Language as a biomarker in those at high-risk for psychosis

Reflections on the nature of measurement in language-based automated assessments of patients' mental state and cognitive function

Modern advances in computational language processing methods have enabled new approaches to the measurement of mental processes. However, the field has primarily focused on model accuracy in predicting performance on a task or a diagnostic category. Instead the field should be more focused on determining which computational analyses align best with the targeted neurocognitive/psychological functions that we want to assess. In this paper we reflect on two decades of experience with the application of language-based assessment to patients' mental state and cognitive function by addressing the questions of what we are measuring, how it should be measured and why we are measuring the phenomena. We address the questions by advocating for a principled framework for aligning computational models to the constructs being assessed and the tasks being used, as well as defining how those constructs relate to patient clinical states. We further examine the assumptions that go into the computational models and the effects that model design decisions may have on the accuracy, bias and generalizability of models for assessing clinical states. Finally, we describe how this principled approach can further the goal of transitioning language-based computational assessments to part of clinical practice while gaining the trust of critical stakeholders.

Syntactic complexity of spoken language in the diagnosis of schizophrenia: A probabilistic Bayes network model

In the clinical linguistics of schizophrenia, syntactic complexity has received much attention. In this study, we address whether syntactic complexity deteriorates within the six months following the first episode of psychosis in those who develop a diagnosis of schizophrenia. We collected data from a cohort of twenty-six first-episode psychosis and 12 healthy control subjects using the Thought and Language Index interview in response to three pictures from the Thematic Apperception Test at first assessment and after six months (the time of consensus diagnosis). An automated labeling (part-of-speech tagging) for specific syntactic elements calculated large and granular syntactic complexity indices with a focus on clause complexity as a particular case from this spoken language data. Probabilistic reasoning leveraging the conditional independence properties of Bayes networks revealed that consensus diagnosis of schizophrenia predicted a decrease in nominal subjects per clause among individuals with first episode psychosis. From the entire sample, we estimate a 95.4 % probability that a 50 % decrease in mean nominal subjects per clause after six months is explained by the presence of first episode psychosis. Among those with psychosis, a 30 % decrease in this clause-complexity index after six months of experiencing the first episode predicted with 95 % probability a consensus diagnosis of schizophrenia, representing a conditional relationship between a longitudinal decrease in syntactic complexity and a diagnosis of schizophrenia. We conclude that an early drift towards linguistic disorganization/impoverishment of clause complexity-at the granular level of nominal subject per clause-is a distinctive feature of schizophrenia that decreases longitudinally, thus differentiating schizophrenia from other psychotic illnesses with shared phenomenology.

Reflections on measuring disordered thoughts as expressed via language

Thought disorder, as inferred from disorganized and incoherent speech, is an important part of the clinical presentation in schizophrenia. Traditional measurement approaches essentially count occurrences of certain speech events which may have restricted their usefulness. Applying speech technologies in assessment can help automate traditional clinical rating tasks and thereby complement the process. Adopting these computational approaches affords clinical translational opportunities to enhance the traditional assessment by applying such methods remotely and scoring various parts of the assessment automatically. Further, digital measures of language may help detect subtle clinically significant signs and thus potentially disrupt the usual manner by which things are conducted. If proven beneficial to patient care, methods where patients' voice are the primary data source could become core components of future clinical decision support systems that improve risk assessment. However, even if it is possible to measure thought disorder in a sensitive, reliable and efficient manner, there remain many challenges to then translate into a clinically implementable tool that can contribute towards providing better care. Indeed, embracing technology - notably artificial intelligence - requires vigorous standards for reporting underlying assumptions so as to ensure a trustworthy and ethical clinical science.

Progressive changes in descriptive discourse in First Episode Schizophrenia: a longitudinal computational semantics study

