Social isolation is an important social determinant that impacts health outcomes and mortality among patients. The National Academy of Medicine recently recommended that social isolation be documented in electronic health records (EHR). However, social isolation usually is not recorded or obtained as coded data but rather collected from patient self-report or documented in clinical narratives. This study explores the feasibility and effectiveness of natural language processing (NLP) strategy for identifying patients who are socially isolated from clinical narratives. We used data from the Medical University of South Carolina (MUSC) Research Data Warehouse. Patients 18 years-of-age or older who were diagnosed with prostate cancer between January 1, 2014 and May 31, 2017 were eligible for this study. NLP pipelines identifying social isolation were developed via extraction of notes on progress, history and physical, consult, emergency department provider, telephone encounter, discharge summary, plan of care, and radiation oncology. Of 4195 eligible prostate cancer patients, we randomly sampled 3138 patients (75%) as a training dataset. The remaining 1057 patients (25%) were used as a test dataset to evaluate NLP algorithm performance. Standard performance measures for the NLP algorithm, including precision, recall, and F-measure, were assessed by expert manual review using the test dataset. A total of 55,516 clinical notes from 3138 patients were included to develop the lexicon and NLP pipelines for social isolation. Of those, 35 unique patients (1.2%) had social isolation mention(s) in 217 notes. Among 24 terms relevant to social isolation, the most prevalent were “lack of social support,” “lonely,” “social isolation,” “no friends,” and “loneliness”. Among 1057 patients in the test dataset, 17 patients (1.6%) were identified as having social isolation mention(s) in 40 clinical notes. Manual review identified four false positive mentions of social isolation and one false negatives in 154 notes from randomly selected 52 controls. The NLP pipeline demonstrated 90% precision, 97% recall, and 93% F-measure. The major reasons for a false positive included the ambiguities of the experiencer of social isolation, negation, and alternate meaning of words. Our NLP algorithms demonstrate a highly accurate approach to identify social isolation.

The COVID-19 pandemic caused widespread challenges and revealed vulnerabilities across global health care systems. In response, many health care providers turned to telehealth solutions, which have been widely embraced and are likely to become standard for modern care. Immersive extended reality (XR) technologies have the potential to enhance telehealth with greater acceptability, engagement, and presence. However, numerous technical, logistic, and clinical barriers remain to the incorporation of XR technology into telehealth practice. COVID-19 may accelerate the union of XR and telehealth as researchers explore novel solutions to close social distances. In this viewpoint, we highlight research demonstrations of XR telehealth during the COVID-19 pandemic and discuss future directions to make XR the next evolution of remote health care.

Understanding what motivates mental health providers to use telemedicine (i.e., telemental health) is critical for optimizing its uptake, especially during unprecedented times (e.g., the COVID-19 pandemic). Drawing from the Technology Acceptance Model (TAM), this report examined the characteristics of telemental health providers and how the acceptability of telemedicine features contributes to their intention to use the technology more often in practice. Telemental health providers (N = 177) completed an online survey between March and May 2019. Most providers (75%) spent less than 25% of their work-week using telemedicine, but 70% reported an intention to use telemedicine more in the future. The belief that telemedicine affords greater access to patients, work-life balance, flexibility in providing care, and the opportunity to be at the forefront of innovative care were significant predictors of intentions to use the technology more in the future. Other significant predictors included needing assistance to coordinate insurance reimbursements, manage a successful telemedicine practice, and integrate the telemedicine program with other health IT software. Findings have important implications for increasing the frequency of telemedicine use among telemental health providers. Future research and practice should leverage providers’ positive beliefs about telemedicine acceptability and consider their needs to enhance its uptake.

Multi-informant assessments of adult psychopathology often result in discrepancies among informants' reports. Among 157 adults meeting criteria for either the generalized (n = 106) or nongeneralized (n = 51) social anxiety disorder (SAD) subtype, we examined whether discrepancies between patients' and clinicians' reports of patients' symptoms related to variations in both SAD subtype and expressions of social skills deficits across multiple social interaction tasks. Latent class analyses revealed two behavioral patterns: (a) context-specific social skills deficits and (b) cross-context social skills deficits. Similarly, patients' symptom reports could be characterized by concordance or discordance with clinicians' reports. Patient-clinician concordance on relatively high levels of patients' symptoms related to an increased likelihood of the patient meeting criteria for the generalized relative to nongeneralized subtype. Further, patient-clinician concordance on relatively high levels of patients' symptoms related to an increased likelihood of consistently exhibiting social skills deficits across social interaction tasks (relative to context-specific social skills deficits). These relations were robust in accounting for patient age, clinical severity, and Axis I and II comorbidity. Further, clinical severity did not completely explain variability in patients' behavior on laboratory tasks or discrepancies between patient and clinician reports. Findings provide the first laboratory-based support for the ability of informant discrepancies to indicate cross-contextual variability in clinical adult assessments, and the first of any developmental period to indicate this for SAD assessments. These findings have important implications for clinical assessment and developmental psychopathology research.

Although children with social phobia (SP) and selective mutism (SM) present similarly in a clinical setting, it remains unclear whether children with SM are unable to speak due to overwhelming anxiety, or whether withholding speech functions as an avoidance mechanism. A total of 35 children (ages 5-12 years) with either SM ( n = 10), SP ( n = 11), or no diagnosis ( n = 14) participated in the current study. Measurements included clinician, child, and parent ratings as well as behavioral observations and psychophysiological measures. Independent evaluators and clinicians rated children with SM as more severely impaired, more anxious, and less socially effective, but the groups did not differ in self- or parent-reported anxiety. Psychophysiological measures indicated that children in the SM group experienced less arousal than other children during social interaction tasks. The authors postulate that lack of speech may serve as an avoidance mechanism and thus account for this lack of arousal.