Search

Objective Train machine learning models that automatically predict emotional valence of patient and physician in primary care visits. Methods Using transcripts from 353 primary care office visits with 350 patients and 84 physicians (Cook, 2002 [ 1 ], Tai-Seale et al., 2015 [ 2 ]), we developed two machine learning models (a recurrent neural network with a hierarchical structure and a logistic regression classifier) to recognize the emotional valence (positive, negative, neutral) (Posner et al., 2005 [ 3 ]) of each utterance. We examined the agreement of human-generated ratings of emotional valence with machine learning model ratings of emotion. Results The agreement of emotion ratings from the recurrent neural network model with human ratings was comparable to that of human-human inter-rater agreement. The weighted-average of the correlation coefficients for the recurrent neural network model with human raters was 0.60, and the human rater agreement was also 0.60. Conclusions The recurrent neural network model predicted the emotional valence of patients and physicians in primary care visits with similar reliability as human raters. Practice implications As the first machine learning-based evaluation of emotion recognition in primary care visit conversations, our work provides valuable baselines for future applications that might help monitor patient emotional signals, supporting physicians in empathic communication, or examining the role of emotion in patient-centered care.

Spoken language understanding tasks usually rely on pipelines involving complex processing blocks such as voice activity detection, speaker diarization and Automatic speech recognition (ASR). We propose a novel framework for predicting utterance level labels directly from speech features, thus removing the dependency on first generating transcripts, and transcription free behavioral coding. Our classifier uses a pretrained Speech-2-Vector encoder as bottleneck to generate word-level representations from speech features. This pre-trained encoder learns to encode speech features for a word using an objective similar to Word2Vec. Our proposed approach just uses speech features and word segmentation information for predicting spoken utterance-level target labels. We show that our model achieves competitive results to other state-of-the-art approaches which use transcribed text for the task of predicting psychotherapy-relevant behavior codes.

Objective Auditory verbal hallucinations (AVH) are common in multiple clinical populations but also occur in individuals who are otherwise considered healthy. Adopting the National Institute of Mental Health’s Research Domain Criteria (RDoC) framework, the aim of the current study was to integrate a variety of measures to evaluate whether AVH experience varies across clinical and nonclinical individuals. Methods A total of 384 people with AVH from 41 US states participated in the study; 295 participants (77%) who received inpatient, outpatient, or combination treatments for AVH and 89 participants (23%) who never received care. Participants used a multi-modal smartphone data collection system to report on their AVH experiences and co-occurring psychological states multiple times daily, over 30 days. In parallel, smartphone sensors recorded their physical activity, geolocation, and calling and texting behavior continuously. Results The clinical sample experienced AVH more frequently than the nonclinical group and rated their AVH as significantly louder and more powerful. They experienced more co-occurring negative affect and were more socially withdrawn, spending significantly more time at home and significantly less time near other people. Participants with a history of inpatient care also rated their AVH as infused with significantly more negative content. The groups did not differ in their physical activity or use of their smartphones for digital communication. Conclusion Smartphone-assisted remote data collection revealed real-time/real-place phenomenological, affective, and behavioral differences between clinical and nonclinical samples of people who experience AVH. The study provided strong support for the application of RDoC-informed approaches in psychosis research.

Community partners contribute to fostering and sustaining service-learning partnerships. In the service-learning pedagogy, their leadership roles, although identified as partners and co-collaborator, have been under-investigated in the context of their perceptions and contributions. To contribute to the understanding of partners’ collaborative involvement, and leadership strategies, we interviewed four partners from two non-profit agencies that had collaborated on projects with a small liberal arts university for more than six years. The partners described their motivations for committing to the partnership, discussed the perceived benefits of the collaboration, and explained the strategies they implemented to address partnership challenges. We demonstrate that in service-learning collaborations, active community partners exhibit leadership competencies of knowing, being and doing, and they display the five components of leadership success outlined in the Relational Leadership Model: supporting purpose, sustaining process, ensuring ethics, maintaining inclusiveness, and creating empowerment.

