The EPSRC DRIVE-Health Centre for Doctoral Training in Data-Driven Health
Vasa Ćurčin is a Professor in Health Informatics at King’s College London and leads the Digital Health Group, focusing on reproducibility solutions based on data provenance, embedding clinical trials into routine practice, decision support systems as means of implementing Learning Health Systems in practice, and machine learning methods for detecting depression and anxiety disorders from social network behaviours.
Professor Ćurčin’s recent work has been on computable guidelines as a means of implementing decision support systems and digital interventions in patient care. Vasa completed his PhD at Imperial College London on the semantics of scientific workflow systems. The application of his thesis to large real-world patient databases resulted in one of the earliest workflow-based phenotyping tools that has been used in both academic and industrial settings.
Professor Ćurčin is a co-director of the DRIVE-Health Centre for Doctoral Training in Data-Driven Health and the joint Head of Department of Population Health Sciences.
Vasa Ćurčin is a Professor in Health Informatics at King’s College London and leads the Digital Health Group, focusing on reproducibility solutions based on data provenance, embedding clinical trials into routine practice, decision support systems as means of implementing Learning Health Systems in practice, and machine learning methods for detecting depression and anxiety disorders from social network behaviours.
Professor Ćurčin’s recent work has been on computable guidelines as a means of implementing decision support systems and digital interventions in patient care. Vasa completed his PhD at Imperial College London on the semantics of scientific workflow systems. The application of his thesis to large real-world patient databases resulted in one of the earliest workflow-based phenotyping tools that has been used in both academic and industrial settings.
Professor Ćurčin is a co-director of the DRIVE-Health Centre for Doctoral Training in Data-Driven Health and the joint Head of Department of Population Health Sciences.
Vasa Ćurčin is a Professor in Health Informatics at King’s College London and leads the Digital Health Group, focusing on reproducibility solutions based on data provenance, embedding clinical trials into routine practice, decision support systems as means of implementing Learning Health Systems in practice, and machine learning methods for detecting depression and anxiety disorders from social network behaviours.
Professor Ćurčin’s recent work has been on computable guidelines as a means of implementing decision support systems and digital interventions in patient care. Vasa completed his PhD at Imperial College London on the semantics of scientific workflow systems. The application of his thesis to large real-world patient databases resulted in one of the earliest workflow-based phenotyping tools that has been used in both academic and industrial settings.
Professor Ćurčin is a co-director of the DRIVE-Health Centre for Doctoral Training in Data-Driven Health and the joint Head of Department of Population Health Sciences.
The EPSRC DRIVE-Health Centre for Doctoral Training in Data-Driven Health
Vasa Ćurčin is a Professor in Health Informatics at King’s College London and leads the Digital Health Group, focusing on reproducibility solutions based on data provenance, embedding clinical trials into routine practice, decision support systems as means of implementing Learning Health Systems in practice, and machine learning methods for detecting depression and anxiety disorders from social network behaviours.
Professor Ćurčin’s recent work has been on computable guidelines as a means of implementing decision support systems and digital interventions in patient care. Vasa completed his PhD at Imperial College London on the semantics of scientific workflow systems. The application of his thesis to large real-world patient databases resulted in one of the earliest workflow-based phenotyping tools that has been used in both academic and industrial settings.
Professor Ćurčin is a co-director of the DRIVE-Health Centre for Doctoral Training in Data-Driven Health and the joint Head of Department of Population Health Sciences.
Richard Dobson holds a dual appointment as Professor of Health and Medical Informatics at King's College London and at the Institute of Health Informatics, University College London. He is the Head of Department of Biostatistics and Health Informatics, and Theme Lead for Informatics at the NIHR Maudsley Biomedical Research Centre, King’s College London, and UCLH NIHR Biomedical Research Centre Computational Medicine board member. He co-chairs the Centre for Translational Informatics (CTI) and is co-director of the EPSRC Centre for Doctoral Training in Data Driven Health (drive-health.org.uk).
Richard has 20+ years of experience in developing data & AI with the NHS with significant contributions to the healthcare sector. He partners with regulators at the DSIT, ICO, InnovateUK and the Equalities Commission on initiatives such as the fairness innovation challenge to ensure safe and fair use of AI in healthcare.
