Toolkit to Examine Lifelike Language (TELL): An app to capture speech and language markers of neurodegeneration.

Automated speech and language analysis (ASLA) is a promising approach for capturing early markers of neurodegenerative diseases. However, its potential remains underexploited in research and translational settings, partly due to the lack of a unified tool for data collection, encryption, processing, download, and visualization. Here we introduce the Toolkit to Examine Lifelike Language (TELL) v.1.0.0, a web-based app designed to bridge such a gap. First, we outline general aspects of its development. Second, we list the steps to access and use the app. Third, we specify its data collection protocol, including a linguistic profile survey and 11 audio recording tasks. Fourth, we describe the outputs the app generates for researchers (downloadable files) and for clinicians (real-time metrics). Fifth, we survey published findings obtained through its tasks and metrics. Sixth, we refer to TELL's current limitations and prospects for expansion. Overall, with its current and planned features, TELL aims to facilitate ASLA for research and clinical aims in the neurodegeneration arena. A demo version can be accessed here:  https://demo.sci.tellapp.org/ .

Natural language signatures of psilocybin microdosing.

RATIONALE: Serotonergic psychedelics are being studied as novel treatments for mental health disorders and as facilitators of improved well-being, mental function, and creativity. Recent studies have found mixed results concerning the effects of low doses of psychedelics ("microdosing") on these domains. However, microdosing is generally investigated using instruments designed to assess larger doses of psychedelics, which might lack sensitivity and specificity for this purpose. OBJECTIVES: Determine whether unconstrained speech contains signatures capable of identifying the acute effects of psilocybin microdoses. METHODS: Natural speech under psilocybin microdoses (0.5 g of psilocybin mushrooms) was acquired from thirty-four healthy adult volunteers (11 females: 32.09 ± 3.53 years; 23 males: 30.87 ± 4.64 years) following a double-blind and placebo-controlled experimental design with two measurement weeks per participant. On Wednesdays and Fridays of each week, participants consumed either the active dose (psilocybin) or the placebo (edible mushrooms). Features of interest were defined based on variables known to be affected by higher doses: verbosity, semantic variability, and sentiment scores. Machine learning models were used to discriminate between conditions. Classifiers were trained and tested using stratified cross-validation to compute the AUC and p-values. RESULTS: Except for semantic variability, these metrics presented significant differences between a typical active microdose and the inactive placebo condition. Machine learning classifiers were capable of distinguishing between conditions with high accuracy (AUC [Formula: see text] 0.8). CONCLUSIONS: These results constitute first evidence that low doses of serotonergic psychedelics can be identified from unconstrained natural speech, with potential for widely applicable, affordable, and ecologically valid monitoring of microdosing schedules.

Automated text-level semantic markers of Alzheimer's disease.

INTRODUCTION: Automated speech analysis has emerged as a scalable, cost-effective tool to identify persons with Alzheimer's disease dementia (ADD). Yet, most research is undermined by low interpretability and specificity. METHODS: Combining statistical and machine learning analyses of natural speech data, we aimed to discriminate ADD patients from healthy controls (HCs) based on automated measures of domains typically affected in ADD: semantic granularity (coarseness of concepts) and ongoing semantic variability (conceptual closeness of successive words). To test for specificity, we replicated the analyses on Parkinson's disease (PD) patients. RESULTS: Relative to controls, ADD (but not PD) patients exhibited significant differences in both measures. Also, these features robustly discriminated between ADD patients and HC, while yielding near-chance classification between PD patients and HCs. DISCUSSION: Automated discourse-level semantic analyses can reveal objective, interpretable, and specific markers of ADD, bridging well-established neuropsychological targets with digital assessment tools.

The entropic tongue: Disorganization of natural language under LSD.

Serotonergic psychedelics have been suggested to mirror certain aspects of psychosis, and, more generally, elicit a state of consciousness underpinned by increased entropy of on-going neural activity. We investigated the hypothesis that language produced under the effects of lysergic acid diethylamide (LSD) should exhibit increased entropy and reduced semantic coherence. Computational analysis of interviews conducted at two different time points after 75 µg of intravenous LSD verified this prediction. Non-semantic analysis of speech organization revealed increased verbosity and a reduced lexicon, changes that are more similar to those observed during manic psychoses than in schizophrenia, which was confirmed by direct comparison with reference samples. Importantly, features related to language organization allowed machine learning classifiers to identify speech under LSD with accuracy comparable to that obtained by examining semantic content. These results constitute a quantitative and objective characterization of disorganized natural speech as a landmark feature of the psychedelic state.