Despite high rates of posttraumatic stress disorder (PTSD) and depression among traumatically injured patients, engagement in session-based psychotherapy early after trauma is limited due to various service utilization and readiness barriers. Task-shifting brief mental health interventions to routine trauma center providers is an understudied but potentially critical part of the continuum of care. This pilot study assessed the feasibility of training trauma nurses to engage patients in patient-centered activity scheduling based on a Behavioral Activation paradigm, which is designed to counteract dysfunctional avoidance/withdrawal behavior common among patients after injury. Nurses (N = 4) and patients (N = 40) were recruited from two level II trauma centers. A portion of a one day in-person workshop included didactics, demonstrations, and experiential activities to teach brief intervention delivery. Nurses completed pre- and post-training standardized patient role-plays prior to and two months after training, which were coded for adherence to the intervention. Nurses also completed exit interviews to assess their perspectives on the training and addressing patient mental health concerns. Findings support the feasibility of training trauma nurses in a brief mental health intervention. Task-shifting brief interventions holds promise for reaching more of the population in need of post-trauma mental health care.

OBJECTIVE This commentary summarizes the methods and topics addressed in the special issue of HSR focused on linkage of United States Department of Veterans Affairs (VA) and non-VA datasets. The issue illustrates that researchers are increasingly linking diverse datasets as a valuable method for obtaining outcomes, treatments, and covariates to evaluate and examine health care delivery that includes non-VA services. The issue serves as a reference to VA and non-VA investigators alike who employ data linkage methods to address high-impact clinical and health policy evaluations that span different care systems and different datasets.

Maladaptive emotional reactivity and dysfunctional communication during couple conflict are both destructive to couple functioning, and observational research has elucidated how conflict escalates. However, much of the evidence is based on measures that combine content (i.e., what was said) and the emotion with which it was said, which are then examined using sequential analyses. Despite the general presumptions about underlying emotional reactivity and escalation in negative emotions as part of relationship distress and deterioration, little empirical data are available that directly examine these continuous shifts in emotions. The current study examined concurrent and longitudinal associations between relationship satisfaction and trajectories of change in vocally expressed emotional arousal during couple conflict in 62 couples who participated in a relationship education program. Contrary to expectations and patterns found in distressed couples, trajectories followed a U-shape rather than an inverted U-shape curve, with steeper and more persistent decreases in emotional arousal predicting more stable relationship satisfaction over time. In addition, there were within-couple effects. These results suggest that early signs for relationship deterioration may be less in the form of overt escalation as would be seen in distressed couples. Instead, couples who subsequently deteriorate more are less effective in calming emotional arousal. They also are less able to remain at lower emotional arousal. It is possible that the more pronounced escalation toward the end of the conversation in more at-risk couples is a precursor of the greater escalation patterns seen in distressed couples; this should be examined empirically. Limitations and implications are discussed.La reactividad emocional desadaptativa y la comunicación disfuncional durante el conflicto de pareja son destructivas para el funcionamiento de la pareja, y la investigación observacional ha dilucidado cómo escala el conflicto. Sin embargo, gran parte de la evidencia está basada en mediciones que combinan el contenido (p. ej.: lo que se dijo) y la emoción con la que se dijo, que luego se analizan usando análisis secuenciales. A pesar de las presunciones generales acerca de la reactividad emocional subyacente y la escalada de las emociones negativas como parte del distrés y el deterioro de la relación, existen pocos datos empíricos que analicen directamente estos cambios continuos en las emociones. El presente estudio analizó las asociaciones simultáneas y longitudinales entre la satisfacción con la relación y las trayectorias de cambio en la agitación emocional expresada vocalmente durante el conflicto de pareja en 62 parejas que participaron en un programa de capacitación en relaciones. Contrariamente a las expectativas y los patrones hallados en las parejas problemáticas, las trayectorias siguieron una forma de U en lugar de una curva con forma de U invertida, con disminuciones más pronunciadas y más constantes de la agitación emocional que predicen una satisfacción más estable con la relación en el transcurso del tiempo. Además, hubo efectos dentro de la pareja. Estos resultados sugieren que las primeras señales de deterioro de la relación pueden ser menores en forma de escalada abierta de lo que se vería en las parejas problemáticas. En cambio, las parejas que posteriormente se deterioran más son menos eficaces a la hora de calmar la agitación emocional. También son menos capaces de permanecer en una agitación emocional más baja. Es posible que la escalada más pronunciada hacia el final de la conversación en las parejas con mayor riesgo sea una precursora de los patrones de mayor escalada observados en las parejas problemáticas; esto debería analizarse empíricamente. Se debaten las limitaciones y las consecuencias.伴侣冲突中不适当情绪反应和功能紊乱沟通都对伴侣功能有破环性。观察性研究已经阐明冲突是如何恶化的。然而,大部分证据是基于综合语言内容和语言情感的度量,而这些证据又通过使用序列分析方法进行研究。虽然存在关于潜在情绪反应和消极情绪升级作为关系困扰和恶化的一部分的普遍推定,很少有实证数据直接考察这些情绪连续转变。该研究考察了参与到关系教育项目的62对伴侣中关系满意度和伴侣冲突中口头表达情绪变化轨迹同时以及纵向关联性。和预期以及受困扰伴侣中发现的模式相反,轨迹遵循U形而不是翻转U形曲线,而情绪觉醒较持续和明显的降低预测长期较稳定的关系满意度。此外,还存在伴侣内部效果。这些结果显示关系恶化的早期征兆可能较少以在困扰伴侣中间发现的公开升级形式出现,而表现在后期恶化明显的伴侣较难平息情绪觉醒。他们将情绪觉醒维持在较低水平的能力也较差。高危伴侣在谈话后期较明显的升级可能是受困扰伴侣中发现的较大升级模型的先兆。这一假设还需实证考察。我们还探讨了局限和影响。.

