Harnessing the potential of machine learning and artificial intelligence for dementia research

Janice M. Ranson; Magda Bucholc; Donald Lyall; Danielle Newby; Laura Winchester; Neil  Oxtoby; Michele Veldsman; Timothy Rittman; Sarah Marzi; Nathan Skene; Ahmad Al Khleifat; Isabelle F Foote; Vasiliki Orgeta; Andrey Kormilitzin; Ilianna  Lourida; David J  Llewellyn

doi:10.1186/s40708-022-00183-3

Harnessing the potential of machine learning and artificial intelligence for dementia research

Janice M. Ranson
, Magda Bucholc
, Donald Lyall
, Danielle Newby
, Laura Winchester
, Neil Oxtoby
, Michele Veldsman
, Timothy Rittman
, Sarah Marzi
, Nathan Skene
, Ahmad Al Khleifat
, Isabelle F Foote
, Vasiliki Orgeta
, Andrey Kormilitzin
, Ilianna Lourida
, David J Llewellyn

Research output: Contribution to journal › Article › peer-review

22 Citations (Scopus)

105 Downloads (Pure)

Abstract

Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal datasets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal datasets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

Original language	English
Article number	6
Pages (from-to)	1-12
Number of pages	12
Journal	Brain Informatics
Volume	10
Issue number	1
Early online date	24 Feb 2023
DOIs	https://doi.org/10.1186/s40708-022-00183-3
Publication status	Published online - 24 Feb 2023

Bibliographical note

Funding Information:
This paper was the product of a DEMON Network state of the science symposium entitled “Harnessing Data Science and AI in Dementia Research” funded by Alzheimer’s Research UK. JMR is supported by Alzheimer’s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL is supported by Alzheimer’s Research UK, National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), National Institute on Aging/National Institutes of Health (RF1AG055654), and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). NO is a UKRI Future Leaders Fellow (MR/S03546X/1) and acknowledges funding from the National Institute for Health Research University College London Hospitals Biomedical Research Centre. AAK is funded by ALS Association Milton Safenowitz Research Fellowship, The Motor Neurone Disease Association (MNDA) Fellowship (Al Khleifat/Oct21/975–799) and The NIHR Maudsley Biomedical Research Centre. TR is supported by the Cambridge Centre for Parkinson's Plus Disorders and the Cambridge Biomedical Research Centre. This work was additionally supported by the following funding: Alzheimer’s Research UK and Dr George Moore Endowment for Data Science at Ulster University (MB), George Henry Woolfe Legacy Fund (IFF).

Funding Information:
All authors are members of the Leadership Team for the non-profit Deep Dementia Phenotyping (DEMON) Network. DL and JR are founders of the DEMON Network, the Alzheimer’s Association ISTAART Professional Interest Area in AI for Precision Dementia Medicine, and the Alan Turing Institute Interest Group in Precision Dementia Medicine. With thanks to collaborators from the DEMON Network State of the Science Symposium participants (in alphabetical order): Peter Bagshaw, Robin Borchert, Magda Bucholc, James Duce, Charlotte James, David Llewellyn, Donald Lyall, Sarah Marzi, Danielle Newby, Neil Oxtoby, Janice Ranson, Tim Rittman, Nathan Skene, Eugene Tang, Michele Veldsman, Laura Winchester, Zhi Yao.

Funding Information:
AK declares research grant funding from GlaxoSmithKline. All other authors declare no competing interests.

Publisher Copyright:
© 2023, The Author(s).

Funding

Funding Information: This paper was the product of a DEMON Network state of the science symposium entitled “Harnessing Data Science and AI in Dementia Research” funded by Alzheimer’s Research UK. JMR is supported by Alzheimer’s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL is supported by Alzheimer’s Research UK, National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), National Institute on Aging/National Institutes of Health (RF1AG055654), and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). NO is a UKRI Future Leaders Fellow (MR/S03546X/1) and acknowledges funding from the National Institute for Health Research University College London Hospitals Biomedical Research Centre. AAK is funded by ALS Association Milton Safenowitz Research Fellowship, The Motor Neurone Disease Association (MNDA) Fellowship (Al Khleifat/Oct21/975–799) and The NIHR Maudsley Biomedical Research Centre. TR is supported by the Cambridge Centre for Parkinson's Plus Disorders and the Cambridge Biomedical Research Centre. This work was additionally supported by the following funding: Alzheimer’s Research UK and Dr George Moore Endowment for Data Science at Ulster University (MB), George Henry Woolfe Legacy Fund (IFF). Funding Information: All authors are members of the Leadership Team for the non-profit Deep Dementia Phenotyping (DEMON) Network. DL and JR are founders of the DEMON Network, the Alzheimer’s Association ISTAART Professional Interest Area in AI for Precision Dementia Medicine, and the Alan Turing Institute Interest Group in Precision Dementia Medicine. With thanks to collaborators from the DEMON Network State of the Science Symposium participants (in alphabetical order): Peter Bagshaw, Robin Borchert, Magda Bucholc, James Duce, Charlotte James, David Llewellyn, Donald Lyall, Sarah Marzi, Danielle Newby, Neil Oxtoby, Janice Ranson, Tim Rittman, Nathan Skene, Eugene Tang, Michele Veldsman, Laura Winchester, Zhi Yao. Funding Information: AK declares research grant funding from GlaxoSmithKline. All other authors declare no competing interests. Publisher Copyright: © 2023, The Author(s).