Relationship among subjective responses, flavor, and chemical composition across more than 800 commercial cannabis varieties.

BACKGROUND: Widespread commercialization of cannabis has led to the introduction of brand names based on users' subjective experience of psychological effects and flavors, but this process has occurred in the absence of agreed standards. The objective of this work was to leverage information extracted from large databases to evaluate the consistency and validity of these subjective reports, and to determine their correlation with the reported cultivars and with estimates of their chemical composition (delta-9-THC, CBD, terpenes). METHODS: We analyzed a large publicly available dataset extracted from Leafly.com where users freely reported their experiences with cannabis cultivars, including different subjective effects and flavour associations. This analysis was complemented with information on the chemical composition of a subset of the cultivars extracted from Psilabs.org . The structure of this dataset was investigated using network analysis applied to the pairwise similarities between reported subjective effects and/or chemical compositions. Random forest classifiers were used to evaluate whether reports of flavours and subjective effects could identify the labelled species cultivar. We applied Natural Language Processing (NLP) tools to free narratives written by the users to validate the subjective effect and flavour tags. Finally, we explored the relationship between terpenoid content, cannabinoid composition and subjective reports in a subset of the cultivars. RESULTS: Machine learning classifiers distinguished between species tags given by "Cannabis sativa" and "Cannabis indica" based on the reported flavours: = 0.828 ± 0.002 (p < 0.001); and effects: = 0.9965 ± 0.0002 (p < 0.001). A significant relationship between terpene and cannabinoid content was suggested by positive correlations between subjective effect and flavour tags (p < 0.05, False-Discovery-rate (FDR)-corrected); these correlations clustered the reported effects into three groups that represented unpleasant, stimulant and soothing effects. The use of predefined tags was validated by applying latent semantic analysis tools to unstructured written reviews, also providing breed-specific topics consistent with their purported subjective effects. Terpene profiles matched the perceptual characterizations made by the users, particularly for the terpene-flavours graph (Q = 0.324). CONCLUSIONS: Our work represents the first data-driven synthesis of self-reported and chemical information in a large number of cannabis cultivars. Since terpene content is robustly inherited and less influenced by environmental factors, flavour perception could represent a reliable marker to indirectly characterize the psychoactive effects of cannabis. Our novel methodology helps meet demands for reliable cultivar characterization in the context of an ever-growing market for medicinal and recreational cannabis.

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

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.

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

BACKGROUND: Natural speech analytics has seen some improvements over recent years, and this has opened a window for objective and quantitative diagnosis in psychiatry. Here, we used a machine learning algorithm applied to natural speech to ask whether language properties measured before psilocybin for treatment-resistant can predict for which patients it will be effective and for which it will not. METHODS: A baseline autobiographical memory interview was conducted and transcribed. Patients with treatment-resistant depression received 2 doses of psilocybin, 10 mg and 25 mg, 7 days apart. Psychological support was provided before, during and after all dosing sessions. Quantitative speech measures were applied to the interview data from 17 patients and 18 untreated age-matched healthy control subjects. A machine learning algorithm was used to classify between controls and patients and predict treatment response. RESULTS: Speech analytics and machine learning successfully differentiated depressed patients from healthy controls and identified treatment responders from non-responders with a significant level of 85% of accuracy (75% precision). CONCLUSIONS: Automatic natural language analysis was used to predict effective response to treatment with psilocybin, suggesting that these tools offer a highly cost-effective facility for screening individuals for treatment suitability and sensitivity. LIMITATIONS: The sample size was small and replication is required to strengthen inferences on these results.

Prediction of psychosis across protocols and risk cohorts using automated language analysis.

Language and speech are the primary source of data for psychiatrists to diagnose and treat mental disorders. In psychosis, the very structure of language can be disturbed, including semantic coherence (e.g., derailment and tangentiality) and syntactic complexity (e.g., concreteness). Subtle disturbances in language are evident in schizophrenia even prior to first psychosis onset, during prodromal stages. Using computer-based natural language processing analyses, we previously showed that, among English-speaking clinical (e.g., ultra) high-risk youths, baseline reduction in semantic coherence (the flow of meaning in speech) and in syntactic complexity could predict subsequent psychosis onset with high accuracy. Herein, we aimed to cross-validate these automated linguistic analytic methods in a second larger risk cohort, also English-speaking, and to discriminate speech in psychosis from normal speech. We identified an automated machine-learning speech classifier - comprising decreased semantic coherence, greater variance in that coherence, and reduced usage of possessive pronouns - that had an 83% accuracy in predicting psychosis onset (intra-protocol), a cross-validated accuracy of 79% of psychosis onset prediction in the original risk cohort (cross-protocol), and a 72% accuracy in discriminating the speech of recent-onset psychosis patients from that of healthy individuals. The classifier was highly correlated with previously identified manual linguistic predictors. Our findings support the utility and validity of automated natural language processing methods to characterize disturbances in semantics and syntax across stages of psychotic disorder. The next steps will be to apply these methods in larger risk cohorts to further test reproducibility, also in languages other than English, and identify sources of variability. This technology has the potential to improve prediction of psychosis outcome among at-risk youths and identify linguistic targets for remediation and preventive intervention. More broadly, automated linguistic analysis can be a powerful tool for diagnosis and treatment across neuropsychiatry.

