Artificial Intelligence for Dementia Research Methods Optimization

Magda Bucholc; Charlotte James; Ahmad Al Khleifat; AmanPreet Badhwar; Natasha Clarke; Amir Dehsarvi; Christopher R Madan; Sarah J Marzi; Cameron Shand; Brian M Schilder; Stefano Tamburin; Hanz M Tantiangco; Ilianna Lourida; David J Llewellyn; Janice M Ranson

doi:10.48550/arXiv.2303.01949

Artificial Intelligence for Dementia Research Methods Optimization

Magda Bucholc^* (Corresponding Author), Charlotte James, Ahmad Al Khleifat, AmanPreet Badhwar, Natasha Clarke, Amir Dehsarvi, Christopher R Madan, Sarah J Marzi, Cameron Shand, Brian M Schilder, Stefano Tamburin, Hanz M Tantiangco, Ilianna Lourida, David J Llewellyn, Janice M Ranson

^*Corresponding author for this work

Research output: Working paper

Abstract

INTRODUCTION: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Original language	English
Publisher	ArXiv
Number of pages	47
DOIs	https://doi.org/10.48550/arXiv.2303.01949
Publication status	Published - 2 Mar 2023

Bibliographical note

Funding
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 and DJL are supported by Alzheimer’s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL has also received funding from the National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), JP Moulton Foundation, National Institute on Aging/National Institutes of Health (RF1AG055654), Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). This work was additionally supported by Alzheimer’s Research UK (MB, CJ), European Union INTERREG VA Programme (MB), Dr George Moore Endowment for Data 31 Science at Ulster University (MB), National Institute for Health and Care Research Bristol Biomedical Research Centre (CJ), Fonds de recherche du Québec Santé - Chercheur boursiers Junior 1 (AB), Canadian Consortium for Neurodegeneration in Aging and the Courtois Foundation (AB, NC), The Motor Neurone Disease Association Fellowship (Al Khleifat/Oct21/975-799) (AAK), ALS Association Milton Safenowitz Research Fellowship (grant number 22-PDF 609. doi:10.52546/pc.gr.150909) (AAK), NIHR Maudsley Biomedical Research Centre (AAK), The Darby Rimmer Foundation (AAK), UKRI Future Leaders Fellowship (MR/S03546X/1) (CS), E-DADS project (EU JPND) (CS), EuroPOND project (EU Horizon 2020, no. 666992) (CS). SJM is funded by the Edmond and Lily Safra Early Career Fellowship Program and the UK Dementia Research Institute, which receives its funding from UK DRI Ltd, funded by the UK Medical Research Council, Alzheimer's Society and Alzheimer's Research UK.

Keywords

dementia
artificial intelligence
machine learning
deep learning
classification
regression
supervised learning
unsupervised learning
semi-supervised learning
methods optimization
generalisability
interpretability
replicability
transferability
clinical utility

UN SDGs

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

Access to Document

10.48550/arXiv.2303.01949Licence: CC BY

Cite this

@techreport{5ec8129015784987a38d20dcd1ee70f9,

title = "Artificial Intelligence for Dementia Research Methods Optimization",

abstract = "INTRODUCTION: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.METHODS: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.RESULTS: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.DISCUSSION: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.",

keywords = "dementia, artificial intelligence, machine learning, deep learning, classification, regression, supervised learning, unsupervised learning, semi-supervised learning, methods optimization, generalisability, interpretability, replicability, transferability, clinical utility",

author = "Magda Bucholc and Charlotte James and Khleifat, {Ahmad Al} and AmanPreet Badhwar and Natasha Clarke and Amir Dehsarvi and Madan, {Christopher R} and Marzi, {Sarah J} and Cameron Shand and Schilder, {Brian M} and Stefano Tamburin and Tantiangco, {Hanz M} and Ilianna Lourida and Llewellyn, {David J} and Ranson, {Janice M}",