Computational semantics, a branch of computational linguistics, involves automated meaning analysis that relies on how words occur together in natural language. This offers a promising tool to study schizophrenia. At present, we do not know if these word-level choices in speech are sensitive to the illness stage (i.e., acute untreated vs. stable established state), track cognitive deficits in major domains (e.g., cognitive control, processing speed) or relate to established dimensions of formal thought disorder. In this study, we collected samples of descriptive discourse in patients experiencing an untreated first episode of schizophrenia and healthy control subjects (246 samples of 1-minute speech; n = 82, FES = 46, HC = 36) and used a co-occurrence based vector embedding of words to quantify semantic similarity in speech. We obtained six-month follow-up data in a subsample (99 speech samples, n = 33, FES = 20, HC = 13). At baseline, semantic similarity was evidently higher in patients compared to healthy individuals, especially when social functioning was impaired; but this was not related to the severity of clinically ascertained thought disorder in patients. Across the study sample, higher semantic similarity at baseline was related to poorer Stroop performance and processing speed. Over time, while semantic similarity was stable in healthy subjects, it increased in patients, especially when they had an increasing burden of negative symptoms. Disruptions in word-level choices made by patients with schizophrenia during short 1-min descriptions are sensitive to interindividual differences in cognitive and social functioning at first presentation and persist over the early course of the illness.

Sch-net: a deep learning architecture for automatic detection of schizophrenia

BACKGROUND

Schizophrenia is a chronic and severe mental disease, which largely influences the daily life and work of patients. Clinically, schizophrenia with negative symptoms is usually misdiagnosed. The diagnosis is also dependent on the experience of clinicians. It is urgent to develop an objective and effective method to diagnose schizophrenia with negative symptoms. Recent studies had shown that impaired speech could be considered as an indicator to diagnose schizophrenia. The literature about schizophrenic speech detection was mainly based on feature engineering, in which effective feature extraction is difficult because of the variability of speech signals.

METHODS

This work designs a novel Sch-net neural network based on a convolutional neural network, which is the first work for end-to-end schizophrenic speech detection using deep learning techniques. The Sch-net adds two components, skip connections and convolutional block attention module (CBAM), to the convolutional backbone architecture. The skip connections enrich the information used for the classification by emerging low- and high-level features. The CBAM highlights the effective features by giving learnable weights. The proposed Sch-net combines the advantages of the two components, which can avoid the procedure of manual feature extraction and selection.

RESULTS

We validate our Sch-net through ablation experiments on a schizophrenic speech data set that contains 28 patients with schizophrenia and 28 healthy controls. The comparisons with the models based on feature engineering and deep neural networks are also conducted. The experimental results show that the Sch-net has a great performance on the schizophrenic speech detection task, which can achieve 97.68% accuracy on the schizophrenic speech data set. To further verify the generalization of our model, the Sch-net is tested on open access LANNA children speech database for specific language impairment detection. The results show that our model achieves 99.52% accuracy in classifying patients with SLI and healthy controls. Our code will be available at https://github.com/Scu-sen/Sch-net .

CONCLUSIONS

Extensive experiments show that the proposed Sch-net can provide aided information for the diagnosis of schizophrenia and specific language impairment.

Higher order language impairments can predict the transition of ultrahigh risk state to psychosis-An empirical study

AIM

Higher order language skills, for example, non-literal language, humour, prosody deal with 'what is meant' and they are necessary for communicative exchange and relationships; No study has investigated their link with conversion to psychosis. The purpose of this study was to determine whether such skills could act as predictors of the onset of psychosis, and compare those of individuals converting and non-converting to psychosis with control of cognitive functions.

METHODS

Seventy-three patients, aged 15 to 32 years, fulfilling ultrahigh risk criteria took part: 14% of whom were receiving antipsychotic drugs. The study was observational, prospective and longitudinal in nature, and scheduled for 60 months. Pragmatic language skills were evaluated using the Polish version of the right hemisphere language battery. The ultrahigh risk (UHR) criteria were evaluated with Comprehensive Assessment of At-Risk Mental States; attention, intelligence and verbal fluency were controlled.

RESULTS

The conversion rate was 25%; converters demonstrated impaired humour comprehension and metaphor explanation abilities; composite score of pragmatic language was associated with a hazard ratio of 6.0 (95% CI 1.8-20.5) and AUC of .73. Verbal fluency was an independent predictor of conversion, but attention and intelligence were not; pragmatic language skills were associated with social function but not with prodromal symptoms.

CONCLUSIONS

The results suggest that deficits in humour comprehension and metaphor explanation could predict conversion to psychosis. These findings could improve diagnosis and create implications for speech and language therapy in UHR groups. Further studies on the mechanisms of pragmatic skills should analyze their relationship with abstract measures and semantic coherence.

