Lowering costs for large-scale screening in psychosis: a systematic review and meta-analysis of performance and value of information for speech-based psychiatric evaluation

Felipe Argolo Guilherme Magnavita Natalia Bezerra Mota Carolina Ziebold Dirceu Mabunda Pedro M. Pan André Zugman Ary Gadelha Cheryl Corcoran Rodrigo A. Bressan About the authors

Abstract

Objective:

Obstacles for computational tools in psychiatry include gathering robust evidence and keeping implementation costs reasonable. We report a systematic review of automated speech evaluation for the psychosis spectrum and analyze the value of information for a screening program in a healthcare system with a limited number of psychiatrists (Maputo, Mozambique).

Methods:

Original studies on speech analysis for forecasting of conversion in individuals at clinical high risk (CHR) for psychosis, diagnosis of manifested psychotic disorder, and first-episode psychosis (FEP) were included in this review. Studies addressing non-verbal components of speech (e.g., pitch, tone) were excluded.

Results:

Of 168 works identified, 28 original studies were included. Valuable speech features included direct measures (e.g., relative word counting) and mathematical embeddings (e.g.: word-to-vector, graphs). Accuracy estimates reported for schizophrenia diagnosis and CHR conversion ranged from 71 to 100% across studies. Studies used structured interviews, directed tasks, or prompted free speech. Directed-task protocols were faster while seemingly maintaining performance. The expected value of perfect information is USD 9.34 million. Imperfect tests would nevertheless yield high value.

Conclusion:

Accuracy for screening and diagnosis was high. Larger studies are needed to enhance precision of classificatory estimates. Automated analysis presents itself as a feasible, low-cost method which should be especially useful for regions in which the physician pool is insufficient to meet demand.

Psychosis; automated speech analysis; speech analysis; verbal behavior; schizophrenia


Introduction

As the research community closes gaps in translational neuroscience, psychiatry revisits classical topics, such as verbal behavior in mental disorders.11. Huys QJ, Maia TV, Frank MJ. Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci. 2016;19:404-13. Evidence from the early 20th century suggested that speech contains valuable information for psychopathology (reviewed in Cohen & Elvevåg22. Cohen AS, Elvevåg B. Automated computerized analysis of speech in psychiatric disorders. Curr Opin Psychiatry. 2014;27:203-9.). The first descriptions of psychosis already distinguished language disturbance as a core feature in the disease.33. Kuperberg GR. Language in schizophrenia part 1: an introduction. Lang Linguist Compass. 2010;4:576-89.

4. Kraepelin E. [100 years of psychiatry]. Vertex. 2010;21:317-20.
-55. Bleuler E. [Dementia praecox or the group of schizophrenias]. Vertex. 2010;21:394-400. Recent efforts combine computational processing of human natural language (natural language processing, NLP) with clinical expertise in order to obtain predictive models, with prominent results in the psychosis spectrum. We systematically reviewed the literature to assess the current knowledge on automated speech evaluation. Our study compiles 1) common theoretical grounds, 2) pooled accuracy estimates for predictive models, and 3) the value of perfect and imperfect information for developing a screening program for clinical high risk (CHR) of psychosis and subsequent intervention to prevent psychosis.

Biology of speech production in humans

Verbal behavior mechanisms have been extensively studied in humans using numerous heuristics, such as formal complexity of language,66. Chomsky N. Syntactic structures. Berlin: ?Mouton; 1957.,77. Jager G, Rogers J. Formal language theory: refining the Chomsky hierarchy. Philos Trans R Soc Lond B Biol Sci. 2012;367:1956-70. errors in spontaneous production,88. Fromkin VA. Grammatical aspects of speech errors. In: Newmeyer FJ. Linguistic theory: extensions and implications. Cambridge: Cambridge; 1988. Linguistics: The Cambridge Survey, v. 2, p. 117-38. clinical presentation of aphasia,99. Tremblay P, Dick AS. Broca and Wernicke are dead, or moving past the classic model of language neurobiology. Brain Lang. 2016;162:60-71. and comparative grammar.1010. Bresnan J, Kaplan R, Peters S, Zaenen A. Cross-serial dependencies in Dutch. In: Savitch WJ, Bach E, Marsh W, Safran-Naveh G, editors. The formal complexity of natural language. Dordrecht: Springer; 1982. Studies in Linguistics and Philosophy (formerly Synthese Language Library), v. 33, p. 286-319.

The investigation of specific speech features to assess underlying brain structure is connected to the very earliest days of psychometrics, when pioneer Francis Galton designed the word association test, later modified by Jung.1111. Jung CG. The structure and dynamics of the psyche [Internet]. Vol. 8. 1969 [cited 2019 Feb 10]. http://www.jungiananalysts.org.uk/wp-content/uploads/2018/07/C.-G.-Jung-Collected-Works-Volume-8_-The-Structure-and-Dynamics-of-the-Psyche.pdf
http://www.jungiananalysts.org.uk/wp-con...
Other instruments1212. Rorschach H. Psychodiagnostics. Oxford: Grune & Stratton Psychodiagnostics; 1942.,1313. Freed H, Eccker WF. The thematic apperception test. Dis Nerv Syst. 1946;7:146-51. stimulated spontaneous speech production from context with total or partial freedom for the subject, such as the Thematic Apperception Test (TAT).

Symbolic structure, phonological variations, and semantic connections were considered to communicate subtle characteristics intrinsic to one’s brain phenotype. A preponderance of evidence supports – and most theories agree with – the existence of hierarchical, sequentially distinct stages in language production, from conception of words to articulation of speech.1414. Baese-Berk M, Goldrick M. Mechanisms of interaction in speech production. Lang Cogn Process. 2009;24:527-54. These differences are topologically related to an evolutionary hierarchy of cortical development,1515. Aboitiz F. A Brain for speech. Evolutionary continuity in primate and human auditory-vocal processing. Front Neurosci. 2018;12:174. with cortical expansion in temporoparietal and frontal hub regions.1616. Hill J, Inder T, Neil J, Dierker D, Harwell J, Van Essen D. Similar patterns of cortical expansion during human development and evolution. Proc Natl Acad Sci U S A. 2010;107:1315-40.

Verbal impairments in psychosis

Early psychopathologists carefully described communication impairments in psychosis which were generally regarded to reflect deep disturbances of thought.1717. Andreasen NC, Grove WM. Thought, language, and communication in schizophrenia: diagnosis and prognosis. Schizophr Bull. 1986;12:348-59. These features included word salad, speech disorganization, clanging, derailment, tangentiality, and assonance.33. Kuperberg GR. Language in schizophrenia part 1: an introduction. Lang Linguist Compass. 2010;4:576-89.,1818. Engels H, Heynick F, van der Staak C. Emil Kraepelin’s dream speech: a psychoanalytic interpretation. Int J Psychoanal. 2003;84:1281-94. Although observations were consistent, limitations (e.g., real-time measurement and subjective scoring) precluded practical applications of speech assessment.1919. Cohen AS, Mitchell KR, Docherty NM, Horan WP. Vocal expression in schizophrenia: less than meets the ear. J Abnorm Psychol. 2016;125:299-309.

Abnormal neuroimaging findings in multiple cortical and subcortical regions are observed in schizophrenia.2020. Tagamets MA, Cortes CR, Griego JA, Elvevåg B. Neural correlates of the relationship between discourse coherence and sensory monitoring in schizophrenia. Cortex. 2014;55:77-87.

21. Hagoort P. Nodes and networks in the neural architecture for language: Broca’s region and beyond. Curr Opin Neurobiol. 2014;28:136-41.

22. Xiang HD, Fonteijn HM, Norris DG, Hagoort P. Topographical functional connectivity pattern in the perisylvian language networks. Cereb Cortex. 2010;20:549-60.

