to compare models based on different approaches in terms of performance (discrimination, calibration), explainability, and feasibility to apply in live clinical data. There will be flexibility for the student to develop a focus and choice of methods that suits their own interests.
More information and application details can be found here.
Research Associate in Neurosymbolic AI
We are looking for a postdoctoral researcher in neurosymbolic Artificial Intelligence. The researcher will work on the integration of interactive theorem proving and neural learning for safe human-robot interaction.
Further Information
This project will develop a neurosymbolic AI approach that tightly integrates logical reasoning and learning to formally constrain the training of neural networks. It will involve extending a theorem-proving framework in Isabelle to allow the tensor-based (formal) representation, machine proofs and faithful code-generation of spatio-temporal logical constraints that can be injected into the training of neural networks. The effectiveness of the methodology will be demonstrated using scenarios and specifications arising from the human-robot interaction domain, where safety is crucial.
Salary: £35,333 – £42,155
Closing date: 16th January 2023 (17:00, UK time)
Informal enquiries can be addressed to the principal investigators: Jacques Fleuriot (jdf@ed.ac.uk) and Ram Ramamoorthy (s.ramamoorthy@ed.ac.uk).
The application procedure is available here.
Multimorbidity PhD Programme for Health Professionals
Topic: Co-existing mental and physical multimorbidity, adverse events, and longer term outcomes in hospitalised patients with sepsis
Summary:
Sepsis is a common, life-threatening condition, causing over 45,000 deaths annually. Sepsis survivors commonly experience new physical and mental health problems. Multimorbidity is common in patients who develop sepsis, of whom 20% of critically ill patients have mental health comorbidity and is associated with higher mortality and post-discharge rehospitalisation. However, the impact of co-existing mental and physical multimorbidity in the context of sepsis is unclear. In particular, its impact on adverse events, outcomes and recovery has not been previously investigated.
The overall aim of the studentship is to evaluate the impact of co-existing mental and physical multimorbidity on in-hospital adverse events and outcomes, and longer-term recovery, for hospitalised patients with sepsis in order to inform improvements in care quality.
During the studentship, epidemiological analyses will be undertaken to determine associations between co-existing mental illness/physical multimorbidity and both acute outcomes and post-discharge recovery, underpinned by explicit causal frameworks. Subsequently, clusters of mental/physical multimorbidity will be examined using artificial intelligence methods.
The studentship will provide training in epidemiology, causal inference, and machine learning methods. The student will benefit from the vibrant, academic environment in the Usher Institute and synergistic learning from other multimorbidity work undertaken by the team (https://edin.ac/3CqoERz).
Supervisors:
Dr Nazir Lone, Usher Institute (University of Edinburgh)
Prof Jacques Fleuriot, School of Informatics (University of Edinburgh)
Prof Manu Shankar-Hari, Centre for Inflammation Research (University of Edinburgh)
Closing date: 19th September 2022
Further information and the application procedure are available here.
Research Fellow in Knowledge Representation for Medical Artificial Intelligence
We have an open position for a Research Fellow in Knowledge Representation for Medical Artificial Intelligence
Salary: £34,304-£40,927
Closing date: 9th August 2022 (17:00, UK time)
Informal enquiries may be directed to Bruce Guthrie, Professor of General Practice at the University of Edinburgh (Bruce.Guthrie@ed.ac.uk) or Jacques Fleuriot, Director of the Artificial Intelligence and its Applications Institute, School of Informatics (Jacques.Fleuriot@ed.ac.uk)
Further information
We are looking for a AI researcher with experience in knowledge representation/modelling and reasoning to join our inter-disciplinary programme of research (AIM-CISC), which focuses on the application of advanced AI methods to better understand and address the increasing challenge posed to healthcare systems by multimorbidity (i.e. multiple chronic conditions in people).
The application procedure is available here.
Research Associate in Machine Learning for Health and Medicine
Applications are invited for a Postdoctoral Research Associate in machine learning for health and medicine in the School of Informatics, University of Edinburgh.
We are looking for an exceptional researcher to apply AI/machine learning techniques to the analysis and prediction of health-related, adverse events for people with complex, long-term conditions (multimorbidity) and polypharmacy.
Experience in machine learning for graph-structured data is highly desirable.
This full-time position is fixed term till the 31st of July 2024.
