A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction
Abstract Data collected from clinical trials and cohort studies, such as dementia studies, are often high-dimensional, censored, heterogeneous and contain missing information, presenting challenges to traditional statistical analysis. There is an urgent need for methods that can overcome these chall...
Guardado en:
Autores principales: | , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2020
|
Materias: | |
Acceso en línea: | https://doaj.org/article/241adb643d7845fea517bcfa07bbbc26 |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:241adb643d7845fea517bcfa07bbbc26 |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:241adb643d7845fea517bcfa07bbbc262021-12-02T16:08:59ZA comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction10.1038/s41598-020-77220-w2045-2322https://doaj.org/article/241adb643d7845fea517bcfa07bbbc262020-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-77220-whttps://doaj.org/toc/2045-2322Abstract Data collected from clinical trials and cohort studies, such as dementia studies, are often high-dimensional, censored, heterogeneous and contain missing information, presenting challenges to traditional statistical analysis. There is an urgent need for methods that can overcome these challenges to model this complex data. At present there is no cure for dementia and no treatment that can successfully change the course of the disease. Machine learning models that can predict the time until a patient develops dementia are important tools in helping understand dementia risks and can give more accurate results than traditional statistical methods when modelling high-dimensional, heterogeneous, clinical data. This work compares the performance and stability of ten machine learning algorithms, combined with eight feature selection methods, capable of performing survival analysis of high-dimensional, heterogeneous, clinical data. We developed models that predict survival to dementia using baseline data from two different studies. The Sydney Memory and Ageing Study (MAS) is a longitudinal cohort study of 1037 participants, aged 70–90 years, that aims to determine the effects of ageing on cognition. The Alzheimer's Disease Neuroimaging Initiative (ADNI) is a longitudinal study aimed at identifying biomarkers for the early detection and tracking of Alzheimer's disease. Using the concordance index as a measure of performance, our models achieve maximum performance values of 0.82 for MAS and 0.93 For ADNI.Annette SpoonerEmily ChenArcot SowmyaPerminder SachdevNicole A. KochanJulian TrollorHenry BrodatyNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-10 (2020) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Annette Spooner Emily Chen Arcot Sowmya Perminder Sachdev Nicole A. Kochan Julian Trollor Henry Brodaty A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
description |
Abstract Data collected from clinical trials and cohort studies, such as dementia studies, are often high-dimensional, censored, heterogeneous and contain missing information, presenting challenges to traditional statistical analysis. There is an urgent need for methods that can overcome these challenges to model this complex data. At present there is no cure for dementia and no treatment that can successfully change the course of the disease. Machine learning models that can predict the time until a patient develops dementia are important tools in helping understand dementia risks and can give more accurate results than traditional statistical methods when modelling high-dimensional, heterogeneous, clinical data. This work compares the performance and stability of ten machine learning algorithms, combined with eight feature selection methods, capable of performing survival analysis of high-dimensional, heterogeneous, clinical data. We developed models that predict survival to dementia using baseline data from two different studies. The Sydney Memory and Ageing Study (MAS) is a longitudinal cohort study of 1037 participants, aged 70–90 years, that aims to determine the effects of ageing on cognition. The Alzheimer's Disease Neuroimaging Initiative (ADNI) is a longitudinal study aimed at identifying biomarkers for the early detection and tracking of Alzheimer's disease. Using the concordance index as a measure of performance, our models achieve maximum performance values of 0.82 for MAS and 0.93 For ADNI. |
format |
article |
author |
Annette Spooner Emily Chen Arcot Sowmya Perminder Sachdev Nicole A. Kochan Julian Trollor Henry Brodaty |
author_facet |
Annette Spooner Emily Chen Arcot Sowmya Perminder Sachdev Nicole A. Kochan Julian Trollor Henry Brodaty |
author_sort |
Annette Spooner |
title |
A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
title_short |
A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
title_full |
A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
title_fullStr |
A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
title_full_unstemmed |
A comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
title_sort |
comparison of machine learning methods for survival analysis of high-dimensional clinical data for dementia prediction |
publisher |
Nature Portfolio |
publishDate |
2020 |
url |
https://doaj.org/article/241adb643d7845fea517bcfa07bbbc26 |
work_keys_str_mv |
AT annettespooner acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT emilychen acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT arcotsowmya acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT permindersachdev acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT nicoleakochan acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT juliantrollor acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT henrybrodaty acomparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT annettespooner comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT emilychen comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT arcotsowmya comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT permindersachdev comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT nicoleakochan comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT juliantrollor comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction AT henrybrodaty comparisonofmachinelearningmethodsforsurvivalanalysisofhighdimensionalclinicaldatafordementiaprediction |
_version_ |
1718384457788948480 |