23. Sabb FW, van Erp TG, Hardt ME, Dapretto M, Caplan R, Cannon TD, et al. Language network dysfunction as a predictor of outcome in youth at clinical high risk for psychosis. Schizophr Res. 2010;116:173-83.
-2424. Collin G, Seidman LJ, Keshavan MS, Stone WS, Qi Z, Zhang T, et al. Functional connectome organization predicts conversion to psychosis in clinical high-risk youth from the SHARP program. Mol Psychiatry. 2018 Nov 8. doi: http://10.1038/s41380-018-0288-x. [Epub ahead of print]
http://10.1038/s41380-018-0288-x...
Within the speech domain, semantic processing seems to be altered in associative areas, namely the dorsolateral prefrontal cortex (DLPC) and inferior parietal cortex (IPC).2525. Kuperberg GR, West WC, Lakshmanan BM, Goff D. Functional magnetic resonance imaging reveals neuroanatomical dissociations during semantic integration in schizophrenia. Biol Psychiatry. 2008;64:407-18.

Recent approaches have employed automated analysis of speech, in which mathematical models provide insight about observed behavioral patterns, with implications for risk assessment,2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030. diagnostic support, and prognostic monitoring.2727. Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16. This avenue of investigation has led to a steady accrual of evidence that supports the potential of automated speech analysis to transform prediction and diagnosis of psychosis, although an overarching framework is still lacking.

Value of information for speech screening in distributed health systems

Randomized clinical trials (RCTs) allow estimation of the causal effect of interventions – or “decisions” – in nearly counterfactual scenarios with minimal assumptions. However, RCTs are not available for all interventions, in all outcomes, for all timeframes, in every population. In such cases, decision science models allow us to expand the conclusions of empirical studies given a set of mathematical assumptions. As such, we may integrate data from different sources in the medical literature to simulate a population under two – or more – counterfactual scenarios, or decisions, as if they were parallel arms in an RCT. We can incorporate population heterogeneity, adapt findings from studies in one population to another by changing the distribution of effect modifiers, and incorporate cost and life expectancy information to extend the horizon of analysis of the original RCT. All this surplus information comes with the price that the answer is only correct if the mathematical assumptions embedded in the model are correct.

As there is no empirical RCT to evaluate the impact of a population-based screening program for identification of psychosis risk, preventive intervention, and the effect thereof on reducing incidence of schizophrenia (improving quality of life or life expectancy), we chose to simulate the Mozambique population under the counterfactual scenarios of “screening and treating” vs. “no screening.” We model the expected benefit of a distributed screening program as the increase in quality-adjusted life years (QALYs) in a scenario with few mental health specialists. Effectiveness and related costs are simulated for the city of Maputo, Mozambique, which serves a country of nearly 30 million people, yet has only 30 primary health care facilities, four general hospitals, 13 psychiatrists, and one psychiatric hospital.

The value of information of such a screening tool for a potential funding agency is estimated as the expected impact given the metrics of sensitivity and specificity achieved by the instrument. The expected value of perfect information (EVPI) represents an upper bound for investment in a new test. We conducted our analysis to calculate both the EVPI (e.g., for a perfect test) and the value of information at lower sensitivity and specificity (e.g., an imperfect test), to calculate the upper limits of costs for developing software to detect individuals with psychosis risk at that accuracy level.

Methods

Systematic review

We proceeded according to the Cochrane protocol and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement guidelines for reporting. We report: 1) main common theoretical grounds; 2) accuracy findings for risk assessment in CHR and diagnosis in schizophrenia; and 3) the value of information for implementing decentralized screening.

Eligibility criteria

We included all original studies assessing psychosis and psychosis risk through automated analysis of speech. The reference lists of articles found through database searches were hand-searched to identify additional relevant publications. Studies were included regardless of population characteristics, types of outcomes, or design. We limited the scope of this review to verbal behavior, excluding studies of nonverbal aspects of expression, such as intonation and pitch (e.g., prosody and pauses). Although they carry information, audio wave analyses require different assumptions, methods, and techniques. We consider analysis of transcriptions to be more feasible in clinical settings and less susceptible to noise from technological issues and the environment. They also rely on the quality of the recorded audio; hence, they are not robust to input noise. Studies published through August 2018 in English, Spanish, and Portuguese were included.

Literature sources and study selection

We used the PubMed search engine (granting access to the MEDLINE database and additional references from the National Library of Medicine), including all material published through August 2018.

Keywords

We designed a search query with a combination of semantically similar keywords to capture (a) “automated analysis” of (b) “speech” in (c) “psychosis.” Consonant with the objective of investigating conditions with underlying related phenotypes (e.g., endophenotypes), we directly searched for disorders with consistently reported coheritability, in addition to general terms.2828. Cross-Disorder Group of the Psychiatric Genomics Consortium, Lee SH, Ripke S, Neale BM, Faraone SV, Purcell SM, et al. Genetic relationship between five psychiatric disorders estimated from genome-wide SNPs. Nat Genet. 2013;45:984-94.

29. Cross-Disorder Group of the Psychiatric Genomics Consortium. Identification of risk loci with shared effects on five major psychiatric disorders: a genome-wide analysis. Lancet. 2013;381:1371-9.
-3030. Geschwind DH, Flint J. Genetics and genomics of psychiatric disease. Science. 2015;349:1489-94.

Search query:

  1. (“automated” OR “computerized” OR “computational”) AND (“analysis” OR “assessment” OR “evaluation”) AND

  2. (“speech” OR “semantics” OR “language” OR “prosody” OR “pauses” OR “acoustics” OR “paralinguistic” OR “fundamental frequency” OR “nonverbal expression”) AND

  3. (“mental disorder” OR “psychiatric” OR “psychotic” OR “schizophrenia”)

Data extraction

For each manuscript, we assessed the following key data: 1) study design; 2) demographics; 3) sample characteristics, including psychopathological measures and/or diagnostic criteria; 4) protocol for elicitation of verbal response; 5) speech metrics used; 6) validity analysis/classification techniques; 7) main findings and classification accuracy (if available); and 8) software toolkit (when available) and reference language corpus used for analyses.

Accuracy estimates

We used pooled discriminatory estimates obtained from the review to assess accuracy performance. Errors and confidence intervals (CIs) for classification were obtained, assuming an underlying binomial distribution.

Value of information model methods

Model overview

We analyzed the value of perfect and imperfect information for implementing a screening program based on automated speech analysis to assess psychosis and psychosis risk in Maputo, the capital of Mozambique, a country with less than 15 psychiatrists3131. Wagenaar BH, Cumbe V, Raunig-Berhó M, Rao D, Kohrt BA, Stergachis A, et al. Outpatient mental health services in Mozambique: use and treatments [Internet]. 2016 Feb 1 [cited 2020 Mar 12]. http://ps.psychiatryonline.org/doi/full/10.1176/appi.ps.201500508
http://ps.psychiatryonline.org/doi/full/...
for a population of 28,571,310 (source: http://www.ine.gov.mz/). We developed a Markov cohort to assess the value of information of a software for screening once for CHR of psychosis over a lifetime horizon of cost per QALY. The model includes two different strategies: screening once + preventive treatment vs. no screening. For the no-screening strategy, four health states are possible: regular risk, CHR, schizophrenia, and death. For the screen-and-treat strategy, six health states are possible: untreated regular risk, treated regular risk, untreated high risk, treated high risk, schizophrenia, and death (absorbing state). Possible state transitions are shown in Figure 1.

Figure 1
Bubble diagram for the screen + treat strategy (top) and no-screening strategy (bottom).