note = "Funding 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 and DJL are supported by Alzheimer{\textquoteright}s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL has also received funding from the National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), JP Moulton Foundation, National Institute on Aging/National Institutes of Health (RF1AG055654), Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). This work was additionally supported by Alzheimer{\textquoteright}s Research UK (MB, CJ), European Union INTERREG VA Programme (MB), Dr George Moore Endowment for Data 31 Science at Ulster University (MB), National Institute for Health and Care Research Bristol Biomedical Research Centre (CJ), Fonds de recherche du Qu{\'e}bec Sant{\'e} - Chercheur boursiers Junior 1 (AB), Canadian Consortium for Neurodegeneration in Aging and the Courtois Foundation (AB, NC), The Motor Neurone Disease Association Fellowship (Al Khleifat/Oct21/975-799) (AAK), ALS Association Milton Safenowitz Research Fellowship (grant number 22-PDF 609. doi:10.52546/pc.gr.150909) (AAK), NIHR Maudsley Biomedical Research Centre (AAK), The Darby Rimmer Foundation (AAK), UKRI Future Leaders Fellowship (MR/S03546X/1) (CS), E-DADS project (EU JPND) (CS), EuroPOND project (EU Horizon 2020, no. 666992) (CS). SJM is funded by the Edmond and Lily Safra Early Career Fellowship Program and the UK Dementia Research Institute, which receives its funding from UK DRI Ltd, funded by the UK Medical Research Council, Alzheimer's Society and Alzheimer's Research UK. ",

year = "2023",

month = mar,

day = "2",

doi = "10.48550/arXiv.2303.01949",

language = "English",

publisher = "ArXiv",

type = "WorkingPaper",

institution = "ArXiv",

}

TY - UNPB

T1 - Artificial Intelligence for Dementia Research Methods Optimization

AU - Bucholc, Magda

AU - James, Charlotte

AU - Khleifat, Ahmad Al

AU - Badhwar, AmanPreet

AU - Clarke, Natasha

AU - Dehsarvi, Amir

AU - Madan, Christopher R

AU - Marzi, Sarah J

AU - Shand, Cameron

AU - Schilder, Brian M

AU - Tamburin, Stefano

AU - Tantiangco, Hanz M

AU - Lourida, Ilianna

AU - Llewellyn, David J

AU - Ranson, Janice M

N1 - Funding 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 and DJL are supported by Alzheimer’s Research UK and the Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). DJL has also received funding from the National Institute for Health Research (NIHR) Applied Research Collaboration (ARC) South West Peninsula, National Health and Medical Research Council (NHMRC), JP Moulton Foundation, National Institute on Aging/National Institutes of Health (RF1AG055654), Alan Turing Institute/Engineering and Physical Sciences Research Council (EP/N510129/1). This work was additionally supported by Alzheimer’s Research UK (MB, CJ), European Union INTERREG VA Programme (MB), Dr George Moore Endowment for Data 31 Science at Ulster University (MB), National Institute for Health and Care Research Bristol Biomedical Research Centre (CJ), Fonds de recherche du Québec Santé - Chercheur boursiers Junior 1 (AB), Canadian Consortium for Neurodegeneration in Aging and the Courtois Foundation (AB, NC), The Motor Neurone Disease Association Fellowship (Al Khleifat/Oct21/975-799) (AAK), ALS Association Milton Safenowitz Research Fellowship (grant number 22-PDF 609. doi:10.52546/pc.gr.150909) (AAK), NIHR Maudsley Biomedical Research Centre (AAK), The Darby Rimmer Foundation (AAK), UKRI Future Leaders Fellowship (MR/S03546X/1) (CS), E-DADS project (EU JPND) (CS), EuroPOND project (EU Horizon 2020, no. 666992) (CS). SJM is funded by the Edmond and Lily Safra Early Career Fellowship Program and the UK Dementia Research Institute, which receives its funding from UK DRI Ltd, funded by the UK Medical Research Council, Alzheimer's Society and Alzheimer's Research UK.

PY - 2023/3/2

Y1 - 2023/3/2

N2 - INTRODUCTION: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.METHODS: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.RESULTS: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.DISCUSSION: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

AB - INTRODUCTION: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.METHODS: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.RESULTS: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.DISCUSSION: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

KW - dementia

KW - artificial intelligence

KW - machine learning

KW - deep learning

KW - classification

KW - regression

KW - supervised learning

KW - unsupervised learning

KW - semi-supervised learning

KW - methods optimization

KW - generalisability

KW - interpretability

KW - replicability

KW - transferability

KW - clinical utility

UR - https://arxiv.org/abs/2303.01949

U2 - 10.48550/arXiv.2303.01949

DO - 10.48550/arXiv.2303.01949

M3 - Working paper

C2 - 36911275

BT - Artificial Intelligence for Dementia Research Methods Optimization

PB - ArXiv

ER -

Artificial Intelligence for Dementia Research Methods Optimization

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Aberdeen Biomedical Imaging Centre

Cite this

Artificial Intelligence for Dementia Research Methods Optimization

Abstract

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Equipment

Aberdeen Biomedical Imaging Centre

Cite this