Automated Detection of Cognitive Distortions in Text Exchanges Between Clinicians and People With Serious Mental Illness.

OBJECTIVE: The authors tested whether natural language processing (NLP) methods can detect and classify cognitive distortions in text messages between clinicians and people with serious mental illness as effectively as clinically trained human raters. METHODS: Text messages (N=7,354) were collected from 39 clients in a randomized controlled trial of a 12-week texting intervention. Clinical annotators labeled messages for common cognitive distortions: mental filtering, jumping to conclusions, catastrophizing, "should" statements, and overgeneralizing. Multiple NLP classification methods were applied to the same messages, and performance was compared. RESULTS: A tuned model that used bidirectional encoder representations from transformers (F1=0.62) achieved performance comparable to that of clinical raters in classifying texts with any distortion (F1=0.63) and superior to that of other models. CONCLUSIONS: NLP methods can be used to effectively detect and classify cognitive distortions in text exchanges, and they have the potential to inform scalable automated tools for clinical support during message-based care for people with serious mental illness.

Validation of the Emotional Tone Index for Families (ETIF): A Multi-Informant Measure of Emotional Closeness.

Despite the importance of emotional closeness (EC) in families, few researchers have accurately measured the construct in a systemic way. Additionally, existing measures rely on ratings from one informant, typically the mother, to provide information on closeness within the entire family system. We examined EC in 140 individuals (37 families) using the Emotional Tone Index for Families (ETIF), a novel, multi-informant measure that obtains bidirectional information about EC within every family relationship. The parent identified as most familiar with the family also completed two widely used single-informant measures: The McMaster Family Assessment Device and the Family Adaptability and Cohesion Evaluation Scales, version IV. The ETIF exhibited good test-retest reliability, high internal consistency, and concurrent validity with the single-informant measures. Though the primary respondent scores correlated highly with overall family closeness, results revealed only a modest association between closeness ratings within each dyad and parents rated higher levels of closeness toward their children than children rated closeness toward parents. These findings suggest that ratings from multiple informants provide valuable information about discrepancies in perceived closeness between family members and other complex family dynamics that cannot be captured by single-informant measures. Limitations, future directions, and implications for practice are discussed.

A pesar de la importancia de la cercanía emocional en las familias, pocos investigadores han medido con precisión el constructo de una manera sistémica. Además, las herramientas de medición existentes dependen de las valoraciones de un informante, normalmente la madre, para proporcionar información sobre la cercanía dentro de todo el sistema familiar. Analizamos la cercanía emocional en 140 personas (37 familias) usando el Índice de Tono Emocional para las Familias (ITEF), una herramienta de medición novedosa que obtiene información bidireccional sobre la cercanía emocional dentro de cada relación familiar por parte de varios informantes. El progenitor identificado como el más familiarizado con la familia también completó dos evaluaciones de un solo informante ampliamente utilizadas: el Dispositivo de McMaster de Evaluación Familiar (McMaster Family Assessment Device) y las Escalas de Evaluación de la Cohesión y la Adaptabilidad Familiar (Family Adapatability and Cohesion Evaluation Scales), versión IV. El ITEF demostró buena fiabilidad de prueba-reprueba, una alta coherencia interna y validez simultánea con las evaluaciones de un solo informante. Aunque los puntajes del encuestado principal se correlacionaron en gran medida con la cercanía familiar general, los resultados revelaron solo una asociación modesta entre las valoraciones de cercanía dentro de cada díada, y los padres indicaron niveles más altos de cercanía hacia sus hijos de lo que los hijos lo hicieron hacia sus padres. Estos resultados sugieren que las valoraciones de varios informantes proporcionan información valiosa acerca de las discrepancias en la cercanía percibida entre los miembros de la familia y otra dinámica familiar compleja que no puede captarse mediante las mediciones de un solo informante. Se explican las limitaciones, las futuras direcciones y las implicancias para la práctica.

Augmenting Evidence-Based Care With a Texting Mobile Interventionist: A Pilot Randomized Controlled Trial.

OBJECTIVE: This study aimed to evaluate the feasibility and clinical utility of training intensive psychiatric community care team members to serve as "mobile interventionists" who engage patients in recovery-oriented texting exchanges. METHODS: A 3-month pilot randomized controlled trial was conducted to compare the mobile interventionist approach as an add-on to assertive community treatment (ACT) versus ACT alone. Participants were 49 individuals with serious mental illness (62% with schizophrenia/schizoaffective disorder, 24% with bipolar disorder, and 14% with depression). Clinical outcomes were evaluated at baseline, posttreatment, and 6-month follow-up, and satisfaction was evaluated posttreatment. RESULTS: The intervention appeared feasible (95% of participants assigned to the mobile interventionist arm initiated the intervention, texting on 69% of possible days and averaging four messages per day), acceptable (91% reported satisfaction), and safe (no adverse events reported). Exploratory posttreatment clinical effect estimations suggested greater reductions in the severity of paranoid thoughts (Cohen's d=-0.61) and depression (d=-0.59) and improved illness management (d=0.31) and recovery (d=0.23) in the mobile interventionist group. CONCLUSIONS: Augmentation of care with a texting mobile interventionist proved to be feasible, acceptable, safe, and clinically promising. The findings are encouraging given the relative ease of training practitioners to serve as mobile interventionists, the low burden placed on patients and practitioners, and the simplicity of the technology. The technical resources are widely accessible to patients and practitioners, boding well for potential intervention scalability. When pandemics such as COVID-19 block the possibility of in-person patient-provider contact, evidence-based texting interventions can serve a crucial role in supporting continuity of care.

Listeners prefer the laughs of children with autism to those of typically developing children.

The purpose of this study was to investigate the impact of laugh sounds produced by 8- to 10-year-old children with and without autism on naïve listeners, and to evaluate if listeners could distinguish between the laughs of the two groups. Results showed that listeners rated the laughs of children with autism more positively than the laughs of typically developing children, and that they were slightly above chance levels at judging which group produced the laugh. A subset of participants who reported listening for "uncontrolled" or "longer" laughs were significantly better at discriminating between the laughs of the two groups. Our results suggest that the laughs of children with autism have the potential to promote the formation of relationships.

Laughter differs in children with autism: an acoustic analysis of laughs produced by children with and without the disorder.

Few studies have examined vocal expressions of emotion in children with autism. We tested the hypothesis that during social interactions, children diagnosed with autism would exhibit less extreme laugh acoustics than their nonautistic peers. Laughter was recorded during a series of playful interactions with an examiner. Results showed that children with autism exhibited only one type of laughter, whereas comparison participants exhibited two types. No group differences were found for laugh duration, mean fundamental frequency (F(0)) values, change in F(0), or number of laughs per bout. Findings are interpreted to suggest that children with autism express laughter primarily in response to positive internal states, rather than using laughter to negotiate social interactions.

Infants of depressed mothers, although competent learners, fail to learn in response to their own mothers' infant-directed speech.

Depressed mothers use less of the exaggerated prosody that is typical of infant-directed (ID) speech than do nondepressed mothers. We investigated the consequences of this reduced perceptual salience in ID speech for infant learning. Infants of nondepressed mothers readily learned that their mothers' speech signaled a face, whereas infants of depressed mothers failed to learn that their mothers' speech signaled the face. Infants of depressed mothers did, however, show strong learning in response to speech produced by an unfamiliar nondepressed mother. These outcomes indicate that the reduced perceptual salience of depressed mothers' ID speech could lead to deficient learning in otherwise competent learners.