How language flows when movements don't: An automated analysis of spontaneous discourse in Parkinson's disease.

To assess the impact of Parkinson's disease (PD) on spontaneous discourse, we conducted computerized analyses of brief monologues produced by 51 patients and 50 controls. We explored differences in semantic fields (via latent semantic analysis), grammatical choices (using part-of-speech tagging), and word-level repetitions (with graph embedding tools). Although overall output was quantitatively similar between groups, patients relied less heavily on action-related concepts and used more subordinate structures. Also, a classification tool operating on grammatical patterns identified monologues as pertaining to patients or controls with 75% accuracy. Finally, while the incidence of dysfluent word repetitions was similar between groups, it allowed inferring the patients' level of motor impairment with 77% accuracy. Our results highlight the relevance of studying naturalistic discourse features to tap the integrity of neural (and, particularly, motor) networks, beyond the possibilities of standard token-level instruments.

Quantitative Pedagogy: A Digital Two Player Game to Examine Communicative Competence.

Inner concepts are much richer than the words that describe them. Our general objective is to inquire what are the best procedures to communicate conceptual knowledge. We construct a simplified and controlled setup emulating important variables of pedagogy amenable to quantitative analysis. To this aim, we designed a game inspired in Chinese Whispers, to investigate which attributes of a description affect its capacity to faithfully convey an image. This is a two player game: an emitter and a receiver. The emitter was shown a simple geometric figure and was asked to describe it in words. He was informed that this description would be passed to the receiver who had to replicate the drawing from this description. We capitalized on vast data obtained from an android app to quantify the effect of different aspects of a description on communication precision. We show that descriptions more effectively communicate an image when they are coherent and when they are procedural. Instead, the creativity, the use of metaphors and the use of mathematical concepts do not affect its fidelity.

Fast Distributed Dynamics of Semantic Networks via Social Media.

We investigate the dynamics of semantic organization using social media, a collective expression of human thought. We propose a novel, time-dependent semantic similarity measure (TSS), based on the social network Twitter. We show that TSS is consistent with static measures of similarity but provides high temporal resolution for the identification of real-world events and induced changes in the distributed structure of semantic relationships across the entire lexicon. Using TSS, we measured the evolution of a concept and its movement along the semantic neighborhood, driven by specific news/events. Finally, we showed that particular events may trigger a temporary reorganization of elements in the semantic network.

Automated analysis of free speech predicts psychosis onset in high-risk youths.

BACKGROUND/OBJECTIVES: Psychiatry lacks the objective clinical tests routinely used in other specializations. Novel computerized methods to characterize complex behaviors such as speech could be used to identify and predict psychiatric illness in individuals. AIMS: In this proof-of-principle study, our aim was to test automated speech analyses combined with Machine Learning to predict later psychosis onset in youths at clinical high-risk (CHR) for psychosis. METHODS: Thirty-four CHR youths (11 females) had baseline interviews and were assessed quarterly for up to 2.5 years; five transitioned to psychosis. Using automated analysis, transcripts of interviews were evaluated for semantic and syntactic features predicting later psychosis onset. Speech features were fed into a convex hull classification algorithm with leave-one-subject-out cross-validation to assess their predictive value for psychosis outcome. The canonical correlation between the speech features and prodromal symptom ratings was computed. RESULTS: Derived speech features included a Latent Semantic Analysis measure of semantic coherence and two syntactic markers of speech complexity: maximum phrase length and use of determiners (e.g., which). These speech features predicted later psychosis development with 100% accuracy, outperforming classification from clinical interviews. Speech features were significantly correlated with prodromal symptoms. CONCLUSIONS: Findings support the utility of automated speech analysis to measure subtle, clinically relevant mental state changes in emergent psychosis. Recent developments in computer science, including natural language processing, could provide the foundation for future development of objective clinical tests for psychiatry.

A window into the intoxicated mind? Speech as an index of psychoactive drug effects.

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.