Ambulatory digital phenotyping of blunted affect and alogia using objective facial and vocal analysis: Proof of concept

Cohen, Alex S.; Cowan, Tovah; Le, Thanh P.; Schwartz, Elana K.; Kirkpatrick, Brian; Raugh, Ian M.; Chapman, Hannah C.; Strauss, Gregory P.

doi:10.1016/j.schres.2020.03.043

Cited by 39 publications

(28 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Participants included 32 outpatients meeting DSM5 criteria for schizophrenia or schizoaffective disorder (SZ) and 31 healthy controls (CN). Participants with SZ were originally recruited for studies investigating mechanisms of negative symptoms that occurred prior to the COVID-19 pandemic [3,11,12,51]. Original recruitment occurred at outpatient mental health clinics in northeast Georgia, USA and online or printed advertisements.…”

Section: Samplementioning

confidence: 99%

The impact of the COVID-19 pandemic on negative symptoms in individuals at clinical high-risk for psychosis and outpatients with chronic schizophrenia

Strauss

Macdonald

Ruiz

et al. 2021

Eur Arch Psychiatry Clin Neurosci

Self Cite

View full text Add to dashboard Cite

Negative symptoms are core features of schizophrenia-spectrum disorders that are frequently observed across all phases of illness. By their nature, COVID-19 social isolation, physical distancing, and health precautions induce behavioural aspects of negative symptoms. However, it is unclear whether these prevention measures also lead to increases in experiential negative symptoms, whether such effects are equivalent across individual negative symptom domains, and if exacerbations occur equivalently across phases of illness. The current study compared negative symptom severity scores obtained during the pandemic to pre-pandemic assessments in two samples: (1) outpatients with chronic schizophrenia (SZ: n = 32) and matched healthy controls (CN: n = 31) and (2) individuals at clinical high risk for psychosis (CHR: n = 25) and matched CN (n = 30). Pre-pandemic ratings of negative symptoms were clinically elevated in SZ and CHR groups, which did not differ from each other in severity. In SZ, ratings obtained during the pandemic were significantly higher than pre-pandemic ratings for all 5 domains (alogia, blunted affect, anhedonia, avolition, and asociality) and item-level analyses indicated that exacerbations occurred on both experiential and behavioral symptoms of anhedonia, avolition, and asociality. In contrast, CHR only exhibited increases in anhedonia and avolition items during the pandemic compared to pre-ratings. Findings suggest that negative symptoms should be a critical treatment target during and after the pandemic in the schizophrenia spectrum given that they are worsening and critically related to risk for conversion, functional outcome, and recovery.

show abstract

Section: Samplementioning

confidence: 99%

The impact of the COVID-19 pandemic on negative symptoms in individuals at clinical high-risk for psychosis and outpatients with chronic schizophrenia

Strauss

Macdonald

Ruiz

et al. 2021

Eur Arch Psychiatry Clin Neurosci

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus, thought disorder in psychosis has often been equated with speech disturbance 6 . Novel digital phenotyping and computerized natural language processing (NLP) methods offer the opportunity to capture speech in ecologically valid settings and automatically quantify objective parameters that reflect underlying thought disturbance 7 . This would enable substantial advancements in assessment and monitoring of treatment response and could be used in research to probe more deeply into the psychosis disease process.…”

Section: Introductionmentioning

confidence: 99%

“…Cohesion was not significantly reduced in another study comparing first-episode psychosis and healthy control (HC) participants 23 . Multiple levels of acoustic and linguistic analysis were shown to have a poor correlation with clinician ratings for negative symptoms 7 . In general, despite seemingly straightforward analogies between acoustic features like pitch variability and pause duration with negative symptoms like affective flattening and alogia, NLP measures have shown poor ability to track negative symptoms, including affective flattening and alogia 24 .…”

