PMID- 32928617
OWN - NLM
STAT- MEDLINE
DCOM- 20210617
LR  - 20210617
IS  - 1573-2509 (Electronic)
IS  - 0920-9964 (Linking)
VI  - 223
DP  - 2020 Sep
TI  - Quantitative biomarkers to predict response to clozapine treatment using resting 
      EEG data.
PG  - 289-296
LID - S0920-9964(20)30445-X [pii]
LID - 10.1016/j.schres.2020.08.017 [doi]
AB  - Clozapine is an anti-psychotic drug that is known to be effective in the 
      treatment of patients with chronic treatment-resistant schizophrenia (TRS-SCZ), 
      commonly estimated to be around one third of all cases. However, clinicians 
      sometimes delay the initiation of this drug because of its adverse side-effects. 
      Therefore, identification of predictive biomarkers of clozapine response is 
      extremely valuable to aid on-time initiation of clozapine treatment. In this 
      study, we develop a machine learning (ML) algorithm based on the pre-treatment 
      electroencephalogram (EEG) data sets to predict response to clozapine treatment 
      in TRS-SCZs, where the treatment outcome, after at least one-year follow-up is 
      determined using the Positive and Negative Syndrome Scale (PANSS). The ML 
      algorithm has two steps: 1) an effective connectivity named symbolic transfer 
      entropy (STE) is applied to resting state EEG waveforms, 2) the ML algorithm is 
      applied to STE matrix to determine whether a set of features can be found to 
      discriminate most responder (MR) SCZ patients from least responder (LR) ones. The 
      findings of this study revealed that the STE features could achieve an accuracy 
      of 89.90%. This finding implies that analysis of pre-treatment EEG could 
      contribute to our ability to distinguish MR from LR SCZs, and that the STE matrix 
      may prove to be a promising tool for the prediction of the clinical response to 
      clozapine.
CI  - Copyright (c) 2020 Elsevier B.V. All rights reserved.
FAU - Masychev, Kirill
AU  - Masychev K
AD  - Department of Computing Science, New York Institute of Technology, New York, NY, 
      USA.
FAU - Ciprian, Claudio
AU  - Ciprian C
AD  - Department of Computing Science, New York Institute of Technology, New York, NY, 
      USA.
FAU - Ravan, Maryam
AU  - Ravan M
AD  - Department of Electrical and Computer Engineering, New York Institute of 
      Technology, New York, NY, USA. Electronic address: mravan@nyit.edu.
FAU - Manimaran, Akshaya
AU  - Manimaran A
AD  - Department of Electrical and Computer Engineering, New York Institute of 
      Technology, New York, NY, USA.
FAU - Deshmukh, AnkitaAmol
AU  - Deshmukh A
AD  - Department of Computing Science, New York Institute of Technology, New York, NY, 
      USA.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20200911
PL  - Netherlands
TA  - Schizophr Res
JT  - Schizophrenia research
JID - 8804207
RN  - 0 (Antipsychotic Agents)
RN  - 0 (Biomarkers)
RN  - J60AR2IKIC (Clozapine)
SB  - IM
MH  - *Antipsychotic Agents/therapeutic use
MH  - Biomarkers
MH  - *Clozapine/therapeutic use
MH  - Electroencephalography
MH  - Humans
MH  - *Schizophrenia/drug therapy
OTO - NOTNLM
OT  - Clozapine treatment
OT  - Effective connectivity
OT  - Machine learning
OT  - Resting state electroencephalography (EEG)
OT  - Schizophrenia
OT  - Symbolic transfer entropy
EDAT- 2020/09/16 06:00
MHDA- 2021/06/22 06:00
CRDT- 2020/09/15 05:40
PHST- 2020/06/08 00:00 [received]
PHST- 2020/08/23 00:00 [revised]
PHST- 2020/08/24 00:00 [accepted]
PHST- 2020/09/16 06:00 [pubmed]
PHST- 2021/06/22 06:00 [medline]
PHST- 2020/09/15 05:40 [entrez]
AID - S0920-9964(20)30445-X [pii]
AID - 10.1016/j.schres.2020.08.017 [doi]
PST - ppublish
SO  - Schizophr Res. 2020 Sep;223:289-296. doi: 10.1016/j.schres.2020.08.017. Epub 2020 
      Sep 11.