Informal enquiries to be directed to Jacques Fleuriot
(jdf@inf.ed.ac.uk).
Salary grade scale: UE07 (£34,304 – £40,927pa)
Feedback is only provided to interviewed candidates.
Closing date 5pm (GMT) on 25th April 2022.
Further information
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.
Further information and the application procedure are available here.
Research Associate in Formal Modelling for Health and Care
Applications are invited for a Research Associate in Formal Modelling for Health and Care in the School of Informatics, University of Edinburgh.
This post will contribute to the New Technologies of Care Programme within the Advanced Care Research Centre (ACRC) at the University of Edinburgh.
This full-time position is fixed term for 30 months.
(jdf@inf.ed.ac.uk), Petros Papapanagiotou (pe.p@ed.ac.uk) and Jane
Hillston (Jane.Hillston@ed.ac.uk).
Salary grade scale: UE07 (£34,304 – £40,927pa)
Feedback is only provided to interviewed candidates.
Closing date 5pm (GMT) on 24th January 2022.
Further information
To support meaningful inference and decision making in the context of advanced care delivery for the older person, computer-based models are needed that can capture the vast body of
knowledge both around general and specific care pathways and incorporate
data from real-time sources such as sensors. In the case of the person
in later life, there is a need for contextualisation with respect to
both the care recipient and their environment.
One objective of this project is to build computer-based models that enable both the management and analysis of care,
while supporting decision making. Process-based models can help map
complex sequences of events, such as routines of daily living or care
plans and pathways. Models will be constructed and parameterised based
on sensor, video and recorded care data (coming from other streams of
the New Technologies of Care Programme and the broader ACRC). AI-based workflow analytics and other techniques will be applied to the models to understand the context of and predict adverse events and health outcomes.
Bridging the gap between the high complexity of the care landscape, the individual needs and circumstances of the older person, and the development of computer-based workflows that interface between data and processes in order to drive decision-making will be one of the important goals of this multidisciplinary project.
Further information and the application procedure are available here.
Fully Funded PhD: Monitoring daily living to predict health outcomes
Supervisors: Petros Papapanagiotou (principal), Atul Anand, Phillip Whitehead (Newcastle), John Vines
Funding: Advanced Care Research Centre (ACRC).
Deadline: 26 November 2021
More info and links
Aim
The aim is to build a data- and process-driven, long-term predictive model of health outcomes based on the monitoring of Activities of Daily Living (ADLs) of the target older population.
Objectives
- Data curation for ADLs working with actual users
- Investigation of links of ADL monitoring data to health indicators based on medical and empirical evidence
- Development of combined data- and process-based AI techniques for long-term prediction of deterioration
Description
The Internet of Things and modern smart homes offer us unprecedented insights in our daily activities and the means to improve and automate them. This project aims to exploit the available sensor data to help detect and predict health deterioration in older people. This involves collecting and curating real data, from sleeping and eating habits, to the speed of climbing the stairs. You will then employ and develop advanced process modelling techniques to capture daily routines and data-driven AI to predict long-term changes. The project requires a multi-disciplinary approach that incorporates relevant medical information and ethical considerations.
The project will be part of the ACRC theme on New Technologies of Care and is aligned with other themes such as the one on understanding the person in context.
The PhD position is fully funded by a studentship and the deadline for applications is the 26 November 2021. Informal inquiries can be sent to Petros Papapanagiotou (pe.p@ed.ac.uk).
More information and application details can be found here.
Fully Funded PhD: Building explainable user models of older adults from data
Supervisors: Jacques Fleuriot (principal), Sohan Seth & Susan Shenkin
Funding: Advanced Care Research Centre (ACRC).
Deadline: 5 May 2021
As artificial intelligence increasingly permeates all spheres of life, it is becoming clear that there is a need for predictive models that can explain their decisions. This is particularly important in safety-critical areas such as health and care, where the wrong decision can be a matter of life or death.
This project will explore how health and care outcomes for the older person can be improved through explainable, predictive machine learning. In particular, it will develop interpretable AI models of older adults, based on a combination of statistical and symbolic approaches using data related to care, physiological monitoring, activities of daily living and other events (e.g. social network interactions).
By developing robust, yet adaptive and transparent, user models that can support the individual’s needs and are attentive to physical/non-physical decline over time, it should be possible to increase the reliance on AI when making non-trivial care interventions.