Keywords

dementia
artificial intelligence
machine learning
genetics
drug discovery
neuroimaging
prevention
iPSC
animal models
Neuroimaging
Animal models
Prevention
Machine learning
Genetics
Drug discovery
Artificial intelligence
Dementia

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1186/s40708-022-00183-3

s40708-022-00183-3Final published version, 846 KBLicence: CC BY

Cite this

Ranson, J. M., Bucholc, M., Lyall, D., Newby, D., Winchester, L., Oxtoby, N., Veldsman, M., Rittman, T., Marzi, S., Skene, N., Khleifat, A. A., Foote, I. F., Orgeta, V., Kormilitzin, A., Lourida, I., & Llewellyn, D. J. (2023). Harnessing the potential of machine learning and artificial intelligence for dementia research. Brain Informatics, 10(1), 1-12. Article 6. Advance online publication. https://doi.org/10.1186/s40708-022-00183-3

@article{839330f0d4b646d78ab577a4237329ce,

title = "Harnessing the potential of machine learning and artificial intelligence for dementia research",

abstract = "Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal datasets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal datasets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine. ",

keywords = "dementia, artificial intelligence, machine learning, genetics, drug discovery, neuroimaging, prevention, iPSC, animal models, Neuroimaging, Animal models, Prevention, Machine learning, Genetics, Drug discovery, Artificial intelligence, Dementia",

author = "Ranson, \{Janice M.\} and Magda Bucholc and Donald Lyall and Danielle Newby and Laura Winchester and Neil Oxtoby and Michele Veldsman and Timothy Rittman and Sarah Marzi and Nathan Skene and Khleifat, \{Ahmad Al\} and Foote, \{Isabelle F\} and Vasiliki Orgeta and Andrey Kormilitzin and Ilianna Lourida and Llewellyn, \{David J\}",

note = "Funding Information: This paper was the product of a DEMON Network state of the science symposium entitled “Harnessing Data Science and AI in Dementia Research” funded by Alzheimer{\textquoteright}s Research UK. JMR is supported by Alzheimer{\textquoteright}s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL is supported by Alzheimer{\textquoteright}s Research UK, National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), National Institute on Aging/National Institutes of Health (RF1AG055654), and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). NO is a UKRI Future Leaders Fellow (MR/S03546X/1) and acknowledges funding from the National Institute for Health Research University College London Hospitals Biomedical Research Centre. AAK is funded by ALS Association Milton Safenowitz Research Fellowship, The Motor Neurone Disease Association (MNDA) Fellowship (Al Khleifat/Oct21/975–799) and The NIHR Maudsley Biomedical Research Centre. TR is supported by the Cambridge Centre for Parkinson's Plus Disorders and the Cambridge Biomedical Research Centre. This work was additionally supported by the following funding: Alzheimer{\textquoteright}s Research UK and Dr George Moore Endowment for Data Science at Ulster University (MB), George Henry Woolfe Legacy Fund (IFF). Funding Information: All authors are members of the Leadership Team for the non-profit Deep Dementia Phenotyping (DEMON) Network. DL and JR are founders of the DEMON Network, the Alzheimer{\textquoteright}s Association ISTAART Professional Interest Area in AI for Precision Dementia Medicine, and the Alan Turing Institute Interest Group in Precision Dementia Medicine. With thanks to collaborators from the DEMON Network State of the Science Symposium participants (in alphabetical order): Peter Bagshaw, Robin Borchert, Magda Bucholc, James Duce, Charlotte James, David Llewellyn, Donald Lyall, Sarah Marzi, Danielle Newby, Neil Oxtoby, Janice Ranson, Tim Rittman, Nathan Skene, Eugene Tang, Michele Veldsman, Laura Winchester, Zhi Yao. Funding Information: AK declares research grant funding from GlaxoSmithKline. All other authors declare no competing interests. Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = feb,

