File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Tractography-based classification in distinguishing patients with first-episode schizophrenia from healthy individuals

TitleTractography-based classification in distinguishing patients with first-episode schizophrenia from healthy individuals
Authors
KeywordsCorpus callosum
Diffusion tensor imaging
Discriminant analysis
Psychosis
Machine learning
Random forest
Issue Date2019
PublisherElsevier Inc.
Citation
Progress in Neuro-Psychopharmacology and Biological Psychiatry, 2019, v. 88, p. 66-73 How to Cite?
AbstractBackground: Schizophrenia has been characterized as a neurodevelopmental disorder of brain disconnectivity. However, whether disrupted integrity of white matter tracts in schizophrenia can potentially serve as individual discriminative biomarkers remains unclear. Methods: A random forest algorithm was applied to tractography-based diffusion properties obtained from a cohort of 65 patients with first-episode schizophrenia (FES) and 60 healthy individuals to investigate the machine-learning discriminative power of white matter disconnectivity. Recursive feature elimination was used to select the ultimate white matter features in the classification. Relationships between algorithm-predicted probabilities and clinical characteristics were also examined in the FES group. Results: The classifier was trained by 80% of the sample. Patients were distinguished from healthy individuals with an overall accuracy of 71.0% (95% confident interval: 61.1%, 79.6%), a sensitivity of 67.3%, a specificity of 75.0%, and the area under receiver operating characteristic curve (AUC) was 79.3% (χ2 p < 0.001). In validation using the held-up 20% of the sample, patients were distinguished from healthy individuals with an overall accuracy of 76.0% (95% confident interval: 54.9%, 90.6%), a sensitivity of 76.9%, a specificity of 75.0%, and an AUC of 73.1% (χ2 p = 0.012). Diffusion properties of inter-hemispheric fibres, the cerebello-thalamo-cortical circuits and the long association fibres were identified to be the most discriminative in the classification. Higher predicted probability scores were found in younger patients. Conclusions: Our findings suggest that the widespread connectivity disruption observed in FES patients, especially in younger patients, might be considered potential individual discriminating biomarkers.
Persistent Identifierhttp://hdl.handle.net/10722/261746
ISSN
2017 Impact Factor: 4.185
2015 SCImago Journal Rankings: 1.794
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorDeng, Y-
dc.contributor.authorHung, KSY-
dc.contributor.authorLui, SSY-
dc.contributor.authorChui, WWH-
dc.contributor.authorLee, JCW-
dc.contributor.authorWang, Y-
dc.contributor.authorLi, Z-
dc.contributor.authorMak, HKF-
dc.contributor.authorSham, PC-
dc.contributor.authorChan, RCK-
dc.contributor.authorCheung, EFC-
dc.date.accessioned2018-09-28T04:47:04Z-
dc.date.available2018-09-28T04:47:04Z-
dc.date.issued2019-
dc.identifier.citationProgress in Neuro-Psychopharmacology and Biological Psychiatry, 2019, v. 88, p. 66-73-
dc.identifier.issn0278-5846-
dc.identifier.urihttp://hdl.handle.net/10722/261746-
dc.description.abstractBackground: Schizophrenia has been characterized as a neurodevelopmental disorder of brain disconnectivity. However, whether disrupted integrity of white matter tracts in schizophrenia can potentially serve as individual discriminative biomarkers remains unclear. Methods: A random forest algorithm was applied to tractography-based diffusion properties obtained from a cohort of 65 patients with first-episode schizophrenia (FES) and 60 healthy individuals to investigate the machine-learning discriminative power of white matter disconnectivity. Recursive feature elimination was used to select the ultimate white matter features in the classification. Relationships between algorithm-predicted probabilities and clinical characteristics were also examined in the FES group. Results: The classifier was trained by 80% of the sample. Patients were distinguished from healthy individuals with an overall accuracy of 71.0% (95% confident interval: 61.1%, 79.6%), a sensitivity of 67.3%, a specificity of 75.0%, and the area under receiver operating characteristic curve (AUC) was 79.3% (χ2 p < 0.001). In validation using the held-up 20% of the sample, patients were distinguished from healthy individuals with an overall accuracy of 76.0% (95% confident interval: 54.9%, 90.6%), a sensitivity of 76.9%, a specificity of 75.0%, and an AUC of 73.1% (χ2 p = 0.012). Diffusion properties of inter-hemispheric fibres, the cerebello-thalamo-cortical circuits and the long association fibres were identified to be the most discriminative in the classification. Higher predicted probability scores were found in younger patients. Conclusions: Our findings suggest that the widespread connectivity disruption observed in FES patients, especially in younger patients, might be considered potential individual discriminating biomarkers.-
dc.languageeng-
dc.publisherElsevier Inc.-
dc.relation.ispartofProgress in Neuro-Psychopharmacology and Biological Psychiatry-
dc.subjectCorpus callosum-
dc.subjectDiffusion tensor imaging-
dc.subjectDiscriminant analysis-
dc.subjectPsychosis-
dc.subjectMachine learning-
dc.subjectRandom forest-
dc.titleTractography-based classification in distinguishing patients with first-episode schizophrenia from healthy individuals-
dc.typeArticle-
dc.identifier.emailMak, HKF: makkf@hku.hk-
dc.identifier.emailSham, PC: pcsham@hku.hk-
dc.identifier.authorityMak, HKF=rp00533-
dc.identifier.authoritySham, PC=rp00459-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.pnpbp.2018.06.010-
dc.identifier.pmid29935206-
dc.identifier.scopuseid_2-s2.0-85049313757-
dc.identifier.hkuros293211-
dc.identifier.volume88-
dc.identifier.spage66-
dc.identifier.epage73-
dc.identifier.isiWOS:000445634300007-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats