Search

It remains challenging to identify depression accurately due to its biological heterogeneity. As people suffering from depression are associated with functional brain network alterations, we investigated subtypes of patients with first‐episode drug‐naive (FEDN) depression based on brain network characteristics. This study included data from 91 FEDN patients and 91 matched healthy individuals obtained from the International Big‐Data Center for Depression Research. Twenty large‐scale functional connectivity networks were computed using group information guided independent component analysis. A multivariate unsupervised normative modeling method was used to identify subtypes of FEDN and their associated networks, focusing on individual‐level variability among the patients for quantifying deviations of their brain networks from the normative range. Two patient subtypes were identified with distinctive abnormal functional network patterns, consisting of 10 informative connectivity networks, including the default mode network and frontoparietal network. 16% of patients belonged to subtype I with larger extreme deviations from the normal range and shorter illness duration, while 84% belonged to subtype II with weaker extreme deviations and longer illness duration. Moreover, the structural changes in subtype II patients were more complex than the subtype I patients. Compared with healthy controls, both increased and decreased gray matter (GM) abnormalities were identified in widely distributed brain regions in subtype II patients. In contrast, most abnormalities were decreased GM in subtype I. The informative functional network connectivity patterns gleaned from the imaging data can facilitate the accurate identification of FEDN‐MDD subtypes and their associated neurobiological heterogeneity. [ABSTRACT FROM AUTHOR]

Schizophrenia (SCZ) patients and their unaffected first‐degree relatives (FDRs) share similar functional neuroanatomy. However, it remains largely unknown to what extent unaffected FDRs with functional neuroanatomy patterns similar to patients can be identified at an individual level. In this study, we used a multivariate pattern classification method to learn informative large‐scale functional networks (FNs) and build classifiers to distinguish 32 patients from 30 healthy controls and to classify 34 FDRs as with or without FNs similar to patients. Four informative FNs—the cerebellum, default mode network (DMN), ventral frontotemporal network, and posterior DMN with parahippocampal gyrus—were identified based on a training cohort and pattern classifiers built upon these FNs achieved a correct classification rate of 83.9% (sensitivity 87.5%, specificity 80.0%, and area under the receiver operating characteristic curve [AUC] 0.914) estimated based on leave‐one‐out cross‐validation for the training cohort and a correct classification rate of 77.5% (sensitivity 72.5%, specificity 82.5%, and AUC 0.811) for an independent validation cohort. The classification scores of the FDRs and patients were negatively correlated with their measures of cognitive function. FDRs identified by the classifiers as having SCZ patterns were similar to the patients, but significantly different from the controls and FDRs with normal patterns in terms of their cognitive measures. These results demonstrate that the pattern classifiers built upon the informative FNs can serve as biomarkers for quantifying brain alterations in SCZ and help to identify FDRs with FN patterns and cognitive impairment similar to those of SCZ patients. [ABSTRACT FROM AUTHOR]