Baseline Cortical Thickness Reductions in Clinical High Risk for Psychosis: Brain Regions Associated with Conversion to Psychosis Versus Non-Conversion as Assessed at One-Year Follow-Up in the Shanghai-At-Risk-for-Psychosis (SHARP) Study

OBJECTIVE

To assess cortical thickness (CT) and surface area (SA) of frontal, temporal, and parietal brain regions in a large clinical high risk for psychosis (CHR) sample, and to identify cortical brain abnormalities in CHR who convert to psychosis and in the whole CHR sample, compared with the healthy controls (HC).

METHODS

Magnetic resonance imaging, clinical, and cognitive data were acquired at baseline in 92 HC, 130 non-converters, and 22 converters (conversion assessed at 1-year follow-up). CT and SA at baseline were calculated for frontal, temporal, and parietal subregions. Correlations between regions showing group differences and clinical scores and age were also obtained.

RESULTS

CT but not SA was significantly reduced in CHR compared with HC. Two patterns of findings emerged: (1) In converters, CT was significantly reduced relative to non-converters and controls in the banks of superior temporal sulcus, Heschl's gyrus, and pars triangularis and (2) CT in the inferior parietal and supramarginal gyrus, and at trend level in the pars opercularis, fusiform, and middle temporal gyri was significantly reduced in all high-risk individuals compared with HC. Additionally, reduced CT correlated significantly with older age in HC and in non-converters but not in converters.

CONCLUSIONS

These results show for the first time that fronto-temporo-parietal abnormalities characterized all CHR, that is, both converters and non-converters, relative to HC, while CT abnormalities in converters relative to CHR-NC and HC were found in core auditory and language processing regions.

Understanding communicative intentions in schizophrenia using an error analysis approach

Patients with schizophrenia (SCZ) have a core impairment in the communicative-pragmatic domain, characterized by severe difficulties in correctly inferring the speaker's communicative intentions. While several studies have investigated pragmatic performance of patients with SCZ, little research has analyzed the errors committed in the comprehension of different communicative acts. The present research investigated error patterns in 24 patients with SCZ and 24 healthy controls (HC) during a task assessing the comprehension of different communicative acts, i.e., sincere, deceitful and ironic, and their relationship with the clinical features of SCZ. We used signal detection analysis to quantify participants' ability to correctly detect the speakers' communicative intention, i.e., sensitivity, and their tendency to wrongly perceive a communicative intention when not present, i.e., response bias. Further, we investigated the relationship between sensitivity and response bias, and the clinical features of the disorder, namely symptom severity, pharmacotherapy, and personal and social functioning. The results showed that the ability to infer the speaker's communicative intention is impaired in SCZ, as patients exhibited lower sensitivity, compared to HC, for all the pragmatic phenomena evaluated, i.e., sincere, deceitful, and ironic communicative acts. Further, we found that the sensitivity measure for irony was related to disorganized/concrete symptoms. Moreover, patients with SCZ showed a stronger response bias for deceitful communicative acts compared to HC: when committing errors, they tended to misattribute deceitful intentions more often than sincere and ironic ones. This tendency to misattribute deceitful communicative intentions may be related to the attributional bias characterizing the disorder.

How to do things with (thousands of) words: Computational approaches to discourse analysis in Alzheimer's disease

Natural Language Processing (NLP) is an ever-growing field of computational science that aims to model natural human language. Combined with advances in machine learning, which learns patterns in data, it offers practical capabilities including automated language analysis. These approaches have garnered interest from clinical researchers seeking to understand the breakdown of language due to pathological changes in the brain, offering fast, replicable and objective methods. The study of Alzheimer's disease (AD), and preclinical Mild Cognitive Impairment (MCI), suggests that changes in discourse (connected speech or writing) may be key to early detection of disease. There is currently no disease-modifying treatment for AD, the leading cause of dementia in people over the age of 65, but detection of those at risk of developing the disease could help with the identification and testing of medications which can take effect before the underlying pathology has irreversibly spread. We outline important components of natural language, as well as NLP tools and approaches with which they can be extracted, analysed and used for disease identification and risk prediction. We review literature using these tools to model discourse across the spectrum of AD, including the contribution of machine learning approaches and Automatic Speech Recognition (ASR). We conclude that NLP and machine learning techniques are starting to greatly enhance research in the field, with measurable and quantifiable language components showing promise for early detection of disease, but there remain research and practical challenges for clinical implementation of these approaches. Challenges discussed include the availability of large and diverse datasets, ethics of data collection and sharing, diagnostic specificity and clinical acceptability.