Some of the objectives include:
- Exploring how already-labelled data about care treatment, alarm calls, history of falls etc. can be used to detect adverse events and trigger personalised alerts that are robust to noise;
- Investigate whether decline can be predicted based on reduced interactions with entertainment systems, games, frequency of audio/video chats family and friends, etc.;
- Investigate how public datasets can be used to extend the explainable models with data about activities of daily living (ADL), physiological monitoring and other events.
The project will be part of the ACRC theme on New Technologies of Care and is aligned with other themes such as the one on data-driven insight and prediction.
The PhD position is fully funded by a studentship and the deadline for applications is the 5th of May 2021. Informal inquiries can be sent to Jacques Fleuriot (jdf@inf.ed.ac.uk).
More information and application details can be found here.
Fully Funded PhD in (AI for) Precision Medicine: Predicting rehabilitation needs and trajectories in older patients
Supervisors: Atul Anand, Jacques Fleuriot, Joanne McPeake (U of Glasgow) & Susan Shenkin
Funding: Studentship from the Precision Medicine Doctoral Training Programme.
Deadline: 7th January 2021
Our population is ageing. The majority of hospital resources are used by older and increasingly frail patients. When older people become ill with conditions like pneumonia, their ability to complete basic functions like walking and eating can be affected. Such loss of independence is a great fear for many older people. Rehabilitation tries to maximise functional recovery of older patients and restore independence. This process involves a multidisciplinary team of healthcare professionals and can be the difference between a person leaving hospital independently or requiring extensive carer support.
With the transition to electronic health records (EHRs), the quantity, timing and outcomes of hospital rehabilitation contacts are now available to drive new insights. These EHRs are central to the DataLoch, a funded linked repository of health and social care records for residents across South East Scotland. There are new opportunities to use process mining techniques, commonly applied in the business world, to understand existing trajectories of rehabilitation.
Aims
- To develop predictive models for estimation of rehabilitation needs using routine EHR data. This will use both standard multivariate and machine learning approaches.
- To use process mining of healthcare contact data to define trajectories of inpatient rehabilitation.
- To develop data visualisation tools for the EHR to aid patient and professional understanding of trajectories of rehabilitation in an individual.
This exciting project will develop a wide range of cutting-edge skills in healthcare data science and Explainable AI. The student will gain competences in complex predictive model development including interpretable machine learning techniques, process mining and development of interactive data visualisation tools. Many of these applications are novel and have direct translation potential to change clinical care.
The PhD position is fully funded by a studentship and the deadline for applications is Thursday 7th January 2021. Informal inquiries can be sent to Jacques Fleuriot (jdf@inf.ed.ac.uk).
More information and application details can be found here.
Research Associate in Formal Modelling and Explainable AI for Health and Care
Applications are invited for a Research Associate in Formal Modelling and Explainable AI for Health and Care in the School of Informatics, University of Edinburgh.
This post will contribute to the New Technologies of Care Programme within the Advanced Care Research Centre ACRC) at the University of Edinburgh.
This full-time position is fixed term for 36 months.
Informal enquiries to be directed to Jacques Fleuriot (jdf@inf.ed.ac.uk) and Petros Papapanagiotou (pe.p@ed.ac.uk)
Salary grade scale: UE07 (£33,797 – £40,322pa)
Feedback is only provided to interviewed candidates.
Closing date 5pm (GMT) on 14th October 2020.
Further information
In order to allow for meaningful inference and decision making in the context of advanced care delivery for the older person, explainable computer-based models are needed that can capture the vast body of knowledge both around general and specific care pathways and incorporate data from real-time sources such as sensors. In the case of the person in later life, there is a need for contextualisation when it comes to both the care recipient and their environment.
One objective of this project is to build computer-based models that enable both the management and analysis of care, while supporting decision making via Explainable AI methods. Workflow management systems will be used to automate parts of care delivery, so that we can maintain consistent, accountable and continuous levels over time. AI-based workflow analytics and other techniques will be used to understand and predict outcomes based on sensor, video and recorded care data (coming from other streams of the New Technologies of Care Programme and the broader ACRC). Bridging the gap between the high complexity of the care landscape, the individual needs and circumstances of the older person, and the development of computer-based workflows that interface between data and processes in order to drive decision-making will be one of the important goals of this multidisciplinary project.
Further information and the application procedure are available here.