Richard has established strong links with the technology and pharma industry, charities, and academia. He sits on advisory groups for UK national strategy, policy and funding including the Department of Heath's 10-year strategy for Population & Health Services Research in mental health working group. He leads data and AI work streams for several industrial and academic pan European major programmes and the UK collaborations including the Office for Life Sciences Mental Health Mission.
Richard’s research has garnered significant media attention, particularly for its impactful contributions to healthcare through the development of innovative technology. His work has received numerous awards for Artificial Intelligence in Health and Care and the societal benefits of his research are profound; improving healthcare delivery, enhancing patient experiences, and contributing to better health outcomes on a broad scale.
Vasa Ćurčin is a Professor in Health Informatics at King’s College London and leads the Digital Health Group, focusing on reproducibility solutions based on data provenance, embedding clinical trials into routine practice, decision support systems as means of implementing Learning Health Systems in practice, and machine learning methods for detecting depression and anxiety disorders from social network behaviours.
Professor Ćurčin’s recent work has been on computable guidelines as a means of implementing decision support systems and digital interventions in patient care. Vasa completed his PhD at Imperial College London on the semantics of scientific workflow systems. The application of his thesis to large real-world patient databases resulted in one of the earliest workflow-based phenotyping tools that has been used in both academic and industrial settings.
Professor Ćurčin is a co-director of the DRIVE-Health Centre for Doctoral Training in Data-Driven Health and the joint Head of Department of Population Health Sciences.
Richard Dobson holds a dual appointment as Professor of Health and Medical Informatics at King's College London and at the Institute of Health Informatics, University College London. He is the Head of Department of Biostatistics and Health Informatics, and Theme Lead for Informatics at the NIHR Maudsley Biomedical Research Centre, King’s College London, and UCLH NIHR Biomedical Research Centre Computational Medicine board member. He co-chairs the Centre for Translational Informatics (CTI) and is co-director of the EPSRC Centre for Doctoral Training in Data Driven Health (drive-health.org.uk).
Richard has 20+ years of experience in developing data & AI with the NHS with significant contributions to the healthcare sector. He partners with regulators at the DSIT, ICO, InnovateUK and the Equalities Commission on initiatives such as the fairness innovation challenge to ensure safe and fair use of AI in healthcare.
Richard has established strong links with the technology and pharma industry, charities, and academia. He sits on advisory groups for UK national strategy, policy and funding including the Department of Heath's 10-year strategy for Population & Health Services Research in mental health working group. He leads data and AI work streams for several industrial and academic pan European major programmes and the UK collaborations including the Office for Life Sciences Mental Health Mission.
Richard’s research has garnered significant media attention, particularly for its impactful contributions to healthcare through the development of innovative technology. His work has received numerous awards for Artificial Intelligence in Health and Care and the societal benefits of his research are profound; improving healthcare delivery, enhancing patient experiences, and contributing to better health outcomes on a broad scale.
Data lies at the heart of healthcare. DRIVE-Health focuses on the sources and use of data, and the design systems that deepen its use, to improve care.
Digitised healthcare drives global healthcare sustainability. Digitised healthcare technologies address the complex needs of individuals with multiple health conditions.
By optimising digital healthcare, DRIVE-Health aims to ensure equitable access to healthcare across diverse socio-economic groups globally.
DRIVE-Health aims to train 85 digital health PhDs over the course of 9 years.
Healthcare systems worldwide face complex challenges brought about by ageing populations, rising healthcare costs, and increasing demands for personalised care. Medicine has always relied on data, and today’s clinicians have access to a wider range of data sources than ever before - progress in healthcare relies on the effective marshalling and adoption of the available data. DRIVE-Health’s PhD students will advance the use and adoption of data in healthcare, from deepening the use of AI through to the application of digital simulations for healthcare experiments, and the design of interfaces for use in practice.
