Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis
The recent biological redefinition of Alzheimer’s Disease (AD) has spurred the development of statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. The ability to measure such changes may facilitate earlier diagnoses for affected individual...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811923004305 |
| _version_ | 1797744358977437696 |
|---|---|
| author | Martin Saint-Jalmes Victor Fedyashov Daniel Beck Timothy Baldwin Noel G. Faux Pierrick Bourgeat Jurgen Fripp Colin L. Masters Benjamin Goudey |
| author_facet | Martin Saint-Jalmes Victor Fedyashov Daniel Beck Timothy Baldwin Noel G. Faux Pierrick Bourgeat Jurgen Fripp Colin L. Masters Benjamin Goudey |
| author_sort | Martin Saint-Jalmes |
| collection | DOAJ |
| description | The recent biological redefinition of Alzheimer’s Disease (AD) has spurred the development of statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. The ability to measure such changes may facilitate earlier diagnoses for affected individuals and help in monitoring the evolution of their condition. Amongst such statistical tools, disease progression models (DPMs) are quantitative, data-driven methods that specifically attempt to describe the temporal dynamics of biomarkers relevant to AD. Due to the heterogeneous nature of this disease, with patients of similar age experiencing different AD-related changes, a challenge facing longitudinal mixed-effects-based DPMs is the estimation of patient-realigning time-shifts. These time-shifts are indispensable for meaningful biomarker modelling, but may impact fitting time or vary with missing data in jointly estimated models. In this work, we estimate an individual’s progression through Alzheimer’s disease by combining multiple biomarkers into a single value using a probabilistic formulation of principal components analysis. Our results show that this variable, which summarises AD through observable biomarkers, is remarkably similar to jointly estimated time-shifts when we compute our scores for the baseline visit, on cross-sectional data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Reproducing the expected properties of clinical datasets, we confirm that estimated scores are robust to missing data or unavailable biomarkers. In addition to cross-sectional insights, we can model the latent variable as an individual progression score by repeating estimations at follow-up examinations and refining long-term estimates as more data is gathered, which would be ideal in a clinical setting. Finally, we verify that our score can be used as a pseudo-temporal scale instead of age to ignore some patient heterogeneity in cohort data and highlight the general trend in expected biomarker evolution in affected individuals. |
| first_indexed | 2024-03-12T15:08:37Z |
| format | Article |
| id | doaj.art-d10a253954e547b699e2b2e6b86c3995 |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-03-12T15:08:37Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-d10a253954e547b699e2b2e6b86c39952023-08-12T04:33:48ZengElsevierNeuroImage1095-95722023-09-01278120279Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysisMartin Saint-Jalmes0Victor Fedyashov1Daniel Beck2Timothy Baldwin3Noel G. Faux4Pierrick Bourgeat5Jurgen Fripp6Colin L. Masters7Benjamin Goudey8Corresponding author at: ARC Training Centre in Cognitive Computing for Medical Technologies, Level 4, Melbourne Connect (Bldg 290), 700 Swanston Street, Carlton VIC 3010, Australia.; ARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; The Florey Department of Neuroscience and Mental Health, The University of Melbourne, Australia; The Florey Institute of Neuroscience and Mental Health, The University of Melbourne, AustraliaARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; The Florey Department of Neuroscience and Mental Health, The University of Melbourne, AustraliaARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; School of Computing and Information Systems, The University of Melbourne, AustraliaARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; School of Computing and Information Systems, The University of Melbourne, Australia; Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab EmiratesARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; The Florey Department of Neuroscience and Mental Health, The University of Melbourne, Australia; Melbourne Data Analytics Platform, The University of Melbourne, AustraliaCSIRO Health and Biosecurity, Brisbane, AustraliaCSIRO Health and Biosecurity, Brisbane, AustraliaThe Florey Institute of Neuroscience and Mental Health, The University of Melbourne, AustraliaARC Training Centre in Cognitive Computing for Medical Technologies, University of Melbourne, Carlton, VIC, Australia; The Florey Department of Neuroscience and Mental Health, The University of Melbourne, AustraliaThe recent biological redefinition of Alzheimer’s Disease (AD) has spurred the development of statistical models that relate changes in biomarkers with neurodegeneration and worsening condition linked to AD. The ability to measure such changes may facilitate earlier diagnoses for affected individuals and help in monitoring the evolution of their condition. Amongst such statistical tools, disease progression models (DPMs) are quantitative, data-driven methods that specifically attempt to describe the temporal dynamics of biomarkers relevant to AD. Due to the heterogeneous nature of this disease, with patients of similar age experiencing different AD-related changes, a challenge facing longitudinal mixed-effects-based DPMs is the estimation of patient-realigning time-shifts. These time-shifts are indispensable for meaningful biomarker modelling, but may impact fitting time or vary with missing data in jointly estimated models. In this work, we estimate an individual’s progression through Alzheimer’s disease by combining multiple biomarkers into a single value using a probabilistic formulation of principal components analysis. Our results show that this variable, which summarises AD through observable biomarkers, is remarkably similar to jointly estimated time-shifts when we compute our scores for the baseline visit, on cross-sectional data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Reproducing the expected properties of clinical datasets, we confirm that estimated scores are robust to missing data or unavailable biomarkers. In addition to cross-sectional insights, we can model the latent variable as an individual progression score by repeating estimations at follow-up examinations and refining long-term estimates as more data is gathered, which would be ideal in a clinical setting. Finally, we verify that our score can be used as a pseudo-temporal scale instead of age to ignore some patient heterogeneity in cohort data and highlight the general trend in expected biomarker evolution in affected individuals.http://www.sciencedirect.com/science/article/pii/S1053811923004305Alzheimer’s diseaseDisease progression modelingLatent disease timePrincipal components analysisMachine learning |
| spellingShingle | Martin Saint-Jalmes Victor Fedyashov Daniel Beck Timothy Baldwin Noel G. Faux Pierrick Bourgeat Jurgen Fripp Colin L. Masters Benjamin Goudey Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis NeuroImage Alzheimer’s disease Disease progression modeling Latent disease time Principal components analysis Machine learning |
| title | Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis |
| title_full | Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis |
| title_fullStr | Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis |
| title_full_unstemmed | Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis |
| title_short | Disease progression modelling of Alzheimer’s disease using probabilistic principal components analysis |
| title_sort | disease progression modelling of alzheimer s disease using probabilistic principal components analysis |
| topic | Alzheimer’s disease Disease progression modeling Latent disease time Principal components analysis Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S1053811923004305 |
| work_keys_str_mv | AT martinsaintjalmes diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT victorfedyashov diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT danielbeck diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT timothybaldwin diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT noelgfaux diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT pierrickbourgeat diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT jurgenfripp diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT colinlmasters diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis AT benjamingoudey diseaseprogressionmodellingofalzheimersdiseaseusingprobabilisticprincipalcomponentsanalysis |