Verbal and non-verbal information is central to social interaction between humans and has been studied intensively in psychology. Especially, dyadic interactions (e.g. between romantic partners or between psychotherapist and patient) are relevant for a number of psychological research areas. However, psychological methods applied so far have not been able to handle the vast amount of data resulting from human interactions, impeding scientific discovery and progress. This paper presents an interdisciplinary approach using technology from engineering and computer science to work with continuous data from human communication and interaction on the verbal (e.g. use of words, content) and non-verbal (e.g. vocal features of the human voice) level. Text-mining techniques such as topic models take into account the semantic and syntactic information of written text (such as therapy session transcripts) and its structure and intercorrelations. Speech signal processing focuses on the vocal information in a speaker’s voice (e.g. based on audio- or videotaped interactions). For both areas, an introduction defining the respective method and related procedures, and sample applications from psychological publications complementing or generating behavioral codes (e.g. in addition to cardiovascular indices of arousal or as a form to encode empathy) are provided. We close with a summary on the opportunities and challenges of learning and applying tools from the novel approaches described in this manuscript to different areas of psychological research and provide the interested reader with a list of additional readings on the technical aspects of topic modeling and speech signal processing.

Depression is a common mental health problem leading to significant disability world wide. Depression is not only common but also commonly co-occurs with other mental and neurological illnesses. Parkinson's Disease gives rise to symptoms directly impairing a person's ability to function. Early diagnosis and detection of depression can aid treatment, but diagnosis typically requires an interview with a health provider or structured diagnostic questionnaire. Thus, unobtrusive measures to monitor depression symptoms in daily life could have great utility in screening depression for clinical treatment. Vocal biomarkers of depression are a potentially effective method of assessing depression symptoms in daily life, which is the focus of the current research. We have a database of 921 unique patients with Parkinson's disease and their self assessment of whether they felt depressed or not. Voice recordings from these patients were used to extract paralinguistic features, which served as inputs to machine-learning and deep learning techniques to predict depression. The results are presented here and the limitations are discussed given the nature of the recordings which lack language content. Our models achieved accuracies as high as 0.77 in classifying depressed and non-depressed subjects accurately using their voice features and PD severity. We found depression and severity of Parkinson's Disease had a correlation coefficient of 0.3936, providing a valuable feature when predicting depression from voice. Our results indicate a clear correlation between feeling depressed and the severity of the Parkinson's disease. Voice may be an effective digital biomarker to screen for depression among patients suffering from Parkinson's Disease.