Model outcomes were life expectancy, expected QALY, and expected costs of the intervention, but not of the software. Transition probabilities between health states were modeled on the basis of multiple sources from the literature; probabilities and costs which could not be drawn from published literature or official documents were estimated by our board of experts. Details are provided in Table S1, available as online-only supplementary material. Our model calculated the probability of being in each health state at any given time by multiplying the previous state with the corresponding transition matrix. Costing was considered from the screening and treatment program funding-agency perspective. We present a more detailed description of how we modeled clinical progression of disease in the supplementary material.

Intervention

The intervention we designed consisted of a single screening assessment lasting 10-15 minutes followed by 6 months of treatment with cognitive therapy, following the work of Morrison et al.3232. Morrison AP, French P, Walford L, Lewis SW, Kilcommons A, Green J, et al. Cognitive therapy for the prevention of psychosis in people at ultra-high risk: randomised controlled trial. Br J Psychiatry. 2004;185:291-7. For the imperfect information analysis, the screening tool had a sensitivity of 70% and specificity of 70%. As reported by Bearden et al.,3333. Bearden CE, Wu KN, Caplan R, Cannon TD. Thought disorder and communication deviance as predictors of outcome in youth at clinical high risk for psychosis. J Am Acad Child Adolesc Psychiatry. 2011;50:669-80. anual methods already possessed the ability to detect transition to schizophrenia within CHR patients in 2011. Therefore, detecting prodromal states and attenuated symptoms with 70% accuracy is not only feasible, but likely an underestimation of current models. For the perfect information scenario, sensitivity and specificity for the CHR state are set at 100% at the time of screening. Treatment is assumed to be maintained for 6 months for all positively screened patients, except for those who dropped out, developed threshold psychosis (e.g., schizophrenia), or died in the first year. After treatment termination, costs related to treatment and follow-up were set at 0, and – as mentioned above – treatment benefit was only maintained until the end of the second year. In our base case, we assumed a 10% risk of loss to follow-up, with a constant rate of schizophrenia incidence during the 6 months of intervention and dropouts immediately losing all later – but not previous – protective effects from treatment.

Utilities

Regular-risk patients were assumed to have perfect utility. CHR patients were assumed to have a utility of 0.95 due to the burden of prodromal symptoms, as defined by our board of experts based on utility values for schizophrenia patients. Treatment itself was associated with a 0.02 decrease in utility for all treated false-positive patients due to the burden of attending appointments. The schizophrenia state had a utility of 0.75; this refers to the perceived utility of moderate to severe schizophrenia among healthy people according to the work of Lenert et al.3434. Lenert LA, Sturley AP, Rapaport MH, Chavez S, Mohr PE, Rupnow M. Public preferences for health states with schizophrenia and a mapping function to estimate utilities from positive and negative symptom scale scores. Schizophr Res. 2004;71:155-65. One of the authors (DM), a psychiatrist at the Mozambique Ministry of Health, felt that this disease level best reflected the average experience of a patient with schizophrenia in Mozambique, even after treatment, due to diagnostic delay.

Setting

The program is meant to be deployed at the 30 primary health care facilities, four general hospitals, and single psychiatric hospital of the capital, Maputo. Patients would be screened by a program-trained psychologist at one of these centers, and those who screened positive would then receive therapy at one of the primary facilities on an outpatient basis. As the capital has a population of 2,500,000, assuming the most conservative estimate from van Os et al.3535. van Os J, Linscott RJ, Myin-Germeys I, Delespaul P, Krabbendam L. A systematic review and meta-analysis of the psychosis continuum: evidence for a psychosis proneness-persistence-impairment model of psychotic disorder. Psychol Med. 2009;39:179-95. of 1.9% for 1-year prevalence of psychotic episodes, we would still have a pool of 47,500 patients in need of our screening program in 1 year, far above the maximum load our psychologists could take in. If we screened 9,000 patients a year (i.e., 0.7 screening sessions per center per day), our ability to treat both true positives and false positives would not be overextended. We would therefore be able to screen 45,000 patients during the 5-year period we used to calculate costs related to program deployment and fixed costs. We chose to calculate costs aiming to screen 30,000 patients, to yield a more conservative estimate.

Costs

We adopted the costing perspective of the program’s funding agency: therefore, we included costs to train personnel, buy the screening hardware (smartphones), pay for internet access and power (to charge phones), and compensate psychologists for screening and providing therapy. Costs were calculated from a bottom-up approach – i.e., individual costs from the program workforce and infrastructure were added together. As the program would not fund regular schizophrenia treatment for Mozambique, patients who developed threshold psychosis (e.g., schizophrenia) would be accepted for treatment by the government health system and drop out of the program. Also, as all costs are intervention-related, the no-screening strategy had a total cost of 0. Fixed costs related to program set-up were divided by the estimated number of patients we expected the program to cover. All data related to costs and the expected number of patients to be screened were provided by the Mozambique Ministry of Health. Fixed costs and installation costs were calculated for a 5-year period for a total of 30,000 people; as noted above, this yields a conservative estimate if compared to a longer horizon, since some of our costs – e.g., personnel training – would not accrue immediately after the 5-year window. All costs are given in 2018 dollars (Dirceu Mabunda, personal communication, 2018 Oct 08).

Value of information analysis

Willingness-to-pay (WTP) for a QALY was set at three times the current value of Mozambique’s gross domestic product (GDP) per capita, or USD 1,247.154. This is a commonly used (albeit conservative) QALY estimate for developing countries. Similar thresholds for the U.S. would range between USD 50,000 to USD 150,000 per QALY. Differences in expected QALY between strategies were calculated and then multiplied by the WTP value. The program maintenance cost was subtracted from that, and the remaining value would be our value of information for that setting. We calculated both the EVPI and the value for an imperfect test with sensitivity and specificity of 70%.

Sensitivity and scenario analyses

We conducted a deterministic sensitivity analysis on the impact of the initial prevalence of the CHR state in the population, as there is little knowledge of this input in the literature and the prevalence in Mozambique may be different from the one reported in Conrad et al.3636. Conrad AM, Lewin TJ, Sly KA, Schall U, Halpin SA, Hunter M, et al. Utility of risk-status for predicting psychosis and related outcomes: evaluation of a 10-year cohort of presenters to a specialised early psychosis community mental health service. Psychiatry Res. 2017;247:336-44. We display our EVPI, incremental life year (LY), and incremental QALYs as functions of a range of possible prevalence values, set between 5 and 50%, based on the bounds of psychosis-like symptoms shown in the work of van Os et al.3535. van Os J, Linscott RJ, Myin-Germeys I, Delespaul P, Krabbendam L. A systematic review and meta-analysis of the psychosis continuum: evidence for a psychosis proneness-persistence-impairment model of psychotic disorder. Psychol Med. 2009;39:179-95. and in the screening phase of Morrison et al.3232. Morrison AP, French P, Walford L, Lewis SW, Kilcommons A, Green J, et al. Cognitive therapy for the prevention of psychosis in people at ultra-high risk: randomised controlled trial. Br J Psychiatry. 2004;185:291-7.

Validation and calibration

We validated our modeling of the intervention – a risk ratio of 0.263 for schizophrenia conversion according to the CHR conversion risk meta-analysis, followed by a sudden loss of effect compared to controls after the first year of intervention – by predicting the expected risk ratio for conversion to schizophrenia at 3 years and comparing it to the risk ratio reported by Morrison et al. for the 3-year follow-up of their original RCT cohort.3737. Preti A, Cella M. Randomized-controlled trials in people at ultra high risk of psychosis: a review of treatment effectiveness. Schizophr Res. 2010;123:30-6.,3838. Morrison AP, French P, Parker S, Roberts M, Stevens H, Bentall RP, et al. Three-year follow-up of a randomized controlled trial of cognitive therapy for the prevention of psychosis in people at ultrahigh risk. Schizophr Bull. 2007;33:682-7.

