2021
DOI: 10.1093/schbul/sbaa190
|View full text |Cite
|
Sign up to set email alerts
|

Classification of Psychoses Based on Immunological Features: A Machine Learning Study in a Large Cohort of First-Episode and Chronic Patients

Abstract: For several years, the role of immune system in the pathophysiology of psychosis has been well-recognized, showing differences from the onset to chronic phases. Our study aims to implement a biomarker-based classification model suitable for the clinical management of psychotic patients. A machine learning algorithm was used to classify a cohort of 362 subjects, including 160 first-episode psychosis patients (FEP), 70 patients affected by chronic psychiatric disorders (schizophrenia, bipolar disorder, and major… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
7
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 13 publications
(7 citation statements)
references
References 62 publications
0
7
0
Order By: Relevance
“…There are studies using inflammation-profiling approaches to stratify patients by level of inflammation ( 204 , 207 210 ). For example, a recent study showed that using data on mRNA transcript levels of 56 immune genes using machine learning algorithms can distinguish between people with first-episode psychosis, chronic psychosis, and controls with >80% accuracy ( 210 ). The OPTiMiSE cohort study showed that uncontrolled clustering allowed the identification of clinical subtypes of first-episode psychosis patients ( 207 ).…”
Section: Usefulness Of Immunological Data In Psychiatric Clinical Pra...mentioning
confidence: 99%
“…There are studies using inflammation-profiling approaches to stratify patients by level of inflammation ( 204 , 207 210 ). For example, a recent study showed that using data on mRNA transcript levels of 56 immune genes using machine learning algorithms can distinguish between people with first-episode psychosis, chronic psychosis, and controls with >80% accuracy ( 210 ). The OPTiMiSE cohort study showed that uncontrolled clustering allowed the identification of clinical subtypes of first-episode psychosis patients ( 207 ).…”
Section: Usefulness Of Immunological Data In Psychiatric Clinical Pra...mentioning
confidence: 99%
“…A large number of investigations have reported biochemical alterations of the immune system in patients with schizophrenia (SZ), providing support of the immune/inflammatory hypothesis for SZ as a putative pathophysiological mechanism increasing the vulnerability to the illness [ 1 3 ]. Similarly, dysregulated immune/inflammatory responses and differential expression of immune-related genes have been observed in individuals with first-episode of psychosis (FEP) [ 4 7 ], indicating that immune aberrations may exist even at the early stages of psychosis, further corroborating the view that underlying immunological deficiencies could play a role in the development or progression of psychotic disorders [ 8 , 9 ]. In line with the above notion, genetic evidence has also emerged highlighting the involvement of genes coding for immune system components in SZ pathology [ 10 , 11 ].…”
Section: Introductionmentioning
confidence: 95%
“…Interestingly, three out of the four SMAD genes we detected as up‐regulated in schizophrenia, were found to be up‐regulated also in “Type 2”: SMAD4, SMAD5 and SMAD7 (Bowen et al, 2019). In addition, the literature suggests to classify schizophrenia into subtypes according to immunological and inflammatory features (Bishop et al, 2022; Enrico et al, 2021; Lin et al, 2016). Thus, the up‐regulation we detected might characterize only a subgroup of the patients.…”
Section: Discussionmentioning
confidence: 99%