OBJECTIVE: To describe a new Veterans Health Administration (VHA) program to foster the learning health system paradigm by rigorously evaluating health care initiatives and to report key lessons learned in designing those evaluations. PRINCIPAL FINDINGS: The VHA's Quality Enhancement Research Initiative and its Health Services Research and Development Service are cooperating on several large, randomized program evaluations aimed at improving the care veterans receive and the efficiency with which it is delivered. The evaluations we describe involve collaborative design, outcomes assessment, and implementation science through partnerships between VHA operations and researchers. We review key factors to assess before committing to an evaluation. In addition to traditional design issues (such as ensuring adequate power and availability of data), these include others that are easily overlooked: the stability of intervention financing, means of controlling and commitment to adhering to randomized roll‐out, degree of buy‐in from key implementation staff, and feasibility of managing multiple veto points for interventions that span several programs, among others. CONCLUSIONS: Successful program implementation and rigorous evaluation require resources, specialized expertise, and careful planning. If the learning health system model is to be sustained, organizations will need dedicated programs to prioritize resources and continuously adapt evaluation designs.

Background Patient-centered medical homes have made great strides providing comprehensive care for patients with chronic conditions, but may not provide sufficient support for patients at highest risk for acute care use. To address this, the Veterans Health Administration (VHA) initiated a five-site demonstration project to evaluate the effectiveness of augmenting the VA's Patient Aligned Care Team (PACT) medical home with PACT Intensive Management (PIM) teams for Veterans at highest risk for hospitalization. Methods/design Researchers partnered with VHA leadership to design a mixed-methods prospective multi-site evaluation that met leadership's desire for a rigorous evaluation conducted as quality improvement rather than research. We conducted a randomized QI evaluation and assigned high-risk patients to participate in PIM and compared them with high-risk Veterans receiving usual care through PACT. The summative evaluation examines whether PIM: 1) decreases VHA emergency department and hospital use; 2) increases satisfaction with VHA care; 3) decreases provider burnout; and 4) generates positive returns on investment. The formative evaluation aims to support improved care for high-risk patients at demonstration sites and to inform future initiatives for high-risk patients. The evaluation was reviewed by representatives from the VHA Office of Research and Development and the Office of Research Oversight and met criteria for quality improvement. Discussion VHA aims to function as a learning organization by rapidly implementing and rigorously testing QI innovations prior to final program or policy development. We observed challenges and opportunities in designing an evaluation consistent with QI standards and operations priorities, while also maintaining scientific rigor. Trial registration: This trial was retrospectively registered at ClinicalTrials.gov on April 3, 2017: NCT03100526 . Protocol v1, FY14-17.

The U.S. healthcare system is changing, spurred on by increasing use of information technologies, changes in legislation and policy, and consumer demand for more convenient, timely, and patient-centered care. However, the current healthcare system is not prepared to maximize the benefits of these changes to optimize health outcomes for patients with chronic conditions, leaving many to fall through the cracks. New models of care coordination that align clinical activities are needed so that patients receive the right care at the right time. The goal of this commentary is to outline a research agenda for care coordination, drawing upon lessons learned from the VA healthcare system in which care coordination is enhanced through the application of health policy, population health/technology, and implementation science.

Objective To determine if synchrony in emotional arousal and affective regulation between patients and clinicians reflect emotional bonding during emergency behavioral health appointments. Method Audio recordings of suicide risk assessment interviews and crisis intervention planning with 54 suicidal active duty soldiers presenting to an emergency department or behavioral health clinic were analyzed. Emotional arousal was assessed using mean fundamental frequency. Patient-rated emotional bond was assessed with the Working Alliance Inventory, Short Form (Hatcher & Gillaspy, 2014). Actor-partner interdependence modeling was used to identify moment-to-moment patterns of covariance among clinician and patient emotional arousal. Results Greater synchrony in clinician and patient emotional arousal was positively associated with higher emotional bond ratings during the crisis intervention but not the risk assessment interview. During the risk assessment interview, higher emotional bond was associated with a dysregulating effect of the clinician on the patient's emotional arousal (i.e., larger fluctuations in the patient's emotional arousal). The reverse pattern was seen during the intervention: Higher emotional bond was associated with a regulating effect of the clinician on the patient's emotional arousal (i.e., smaller fluctuations in the patient's emotional arousal). Emotional bond during the intervention was also positively associated with a regulating effect of the patient on the clinician's emotional arousal. Conclusion Emotional bonding during emergency clinical encounters is associated with patient-clinician synchrony in emotional states. During crisis interventions, emotional bonding is also associated with mutual down-regulation of emotional arousal among patients and clinicians. (PsycINFO Database Record

