• DOI:10.3389/fpsyt.2020.541659
• Corpus ID: 221765110

Identifying Clinically and Functionally Distinct Groups Among Healthy Controls and First Episode Psychosis Patients by Clustering on EEG Patterns

@article{Qu2020IdentifyingCA,
  title={Identifying Clinically and Functionally Distinct Groups Among Healthy Controls and First Episode Psychosis Patients by Clustering on EEG Patterns},
  author={Xiaodong Qu and Saran Liukasemsarn and Jingxuan Tu and Amy Higgins and T. Hickey and Mei-Hua Hall},
  journal={Frontiers in Psychiatry},
  year={2020},
  volume={11}
}

• Xiaodong Qu, S. Liukasemsarn, +3 authors M. Hall
• Published 18 September 2020
• Psychology, Medicine
• Frontiers in Psychiatry

Objective The mismatch negativity (MMN) is considered as a promising biomarker that can inform future therapeutic studies. However, there is a large variability among patients with first episode psychosis (FEP). Also, most studies report a single electrode site and on comparing case–control group differences. Few have taken advantage of the full wealth of multi-channel EEG signals to examine observable patterns. None, to our knowledge, have used machine learning (ML) approaches to investigate neurophysiological derived subgroups with distinct cognitive and functional outcome characteristics. In this study, we applied ML to empirically stratify individuals into homogeneous subgroups based on multi-channel MMN data. We then characterized the functional, cognitive, and clinical profiles of these neurobiologically derived subgroups. We also explored the underlying low frequency range responses (delta, theta, alpha) during MMN. Methods Clinical, neurocognitive, functioning data of 33 healthy controls and 20 FEP patients were collected. 90% of the patients had 6-month follow-up data. Neurocognition, social cognition, and functioning measures were assessed using the NCCB Cognitive Battery, the Awareness of Social Inference Test, UCSD Performance-Based Skills Assessment, and Multnomah Community Ability Scale. Symptom severity was collected using the PANSS. MMN amplitude and single-trial derived low frequency activity across 24 frontocentral channels were used as main variables in the ML k-means clustering analyses. Results We found a consistent pattern of two distinctive subgroups. We labeled them as “better functioning” and “poorer functioning” clusters, respectively. Each subgroup can be mapped onto either better or poorer clinical, cognitive, and functioning profiles. Also, we identified two subgroups of patients: one showed improved MMN and one showed worsening of MMN over time. Patients with improved MMN had better follow-up clinical, cognitive, and functioning profile than those with worsening MMN. Among the low frequency bands, delta frequency appeared to be the most relevant to the observed MMN responses in all individuals. However, higher delta responses were not necessarily associated with a better functioning profile, suggesting that delta frequency alone may not be useful in clinical characterization. Conclusions The ML approach could be a robust tool to explore heterogeneity and facilitate the identification of neurobiological homogeneous subgroups in FEP.