TY - JOUR
T1 - Predicting changes in substance use following psychedelic experiences
T2 - natural language processing of psychedelic session narratives
AU - Cox, David J.
AU - Garcia-Romeu, Albert
AU - Johnson, Matthew W.
N1 - Funding Information:
Support for MWJ and AGR provided the Johns Hopkins Center for Psychedelic and Consciousness Research funded by Tim Ferriss, Matt Mullenweg, Craig Nerenberg, Blake Mycoskie, and the Steven and Alexandra Cohen Foundation. Support for DJC was provided by National Institute on Drug Abuse Grant [T32DA07209]. MWJ is in advisory relationships with the following organizations regarding the medical development of psychedelics and related compounds: AWAKN Life Sciences Inc., Beckley Psychedelic Ltd., Entheogen Biomedical Corp., Field Trip Psychedelics Inc., Mind Medicine Inc., Otsuka Pharmaceutical Development & Commercialization Inc., Silo Pharma, Inc.
Publisher Copyright:
© 2021 Taylor & Francis Group, LLC.
PY - 2021
Y1 - 2021
N2 - Background: Experiences with psychedelic drugs, such as psilocybin or lysergic acid diethylamide (LSD), are sometimes followed by changes in patterns of tobacco, opioid, and alcohol consumption. But, the specific characteristics of psychedelic experiences that lead to changes in drug consumption are unknown. Objective: Determine whether quantitative descriptions of psychedelic experiences derived using Natural Language Processing (NLP) would allow us to predict who would quit or reduce using drugs following a psychedelic experience. Methods: We recruited 1141 individuals (247 female, 894 male) from online social media platforms who reported quitting or reducing using alcohol, cannabis, opioids, or stimulants following a psychedelic experience to provide a verbal narrative of the psychedelic experience they attributed as leading to their reduction in drug use. We used NLP to derive topic models that quantitatively described each participant’s psychedelic experience narrative. We then used the vector descriptions of each participant’s psychedelic experience narrative as input into three different supervised machine learning algorithms to predict long-term drug reduction outcomes. Results: We found that the topic models derived through NLP led to quantitative descriptions of participant narratives that differed across participants when grouped by the drug class quit as well as the long-term quit/reduction outcomes. Additionally, all three machine learning algorithms led to similar prediction accuracy (~65%, CI = ±0.21%) for long-term quit/reduction outcomes. Conclusions: Using machine learning to analyze written reports of psychedelic experiences may allow for accurate prediction of quit outcomes and what drug is quit or reduced within psychedelic therapy.
AB - Background: Experiences with psychedelic drugs, such as psilocybin or lysergic acid diethylamide (LSD), are sometimes followed by changes in patterns of tobacco, opioid, and alcohol consumption. But, the specific characteristics of psychedelic experiences that lead to changes in drug consumption are unknown. Objective: Determine whether quantitative descriptions of psychedelic experiences derived using Natural Language Processing (NLP) would allow us to predict who would quit or reduce using drugs following a psychedelic experience. Methods: We recruited 1141 individuals (247 female, 894 male) from online social media platforms who reported quitting or reducing using alcohol, cannabis, opioids, or stimulants following a psychedelic experience to provide a verbal narrative of the psychedelic experience they attributed as leading to their reduction in drug use. We used NLP to derive topic models that quantitatively described each participant’s psychedelic experience narrative. We then used the vector descriptions of each participant’s psychedelic experience narrative as input into three different supervised machine learning algorithms to predict long-term drug reduction outcomes. Results: We found that the topic models derived through NLP led to quantitative descriptions of participant narratives that differed across participants when grouped by the drug class quit as well as the long-term quit/reduction outcomes. Additionally, all three machine learning algorithms led to similar prediction accuracy (~65%, CI = ±0.21%) for long-term quit/reduction outcomes. Conclusions: Using machine learning to analyze written reports of psychedelic experiences may allow for accurate prediction of quit outcomes and what drug is quit or reduced within psychedelic therapy.
KW - Psychedelic treatment
KW - hallucinogens
KW - natural language processing
KW - verbal behavior
UR - http://www.scopus.com/inward/record.url?scp=85107464136&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107464136&partnerID=8YFLogxK
U2 - 10.1080/00952990.2021.1910830
DO - 10.1080/00952990.2021.1910830
M3 - Article
C2 - 34096403
AN - SCOPUS:85107464136
SN - 0095-2990
VL - 47
SP - 444
EP - 454
JO - American Journal of Drug and Alcohol Abuse
JF - American Journal of Drug and Alcohol Abuse
IS - 4
ER -