Dimensionality reduction and unsupervised learning techniques applied to 
clinical psychiatric and neuroimaging phenotypes

Paul, Riya

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Thesis

Dimensionality reduction and unsupervised learning techniques applied to clinical psychiatric and neuroimaging phenotypes

MPS-Authors

/persons/resource/persons268756

Paul, Riya
RG Statistical Genetics, Max Planck Institute of Psychiatry, Max Planck Society;

External Resource

No external resources are shared

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

Piya Paul.pdf
(Any fulltext), 4MB

Supplementary Material (public)

There is no public supplementary material available

Citation

Paul, R. (2022). Dimensionality reduction and unsupervised learning techniques applied to clinical psychiatric and neuroimaging phenotypes. PhD Thesis, Technische Universität München, München.

Cite as: https://hdl.handle.net/21.11116/0000-000B-4155-C

Abstract

Unsupervised learning and other multivariate analysis techniques are increasingly recognized in neuropsychiatric research. Here, finite mixture models and random forests were applied to clinical observations of patients with major depression to detect and validate treatment response subgroups. Further, independent component analysis and agglomerative hierarchical clustering were combined to build a brain parcellation solely on structural covariance information of magnetic resonance brain images.
Übersetzte Kurzfassung:
Unüberwachtes Lernen und andere multivariate Analyseverfahren werden zunehmend auf neuropsychiatrische Fragestellungen angewendet. Finite mixture Modelle wurden auf klinische Skalen von Patienten mit schwerer Depression appliziert, um Therapieantwortklassen zu bilden und mit Random Forests zu validieren. Unabhängigkeitsanalysen und agglomeratives hierarchisches Clustering wurden kombiniert, um die strukturelle Kovarianz von Magnetresonanztomographie-Bildern für eine Hirnparzellierung zu nutzen.