How data transforms prognosis, diagnosis and treatment in global healthcare
King's College London’s EPSRC DRIVE-Health Centre for Doctoral Training in Data-Driven Health leads the formation of the next generation of health data scientists - a crucial component in the drive towards sustainable, equitable global healthcare. This interdisciplinary program focuses on optimising informatics technologies to address complex global healthcare challenges. By combining academic rigour with real-world applications, DRIVE-Health bridges the gap between complex healthcare needs and technological advancements. Through collaborations with industry partners and international networks, DRIVE-Health enables the adoption of innovation in patient care and global population health on an unprecedented scale. DRIVE-Health focuses on five themes, addressing some of the most fundamental data challenges in healthcare: sustainable engineering for health systems; the integration of data from different sources; building digital models of real-world patients to evaluate the applications of technologies such as AI; creating interfaces for the use of data in practice; and co-designing and co-producing systems with patients.
DRIVE-Health will train 85 PhD students in cohorts over the next nine years. By offering interdisciplinary training programs, DRIVE-Health equips data scientists with the practical knowledge and skills needed to navigate the intersection of healthcare, data science, and technology.
There is a rapidly growing demand for experts who can harness the power of data to advance healthcare delivery and improve population health. The interdisciplinary programs provided by DRIVE-Health will ultimately lead to better healthcare outcomes for individuals and communities across the full breadth of socio-demographic groupings, and drive innovation and adoption in global patient care and population health.
DRIVE-Health’s focus on data-driven health has the potential to deliver sustainable, equitable healthcare globally, and on an unprecedented scale. This is particularly relevant to low- and middle-income countries, where digital adoption outpaces economic development, enabling digitised healthcare to significantly improve population health.
The EPSRC DRIVE-Health Centre for Doctoral Training in Data-Driven Health will address the application of some of the most high-potential developments in healthcare data - for example, the use of artificial intelligence and the creation of digital twins to simulate its impact and the integration and use of data from novel sources such as smartwatches and genomics.
The application of data will enable personalised healthcare at scale, and the proactive disease prevention and management strategies that are vital for addressing global health challenges in the context of an ageing population.
This has the potential to ultimately reduce the burden on healthcare systems, improve health outcomes at a global level, and reduce global inequalities in healthcare access.
Individual PhD projects within the DRIVE-Health programme, and open for funding on the Science Card platform, are listed below.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.
Enhancing Disorder Diagnosis and Prognosis: Leveraging Artificial Intelligence in Electronic Health Records
This PhD project, led by Professor Richard Dobson, aims to enhance patient care by applying artificial intelligence (AI) to the extensive data collected by the NHS, the vast majority of which exists in narrative form including notes, letters and reports. The goal is to be able to transform unutilised data into predictive insights, and set standards for safe AI use in healthcare. This will lead to the development of personalised treatments, improving patient outcomes.
The AI development in this project focuses on their internationally recognised work, training and fine-tuning large language models (LLMs), using extensive real-world clinical data collected by our NHS partners, with approximately 9m patient contacts per year. By learning from 15 years of diverse patient data, encompassing 190,000 medical concepts across diseases, symptoms, procedures, and medications, these models are designed to understand and predict complex medical scenarios.
The LLMs in this project are designed to be able to predict disease progression, recommend tailored treatments, and identify the most effective medications for individual patients using the clinical text that doctors write. This capability will enable earlier diagnoses, more precise and personalised treatments, and better disease management - ultimately leading to improved health outcomes and quality of life for patients.
This project focuses on conditions such as Alzheimer’s Disease and motor neuron disease (MND), a complex and variable condition. In the case of MND, the team will be collaborating closely with leading MND care centres and utilising data spanning nearly two decades, with the aim of comprehensively understanding and predicting the progression of this disease. By integrating detailed electronic health records with diverse datasets, including genetic markers from whole genome sequencing, the team aims to build a comprehensive profile of MND patients. Their objective is to move beyond standard treatments, creating the ability to craft personalised care plans tailored to each patient's unique needs and disease trajectory. Ultimately, the goal is to enhance outcomes for MND patients by offering more precise therapies and support informed by a profound understanding of the disease's evolving nature.
