Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity. de Pierrefeu, A., Fovet, T., Hadj-Selem, F., Ciuciu, P., Lefebvre, S., Thomas, P., Lopes, R., Jardri, R., & Duchesnay, E.
Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity [link]Website  abstract   bibtex   
Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algo-rithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification meth-ods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The varia-tion in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of prin-cipal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the data-set. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback.
@article{
 title = {Prediction of activation patterns preceding hallucinations in patients with schizophrenia using machine learning with structured sparsity},
 type = {article},
 identifiers = {[object Object]},
 websites = {https://www.researchgate.net/profile/Renaud_Jardri/publication/322539512_Prediction_of_activation_patterns_preceding_hallucinations_in_patients_with_schizophrenia_using_machine_learning_with_structured_sparsity/links/5a5f281daca272d4a3e0d179/Prediction-of},
 id = {0dcabe7b-734c-3b66-a6e0-1f02e47d76b2},
 created = {2018-02-01T09:09:47.202Z},
 accessed = {2018-01-31},
 file_attached = {false},
 profile_id = {078d13e5-632a-3ebf-9e0e-51a0b2c2c66e},
 group_id = {d9389c6c-8ab5-3b8b-86ed-33db09ca0198},
 last_modified = {2018-02-24T20:09:01.622Z},
 tags = {OA},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {DePierrefeu},
 notes = {LB},
 private_publication = {false},
 abstract = {Despite significant progress in the field, the detection of fMRI signal changes during hallucinatory events remains difficult and time-consuming. This article first proposes a machine-learning algo-rithm to automatically identify resting-state fMRI periods that precede hallucinations versus periods that do not. When applied to whole-brain fMRI data, state-of-the-art classification meth-ods, such as support vector machines (SVM), yield dense solutions that are difficult to interpret. We proposed to extend the existing sparse classification methods by taking the spatial structure of brain images into account with structured sparsity using the total variation penalty. Based on this approach, we obtained reliable classifying performances associated with interpretable predictive patterns, composed of two clearly identifiable clusters in speech-related brain regions. The varia-tion in transition-to-hallucination functional patterns not only from one patient to another but also from one occurrence to the next (e.g., also depending on the sensory modalities involved) appeared to be the major difficulty when developing effective classifiers. Consequently, second, this article aimed to characterize the variability within the prehallucination patterns using an extension of prin-cipal component analysis with spatial constraints. The principal components (PCs) and the associated basis patterns shed light on the intrinsic structures of the variability present in the data-set. Such results are promising in the scope of innovative fMRI-guided therapy for drug-resistant hallucinations, such as fMRI-based neurofeedback.},
 bibtype = {article},
 author = {de Pierrefeu, Amicie and Fovet, Thomas and Hadj-Selem, Fouad and Ciuciu, Philippe and Lefebvre, Stephanie and Thomas, Pierre and Lopes, Renaud and Jardri, Renaud and Duchesnay, Edouard}
}

Downloads: 0