We also compare the performance of our model against some of the calibration benchmarks used as references to construct it. Our cumulative incidence of psychosis among the CHR state at 12, 24, and 48 months is compared to the work of Schmidt et al.,3939. Schmidt SJ, Schultze-Lutter F, Schimmelmann BG, Maric NP, Salokangas RK, Riecher-Rössler A, et al. EPA guidance on the early intervention in clinical high risk states of psychoses. Eur Psychiatry. 2015;30:388-404. while our remission risk among CHR individuals at 6 months is compared to the work of Polari et al.4040. Polari A, Lavoie S, Yuen HP, Amminger P, Berger G, Chen E, et al. Clinical trajectories in the ultra-high risk for psychosis population. Schizophr Res. 2018;197:550-6.

Ethical aspects

For automated speech analysis to be helpful in the detection and screening of mental illness, technological barriers are not the only issue. Predictions are based on indirect information about cognitive functioning, as high-risk phenotypes are inferred from language patterns.

Even if high concordance between such algorithms and personalized (face-to-face) diagnostics is achieved, one must keep in mind that psychiatric diagnostics are structured around crucial criteria. We emphasize the need for later in-person confirmation of initial findings. This is incorporated in the screening system outlined, where NLP is used a screening tool. Individuals showing seemingly altered patterns are referred to centers for further evaluation.

Results

One hundred and sixty-eight papers were initially screened, of which 28 were included in the final review, with 24 including psychosis patients and four including CHR individuals. Of the 24 studies including psychotic individuals, three also included first-episode psychosis (FEP) groups. The list of studies included in this systematic review is shown in Table 1.

Table 1
Full summary of studies included for systematic review of automated speech analysis to assess psychosis

Included studies: design, sample size, protocol time

Studies were fairly heterogeneous. Protocol time ranged from 1-minute structured tasks6060. Nicodemus KK, Elvevåg B, Foltz PW, Rosenstein M, Diaz-Asper C, Weinberger DR. Category fluency, latent semantic analysis and schizophrenia: a candidate gene approach. Cortex. 2014;55:182-91. to 60 minutes of open interviews,5454. Mota NB, Vasconcelos N, Lemos N, Pieretti AC, Kinouchi O, Cecchi GA, et al. Speech graphs provide a quantitative measure of thought disorder in psychosis. PLoS One. 2012;7:e34928. while sample sizes ranged from 342727. Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16. to 665 subjects.6060. Nicodemus KK, Elvevåg B, Foltz PW, Rosenstein M, Diaz-Asper C, Weinberger DR. Category fluency, latent semantic analysis and schizophrenia: a candidate gene approach. Cortex. 2014;55:182-91. Nevertheless, 75% of the studies (n=21) included between 40 and 110 patients. One study used a small collection of five speech samples: four schizophrenia patients and one control.6161. Cabana Á, Valle-Lisboa JC, Elvevåg B, Mizraji E. Detecting order-disorder transitions in discourse: iImplications for schizophrenia. Schizophr Res. 2011;131:157-64. 62. Shakeel MK, Halahalli HN, Kumar K, Jain S, John JP. Utility of a computerized, paced semantic verbal fluency paradigm in differentiating schizophrenia and healthy subjects. Asian J Psychiatr. 2014;7:22-7.

There were no large studies providing estimate accuracies for computerized classification. Generally, open interviews were conducted in scenarios close to clinical settings,4545. Corcoran CM, Carrillo F, Fernández-Slezak D, Bedi G, Klim C, Javitt DC, et al. Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry. 2018;17:67-75. while task-based assessment took place in artificial environments.4141. Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20. 42. Pauselli L, Halpern B, Cleary SD, Ku B, Covington MA, Compton MT. Computational linguistic analysis applied to a semantic fluency task to measure derailment and tangentiality in schizophrenia. Psychiatry Res. 2018;263:74-9.

Protocols

Texts were obtained from recordings of either 1) tasks, such as describing a picture for 1 minute,4141. Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20. 2) prompted free speech,5050. Fineberg SK, Leavitt J, Deutsch-Link S, Dealy S, Landry CD, Pirruccio K, et al. Self-reference in psychosis and depression: a language marker of illness. Psychol Med. 2016;46:2605-15. 51. Mota NB, Resende A, Mota-Rolim SA, Copelli M, Ribeiro S. Psychosis and the control of lucid dreaming. Front Psychol. 2016;7:294. 3) structured interviews and scales, such as the Indiana Psychiatric Illness Interview (IPII),4343. Minor KS, Willits JA, Marggraf MP, Jones MN, Lysaker PH. Measuring disorganized speech in schizophrenia: automated analysis explains variance in cognitive deficits beyond clinician-rated scales. Psychol Med. 2019;49:440-8. 44. Gupta T, Hespos SJ, Horton WS, Mittal VA. Automated analysis of written narratives reveals abnormalities in referential cohesion in youth at ultra high risk for psychosis. Schizophr Res. 2018;192:82-8. and 4) open-ended clinical interviews.2727. Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16.

As seen in Table 2, protocols based on tasks and prompted free speech were generally faster, reporting the same pattern of findings as longer protocols did. Open protocols and unstructured interviews resulted in higher heterogeneity due to variability within interviewer-generated stimuli, as well as distinct individual responses.

Table 2
Source data for accuracy estimates used in value of information model of automated speech analysis to assess psychosis

Theoretical grounds

Different ways of measuring similar features yielded valuable information from prediction. Semantic coherence, phrase length, and the frequency of a specific class of words (determiners) were features used to achieve good classification performance for psychosis onset in patients at risk.2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030.,4545. Corcoran CM, Carrillo F, Fernández-Slezak D, Bedi G, Klim C, Javitt DC, et al. Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry. 2018;17:67-75. The underlying constructs being assessed reflect classical clinical characteristics, such as disorganized speech and alogia.

Graph analysis

Graph-based embeddings normally rely on the shortest path between nodes and/or on weighted edges as distance measures. Secondary characteristics include values associated with network structure, such as centrality, modularity, and connectedness.5454. Mota NB, Vasconcelos N, Lemos N, Pieretti AC, Kinouchi O, Cecchi GA, et al. Speech graphs provide a quantitative measure of thought disorder in psychosis. PLoS One. 2012;7:e34928. 55. Thomas P, Romme M, Hamelijnck J. Psychiatry and the politics of the underclass. Br J Psychiatry. 1996;169:401-4. 56. García-Laredo E, Maestú F, Castellanos MÁ, Molina JD, Peréz-Moreno E. The relationship between educational years and Phonemic Verbal Fluency (PVF) and Semantic Verbal Fluency (SVF) tasks in Spanish patients diagnosed with schizophrenia, bipolar disorder, and psychotic bipolar disorder. Medicine (Baltimore). 2015;94:e1596. 57. Buck B, Minor KS, Lysaker PH. Lexical characteristics of anticipatory and consummatory anhedonia in schizophrenia: a study of language in spontaneous life narratives. J Clin Psychol. 2015;71:696-706. 58. Buck B, Minor KS, Lysaker PH. Differential lexical correlates of social cognition and metacognition in schizophrenia; a study of spontaneously-generated life narratives. Compr Psychiatry. 2015;58:138-45. 59. Holshausen K, Harvey PD, Elvevåg B, Foltz PW, Bowie CR. Latent semantic variables are associated with formal thought disorder and adaptive behavior in older inpatients with schizophrenia. Cortex. 2014;55:88-96.

