Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks
In older adults without dementia, White Matter Hyperintensities (WMH) in MRI have been shown to be highly associated with cerebral amyloid deposition, measured by the Pittsburgh compound B (PiB) PET. However, the relation to age, sex, and education in explaining this association is not well understo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | NeuroImage |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1053811923002987 |
| _version_ | 1827934047949553664 |
|---|---|
| author | Linghai Wang Antonija Kolobaric Howard Aizenstein Brian Lopresti Dana Tudorascu Beth Snitz William Klunk Minjie Wu |
| author_facet | Linghai Wang Antonija Kolobaric Howard Aizenstein Brian Lopresti Dana Tudorascu Beth Snitz William Klunk Minjie Wu |
| author_sort | Linghai Wang |
| collection | DOAJ |
| description | In older adults without dementia, White Matter Hyperintensities (WMH) in MRI have been shown to be highly associated with cerebral amyloid deposition, measured by the Pittsburgh compound B (PiB) PET. However, the relation to age, sex, and education in explaining this association is not well understood. We use the voxel counts of regional WMH, age, one-hot encoded sex, and education to predict the regional PiB using a multilayer perceptron with only rectilinear activations using mean squared error. We then develop a novel, robust metric to understand the relevance of each input variable for prediction. Our observations indicate that sex is the most relevant predictor of PiB and that WMH is not relevant for prediction. These results indicate that there is a sex-specific risk architecture for Aβ deposition. |
| first_indexed | 2024-03-13T07:33:44Z |
| format | Article |
| id | doaj.art-f7fe8ca127d54b1d9eade41f25167b9b |
| institution | Directory Open Access Journal |
| issn | 1095-9572 |
| language | English |
| last_indexed | 2024-03-13T07:33:44Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage |
| spelling | doaj.art-f7fe8ca127d54b1d9eade41f25167b9b2023-06-04T04:23:11ZengElsevierNeuroImage1095-95722023-07-01275120147Identifying sex-specific risk architectures for predicting amyloid deposition using neural networksLinghai Wang0Antonija Kolobaric1Howard Aizenstein2Brian Lopresti3Dana Tudorascu4Beth Snitz5William Klunk6Minjie Wu7University of Pittsburgh, Pittsburgh, Pennsylvania, United States; Corresponding author.University of Pittsburgh, Pittsburgh, Pennsylvania, United StatesUniversity of Pittsburgh, Pittsburgh, Pennsylvania, United States; Department of Psychiatry, University of Pittsburgh, Pittsburgh, Pennsylvania, United States; School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, United StatesUniversity of Pittsburgh, Pittsburgh, Pennsylvania, United StatesDepartment of Biostatistics, University of Pittsburgh, Pittsburgh, Pennsylvania, United StatesUniversity of Pittsburgh, Pittsburgh, Pennsylvania, United StatesDepartment of Psychiatry, University of Pittsburgh, Pittsburgh, Pennsylvania, United States; School of Medicine, University of Pittsburgh, Pittsburgh, Pennsylvania, United StatesDepartment of Psychiatry, University of Pittsburgh, Pittsburgh, Pennsylvania, United StatesIn older adults without dementia, White Matter Hyperintensities (WMH) in MRI have been shown to be highly associated with cerebral amyloid deposition, measured by the Pittsburgh compound B (PiB) PET. However, the relation to age, sex, and education in explaining this association is not well understood. We use the voxel counts of regional WMH, age, one-hot encoded sex, and education to predict the regional PiB using a multilayer perceptron with only rectilinear activations using mean squared error. We then develop a novel, robust metric to understand the relevance of each input variable for prediction. Our observations indicate that sex is the most relevant predictor of PiB and that WMH is not relevant for prediction. These results indicate that there is a sex-specific risk architecture for Aβ deposition.http://www.sciencedirect.com/science/article/pii/S1053811923002987Alzheimer's diseaseSmall vessel diseaseMachine learningBeta-amyloidSex differences |
| spellingShingle | Linghai Wang Antonija Kolobaric Howard Aizenstein Brian Lopresti Dana Tudorascu Beth Snitz William Klunk Minjie Wu Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks NeuroImage Alzheimer's disease Small vessel disease Machine learning Beta-amyloid Sex differences |
| title | Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks |
| title_full | Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks |
| title_fullStr | Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks |
| title_full_unstemmed | Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks |
| title_short | Identifying sex-specific risk architectures for predicting amyloid deposition using neural networks |
| title_sort | identifying sex specific risk architectures for predicting amyloid deposition using neural networks |
| topic | Alzheimer's disease Small vessel disease Machine learning Beta-amyloid Sex differences |
| url | http://www.sciencedirect.com/science/article/pii/S1053811923002987 |
| work_keys_str_mv | AT linghaiwang identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT antonijakolobaric identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT howardaizenstein identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT brianlopresti identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT danatudorascu identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT bethsnitz identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT williamklunk identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks AT minjiewu identifyingsexspecificriskarchitecturesforpredictingamyloiddepositionusingneuralnetworks |