Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression

Carrillo, Facundo; Sigman, Mariano; Slezak, Diego Fernández; Ashton, Philip; Fitzgerald, Louise; Stroud, Jack; Nutt, David; Carhart‐Harris, Robin

doi:10.1016/j.jad.2018.01.006

Cited by 42 publications

(24 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recent results have suggested that diverse clinical populations can benefit from psychedelics, with rapid and enduring improvements in mental health outcomes seen after treatment with psychedelics for a range of different disorders (Griffiths and Grob, 2010 ; Anderson et al, 2012 ; Bogenschutz and Pommy, 2012 ; Bogenschutz and Johnson, 2016 ; Mithoefer et al, 2016 ; Johnson and Griffiths, 2017 ; Nichols et al, 2017 ), for a review see Carhart-Harris and Goodwin ( 2017 ). Despite these developments, little progress has been made in our ability to predict, ahead of time, the nature of individual responses to a psychedelic (although see Carrillo et al, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

Predicting Responses to Psychedelics: A Prospective Study

et al. 2018

Self Cite

View full text Add to dashboard Cite

Responses to psychedelics are notoriously difficult to predict, yet significant work is currently underway to assess their therapeutic potential and the level of interest in psychedelics among the general public appears to be increasing. We aimed to collect prospective data in order to improve our ability to predict acute- and longer-term responses to psychedelics. Individuals who planned to take a psychedelic through their own initiative participated in an online survey (www.psychedelicsurvey.com). Traits and variables relating to set, setting and the acute psychedelic experience were measured at five different time points before and after the experience. Principle component and regression methods were used to analyse the data. Sample sizes for the five time points were N = 654, N = 535, N = 379, N = 315, and N = 212 respectively. Psychological well-being was increased 2 weeks after a psychedelic experience and remained at this level after 4 weeks. Higher ratings of a “mystical-type experience” had a positive effect on the change in well-being after a psychedelic experience, whereas the other acute psychedelic experience measures, i.e., “challenging experience” and “visual effects”, did not influence the change in well-being after the psychedelic experience. Having “clear intentions” for the experience was conducive to mystical-type experiences. Having a positive “set” as well as having the experience with intentions related to “recreation” were both found to decrease the likelihood of having a challenging experience. The baseline trait “absorption” and higher drug doses promoted all aspects of the acute experience, i.e., mystical-type and challenging experiences, as well as visual effects. When comparing the relative contribution of different types of variables in explaining the variance in the change in well-being, it seemed that baseline trait variables had the strongest effect on the change in well-being after a psychedelic experience. These results confirm the importance of extra-pharmacological factors in determining responses to a psychedelic. We view this study as an early step towards the development of empirical guidelines that can evolve and improve iteratively with the ultimate purpose of guiding crucial clinical decisions about whether, when, where and how to dose with a psychedelic, thus helping to mitigate risks while maximizing potential benefits in an evidence-based manner.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Responses to Psychedelics: A Prospective Study

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to the British POW study [9], where dream reports were analyzed by the Hall & Van de Castle method [9], based on either positive or negative social interactions (leaving aside those without an emotional valence), in the present study we used natural language processing (NLP) tools to directly quantify (i) non-semantic structural connectedness [32][33][34][35][36], and (ii) emotional valences from dream reports [37][38][39][40][41], and to estimate (iii) semantic distances to specific probe words [42][43][44][45]. The non-semantic connectedness of word graphs is a sensitive marker of structural change in discourse [32][33][34][35][36], and the measurement of emotional contents has been widely applied in the detection of mental suffering [37][38][39][40][41]. Estimating semantic similarity based on the co-occurrence of words in a representative corpus has enabled quantitative measurement of subjective aspects of mental health expressed in memory reports [42][43][44][45].…”

Section: Introductionmentioning

confidence: 99%

Dreaming during the Covid-19 pandemic: Computational assessment of dream reports reveals mental suffering related to fear of contagion

et al. 2020

View full text Add to dashboard Cite

The current global threat brought on by the Covid-19 pandemic has led to widespread social isolation, posing new challenges in dealing with metal suffering related to social distancing, and in quickly learning new social habits intended to prevent contagion. Neuroscience and psychology agree that dreaming helps people to cope with negative emotions and to learn from experience, but can dreaming effectively reveal mental suffering and changes in social behavior? To address this question, we applied natural language processing tools to study 239 dream reports by 67 individuals, made either before the Covid-19 outbreak or during the months of March and April, 2020, when lockdown was imposed in Brazil following the WHO’s declaration of the pandemic. Pandemic dreams showed a higher proportion of anger and sadness words, and higher average semantic similarities to the terms “contamination” and “cleanness”. These features seem to be associated with mental suffering linked to social isolation, as they explained 40% of the variance in the PANSS negative subscale related to socialization (p = 0.0088). These results corroborate the hypothesis that pandemic dreams reflect mental suffering, fear of contagion, and important changes in daily habits that directly impact socialization.

show abstract

“…Specifically, we aimed to test the hypothesis that the cyclic regulation of the MC leaves an imprint in the linguistic production of females engaged in social media, strong enough to be discriminated from that of matching male participants. Previous studies have used language production to characterize changes in mental state elicited by psychoactive drug intake and psychosis, among others (Bedi et al, 2014, 2015; García et al, 2016; Mota et al, 2016; Carrillo, 2017; Carrillo et al, 2018; Corcoran et al, 2018). Massive textual content in social networks has been used to identify abrupt changes in semantic space of concepts caused by salient events (Carrillo et al, 2015), as a possible indicator of depression using subject's Facebook public information (De Choudhury et al, 2013), or more specifically to characterize and predict postpartum depression (De Choudhury et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Differential 28-Days Cyclic Modulation of Affective Intensity in Female and Male Participants via Social Media

Gallino

Carrillo

Cecchi

2019

Front. Integr. Neurosci.

Self Cite

View full text Add to dashboard Cite

The menstrual cycle affects many aspects of female physiology, from the immune system to behavioral and emotional regulation. It is unclear however if these physiological changes are reflected in everyday, naturalistic language production, and moreover whether these putative effects can be consistently quantified. Using a novel approach based on social networks, we characterized linguistic expression differences in female and male volunteers over the course of several months, while having no physiological or reported information of the female participants' menstrual cycles. We used a simple algorithm to quantify the linguistic affect intensity of 418 (184 females and 234 males) subjects using their social networks production and found a 7-day modulatory cycle of affect intensity that corresponds to labor-week fluctuations, with no significant difference by biological sex, and a 28-day cycle over which females are significantly different than males. Our results are consistent with the hypothesis that the menstrual cycle modulates affective features of naturalistic linguistic production.

show abstract

Natural speech algorithm applied to baseline interview data can predict which patients will respond to psilocybin for treatment-resistant depression

Cited by 42 publications

References 17 publications

Predicting Responses to Psychedelics: A Prospective Study

Predicting Responses to Psychedelics: A Prospective Study

Dreaming during the Covid-19 pandemic: Computational assessment of dream reports reveals mental suffering related to fear of contagion

Differential 28-Days Cyclic Modulation of Affective Intensity in Female and Male Participants via Social Media

Contact Info

Product

Resources

About