Palaniyappan et al.4141. Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20. reported that connectedness in speech-derived graphs correlated moderately with degree of centrality in the brain through resting-state functional magnetic resonance imaging (fMRI). Other potential biomarkers include candidate genes (DISC1, KIAA0319, ZNF804A) that are associated with speech features.6060. Nicodemus KK, Elvevåg B, Foltz PW, Rosenstein M, Diaz-Asper C, Weinberger DR. Category fluency, latent semantic analysis and schizophrenia: a candidate gene approach. Cortex. 2014;55:182-91.

Derailment and semantic coherence

Carl Schneider6363. Schneider C. Die Psychologie der Schizophrenen: und ihre Bedeutung für die Klinik der Schizophrenie. Stuttgart: G. Thieme; 1930. described as derailment (entgleisen) the unexpected association of ideas among psychosis patients. Several authors have deployed similar strategies to assess this feature. Sentences are mapped to a set of ordered objects from which coherence can be measured.

Words are first lemmatized into their roots and/or tagged according to syntactical function.

  1. PurifyPure

    Then, they are mapped to new structures according to a given morphism (f) from the set of words to real valued n-dimensional vectors. Their similarity is evaluated adopting an arbitrary metric space and a distance measure. For the common cosine distance:

  2. f: word → u

  3. f: (Pure) = v = [0.11,0.12,0.43,0.75, …]

  4. f: (Love) = v′ = [0.11,0.44,0.99,0.33, …]

  5. Dist. (Pure, Love) = cos (v,v′)

where u, v, and v′ are vector mappings of words and d is a real value bounded by the cosine function in the interval [0, 1]. The distance is taken as a measure of semantic coherence. For each sample, semantic coherence was calculated from phrases relative to previous ones.2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030. These measures are used as input features for predictive models (e.g., logistic regression, support vector machines [SVMs]).

Accuracy

Six studies reported classification accuracy using automated speech processing.

Classification of psychotic disorder

Elvevåg et al.2727. Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16. achieved 82.4% accuracy in distinguishing language in schizophrenia from that of healthy individuals (78.4% using cross-validation). Speech samples were gathered from a language task (“tell me the story of Cinderella”), processed using latent semantic analysis (LSA) (TK Landauer), and classified using a linear discriminant classifier. A similar experiment by this group5252. Elvevåg B, Foltz PW, Rosenstein M, Delisi LE. An automated method to analyze language use in patients with schizophrenia and their first-degree relatives. J Neurolinguistics. 2010;23:270-84. used transcripts from a variety of prompt questions. Features analyzed included surface features, statistical language features, and semantic features derived from LSA. Fisher discriminant analysis correctly classified 86.8% (46 out of 53) patients and 60% (18 out of 30) healthy individuals (healthy family members and unrelated healthy controls), giving an overall cross-validated classification accuracy of 77.1%.

Buck & Penn4747. Buck B, Penn DL. Lexical characteristics of emotional narratives in schizophrenia: relationships with symptoms, functioning, and social cognition. J Nerv Ment Dis. 2015;203:702-8. 48. Bonfils KA, Luther L, Firmin RL, Lysaker PH, Minor KS, Salyers MP. Language and hope in schizophrenia-spectrum disorders. Psychiatry Res. 2016;245:8-14. 49. Moe AM, Breitborde NJ, Shakeel MK, Gallagher CJ, Docherty NM. Idea density in the life-stories of people with schizophrenia: associations with narrative qualities and psychiatric symptoms. Schizophr Res. 2016;172:201-5. used transcripts from the Narrative of Emotions Task (NET) processed by the Linguistic Inquiry Word Count (LIWC) software, which calculates the relative frequency of 83 word categories in a given text. The area under the receiver operating characteristic (AUROC) curve was 0.823 for “words per sentence” and 0.790 for pronoun use.

Hong4646. Hong K, Nenkova A, March ME, Parker AP, Verma R, KohlerCG. Lexical use in emotional autobiographical narratives of persons with schizophrenia and healthy controls. Psychiatry Res. 2015;225:40-9. elicited autobiographical experiences to produce four classes of input: 1) generic features (e.g., words per sentence); 2) word identity features (e.g., frequency of specific words); 3) dictionary features (categories deriving from dictionaries); and 4) language model features (bigram probabilistic model). A SVM was used to evaluate performance and select valuable features. The accuracy reported for the final model was 0.744.

Semi-structured interviews5353. Rosenstein M, Diaz-Asper C, Foltz PW, Elvevåg B. A computational language approach to modeling prose recall in schizophrenia. Cortex. 2014;55:148-66. processed with LSA and analyzed with proportional-odds logistic regression yielded accuracy similar to that obtained with manual analysis (approximately 70%).3333. Bearden CE, Wu KN, Caplan R, Cannon TD. Thought disorder and communication deviance as predictors of outcome in youth at clinical high risk for psychosis. J Am Acad Child Adolesc Psychiatry. 2011;50:669-80. There was no added information when both were combined.

Prediction of conversion of clinical high risk (CHR) to psychosis

Initial investigations3333. Bearden CE, Wu KN, Caplan R, Cannon TD. Thought disorder and communication deviance as predictors of outcome in youth at clinical high risk for psychosis. J Am Acad Child Adolesc Psychiatry. 2011;50:669-80. suggest that speech-based analysis provided good classification performance (70.5%) when predicting CHR conversion to psychosis within 2 years, even when carried out with manually obtained features (true negative: 71%; true positive: 69%).

More recent studies evaluating conversion of CHR state to psychosis within a 2.5-year range suggest high accuracy ratings, including error free results.2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030. Reproduction in a larger sample suggested more parsimonious estimates (83%; cross-validation: 79%). This work included a slightly shorter follow-up of 2 years, using LSA and part-of-speech tagging as features. Values were processed with singular value decomposition and classified with a logistic regression model.4545. Corcoran CM, Carrillo F, Fernández-Slezak D, Bedi G, Klim C, Javitt DC, et al. Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry. 2018;17:67-75. This was also the only study available reporting classification accuracy for FEP, achieving a 72% mark.

Model metrics matched our inputs, and the assumption of no effect after 1 year matched the 3-year follow up estimate by Morrison et al. in 20073737. Preti A, Cella M. Randomized-controlled trials in people at ultra high risk of psychosis: a review of treatment effectiveness. Schizophr Res. 2010;123:30-6. (Figure S1, available as online-only supplementary material).

Results for the base-case and perfect-screening analyses are presented in Table 3. The intervention increased both life expectancy (0.13 years) and QALY (0.17) in the imperfect screening analysis. Under perfect test characteristics, there is a modest improvement in efficacy, with a life expectancy increase of 0.19 years and of 0.26 in QALYs. However, costs are reduced by decreasing therapy personnel costs with false positives.

Table 3
Incremental QALYs and LYs

In Figure 2, increasing CHR prevalence values with imperfect information (sensitivity and specificity of 70%) also increased increments of both QALY and life years in a linear fashion between the likely prevalence range of 5 to 50%, with increments between 0.1 QALY and 0.6 QALY.

Figure 2
Increments in life years (LYs) and quality-adjusted life years (QALYs) as a function of clinical high-risk (CHR) prevalence (%).

Discussion

The role of language in psychopathology has been studied for more than a century; however, recent technological and conceptual advances now allow for innovative approaches. Fast mathematical approaches and low-cost electronic devices provide feasible ways of recording, processing, and obtaining information from patients’ verbal expression.6464. Montague PR, Dolan RJ, Friston KJ, Dayan P. Computational psychiatry. Trends Cogn Sci. 2012;16:72-80.,6565. Iter D, Yoon J, Jurafsky D. Automatic detection of incoherent speech for diagnosing schizophrenia. In: Loveys K, Niederhoffer K, Prud’hommeaux E, Resnik R, Resnik F, editors. Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: from Keyboard to Clinic; 2018; New Orleans, USA. Stroudsburg: Association for Computational Linguistics; 2018. p. 136-46.

