Cross-Platform Detection of Psychiatric Hospitalization via Social Media Data: Comparison Study.

BACKGROUND: Previous research has shown the feasibility of using machine learning models trained on social media data from a single platform (eg, Facebook or Twitter) to distinguish individuals either with a diagnosis of mental illness or experiencing an adverse outcome from healthy controls. However, the performance of such models on data from novel social media platforms unseen in the training data (eg, Instagram and TikTok) has not been investigated in previous literature. OBJECTIVE: Our study examined the feasibility of building machine learning classifiers that can effectively predict an upcoming psychiatric hospitalization given social media data from platforms unseen in the classifiers' training data despite the preliminary evidence on identity fragmentation on the investigated social media platforms. METHODS: Windowed timeline data of patients with a diagnosis of schizophrenia spectrum disorder before a known hospitalization event and healthy controls were gathered from 3 platforms: Facebook (254/268, 94.8% of participants), Twitter (51/268, 19% of participants), and Instagram (134/268, 50% of participants). We then used a 3 × 3 combinatorial binary classification design to train machine learning classifiers and evaluate their performance on testing data from all available platforms. We further compared results from models in intraplatform experiments (ie, training and testing data belonging to the same platform) to those from models in interplatform experiments (ie, training and testing data belonging to different platforms). Finally, we used Shapley Additive Explanation values to extract the top predictive features to explain and compare the underlying constructs that predict hospitalization on each platform. RESULTS: We found that models in intraplatform experiments on average achieved an F1-score of 0.72 (SD 0.07) in predicting a psychiatric hospitalization because of schizophrenia spectrum disorder, which is 68% higher than the average of models in interplatform experiments at an F1-score of 0.428 (SD 0.11). When investigating the key drivers for divergence in construct validities between models, an analysis of top features for the intraplatform models showed both low predictive feature overlap between the platforms and low pairwise rank correlation (<0.1) between the platforms' top feature rankings. Furthermore, low average cosine similarity of data between platforms within participants in comparison with the same measurement on data within platforms between participants points to evidence of identity fragmentation of participants between platforms. CONCLUSIONS: We demonstrated that models built on one platform's data to predict critical mental health treatment outcomes such as hospitalization do not generalize to another platform. In our case, this is because different social media platforms consistently reflect different segments of participants' identities. With the changing ecosystem of social media use among different demographic groups and as web-based identities continue to become fragmented across platforms, further research on holistic approaches to harnessing these diverse data sources is required.

An Open Trial of Telephone-Delivered Mindfulness-Based Cognitive Therapy: Feasibility, Acceptability, and Preliminary Efficacy for Reducing Depressive Symptoms.

Mindfulness-based cognitive therapy (MBCT) is a promising intervention for reducing depressive symptoms in individuals with comorbid chronic disease, but the program's attendance demands make it inaccessible to many who might benefit. We tested the feasibility, acceptability, safety, and preliminary efficacy of an abbreviated, telephone-delivered adaptation of the in-person mindfulness-based cognitive therapy (MBCT-T) program in a sample of patients with depressive symptoms and hypertension. Participants (n = 14; 78.6% female, mean age = 60.6) with mild to moderate depressive symptoms and hypertension participated in the 8-week MBCT-T program. Feasibility was indexed via session attendance and home-based practice completion. Acceptability was indexed via self-reported satisfaction scores. Safety was assessed via reports of symptomatic decline or need for additional mental health treatment. Depressive symptoms (Quick Inventory of Depressive Symptomatology-Self-Report [QIDS-SR]) and anxiety (Hospital Anxiety and Depression Scale-Anxiety subscale; HADS-A) were assessed at baseline and immediately following the intervention. Sixty-four percent of participants (n = 9) attended ≥4 intervention sessions. Seventy-one percent (n = 6) of participants reported completing all assigned formal home practice and 89.2% (n = 8) reported completing all assigned informal practice. Participants were either very satisfied (75%; n = 6) or mostly satisfied (25%; n = 2) with the intervention. There were no adverse events or additional need for mental health treatment. Depressive symptom scores were 4.09 points lower postintervention (p = .004). Anxiety scores were 3.18 points lower postintervention (p = .039). Results support the feasibility, acceptability, safety, and preliminary efficacy of an abbreviated, telephone-delivered version of MBCT for reducing depressive and anxiety symptoms in individuals with co-occurring chronic disease.

Acoustic and Facial Features From Clinical Interviews for Machine Learning-Based Psychiatric Diagnosis: Algorithm Development.

