TY - JOUR
T1 - Neurobiological Divergence of the Positive and Negative Schizophrenia Subtypes Identified on a New Factor Structure of Psychopathology Using Non-negative Factorization
T2 - An International Machine Learning Study
AU - Pharmacotherapy Monitoring
AU - Chen, Ji
AU - Patil, Kaustubh R.
AU - Weis, Susanne
AU - Sim, Kang
AU - Nickl-Jockschat, Thomas
AU - Zhou, Juan
AU - Aleman, Andre
AU - Sommer, Iris E.
AU - Liemburg, Edith J.
AU - Hoffstaedter, Felix
AU - Habel, Ute
AU - Derntl, Birgit
AU - Liu, Xiaojin
AU - Fischer, Jona M.
AU - Kogler, Lydia
AU - Regenbogen, Christina
AU - Diwadkar, Vaibhav A.
AU - Stanley, Jeffrey A.
AU - Riedl, Valentin
AU - Jardri, Renaud
AU - Gruber, Oliver
AU - Sotiras, Aristeidis
AU - Davatzikos, Christos
AU - Eickhoff, Simon B.
AU - Bartels-Velthuis, Agna A.
AU - Bruggeman, Richard
AU - Castelein, Stynke
AU - Jorg, Frederike
AU - Pijnenborg, Gerdina H. M.
AU - Knegtering, Henderikus
AU - Visser, Ellen
PY - 2020/2/1
Y1 - 2020/2/1
N2 - BACKGROUND: Disentangling psychopathological heterogeneity in schizophrenia is challenging, and previous results remain inconclusive. We employed advanced machine learning to identify a stable and generalizable factorization of the Positive and Negative Syndrome Scale and used it to identify psychopathological subtypes as well as their neurobiological differentiations.METHODS: Positive and Negative Syndrome Scale data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients; 586 followed up after 1.35 +/- 0.70 years) were used for learning the factor structure by an orthonormal projective non-negative factorization. An international sample, pooled from 9 medical centers across Europe, the United States, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional magnetic resonance imaging connectivity patterns.RESULTS: A 4-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original Positive and Negative Syndrome Scale subscales and previously proposed factor models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventromedial frontal cortex, temporoparietal junction, and precuneus.CONCLUSIONS: Machine learning applied to multisite data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia.
AB - BACKGROUND: Disentangling psychopathological heterogeneity in schizophrenia is challenging, and previous results remain inconclusive. We employed advanced machine learning to identify a stable and generalizable factorization of the Positive and Negative Syndrome Scale and used it to identify psychopathological subtypes as well as their neurobiological differentiations.METHODS: Positive and Negative Syndrome Scale data from the Pharmacotherapy Monitoring and Outcome Survey cohort (1545 patients; 586 followed up after 1.35 +/- 0.70 years) were used for learning the factor structure by an orthonormal projective non-negative factorization. An international sample, pooled from 9 medical centers across Europe, the United States, and Asia (490 patients), was used for validation. Patients were clustered into psychopathological subtypes based on the identified factor structure, and the neurobiological divergence between the subtypes was assessed by classification analysis on functional magnetic resonance imaging connectivity patterns.RESULTS: A 4-factor structure representing negative, positive, affective, and cognitive symptoms was identified as the most stable and generalizable representation of psychopathology. It showed higher internal consistency than the original Positive and Negative Syndrome Scale subscales and previously proposed factor models. Based on this representation, the positive-negative dichotomy was confirmed as the (only) robust psychopathological subtypes, and these subtypes were longitudinally stable in about 80% of the repeatedly assessed patients. Finally, the individual subtype could be predicted with good accuracy from functional connectivity profiles of the ventromedial frontal cortex, temporoparietal junction, and precuneus.CONCLUSIONS: Machine learning applied to multisite data with cross-validation yielded a factorization generalizable across populations and medical systems. Together with subtyping and the demonstrated ability to predict subtype membership from neuroimaging data, this work further disentangles the heterogeneity in schizophrenia.
KW - Brain imaging
KW - Machine learning
KW - Multivariate classification
KW - Non-negative factorization
KW - Schizophrenia
KW - Subtyping
KW - SYNDROME SCALE PANSS
KW - 5-FACTOR MODEL
KW - PATTERNS
KW - SYMPTOMS
KW - DISORDERS
KW - STABILITY
KW - CLASSIFICATION
KW - MEDICATION
KW - SUBGROUPS
KW - MULTISITE
U2 - 10.1016/j.biopsych.2019.08.031
DO - 10.1016/j.biopsych.2019.08.031
M3 - Article
SN - 1873-2402
VL - 87
SP - 282
EP - 293
JO - Biological Psychiatry
JF - Biological Psychiatry
IS - 3
ER -