The current literature comprises studies with improved ecological validity, such as direct analyses of free speech during clinical assessment. Multiple independent groups from several nations are aiming at robust candidates for clinical practice.

We detected two broad experimental setting styles: some include recording situations close to normal conversations taking place in a healthcare service, while others study brief, well-defined tasks. Most studies seek to identify key features of psychosis, and have achieved good classificatory performance using features as input for machine learning models.

Cross-sectional studies achieved fairly good accuracy for diagnosis of schizophrenia (above 70% in all studies). Using data from longitudinal studies, researchers were capable of predicting conversion to psychosis within 2.0-2.5 years of assessment with high accuracy (70-100% across studies).

Only Mota et al.5454. Mota NB, Vasconcelos N, Lemos N, Pieretti AC, Kinouchi O, Cecchi GA, et al. Speech graphs provide a quantitative measure of thought disorder in psychosis. PLoS One. 2012;7:e34928. included non-English recordings, with speech samples in Brazilian Portuguese. As no studies included large samples, the CIs for performance estimates remain wide. Future meta-analyses including studies with larger sample sizes may settle the diagnostic characteristics. Further studies addressing classification performance will refine and confirm the reliability of accuracy estimates and clinical effectiveness.

Models have shown improved performance when incorporating NLP variables.2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030. Most studies have used LSA, which relies on single value decomposition for embeddings. These models may yet improve even further, since other methods (e.g., skip-n-gram; long-short term memory neural networks) have achieved higher marks in tasks from other domains.6666. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space [Internet]. [cited 2020 Feb 12]. http://arxiv.org/pdf/1301.3781.pdf
http://arxiv.org/pdf/1301.3781.pdf...

Aside from small samples, study-level bias may arise from heterogeneity in settings. Results have been fairly consistent across studies; however, elicitation procedures and analysis strategies vary. We noticed that recent efforts center around predictive models using ecologically obtainable speech samples.

For our specific case of Mozambique (and likely for other countries with limited numbers of psychiatrists), developing software for CHR detection would be valuable for any likely prevalence range we could expect, even if the screening tool had relatively poor performance (sensitivity 70% and specificity 70%) and we assumed a punitive WTP of three times the GDP per capita. It is likely that current algorithms would perform better at detecting prodromal symptoms of psychosis, since current software already fares much better in detecting subsets of patients in the high-risk state who are more likely to convert to schizophrenia. Therefore, any effort to develop software to detect CHR in Mozambique would be expected to yield a large health benefit, probably overshadowing its cost by an ample margin.

One limitation of the value-of-information model is that follow-up of CHR patients who underwent therapy ended at 3 years after randomization. Nevertheless, this may not be problematic, as rates of conversion to psychosis steadily fall off in the years following initial ascertainment.6767. Nelson B, Yuen HP, Wood SJ, Lin A, Spiliotacopoulos D, Bruxner A, et al. Long-term follow-up of a group at ultra high risk (“Prodromal”) for psychosis: the PACE 400 study. JAMA Psychiatry. 2013;70:793-802. Similarly, we included some of the costs to set up the screening program, but assumed it would continue for a limited time period of 5 years. Were it held for longer, the cost-benefit balance might be even more favorable towards screening, since fixed set-up costs would be shared by a wider population.

In sum, this systematic review reports the first meta-analysis of performance and value of information estimates for speech-based psychiatric evaluation using electronic devices.

A decentralized system coupled with support for focused treatment would be highly efficient. The estimates obtained suggest language analysis would be a valuable screening asset, even for imperfect screening metrics which would be easy to obtain, as compared to similar tools.

Construct validity

Mental disorders compromise higher-order functions of the brain. In psychosis, speech may be a valuable window for assessment, manifesting thought disorganization through several disturbances. The notions of early psychopathologists regarding semantic incoherence are now formalized with NLP to provide reliable signals.

Current tools available for language assessment, such as structured interviews, rely on operator characteristics and adequate training. Nevertheless, it is virtually impossible to remove bias from interviewer cues. Conversely, automated analysis of speech provides clinical indicators which can be interviewer-neutral.

Automated analysis of speech is coherently articulated with biological findings,4141. Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20. neuroimaging,2020. Tagamets MA, Cortes CR, Griego JA, Elvevåg B. Neural correlates of the relationship between discourse coherence and sensory monitoring in schizophrenia. Cortex. 2014;55:77-87. measurable behavior,22. Cohen AS, Elvevåg B. Automated computerized analysis of speech in psychiatric disorders. Curr Opin Psychiatry. 2014;27:203-9. abstractions,2727. Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16. and clinical applications.2626. Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030. Although behavioral and technical advances are supported by the clinical results gathered, the identification of putative biomarkers is still under development. Initial cross-validation of computational variables with brain activity (fMRI) has been achieved in in the psychosis spectrum,2020. Tagamets MA, Cortes CR, Griego JA, Elvevåg B. Neural correlates of the relationship between discourse coherence and sensory monitoring in schizophrenia. Cortex. 2014;55:77-87.,6868. Powers AR, Mathys C, Corlett PR. Pavlovian conditioning-induced hallucinations result from overweighting of perceptual priors. Science. 2017;357:596-600. but only once4141. Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20. with NLP. The relation between speech impairment6060. Nicodemus KK, Elvevåg B, Foltz PW, Rosenstein M, Diaz-Asper C, Weinberger DR. Category fluency, latent semantic analysis and schizophrenia: a candidate gene approach. Cortex. 2014;55:182-91. and previously implied genes (e.g., DISC1) supports discrete language patterns as potentially valuable endophenotypes for psychosis.

Further exploration of natural language structure and its counterparts in the brain will enhance the adequacy of mathematical models. Language carries a hierarchical structure which is efficiently embedded in hyperbolic spaces.6969. Nickel M, Kiela D. Poincaré embeddings for learning hierarchical representations. Adv Neural Inf Process Syst. 2017:6338-47. Different embedding strategies (e.g., LSTM networks, Poincaré embeddings) and distance measures yield similar or better results in non-clinical tasks.6666. Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space [Internet]. [cited 2020 Feb 12]. http://arxiv.org/pdf/1301.3781.pdf
http://arxiv.org/pdf/1301.3781.pdf...

We restricted our findings to processing of symbolic outputs. Nonverbal cues, such as intonation and pauses, may provide different information about neurocognitive characteristics in psychosis.1919. Cohen AS, Mitchell KR, Docherty NM, Horan WP. Vocal expression in schizophrenia: less than meets the ear. J Abnorm Psychol. 2016;125:299-309. These perspectives are complementary, and will benefit from combined analysis in order to enhance efficiency.

FA is a doctoral student receiving a scholarship from Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES). CZ is a doctoral student at Departamento de Psiquiatria, Universidade Federal de São Paulo, receiving a scholarship from Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP; grant 2018/05586-7).