Section: Introductionmentioning

confidence: 99%

Natural language processing methods are sensitive to sub-clinical linguistic differences in schizophrenia spectrum disorders

et al. 2021

View full text Add to dashboard Cite

Computerized natural language processing (NLP) allows for objective and sensitive detection of speech disturbance, a hallmark of schizophrenia spectrum disorders (SSD). We explored several methods for characterizing speech changes in SSD (n = 20) compared to healthy control (HC) participants (n = 11) and approached linguistic phenotyping on three levels: individual words, parts-of-speech (POS), and sentence-level coherence. NLP features were compared with a clinical gold standard, the Scale for the Assessment of Thought, Language and Communication (TLC). We utilized Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art embedding algorithm incorporating bidirectional context. Through the POS approach, we found that SSD used more pronouns but fewer adverbs, adjectives, and determiners (e.g., “the,” “a,”). Analysis of individual word usage was notable for more frequent use of first-person singular pronouns among individuals with SSD and first-person plural pronouns among HC. There was a striking increase in incomplete words among SSD. Sentence-level analysis using BERT reflected increased tangentiality among SSD with greater sentence embedding distances. The SSD sample had low speech disturbance on average and there was no difference in group means for TLC scores. However, NLP measures of language disturbance appear to be sensitive to these subclinical differences and showed greater ability to discriminate between HC and SSD than a model based on clinical ratings alone. These intriguing exploratory results from a small sample prompt further inquiry into NLP methods for characterizing language disturbance in SSD and suggest that NLP measures may yield clinically relevant and informative biomarkers.

show abstract

“…The latter data can be scaled and compared as a function of both time and context. In part, the limitations of clinical tests in this regard reflect the fact that they rarely provide ratio level data (i.e., data with an absolute zero and equal/definite ratio between data points) nor specify how these data fluctuate over defined periods of time or over clearly-operationalized spatial contexts [see (8,(23)(24)(25) for elaboration]. Consequently, they are often unable to quantify isolated channels associated with the clinical construct (i.e., poor spectral resolution), beyond general global domains associated with their factor structures.…”

Section: Resolution and Clinical Psychometricsmentioning

confidence: 99%

“…MLM can accommodate data with a "nested" structure, such that observations are hierarchically organized within individuals, settings, and times/days. MLM, for example, has been used to understand how acoustics and facial features change as a function of time, social context and setting in schizophrenia (24,(84)(85)(86).…”

Section: How Should Resolution Be Addressed?mentioning

confidence: 99%

Validating Biobehavioral Technologies for Use in Clinical Psychiatry

et al. 2021

Self Cite

View full text Add to dashboard Cite

The last decade has witnessed the development of sophisticated biobehavioral and genetic, ambulatory, and other measures that promise unprecedented insight into psychiatric disorders. As yet, clinical sciences have struggled with implementing these objective measures and they have yet to move beyond “proof of concept.” In part, this struggle reflects a traditional, and conceptually flawed, application of traditional psychometrics (i.e., reliability and validity) for evaluating them. This paper focuses on “resolution,” concerning the degree to which changes in a signal can be detected and quantified, which is central to measurement evaluation in informatics, engineering, computational and biomedical sciences. We define and discuss resolution in terms of traditional reliability and validity evaluation for psychiatric measures, then highlight its importance in a study using acoustic features to predict self-injurious thoughts/behaviors (SITB). This study involved tracking natural language and self-reported symptoms in 124 psychiatric patients: (a) over 5–14 recording sessions, collected using a smart phone application, and (b) during a clinical interview. Importantly, the scope of these measures varied as a function of time (minutes, weeks) and spatial setting (i.e., smart phone vs. interview). Regarding reliability, acoustic features were temporally unstable until we specified the level of temporal/spatial resolution. Regarding validity, accuracy based on machine learning of acoustic features predicting SITB varied as a function of resolution. High accuracy was achieved (i.e., ~87%), but only when the acoustic and SITB measures were “temporally-matched” in resolution was the model generalizable to new data. Unlocking the potential of biobehavioral technologies for clinical psychiatry will require careful consideration of resolution.

show abstract

Ambulatory digital phenotyping of blunted affect and alogia using objective facial and vocal analysis: Proof of concept

Cited by 39 publications

References 36 publications

The impact of the COVID-19 pandemic on negative symptoms in individuals at clinical high-risk for psychosis and outpatients with chronic schizophrenia

The impact of the COVID-19 pandemic on negative symptoms in individuals at clinical high-risk for psychosis and outpatients with chronic schizophrenia

Natural language processing methods are sensitive to sub-clinical linguistic differences in schizophrenia spectrum disorders

Validating Biobehavioral Technologies for Use in Clinical Psychiatry

Contact Info

Product

Resources

About