PMID- 24694926
OWN - NLM
STAT- MEDLINE
DCOM- 20150415
LR  - 20211021
IS  - 1740-634X (Electronic)
IS  - 0893-133X (Print)
IS  - 0893-133X (Linking)
VI  - 39
IP  - 10
DP  - 2014 Sep
TI  - A window into the intoxicated mind? Speech as an index of psychoactive drug 
      effects.
PG  - 2340-8
LID - 10.1038/npp.2014.80 [doi]
AB  - Abused drugs can profoundly alter mental states in ways that may motivate drug 
      use. These effects are usually assessed with self-report, an approach that is 
      vulnerable to biases. Analyzing speech during intoxication may present a more 
      direct, objective measure, offering a unique 'window' into the mind. Here, we 
      employed computational analyses of speech semantic and topological structure 
      after +/-3,4-methylenedioxymethamphetamine (MDMA; 'ecstasy') and methamphetamine in 
      13 ecstasy users. In 4 sessions, participants completed a 10-min speech task 
      after MDMA (0.75 and 1.5 mg/kg), methamphetamine (20 mg), or placebo. Latent 
      Semantic Analyses identified the semantic proximity between speech content and 
      concepts relevant to drug effects. Graph-based analyses identified topological 
      speech characteristics. Group-level drug effects on semantic distances and 
      topology were assessed. Machine-learning analyses (with leave-one-out 
      cross-validation) assessed whether speech characteristics could predict drug 
      condition in the individual subject. Speech after MDMA (1.5 mg/kg) had greater 
      semantic proximity than placebo to the concepts friend, support, intimacy, and 
      rapport. Speech on MDMA (0.75 mg/kg) had greater proximity to empathy than 
      placebo. Conversely, speech on methamphetamine was further from compassion than 
      placebo. Classifiers discriminated between MDMA (1.5 mg/kg) and placebo with 88% 
      accuracy, and MDMA (1.5 mg/kg) and methamphetamine with 84% accuracy. For the two 
      MDMA doses, the classifier performed at chance. These data suggest that automated 
      semantic speech analyses can capture subtle alterations in mental state, 
      accurately discriminating between drugs. The findings also illustrate the 
      potential for automated speech-based approaches to characterize clinically 
      relevant alterations to mental state, including those occurring in psychiatric 
      illness.
FAU - Bedi, Gillinder
AU  - Bedi G
AD  - 1] Division on Substance Abuse, New York State Psychiatric Institute, and 
      Department of Psychiatry, College of Physicians and Surgeons of Columbia 
      University, New York, NY, USA [2] Human Behavioral Pharmacology Laboratory, 
      Department of Psychiatry and Behavioral Neuroscience, University of Chicago, 
      Chicago, IL, USA.
FAU - Cecchi, Guillermo A
AU  - Cecchi GA
AD  - Computational Biology Center-Neuroscience, IBM T.J. Watson Research Center, 
      Yorktown Heights, NY, USA.
FAU - Slezak, Diego F
AU  - Slezak DF
AD  - Computer Science Department, School of Sciences, Universidad de Buenos Aires, 
      Buenos Aires, Argentina.
FAU - Carrillo, Facundo
AU  - Carrillo F
AD  - Computer Science Department, School of Sciences, Universidad de Buenos Aires, 
      Buenos Aires, Argentina.
FAU - Sigman, Mariano
AU  - Sigman M
AD  - Physics Department, School of Sciences, Universidad de Buenos Aires, Buenos 
      Aires, Argentina.
FAU - de Wit, Harriet
AU  - de Wit H
AD  - Human Behavioral Pharmacology Laboratory, Department of Psychiatry and Behavioral 
      Neuroscience, University of Chicago, Chicago, IL, USA.
LA  - eng
GR  - UL1 TR000430/TR/NCATS NIH HHS/United States
GR  - DA02812/DA/NIDA NIH HHS/United States
GR  - R21 DA026570/DA/NIDA NIH HHS/United States
GR  - K23 DA034877/DA/NIDA NIH HHS/United States
GR  - R01 DA002812/DA/NIDA NIH HHS/United States
GR  - R03 DA029679/DA/NIDA NIH HHS/United States
GR  - DA029679/DA/NIDA NIH HHS/United States
GR  - DA026570/DA/NIDA NIH HHS/United States
GR  - DA034877/DA/NIDA NIH HHS/United States
PT  - Journal Article
PT  - Randomized Controlled Trial
PT  - Research Support, N.I.H., Extramural
DEP - 20140403
PL  - England
TA  - Neuropsychopharmacology
JT  - Neuropsychopharmacology : official publication of the American College of 
      Neuropsychopharmacology
JID - 8904907
RN  - 0 (Illicit Drugs)
RN  - 0 (Psychotropic Drugs)
RN  - 44RAL3456C (Methamphetamine)
RN  - KE1SEN21RM (N-Methyl-3,4-methylenedioxyamphetamine)
SB  - IM
MH  - Adolescent
MH  - Adult
MH  - Artificial Intelligence
MH  - Double-Blind Method
MH  - Female
MH  - Humans
MH  - Illicit Drugs
MH  - Male
MH  - Mental Processes/drug effects
MH  - Methamphetamine/*administration & dosage
MH  - N-Methyl-3,4-methylenedioxyamphetamine/*administration & dosage
MH  - Pattern Recognition, Automated
MH  - Psychotropic Drugs/*administration & dosage
MH  - *Semantics
MH  - Speech/*drug effects
MH  - Substance-Related Disorders/*psychology
MH  - Young Adult
PMC - PMC4138742
EDAT- 2014/04/04 06:00
MHDA- 2015/04/16 06:00
PMCR- 2015/09/01
CRDT- 2014/04/04 06:00
PHST- 2013/09/08 00:00 [received]
PHST- 2014/01/20 00:00 [revised]
PHST- 2014/03/24 00:00 [accepted]
PHST- 2014/04/04 06:00 [entrez]
PHST- 2014/04/04 06:00 [pubmed]
PHST- 2015/04/16 06:00 [medline]
PHST- 2015/09/01 00:00 [pmc-release]
AID - npp201480 [pii]
AID - 10.1038/npp.2014.80 [doi]
PST - ppublish
SO  - Neuropsychopharmacology. 2014 Sep;39(10):2340-8. doi: 10.1038/npp.2014.80. Epub 
      2014 Apr 3.