Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research
We examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healt...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2016-08-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnins.2016.00392/full |
| _version_ | 1819262090224861184 |
|---|---|
| author | Eva Janousova Giovanni Montana Tomas Kasparek Tomas Kasparek Daniel Schwarz |
| author_facet | Eva Janousova Giovanni Montana Tomas Kasparek Tomas Kasparek Daniel Schwarz |
| author_sort | Eva Janousova |
| collection | DOAJ |
| description | We examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healthy controls, this method allowed us to select brain areas relevant to schizophrenia, such as the left prefrontal cortex, the anterior cingulum, the right anterior insula, the thalamus and the hippocampus. Nevertheless, the classification performance based on such reduced data was not significantly better than the classification of data reduced by mass univariate selection using a t-test or unsupervised multivariate reduction using principal component analysis. Moreover, we found no important influence of the type of imaging features, namely local deformations or grey matter volumes, and the classification method, specifically linear discriminant analysis or linear support vector machines, on the classification results. However, we ascertained significant effect of a cross-validation setting on classification performance as classification results were overestimated even though the resampling was performed during the selection of brain imaging features. Therefore, it is critically important to perform cross-validation in all steps of the analysis (not only during classification) in case there is no external validation set to avoid optimistically biasing the results of classification studies. |
| first_indexed | 2024-12-23T19:52:10Z |
| format | Article |
| id | doaj.art-5826a986c5a84ccea27fef8000f939ae |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-23T19:52:10Z |
| publishDate | 2016-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-5826a986c5a84ccea27fef8000f939ae2022-12-21T17:33:20ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2016-08-011010.3389/fnins.2016.00392186491Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia ResearchEva Janousova0Giovanni Montana1Tomas Kasparek2Tomas Kasparek3Daniel Schwarz4Masaryk UniversityKing's College LondonMasaryk UniversityUniversity Hospital Brno and Masaryk UniversityMasaryk UniversityWe examined how penalized linear discriminant analysis with resampling, which is a supervised, multivariate, whole-brain reduction technique, can help schizophrenia diagnostics and research. In an experiment with magnetic resonance brain images of 52 first-episode schizophrenia patients and 52 healthy controls, this method allowed us to select brain areas relevant to schizophrenia, such as the left prefrontal cortex, the anterior cingulum, the right anterior insula, the thalamus and the hippocampus. Nevertheless, the classification performance based on such reduced data was not significantly better than the classification of data reduced by mass univariate selection using a t-test or unsupervised multivariate reduction using principal component analysis. Moreover, we found no important influence of the type of imaging features, namely local deformations or grey matter volumes, and the classification method, specifically linear discriminant analysis or linear support vector machines, on the classification results. However, we ascertained significant effect of a cross-validation setting on classification performance as classification results were overestimated even though the resampling was performed during the selection of brain imaging features. Therefore, it is critically important to perform cross-validation in all steps of the analysis (not only during classification) in case there is no external validation set to avoid optimistically biasing the results of classification studies.http://journal.frontiersin.org/Journal/10.3389/fnins.2016.00392/fullClassificationMagnetic Resonance ImagingSchizophreniaComputational Neuroanatomypattern recognitionSupport Vector Machines |
| spellingShingle | Eva Janousova Giovanni Montana Tomas Kasparek Tomas Kasparek Daniel Schwarz Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research Frontiers in Neuroscience Classification Magnetic Resonance Imaging Schizophrenia Computational Neuroanatomy pattern recognition Support Vector Machines |
| title | Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research |
| title_full | Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research |
| title_fullStr | Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research |
| title_full_unstemmed | Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research |
| title_short | Supervised, Multivariate, Whole-brain Reduction Did Not Help to Achieve High Classification Performance in Schizophrenia Research |
| title_sort | supervised multivariate whole brain reduction did not help to achieve high classification performance in schizophrenia research |
| topic | Classification Magnetic Resonance Imaging Schizophrenia Computational Neuroanatomy pattern recognition Support Vector Machines |
| url | http://journal.frontiersin.org/Journal/10.3389/fnins.2016.00392/full |
| work_keys_str_mv | AT evajanousova supervisedmultivariatewholebrainreductiondidnothelptoachievehighclassificationperformanceinschizophreniaresearch AT giovannimontana supervisedmultivariatewholebrainreductiondidnothelptoachievehighclassificationperformanceinschizophreniaresearch AT tomaskasparek supervisedmultivariatewholebrainreductiondidnothelptoachievehighclassificationperformanceinschizophreniaresearch AT tomaskasparek supervisedmultivariatewholebrainreductiondidnothelptoachievehighclassificationperformanceinschizophreniaresearch AT danielschwarz supervisedmultivariatewholebrainreductiondidnothelptoachievehighclassificationperformanceinschizophreniaresearch |