References

  • 1
    Huys QJ, Maia TV, Frank MJ. Computational psychiatry as a bridge from neuroscience to clinical applications. Nat Neurosci. 2016;19:404-13.
  • 2
    Cohen AS, Elvevåg B. Automated computerized analysis of speech in psychiatric disorders. Curr Opin Psychiatry. 2014;27:203-9.
  • 3
    Kuperberg GR. Language in schizophrenia part 1: an introduction. Lang Linguist Compass. 2010;4:576-89.
  • 4
    Kraepelin E. [100 years of psychiatry]. Vertex. 2010;21:317-20.
  • 5
    Bleuler E. [Dementia praecox or the group of schizophrenias]. Vertex. 2010;21:394-400.
  • 6
    Chomsky N. Syntactic structures. Berlin: ?Mouton; 1957.
  • 7
    Jager G, Rogers J. Formal language theory: refining the Chomsky hierarchy. Philos Trans R Soc Lond B Biol Sci. 2012;367:1956-70.
  • 8
    Fromkin VA. Grammatical aspects of speech errors. In: Newmeyer FJ. Linguistic theory: extensions and implications. Cambridge: Cambridge; 1988. Linguistics: The Cambridge Survey, v. 2, p. 117-38.
  • 9
    Tremblay P, Dick AS. Broca and Wernicke are dead, or moving past the classic model of language neurobiology. Brain Lang. 2016;162:60-71.
  • 10
    Bresnan J, Kaplan R, Peters S, Zaenen A. Cross-serial dependencies in Dutch. In: Savitch WJ, Bach E, Marsh W, Safran-Naveh G, editors. The formal complexity of natural language. Dordrecht: Springer; 1982. Studies in Linguistics and Philosophy (formerly Synthese Language Library), v. 33, p. 286-319.
  • 11
    Jung CG. The structure and dynamics of the psyche [Internet]. Vol. 8. 1969 [cited 2019 Feb 10]. http://www.jungiananalysts.org.uk/wp-content/uploads/2018/07/C.-G.-Jung-Collected-Works-Volume-8_-The-Structure-and-Dynamics-of-the-Psyche.pdf
    » http://www.jungiananalysts.org.uk/wp-content/uploads/2018/07/C.-G.-Jung-Collected-Works-Volume-8_-The-Structure-and-Dynamics-of-the-Psyche.pdf
  • 12
    Rorschach H. Psychodiagnostics. Oxford: Grune & Stratton Psychodiagnostics; 1942.
  • 13
    Freed H, Eccker WF. The thematic apperception test. Dis Nerv Syst. 1946;7:146-51.
  • 14
    Baese-Berk M, Goldrick M. Mechanisms of interaction in speech production. Lang Cogn Process. 2009;24:527-54.
  • 15
    Aboitiz F. A Brain for speech. Evolutionary continuity in primate and human auditory-vocal processing. Front Neurosci. 2018;12:174.
  • 16
    Hill J, Inder T, Neil J, Dierker D, Harwell J, Van Essen D. Similar patterns of cortical expansion during human development and evolution. Proc Natl Acad Sci U S A. 2010;107:1315-40.
  • 17
    Andreasen NC, Grove WM. Thought, language, and communication in schizophrenia: diagnosis and prognosis. Schizophr Bull. 1986;12:348-59.
  • 18
    Engels H, Heynick F, van der Staak C. Emil Kraepelin’s dream speech: a psychoanalytic interpretation. Int J Psychoanal. 2003;84:1281-94.
  • 19
    Cohen AS, Mitchell KR, Docherty NM, Horan WP. Vocal expression in schizophrenia: less than meets the ear. J Abnorm Psychol. 2016;125:299-309.
  • 20
    Tagamets MA, Cortes CR, Griego JA, Elvevåg B. Neural correlates of the relationship between discourse coherence and sensory monitoring in schizophrenia. Cortex. 2014;55:77-87.
  • 21
    Hagoort P. Nodes and networks in the neural architecture for language: Broca’s region and beyond. Curr Opin Neurobiol. 2014;28:136-41.
  • 22
    Xiang HD, Fonteijn HM, Norris DG, Hagoort P. Topographical functional connectivity pattern in the perisylvian language networks. Cereb Cortex. 2010;20:549-60.
  • 23
    Sabb FW, van Erp TG, Hardt ME, Dapretto M, Caplan R, Cannon TD, et al. Language network dysfunction as a predictor of outcome in youth at clinical high risk for psychosis. Schizophr Res. 2010;116:173-83.
  • 24
    Collin G, Seidman LJ, Keshavan MS, Stone WS, Qi Z, Zhang T, et al. Functional connectome organization predicts conversion to psychosis in clinical high-risk youth from the SHARP program. Mol Psychiatry. 2018 Nov 8. doi: http://10.1038/s41380-018-0288-x [Epub ahead of print]
    » http://10.1038/s41380-018-0288-x
  • 25
    Kuperberg GR, West WC, Lakshmanan BM, Goff D. Functional magnetic resonance imaging reveals neuroanatomical dissociations during semantic integration in schizophrenia. Biol Psychiatry. 2008;64:407-18.
  • 26
    Bedi G, Carrillo F, Cecchi GA, Slezak DF, Sigman M, Mota NB, et al. Automated analysis of free speech predicts psychosis onset in high-risk youths. NPJ Schizophr. 2015;1:15030.
  • 27
    Elvevåg B, Foltz PW, Weinberger DR, Goldberg TE. Quantifying incoherence in speech: an automated methodology and novel application to schizophrenia. Schizophr Res. 2007;93:304-16.
  • 28
    Cross-Disorder Group of the Psychiatric Genomics Consortium, Lee SH, Ripke S, Neale BM, Faraone SV, Purcell SM, et al. Genetic relationship between five psychiatric disorders estimated from genome-wide SNPs. Nat Genet. 2013;45:984-94.
  • 29
    Cross-Disorder Group of the Psychiatric Genomics Consortium. Identification of risk loci with shared effects on five major psychiatric disorders: a genome-wide analysis. Lancet. 2013;381:1371-9.
  • 30
    Geschwind DH, Flint J. Genetics and genomics of psychiatric disease. Science. 2015;349:1489-94.
  • 31
    Wagenaar BH, Cumbe V, Raunig-Berhó M, Rao D, Kohrt BA, Stergachis A, et al. Outpatient mental health services in Mozambique: use and treatments [Internet]. 2016 Feb 1 [cited 2020 Mar 12]. http://ps.psychiatryonline.org/doi/full/10.1176/appi.ps.201500508
    » http://ps.psychiatryonline.org/doi/full/10.1176/appi.ps.201500508
  • 32
    Morrison AP, French P, Walford L, Lewis SW, Kilcommons A, Green J, et al. Cognitive therapy for the prevention of psychosis in people at ultra-high risk: randomised controlled trial. Br J Psychiatry. 2004;185:291-7.
  • 33
    Bearden CE, Wu KN, Caplan R, Cannon TD. Thought disorder and communication deviance as predictors of outcome in youth at clinical high risk for psychosis. J Am Acad Child Adolesc Psychiatry. 2011;50:669-80.
  • 34
    Lenert LA, Sturley AP, Rapaport MH, Chavez S, Mohr PE, Rupnow M. Public preferences for health states with schizophrenia and a mapping function to estimate utilities from positive and negative symptom scale scores. Schizophr Res. 2004;71:155-65.
  • 35
    van Os J, Linscott RJ, Myin-Germeys I, Delespaul P, Krabbendam L. A systematic review and meta-analysis of the psychosis continuum: evidence for a psychosis proneness-persistence-impairment model of psychotic disorder. Psychol Med. 2009;39:179-95.
  • 36
    Conrad AM, Lewin TJ, Sly KA, Schall U, Halpin SA, Hunter M, et al. Utility of risk-status for predicting psychosis and related outcomes: evaluation of a 10-year cohort of presenters to a specialised early psychosis community mental health service. Psychiatry Res. 2017;247:336-44.
  • 37
    Preti A, Cella M. Randomized-controlled trials in people at ultra high risk of psychosis: a review of treatment effectiveness. Schizophr Res. 2010;123:30-6.