We use palaeomagnetic methods to decipher the thermal histories of a succession of massive to weakly stratified debris flow deposits (Ngatoro and Te Popo formations) of late Holocene age located on the eastern lower flanks of Mt. Taranaki/Egmont Volcano, western North Island, New Zealand. Results from two sites, Vickers Quarry and Surrey Road Quarry, both c. 9.6 km from the present-day summit, enable us to distinguish between clast incorporation temperatures of about 400 °C and emplacement temperatures between 150 and 200 °C, consistent with observation of superficial charring and desiccation of outer podocarp-hardwood tree trunks at Vickers Quarry. Analysis of palaeomagnetic directions and lithofacies architecture suggest that these deposits were likely initiated as a closely-spaced succession of block-and-ash flows (BAFs) that rapidly cooled as they descended the volcano flanks. Radiocarbon chronology and the widespread occurrence of a palaeosol between the products of the preceding Inglewood eruptive phase, c. 3.4 cal. ka B.P., and the overlying Ngatoro Formation suggest that these two events are temporally unrelated. Certainly, there is no field evidence of contemporaneous explosive volcanic activity that might be related to the emplacement of Ngatoro Formation. However, we suggest that these low-temperature deposits might either relate to collapse of a small emergent lava dome or a cooling dome remnant, possibly emplaced in the aftermath of the Inglewood eruption. How collapse was initiated remains uncertain: the remnant dome may have been rendered unstable by volcano-tectonic or tectonic seismic events and/or by adverse meteorological events. Nevertheless, this study demonstrates that edifice collapse events generating potentially hazardous debris flows can occur independent of specific eruptive activity.

Advances in technology have ushered in exciting potential for smartphone sensors to inform mental health care. This commentary addresses the practical challenges of collecting smartphone-based physical activity data. Using data (N = 353) from a large scale, fully remote randomized clinical trial for depression, we discuss findings and limitations associated with using passively collected mobility data to make inferences about depressive symptom severity. We highlight a range of issues in associating mobility data with mental health symptoms, including a high degree of variability, data featurization, granularity, and sparsity. Given the considerable efforts toward leveraging technology in mental health care, it is important to consider these challenges to optimize assessment and guide best practices. Clinical Trials.gov identifier: NCT01808976.

The cyclin-dependent kinase CDK1 is essential for mitosis in fungi and animals. Plant genomes contain the CDK1 ortholog CDKA and a plant kingdom-specific relative, CDKB. The green alga Chlamydomonas reinhardtii has a long G1 growth period followed by rapid cycles of DNA replication and cell division. We show that null alleles of CDKA extend the growth period prior to the first division cycle and modestly extend the subsequent division cycles, but do not prevent cell division, indicating at most a minor role for the CDK1 ortholog in mitosis in Chlamydomonas. A null allele of cyclin A has a similar though less extreme phenotype. In contrast, both CDKB and cyclin B are essential for mitosis. CDK kinase activity measurements imply that the predominant in vivo complexes are probably cyclin A-CDKA and cyclin B-CDKB. We propose a negative feedback loop: CDKA activates cyclin B-CDKB. Cyclin B-CDKB in turn promotes mitotic entry and inactivates cyclin A-CDKA. Cyclin A-CDKA and cyclin B-CDKB may redundantly promote DNA replication. We show that the anaphase-promoting complex is required for inactivation of both CDKA and CDKB and is essential for anaphase. These results are consistent with findings in Arabidopsis thaliana and may delineate the core of plant kingdom cell cycle control that, compared with the well-studied yeast and animal systems, exhibits deep conservation in some respects and striking divergence in others.