BACKGROUND: In contrast to all other areas of medicine, psychiatry is still nearly entirely reliant on subjective assessments such as patient self-report and clinical observation. The lack of objective information on which to base clinical decisions can contribute to reduced quality of care. Behavioral health clinicians need objective and reliable patient data to support effective targeted interventions. OBJECTIVE: We aimed to investigate whether reliable inferences-psychiatric signs, symptoms, and diagnoses-can be extracted from audiovisual patterns in recorded evaluation interviews of participants with schizophrenia spectrum disorders and bipolar disorder. METHODS: We obtained audiovisual data from 89 participants (mean age 25.3 years; male: 48/89, 53.9%; female: 41/89, 46.1%): individuals with schizophrenia spectrum disorders (n=41), individuals with bipolar disorder (n=21), and healthy volunteers (n=27). We developed machine learning models based on acoustic and facial movement features extracted from participant interviews to predict diagnoses and detect clinician-coded neuropsychiatric symptoms, and we assessed model performance using area under the receiver operating characteristic curve (AUROC) in 5-fold cross-validation. RESULTS: The model successfully differentiated between schizophrenia spectrum disorders and bipolar disorder (AUROC 0.73) when aggregating face and voice features. Facial action units including cheek-raising muscle (AUROC 0.64) and chin-raising muscle (AUROC 0.74) provided the strongest signal for men. Vocal features, such as energy in the frequency band 1 to 4 kHz (AUROC 0.80) and spectral harmonicity (AUROC 0.78), provided the strongest signal for women. Lip corner-pulling muscle signal discriminated between diagnoses for both men (AUROC 0.61) and women (AUROC 0.62). Several psychiatric signs and symptoms were successfully inferred: blunted affect (AUROC 0.81), avolition (AUROC 0.72), lack of vocal inflection (AUROC 0.71), asociality (AUROC 0.63), and worthlessness (AUROC 0.61). CONCLUSIONS: This study represents advancement in efforts to capitalize on digital data to improve diagnostic assessment and supports the development of a new generation of innovative clinical tools by employing acoustic and facial data analysis.

Evaluation of the Psychometric Properties of the Five Facet of Mindfulness Questionnaire.

OBJECTIVE: The Five Facet of Mindfulness Questionnaire (FFMQ) is widely used to assess mindfulness. The present study provides a psychometric evaluation of the FFMQ that includes item response theory (IRT) analyses and evaluation of item characteristic curves. METHOD: We administered the FFMQ, the Beck Depression Inventory-II, the Ruminative Response Scale, and the Emotion Regulation Questionnaire to a heterogenous sample of 240 community-based adults. We estimated internal consistency reliability, item-scale correlations, categorical confirmatory factor analysis, and IRT graded response models for the FFMQ. We also estimated correlations among the FFMQ scales and correlations with the other measures included in the study. RESULTS: Internal consistency reliabilities for the five FFMQ scales were 0.82 or higher. A five-factor categorical model fit the data well. IRT-estimated item characteristic curves indicated that the five response options were monotonically ordered for most of the items. Product-moment correlations between simple-summated scoring and IRT scoring of the scales were 0.97 or higher. CONCLUSIONS: The FFMQ accurately identifies varying levels of trait mindfulness. IRT-derived estimates will inform future adaptations to the FFMQ (e.g., briefer versions) and the development of future mindfulness instruments.

Correlates of Physical Activity and Cardiorespiratory Fitness in Racially and Ethnically Diverse People with Serious Mental Illness in Supportive Housing.

We examined demographic, health, and mental health correlates of physical activity and cardiorespiratory fitness (CRF) in racially and ethnically diverse people with serious mental illness (SMI) living in supportive housing. We used baseline data from 314 people with SMI enrolled in a randomized effectiveness trial of a peer-led healthy lifestyle intervention. Sedentary behavior and physical activity were measured with the International Physical Activity Questionnaire. CRF was measured with the 6-min walking test (6MWT). Correlates were identified via ordinary least squares and logistic regressions. Participants were mostly male and racial/ethnic minorities. Thirty-four percent engaged in at least 150-min-per-week of at least moderate-intensity physical activity. On average, participants walked 316.8 m in the 6MWT. Our models show that physical activity and CRF were not evenly distributed in racially and ethnically diverse people with SMI and are associated with multiple demographic, mental health, and health factors. Our findings suggest subgroups and factors that can be targeted to develop health interventions to improve the physical health of people with SMI.