Dissecting psychiatric spectrum disorders by generative embedding
This proof-of-concept study examines the feasibility of defining subgroups in psychiatric spectrum disorders by generative embedding, using dynamical system models which infer neuronal circuit mechanisms from neuroimaging data. To this end, we re-analysed an fMRI dataset of 41 patients diagnosed wit...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2014-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158213001502 |
| _version_ | 1811319537119789056 |
|---|---|
| author | Kay H. Brodersen Lorenz Deserno Florian Schlagenhauf Zhihao Lin Will D. Penny Joachim M. Buhmann Klaas E. Stephan |
| author_facet | Kay H. Brodersen Lorenz Deserno Florian Schlagenhauf Zhihao Lin Will D. Penny Joachim M. Buhmann Klaas E. Stephan |
| author_sort | Kay H. Brodersen |
| collection | DOAJ |
| description | This proof-of-concept study examines the feasibility of defining subgroups in psychiatric spectrum disorders by generative embedding, using dynamical system models which infer neuronal circuit mechanisms from neuroimaging data. To this end, we re-analysed an fMRI dataset of 41 patients diagnosed with schizophrenia and 42 healthy controls performing a numerical n-back working-memory task. In our generative-embedding approach, we used parameter estimates from a dynamic causal model (DCM) of a visual–parietal–prefrontal network to define a model-based feature space for the subsequent application of supervised and unsupervised learning techniques. First, using a linear support vector machine for classification, we were able to predict individual diagnostic labels significantly more accurately (78%) from DCM-based effective connectivity estimates than from functional connectivity between (62%) or local activity within the same regions (55%). Second, an unsupervised approach based on variational Bayesian Gaussian mixture modelling provided evidence for two clusters which mapped onto patients and controls with nearly the same accuracy (71%) as the supervised approach. Finally, when restricting the analysis only to the patients, Gaussian mixture modelling suggested the existence of three patient subgroups, each of which was characterised by a different architecture of the visual–parietal–prefrontal working-memory network. Critically, even though this analysis did not have access to information about the patients' clinical symptoms, the three neurophysiologically defined subgroups mapped onto three clinically distinct subgroups, distinguished by significant differences in negative symptom severity, as assessed on the Positive and Negative Syndrome Scale (PANSS). In summary, this study provides a concrete example of how psychiatric spectrum diseases may be split into subgroups that are defined in terms of neurophysiological mechanisms specified by a generative model of network dynamics such as DCM. The results corroborate our previous findings in stroke patients that generative embedding, compared to analyses of more conventional measures such as functional connectivity or regional activity, can significantly enhance both the interpretability and performance of computational approaches to clinical classification. |
| first_indexed | 2024-04-13T12:44:50Z |
| format | Article |
| id | doaj.art-85192691062c4e1f8a2f2a843b62db52 |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-04-13T12:44:50Z |
| publishDate | 2014-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-85192691062c4e1f8a2f2a843b62db522022-12-22T02:46:25ZengElsevierNeuroImage: Clinical2213-15822014-01-014C9811110.1016/j.nicl.2013.11.002Dissecting psychiatric spectrum disorders by generative embeddingKay H. Brodersen0Lorenz Deserno1Florian Schlagenhauf2Zhihao Lin3Will D. Penny4Joachim M. Buhmann5Klaas E. Stephan6Translational Neuromodeling Unit (TNU), Institute for Biomedical Engineering, University of Zurich & ETH Zurich, SwitzerlandDepartment of Psychiatry and Psychotherapy, Charité-Universitätsmedizin Berlin, GermanyDepartment of Psychiatry and Psychotherapy, Charité-Universitätsmedizin Berlin, GermanyTranslational Neuromodeling Unit (TNU), Institute for Biomedical Engineering, University of Zurich & ETH Zurich, SwitzerlandWellcome Trust Centre for Neuroimaging, University College London, United KingdomMachine Learning Laboratory, Department of Computer Science, ETH Zurich, SwitzerlandTranslational Neuromodeling Unit (TNU), Institute for Biomedical Engineering, University of Zurich & ETH Zurich, SwitzerlandThis proof-of-concept study examines the feasibility of defining subgroups in psychiatric spectrum disorders by generative embedding, using dynamical system models which infer neuronal circuit mechanisms from neuroimaging data. To this end, we re-analysed an fMRI dataset of 41 patients diagnosed with schizophrenia and 42 healthy controls performing a numerical n-back working-memory task. In our generative-embedding approach, we used parameter estimates from a dynamic causal model (DCM) of a visual–parietal–prefrontal network to define a model-based feature space for the subsequent application of supervised and unsupervised learning techniques. First, using a linear support vector machine for classification, we were able to predict individual diagnostic labels significantly more accurately (78%) from DCM-based effective connectivity estimates than from functional connectivity between (62%) or local activity within the same regions (55%). Second, an unsupervised approach based on variational Bayesian Gaussian mixture modelling provided evidence for two clusters which mapped onto patients and controls with nearly the same accuracy (71%) as the supervised approach. Finally, when restricting the analysis only to the patients, Gaussian mixture modelling suggested the existence of three patient subgroups, each of which was characterised by a different architecture of the visual–parietal–prefrontal working-memory network. Critically, even though this analysis did not have access to information about the patients' clinical symptoms, the three neurophysiologically defined subgroups mapped onto three clinically distinct subgroups, distinguished by significant differences in negative symptom severity, as assessed on the Positive and Negative Syndrome Scale (PANSS). In summary, this study provides a concrete example of how psychiatric spectrum diseases may be split into subgroups that are defined in terms of neurophysiological mechanisms specified by a generative model of network dynamics such as DCM. The results corroborate our previous findings in stroke patients that generative embedding, compared to analyses of more conventional measures such as functional connectivity or regional activity, can significantly enhance both the interpretability and performance of computational approaches to clinical classification.http://www.sciencedirect.com/science/article/pii/S2213158213001502ClusteringClinical validationBalanced puritySchizophreniaVariational Bayes |
| spellingShingle | Kay H. Brodersen Lorenz Deserno Florian Schlagenhauf Zhihao Lin Will D. Penny Joachim M. Buhmann Klaas E. Stephan Dissecting psychiatric spectrum disorders by generative embedding NeuroImage: Clinical Clustering Clinical validation Balanced purity Schizophrenia Variational Bayes |
| title | Dissecting psychiatric spectrum disorders by generative embedding |
| title_full | Dissecting psychiatric spectrum disorders by generative embedding |
| title_fullStr | Dissecting psychiatric spectrum disorders by generative embedding |
| title_full_unstemmed | Dissecting psychiatric spectrum disorders by generative embedding |
| title_short | Dissecting psychiatric spectrum disorders by generative embedding |
| title_sort | dissecting psychiatric spectrum disorders by generative embedding |
| topic | Clustering Clinical validation Balanced purity Schizophrenia Variational Bayes |
| url | http://www.sciencedirect.com/science/article/pii/S2213158213001502 |
| work_keys_str_mv | AT kayhbrodersen dissectingpsychiatricspectrumdisordersbygenerativeembedding AT lorenzdeserno dissectingpsychiatricspectrumdisordersbygenerativeembedding AT florianschlagenhauf dissectingpsychiatricspectrumdisordersbygenerativeembedding AT zhihaolin dissectingpsychiatricspectrumdisordersbygenerativeembedding AT willdpenny dissectingpsychiatricspectrumdisordersbygenerativeembedding AT joachimmbuhmann dissectingpsychiatricspectrumdisordersbygenerativeembedding AT klaasestephan dissectingpsychiatricspectrumdisordersbygenerativeembedding |