File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1002/brb3.3348
- Scopus: eid_2-s2.0-85182401820
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI
Title | Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI |
---|---|
Authors | |
Keywords | convolutional neural network cross-sample entropy machine learning older adult resting-state fMRI suicide suicide attempt |
Issue Date | 15-Jan-2024 |
Publisher | Wiley Open Access |
Citation | Brain and Behavior, 2024, v. 14, n. 1 How to Cite? |
Abstract | Background: Predicting suicide is a pressing issue among older adults; however, predicting its risk is difficult. Capitalizing on the recent development of machine learning, considerable progress has been made in predicting complex behavior such as suicide. As depression remained the strongest risk for suicide, we aimed to apply deep learning algorithms to identify suicidality in a group with late-life depression (LLD). Methods: We enrolled 83 patients with LLD, 35 of which were non-suicidal and 48 were suicidal, including 26 with only suicidal ideation and 22 with past suicide attempts, for resting-state functional magnetic resonance imaging (MRI). Cross-sample entropy (CSE) analysis was conducted to examine the complexity of MRI signals among brain regions. Three-dimensional (3D) convolutional neural networks (CNNs) were used, and the classification accuracy in each brain region was averaged to predict suicidality after sixfold cross-validation. Results: We found brain regions with a mean accuracy above 75% to predict suicidality located mostly in default mode, fronto-parietal, and cingulo-opercular resting-state networks. The models with right amygdala and left caudate provided the most reliable accuracy in all cross-validation folds, indicating their neurobiological importance in late-life suicide. Conclusion: Combining CSE analysis and the 3D CNN, several brain regions were found to be associated with suicidality. |
Persistent Identifier | http://hdl.handle.net/10722/348470 |
ISSN | 2023 Impact Factor: 2.6 2023 SCImago Journal Rankings: 0.908 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lin, Chemin | - |
dc.contributor.author | Huang, Chih Mao | - |
dc.contributor.author | Chang, Wei | - |
dc.contributor.author | Chang, You Xun | - |
dc.contributor.author | Liu, Ho Ling | - |
dc.contributor.author | Ng, Shu Hang | - |
dc.contributor.author | Lin, Huang Li | - |
dc.contributor.author | Lee, Tatia Mei Chun | - |
dc.contributor.author | Lee, Shwu Hua | - |
dc.contributor.author | Wu, Shun Chi | - |
dc.date.accessioned | 2024-10-10T00:30:48Z | - |
dc.date.available | 2024-10-10T00:30:48Z | - |
dc.date.issued | 2024-01-15 | - |
dc.identifier.citation | Brain and Behavior, 2024, v. 14, n. 1 | - |
dc.identifier.issn | 2162-3279 | - |
dc.identifier.uri | http://hdl.handle.net/10722/348470 | - |
dc.description.abstract | Background: Predicting suicide is a pressing issue among older adults; however, predicting its risk is difficult. Capitalizing on the recent development of machine learning, considerable progress has been made in predicting complex behavior such as suicide. As depression remained the strongest risk for suicide, we aimed to apply deep learning algorithms to identify suicidality in a group with late-life depression (LLD). Methods: We enrolled 83 patients with LLD, 35 of which were non-suicidal and 48 were suicidal, including 26 with only suicidal ideation and 22 with past suicide attempts, for resting-state functional magnetic resonance imaging (MRI). Cross-sample entropy (CSE) analysis was conducted to examine the complexity of MRI signals among brain regions. Three-dimensional (3D) convolutional neural networks (CNNs) were used, and the classification accuracy in each brain region was averaged to predict suicidality after sixfold cross-validation. Results: We found brain regions with a mean accuracy above 75% to predict suicidality located mostly in default mode, fronto-parietal, and cingulo-opercular resting-state networks. The models with right amygdala and left caudate provided the most reliable accuracy in all cross-validation folds, indicating their neurobiological importance in late-life suicide. Conclusion: Combining CSE analysis and the 3D CNN, several brain regions were found to be associated with suicidality. | - |
dc.language | eng | - |
dc.publisher | Wiley Open Access | - |
dc.relation.ispartof | Brain and Behavior | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | convolutional neural network | - |
dc.subject | cross-sample entropy | - |
dc.subject | machine learning | - |
dc.subject | older adult | - |
dc.subject | resting-state fMRI | - |
dc.subject | suicide | - |
dc.subject | suicide attempt | - |
dc.title | Predicting suicidality in late-life depression by 3D convolutional neural network and cross-sample entropy analysis of resting-state fMRI | - |
dc.type | Article | - |
dc.identifier.doi | 10.1002/brb3.3348 | - |
dc.identifier.scopus | eid_2-s2.0-85182401820 | - |
dc.identifier.volume | 14 | - |
dc.identifier.issue | 1 | - |
dc.identifier.eissn | 2157-9032 | - |
dc.identifier.issnl | 2162-3279 | - |