Enhancing Disorder Diagnosis and Prognosis: Leveraging Artificial Intelligence in Electronic Health Records
This PhD project, led by Professor Richard Dobson, aims to enhance patient care by applying artificial intelligence (AI) to the extensive data collected by the NHS, the vast majority of which exists in narrative form including notes, letters and reports. The goal is to be able to transform unutilised data into predictive insights, and set standards for safe AI use in healthcare. This will lead to the development of personalised treatments, improving patient outcomes.
The AI development in this project focuses on their internationally recognised work, training and fine-tuning large language models (LLMs), using extensive real-world clinical data collected by our NHS partners, with approximately 9m patient contacts per year. By learning from 15 years of diverse patient data, encompassing 190,000 medical concepts across diseases, symptoms, procedures, and medications, these models are designed to understand and predict complex medical scenarios.
The LLMs in this project are designed to be able to predict disease progression, recommend tailored treatments, and identify the most effective medications for individual patients using the clinical text that doctors write. This capability will enable earlier diagnoses, more precise and personalised treatments, and better disease management - ultimately leading to improved health outcomes and quality of life for patients.
This project focuses on conditions such as Alzheimer’s Disease and motor neuron disease (MND), a complex and variable condition. In the case of MND, the team will be collaborating closely with leading MND care centres and utilising data spanning nearly two decades, with the aim of comprehensively understanding and predicting the progression of this disease. By integrating detailed electronic health records with diverse datasets, including genetic markers from whole genome sequencing, the team aims to build a comprehensive profile of MND patients. Their objective is to move beyond standard treatments, creating the ability to craft personalised care plans tailored to each patient's unique needs and disease trajectory. Ultimately, the goal is to enhance outcomes for MND patients by offering more precise therapies and support informed by a profound understanding of the disease's evolving nature.
Temporal detection and analyses of interactions when combining multiple clinical guidelines, patient preferences and goals.
This PhD project aims to deliver a step change in healthcare decision support systems by addressing the complexities of managing multiple clinical conditions, preferences, and goals within electronic health record (EHR) workflows and aligning with national and local guidelines.
Managing patients with multiple concurrent medical conditions, known as multimorbidity, poses significant challenges in healthcare delivery. One of the underlying challenges is that guidelines for treating diseases are usually meant for single diseases and it is left to the practitioner to combine them in practice, limiting the applicability of automated decision support systems. With multimorbidities - which include chronic conditions such as cardiovascular diseases, mental health disorders, diabetes, and cancer - affecting approximately one in four adults in the UK, the need for integrated decision-support mechanisms is more pressing than ever.
Focusing on management of stroke and its multimorbidities, the project will compare theoretical models for applying clinical guidelines with guideline adherence in real-world settings. With its emphasis on evidence-based practice, the project has significant implications for enhancing healthcare delivery on a global scale.
Temporal detection and analyses of interactions when combining multiple clinical guidelines, patient preferences and goals.
This PhD project aims to deliver a step change in healthcare decision support systems by addressing the complexities of managing multiple clinical conditions, preferences, and goals within electronic health record (EHR) workflows and aligning with national and local guidelines.
Managing patients with multiple concurrent medical conditions, known as multimorbidity, poses significant challenges in healthcare delivery. One of the underlying challenges is that guidelines for treating diseases are usually meant for single diseases and it is left to the practitioner to combine them in practice, limiting the applicability of automated decision support systems. With multimorbidities - which include chronic conditions such as cardiovascular diseases, mental health disorders, diabetes, and cancer - affecting approximately one in four adults in the UK, the need for integrated decision-support mechanisms is more pressing than ever.
Focusing on management of stroke and its multimorbidities, the project will compare theoretical models for applying clinical guidelines with guideline adherence in real-world settings. With its emphasis on evidence-based practice, the project has significant implications for enhancing healthcare delivery on a global scale.
Science Card’s model is very well suited to what DRIVE-Health is doing. We're operating across several research areas. We're not restricted to a single question, a single field. And we are doing something that is of broad importance, and that will have a massive impact on the quality of life for people in the UK and internationally.
Sign up now for early access and more when we launch this autumn (we only have a few places left on our early access list, but don’t worry, you’re in!)
Tell us about yourself:
We don’t use cookies on this website.
Preserving your privacy is one of our core principles.
1
2
3
4
5
sec