Variability in Language used on Social Media prior to Hospital Visits

Forecasting healthcare utilization has the potential to anticipate care needs, either accelerating needed care or redirecting patients toward care most appropriate to their needs. While prior research has utilized clinical information to forecast readmissions, analyzing digital footprints from social media can inform our understanding of individuals' behaviors, thoughts, and motivations preceding a healthcare visit. We evaluate how language patterns on social media change prior to emergency department (ED) visits and inpatient hospital admissions in this case-crossover study of adult patients visiting a large urban academic hospital system who consented to share access to their history of Facebook statuses and electronic medical records. An ensemble machine learning model forecasted ED visits and inpatient admissions with out-of-sample cross-validated AUCs of 0.64 and 0.70 respectively. Prior to an ED visit, there was a significant increase in depressed language (Cohen's d = 0.238), and a decrease in informal language (d = 0.345). Facebook posts prior to an inpatient admission showed significant increase in expressions of somatic pain (d = 0.267) and decrease in extraverted/social language (d = 0.357). These results are a first step in developing methods to utilize user-generated content to characterize patient care-seeking context which could ultimately enable better allocation of resources and potentially early interventions to reduce unplanned visits.

Applying speech technologies to assess verbal memory in patients with serious mental illness

Verbal memory deficits are some of the most profound neurocognitive deficits associated with schizophrenia and serious mental illness in general. As yet, their measurement in clinical settings is limited to traditional tests that allow for limited administrations and require substantial resources to deploy and score. Therefore, we developed a digital ambulatory verbal memory test with automated scoring, and repeated self-administration via smart devices. One hundred and four adults participated, comprising 25 patients with serious mental illness and 79 healthy volunteers. The study design was successful with high quality speech recordings produced to 92% of prompts (Patients: 86%, Healthy: 96%). The story recalls were both transcribed and scored by humans, and scores generated using natural language processing on transcriptions were comparable to human ratings (R = 0.83, within the range of human-to-human correlations of R = 0.73-0.89). A fully automated approach that scored transcripts generated by automatic speech recognition produced comparable and accurate scores (R = 0.82), with very high correlation to scores derived from human transcripts (R = 0.99). This study demonstrates the viability of leveraging speech technologies to facilitate the frequent assessment of verbal memory for clinical monitoring purposes in psychiatry.

Language disintegration in spontaneous speech in Huntington's disease: a more fine-grained analysis

Huntington's disease (HD) is a neurodegenerative disease causing motor symptoms along with cognitive and affective problems. Recent evidence suggests that HD also affects language across core levels of linguistic organization, including at stages of the disease when standardized neuropsychological test profiles are still normal and motor symptoms do not yet reach clinical thresholds ('pre-manifest HD'). The present study aimed to subject spontaneous speech to a more fine-grained linguistic analysis in a sample of 20 identified HD gene-carriers, 10 with pre-manifest and 10 with early manifest HD. We further explored how language performance related to non-linguistic cognitive impairment, using standardized neuropsychological measures. A distinctive pattern of linguistic impairments marked off participants with both pre-manifest and manifest HD from healthy controls and each other. Fluency patterns in premanifest HD were marked by prolongations, filled pauses, and repetitions, which shifted to a pattern marked by empty (unfilled) pauses, re-phrasings, and truncations in manifest HD. Both HD groups also significantly differed from controls and each other in how they grammatically connected clauses and used noun phrases referentially. Functional deficits in language occurred in pre-manifest HD in the absence of any non-linguistic neuropsychological impairment and did largely not correlate with standardized neuropsychological measures in manifest HD. These results further corroborate that language can act as a fine-grained clinical marker in HD, which can track disease progression from the pre-manifest stage, define critical remediation targets, and inform the role of the basal ganglia in language processing.

Updating verbal fluency analysis for the 21st century: Applications for psychiatry

Evaluating patients' verbal fluency by counting the number of unique words (e.g., animals) produced in a short-period (e.g., 1-3 min) is one of the most widely employed cognitive tests in psychiatric research. We introduce new methods to analyze fluency output that leverage modern computational language technology. This enables moving beyond simple word counts to charting the temporal dynamics of speech and objectively quantifying the semantic relationship of the utterances. These metrics can greatly expand the current psychiatric research toolkit and can help refine clinical theories regarding the nature of putative language differences in patients.