day = "24",

doi = "10.1186/s40708-022-00183-3",

language = "English",

volume = "10",

pages = "1--12",

journal = "Brain Informatics",

issn = "2198-4018",

publisher = "Springer Science and Business Media Deutschland GmbH",

number = "1",

}

Ranson, JM, Bucholc, M, Lyall, D, Newby, D, Winchester, L, Oxtoby, N, Veldsman, M, Rittman, T, Marzi, S, Skene, N, Khleifat, AA, Foote, IF, Orgeta, V, Kormilitzin, A, Lourida, I & Llewellyn, DJ 2023, 'Harnessing the potential of machine learning and artificial intelligence for dementia research', Brain Informatics, vol. 10, no. 1, 6, pp. 1-12. https://doi.org/10.1186/s40708-022-00183-3

TY - JOUR

T1 - Harnessing the potential of machine learning and artificial intelligence for dementia research

AU - Ranson, Janice M.

AU - Bucholc, Magda

AU - Lyall, Donald

AU - Newby, Danielle

AU - Winchester, Laura

AU - Oxtoby, Neil

AU - Veldsman, Michele

AU - Rittman, Timothy

AU - Marzi, Sarah

AU - Skene, Nathan

AU - Khleifat, Ahmad Al

AU - Foote, Isabelle F

AU - Orgeta, Vasiliki

AU - Kormilitzin, Andrey

AU - Lourida, Ilianna

AU - Llewellyn, David J

N1 - Funding Information: This paper was the product of a DEMON Network state of the science symposium entitled “Harnessing Data Science and AI in Dementia Research” funded by Alzheimer’s Research UK. JMR is supported by Alzheimer’s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL is supported by Alzheimer’s Research UK, National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), National Institute on Aging/National Institutes of Health (RF1AG055654), and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). NO is a UKRI Future Leaders Fellow (MR/S03546X/1) and acknowledges funding from the National Institute for Health Research University College London Hospitals Biomedical Research Centre. AAK is funded by ALS Association Milton Safenowitz Research Fellowship, The Motor Neurone Disease Association (MNDA) Fellowship (Al Khleifat/Oct21/975–799) and The NIHR Maudsley Biomedical Research Centre. TR is supported by the Cambridge Centre for Parkinson's Plus Disorders and the Cambridge Biomedical Research Centre. This work was additionally supported by the following funding: Alzheimer’s Research UK and Dr George Moore Endowment for Data Science at Ulster University (MB), George Henry Woolfe Legacy Fund (IFF). Funding Information: All authors are members of the Leadership Team for the non-profit Deep Dementia Phenotyping (DEMON) Network. DL and JR are founders of the DEMON Network, the Alzheimer’s Association ISTAART Professional Interest Area in AI for Precision Dementia Medicine, and the Alan Turing Institute Interest Group in Precision Dementia Medicine. With thanks to collaborators from the DEMON Network State of the Science Symposium participants (in alphabetical order): Peter Bagshaw, Robin Borchert, Magda Bucholc, James Duce, Charlotte James, David Llewellyn, Donald Lyall, Sarah Marzi, Danielle Newby, Neil Oxtoby, Janice Ranson, Tim Rittman, Nathan Skene, Eugene Tang, Michele Veldsman, Laura Winchester, Zhi Yao. Funding Information: AK declares research grant funding from GlaxoSmithKline. All other authors declare no competing interests. Publisher Copyright: © 2023, The Author(s).

PY - 2023/2/24

Y1 - 2023/2/24

N2 - Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal datasets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal datasets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

AB - Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal datasets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal datasets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

KW - dementia

KW - artificial intelligence

KW - machine learning

KW - genetics

KW - drug discovery

KW - neuroimaging

KW - prevention

KW - iPSC

KW - animal models

KW - Neuroimaging

KW - Animal models

KW - Prevention

KW - Machine learning

KW - Genetics

KW - Drug discovery

KW - Artificial intelligence

KW - Dementia

UR - https://pure.ulster.ac.uk/en/publications/839330f0-d4b6-46d7-8ab5-77a4237329ce

UR - https://www.scopus.com/pages/publications/85149207375

U2 - 10.1186/s40708-022-00183-3

DO - 10.1186/s40708-022-00183-3

M3 - Article

C2 - 36829050

SN - 2198-4018

VL - 10

SP - 1

EP - 12

JO - Brain Informatics

JF - Brain Informatics

IS - 1

M1 - 6

ER -

Harnessing the potential of machine learning and artificial intelligence for dementia research

Abstract

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this