  • 38
    Morrison AP, French P, Parker S, Roberts M, Stevens H, Bentall RP, et al. Three-year follow-up of a randomized controlled trial of cognitive therapy for the prevention of psychosis in people at ultrahigh risk. Schizophr Bull. 2007;33:682-7.
  • 39
    Schmidt SJ, Schultze-Lutter F, Schimmelmann BG, Maric NP, Salokangas RK, Riecher-Rössler A, et al. EPA guidance on the early intervention in clinical high risk states of psychoses. Eur Psychiatry. 2015;30:388-404.
  • 40
    Polari A, Lavoie S, Yuen HP, Amminger P, Berger G, Chen E, et al. Clinical trajectories in the ultra-high risk for psychosis population. Schizophr Res. 2018;197:550-6.
  • 41
    Palaniyappan L, Mota NB, Oowise S, Balain V, Copelli M, Ribeiro S, et al. Speech structure links the neural and socio-behavioural correlates of psychotic disorders. Prog Neuropsychopharmacol Biol Psychiatry. 2019;88:112-20.
  • 42
    Pauselli L, Halpern B, Cleary SD, Ku B, Covington MA, Compton MT. Computational linguistic analysis applied to a semantic fluency task to measure derailment and tangentiality in schizophrenia. Psychiatry Res. 2018;263:74-9.
  • 43
    Minor KS, Willits JA, Marggraf MP, Jones MN, Lysaker PH. Measuring disorganized speech in schizophrenia: automated analysis explains variance in cognitive deficits beyond clinician-rated scales. Psychol Med. 2019;49:440-8.
  • 44
    Gupta T, Hespos SJ, Horton WS, Mittal VA. Automated analysis of written narratives reveals abnormalities in referential cohesion in youth at ultra high risk for psychosis. Schizophr Res. 2018;192:82-8.
  • 45
    Corcoran CM, Carrillo F, Fernández-Slezak D, Bedi G, Klim C, Javitt DC, et al. Prediction of psychosis across protocols and risk cohorts using automated language analysis. World Psychiatry. 2018;17:67-75.
  • 46
    Hong K, Nenkova A, March ME, Parker AP, Verma R, KohlerCG. Lexical use in emotional autobiographical narratives of persons with schizophrenia and healthy controls. Psychiatry Res. 2015;225:40-9.
  • 47
    Buck B, Penn DL. Lexical characteristics of emotional narratives in schizophrenia: relationships with symptoms, functioning, and social cognition. J Nerv Ment Dis. 2015;203:702-8.
  • 48
    Bonfils KA, Luther L, Firmin RL, Lysaker PH, Minor KS, Salyers MP. Language and hope in schizophrenia-spectrum disorders. Psychiatry Res. 2016;245:8-14.
  • 49
    Moe AM, Breitborde NJ, Shakeel MK, Gallagher CJ, Docherty NM. Idea density in the life-stories of people with schizophrenia: associations with narrative qualities and psychiatric symptoms. Schizophr Res. 2016;172:201-5.
  • 50
    Fineberg SK, Leavitt J, Deutsch-Link S, Dealy S, Landry CD, Pirruccio K, et al. Self-reference in psychosis and depression: a language marker of illness. Psychol Med. 2016;46:2605-15.
  • 51
    Mota NB, Resende A, Mota-Rolim SA, Copelli M, Ribeiro S. Psychosis and the control of lucid dreaming. Front Psychol. 2016;7:294.
  • 52
    Elvevåg B, Foltz PW, Rosenstein M, Delisi LE. An automated method to analyze language use in patients with schizophrenia and their first-degree relatives. J Neurolinguistics. 2010;23:270-84.
  • 53
    Rosenstein M, Diaz-Asper C, Foltz PW, Elvevåg B. A computational language approach to modeling prose recall in schizophrenia. Cortex. 2014;55:148-66.
  • 54
    Mota NB, Vasconcelos N, Lemos N, Pieretti AC, Kinouchi O, Cecchi GA, et al. Speech graphs provide a quantitative measure of thought disorder in psychosis. PLoS One. 2012;7:e34928.
  • 55
    Thomas P, Romme M, Hamelijnck J. Psychiatry and the politics of the underclass. Br J Psychiatry. 1996;169:401-4.
  • 56
    García-Laredo E, Maestú F, Castellanos MÁ, Molina JD, Peréz-Moreno E. The relationship between educational years and Phonemic Verbal Fluency (PVF) and Semantic Verbal Fluency (SVF) tasks in Spanish patients diagnosed with schizophrenia, bipolar disorder, and psychotic bipolar disorder. Medicine (Baltimore). 2015;94:e1596.
  • 57
    Buck B, Minor KS, Lysaker PH. Lexical characteristics of anticipatory and consummatory anhedonia in schizophrenia: a study of language in spontaneous life narratives. J Clin Psychol. 2015;71:696-706.
  • 58
    Buck B, Minor KS, Lysaker PH. Differential lexical correlates of social cognition and metacognition in schizophrenia; a study of spontaneously-generated life narratives. Compr Psychiatry. 2015;58:138-45.
  • 59
    Holshausen K, Harvey PD, Elvevåg B, Foltz PW, Bowie CR. Latent semantic variables are associated with formal thought disorder and adaptive behavior in older inpatients with schizophrenia. Cortex. 2014;55:88-96.
  • 60
    Nicodemus KK, Elvevåg B, Foltz PW, Rosenstein M, Diaz-Asper C, Weinberger DR. Category fluency, latent semantic analysis and schizophrenia: a candidate gene approach. Cortex. 2014;55:182-91.
  • 61
    Cabana Á, Valle-Lisboa JC, Elvevåg B, Mizraji E. Detecting order-disorder transitions in discourse: iImplications for schizophrenia. Schizophr Res. 2011;131:157-64.
  • 62
    Shakeel MK, Halahalli HN, Kumar K, Jain S, John JP. Utility of a computerized, paced semantic verbal fluency paradigm in differentiating schizophrenia and healthy subjects. Asian J Psychiatr. 2014;7:22-7.
  • 63
    Schneider C. Die Psychologie der Schizophrenen: und ihre Bedeutung für die Klinik der Schizophrenie. Stuttgart: G. Thieme; 1930.
  • 64
    Montague PR, Dolan RJ, Friston KJ, Dayan P. Computational psychiatry. Trends Cogn Sci. 2012;16:72-80.
  • 65
    Iter D, Yoon J, Jurafsky D. Automatic detection of incoherent speech for diagnosing schizophrenia. In: Loveys K, Niederhoffer K, Prud’hommeaux E, Resnik R, Resnik F, editors. Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: from Keyboard to Clinic; 2018; New Orleans, USA. Stroudsburg: Association for Computational Linguistics; 2018. p. 136-46.
  • 66
    Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space [Internet]. [cited 2020 Feb 12]. http://arxiv.org/pdf/1301.3781.pdf
    » http://arxiv.org/pdf/1301.3781.pdf
  • 67
    Nelson B, Yuen HP, Wood SJ, Lin A, Spiliotacopoulos D, Bruxner A, et al. Long-term follow-up of a group at ultra high risk (“Prodromal”) for psychosis: the PACE 400 study. JAMA Psychiatry. 2013;70:793-802.
  • 68
    Powers AR, Mathys C, Corlett PR. Pavlovian conditioning-induced hallucinations result from overweighting of perceptual priors. Science. 2017;357:596-600.
  • 69
    Nickel M, Kiela D. Poincaré embeddings for learning hierarchical representations. Adv Neural Inf Process Syst. 2017:6338-47.

Publication Dates

  • Publication in this collection
    17 Apr 2020
  • Date of issue
    Nov-Dec 2020

History

  • Received
    23 Sept 2019
  • Accepted
    23 Jan 2020
Associação Brasileira de Psiquiatria Rua Pedro de Toledo, 967 - casa 1, 04039-032 São Paulo SP Brazil, Tel.: +55 11 5081-6799, Fax: +55 11 3384-6799, Fax: +55 11 5579-6210 - São Paulo - SP - Brazil
E-mail: editorial@abp.org.br