Precision pharmacotherapy: psychiatry's future direction in preventing, diagnosing, and treating mental disorders

Mental disorders account for around one-third of disability worldwide and cause enormous personal and societal burden. Current pharmacotherapies and nonpharmacotherapies do help many patients, but there are still high rates of partial or no response, delayed effect, and unfavorable adverse effects. The current diagnostic taxonomy of mental disorders by the Diagnostic and Statistical Manual of Mental Disorders and the International Classification of Diseases relies on presenting signs and symptoms, but does not reflect evidence from neurobiological and behavioral systems. However, in the last decades, the understanding of biological mechanisms underlying mental disorders has grown and can be used for the development of precision medicine, that is, to deliver a patient-tailored individual treatment. Precision medicine may incorporate genetic variants contributing to the mental disorder and the response to pharmacotherapies, but also consider gene ¥ environment interactions, blood-based markers, neuropsychological tests, data from electronic health records, early life adversity, stressful life events, and very proximal factors such as lifestyle, nutrition, and sport. Methods such as artificial intelligence and the underlying machine learning and deep learning approaches provide the framework to stratify patients, initiate specific tailored treatments and thus increase response rates, reduce adverse effects and medical errors. In conclusion, precision medicine uses measurable health parameters to identify individuals at risk of a mental disorder, to improve the diagnostic process and to deliver a patient-tailored treatment.

The language profile of formal thought disorder

Formal thought disorder (FTD) is clinically manifested as disorganized speech, but there have been only few investigations of its linguistic properties. We examined how disturbance of thought may relate to the referential function of language as expressed in the use of noun phrases (NPs) and the complexity of sentence structures. We used a comic strip description task to elicit language samples from 30 participants with schizophrenia (SZ), 15 with moderate or severe FTD (SZ + FTD), and 15 minimal or no FTD (SZ−FTD), as well as 15 first-degree relatives of people with SZ (FDRs) and 15 neurotypical controls (NC). We predicted that anomalies in the normal referential use of NPs, sub-divided into definite and indefinite NPs, would identify FTD; and also that FTD would also be linked to reduced linguistic complexity as specifically measured by the number of embedded clauses and of grammatical dependents. Participants with SZ + FTD produced more referential anomalies than NC and produced the fewest definite NPs, while FDRs produced the most and thus also differed from NC. When referential anomalies were classed according to the NP type in which they occurred, the SZ + FTD group produced more anomalies in definite NPs than NC. Syntactic errors did not distinguish groups, but the SZ + FTD group exhibited significantly less syntactic complexity than non-SZ groups. Exploratory regression analyses suggested that production of definite NPs distinguished the two SZ groups. These results demonstrate that FTD can be identified in specific grammatical patterns which provide new targets for detection, intervention, and neurobiological studies.

Deficits in nominal reference identify thought disordered speech in a narrative production task

Formal thought disorder (TD) is a neuropathology manifest in formal language dysfunction, but few behavioural linguistic studies exist. These have highlighted problems in the domain of semantics and more specifically of reference. Here we aimed for a more complete and systematic linguistic model of TD, focused on (i) a more in-depth analysis of anomalies of reference as depending on the grammatical construction type in which they occur, and (ii) measures of formal grammatical complexity and errors. Narrative speech obtained from 40 patients with schizophrenia, 20 with TD and 20 without, and from 14 healthy controls matched on pre-morbid IQ, was rated blindly. Results showed that of 10 linguistic variables annotated, 4 showed significant differences between groups, including the two patient groups. These all concerned mis-uses of noun phrases (NPs) for purposes of reference, but showed sensitivity to how NPs were classed: definite and pronominal forms of reference were more affected than indefinite and non-pronominal (lexical) NPs. None of the measures of formal grammatical complexity and errors distinguished groups. We conclude that TD exhibits a specific and differentiated linguistic profile, which can illuminate TD neuro-cognitively and inform future neuroimaging studies, and can have clinical utility as a linguistic biomarker.

Using Shakespeare's Sotto Voce to Determine True Identity From Text

Little is known of the private life of William Shakespeare, but he is famous for his collection of plays and poems, even though many of the works attributed to him were published anonymously. Determining the identity of Shakespeare has fascinated scholars for 400 years, and four significant figures in English literary history have been suggested as likely alternatives to Shakespeare for some disputed works: Bacon, de Vere, Stanley, and Marlowe. A myriad of computational and statistical tools and techniques have been used to determine the true authorship of his works. Many of these techniques rely on basic statistical correlations, word counts, collocated word groups, or keyword density, but no one method has been decided on. We suggest that an alternative technique that uses word semantics to draw on personality can provide an accurate profile of a person. To test this claim, we analyse the works of Shakespeare, Christopher Marlowe, and Elizabeth Cary. We use Word Accumulation Curves, Hierarchical Clustering overlays, Principal Component Analysis, and Linear Discriminant Analysis techniques in combination with RPAS, a multi-faceted text analysis approach that draws on a writer's personality, or self to identify subtle characteristics within a person's writing style. Here we find that RPAS can separate the known authored works of Shakespeare from Marlowe and Cary. Further, it separates their contested works, works suspected of being written by others. While few authorship identification techniques identify self from the way a person writes, we demonstrate that these stylistic characteristics are as applicable 400 years ago as they are today and have the potential to be used within cyberspace for law enforcement purposes.

The communicative impairment as a core feature of schizophrenia: Frequency of pragmatic deficit, cognitive substrates, and relation with quality of life

BACKGROUND

Impairments in specific aspects of pragmatic competence, supporting the use of language in context, are largely documented in schizophrenia and might represent an indicator of poor outcome. Yet pragmatics is rarely included in clinical settings. This paper aims to promote a clinical consideration of pragmatics as a target of assessment and intervention. We investigated the frequency of the pragmatic deficit, its cognitive substrates, and the relation with quality of life.

METHODS

Pragmatic abilities were compared in a sample of patients with schizophrenia and healthy controls based on a comprehensive pragmatic test (APACS). We assessed also for psychopathology, cognition, social cognition, and quality of life. We explored the co-occurrence of deficits in different domains, and we used multiple regressions to investigate the effect of cognition and social cognition on pragmatics, and of pragmatics on quality of life.

RESULTS

Pragmatic abilities, especially comprehending discourse and non-literal meanings, were compromised in schizophrenia, with 77% of patients falling below cutoff. Pragmatic deficit co-occurred with cognitive or socio-cognitive deficits in approximately 30% of cases. Multiple regression analysis confirmed the interplay of cognition and social cognition in pragmatic behavior. Quality of life was predicted by symptoms and by pragmatic abilities.

CONCLUSIONS

The high frequency of impairment suggests that the pragmatic deficit is a core feature of schizophrenia, associated with quality of life. Cognitive and socio-cognitive abilities might represent necessary though not sufficient building blocks for the acquisition of pragmatic abilities throughout development. Therefore, a more precise incorporation of pragmatics in the description of the pathology is of high clinical and translational relevance.

An examination of the language construct in NIMH's research domain criteria: Time for reconceptualization!

The National Institute of Mental Health's Research Domain Criteria (RDoC) Initiative "calls for the development of new ways of classifying psychopathology based on dimensions of observable behavior." As a result of this ambitious initiative, language has been identified as an independent construct in the RDoC matrix. In this article, we frame language within an evolutionary and neuropsychological context and discuss some of the limitations to the current measurements of language. Findings from genomics and the neuroimaging of performance during language tasks are discussed in relation to serious mental illness and within the context of caveats regarding measuring language. Indeed, the data collection and analysis methods employed to assay language have been both aided and constrained by the available technologies, methodologies, and conceptual definitions. Consequently, different fields of language research show inconsistent definitions of language that have become increasingly broad over time. Individually, they have also shown significant improvements in conceptual resolution, as well as in experimental and analytic techniques. More recently, language research has embraced collaborations across disciplines, notably neuroscience, cognitive science, and computational linguistics and has ultimately re-defined classical ideas of language. As we move forward, the new models of language with their remarkably multifaceted constructs force a re-examination of the NIMH RDoC conceptualization of language and thus the neuroscience and genetics underlying this concept. © 2016 The Authors. American Journal of Medical Genetics Part B: Neuropsychiatric Genetics Published by Wiley Periodicals, Inc.