Background Suicide is the 10th leading cause of death in the United States, with >47,000 deaths in 2019. Most people who died by suicide had contact with the health care system in the year before their death. Health care provider training is a top research priority identified by the National Action Alliance for Suicide Prevention; however, evidence-based approaches that target skill-building are resource intensive and difficult to implement. Advances in artificial intelligence technology hold promise for improving the scalability and sustainability of training methods, as it is now possible for computers to assess the intervention delivery skills of trainees and provide feedback to guide skill improvements. Much remains to be known about how best to integrate these novel technologies into continuing education for health care providers. Objective In Project WISE (Workplace Integrated Support and Education), we aim to develop e-learning training in suicide safety planning, enhanced with novel skill-building technologies that can be integrated into the routine workflow of nurses serving patients hospitalized for medical or surgical reasons or traumatic injury. The research aims include identifying strategies for the implementation and workflow integration of both the training and safety planning with patients, adapting 2 existing technologies to enhance general counseling skills for use in suicide safety planning (a conversational agent and an artificial intelligence–based feedback system), observing training acceptability and nurse engagement with the training components, and assessing the feasibility of recruitment, retention, and collection of longitudinal self-report and electronic health record data for patients identified as at risk of suicide. Methods Our developmental research includes qualitative and observational methods to explore the implementation context and technology usability, formative evaluation of the training paradigm, and pilot research to assess the feasibility of conducting a future cluster randomized pragmatic trial. The trial will examine whether patients hospitalized for medical or surgical reasons or traumatic injury who are at risk of suicide have better suicide-related postdischarge outcomes when admitted to a unit with nurses trained using the skill-building technology than those admitted to a unit with untrained nurses. The research takes place at a level 1 trauma center, which is also a safety-net hospital and academic medical center. Results Project WISE was funded in July 2019. As of September 2021, we have completed focus groups and usability testing with 27 acute care and 3 acute and intensive care nurses. We began data collection for research aims 3 and 4 in November 2021. All research has been approved by the University of Washington institutional review board. Conclusions Project WISE aims to further the national agenda to improve suicide prevention in health care settings by training nurses in suicide prevention with medically hospitalized patients using novel e-learning technologies. International Registered Report Identifier (IRRID) DERR1-10.2196/33695

Internalized HIV-related stigma acts as a barrier to antiretroviral therapy (ART) adherence, but its effects on other HIV care continuum outcomes are unclear.Among 196 HIV clinic patients in Birmingham, AL, we assessed internalized HIV-related stigma and depressive symptom severity using validated multi-item scales and assessed ART adherence using a validated single-item measure. HIV visit adherence (attended out of total scheduled visits) was calculated using data from clinic records. Using covariate-adjusted regression analysis, we investigated the association between internalized stigma and visit adherence. Using path analytic methods with bootstrapping, we tested the mediating role of depressive symptoms in the association between internalized stigma and visit adherence and the mediating role of visit adherence in the association between internalized stigma and ART adherence.Higher internalized stigma was associated with lower visit adherence (B = -0.04, P = 0.04). Black (versus white) race and depressive symptoms were other significant predictors within this model. Mediation analysis yielded no indirect effect through depression in the association between internalized stigma and visit adherence (B = -0.18, SE = 0.11, 95% confidence interval: -0.44 to -0.02) in the whole sample. Supplemental mediated moderation analyses revealed gender-specific effects. Additionally, the effect of internalized stigma on suboptimal ART adherence was mediated by lower visit adherence (B = -0.18, SE = 0.11, 95% confidence interval: -0.44 to -0.02).Results highlight the importance of internalized HIV stigma to multiple and sequential HIV care continuum outcomes. Also, findings suggest multiple intervention targets, including addressing internalized stigma directly, reducing depressive symptoms, and promoting consistent engagement in care.

The purpose of this study was to assess associations between BMI and severe coronavirus disease 2019 (COVID-19) outcomes: hospitalization, intensive care unit (ICU) admission, and mortality. A secondary aim was to investigate whether associations varied by age.The cohort comprised patients in the Veterans Health Administration (VHA) who tested positive for COVID-19 (N = 9,347). For each outcome, we fit piecewise logistic regression models with restricted cubic splines (knots at BMI of 23, 30, and 39), adjusting for age, sex, comorbidities, VHA nursing home residence, and race/ethnicity. Supplemental analyses included age-by-BMI interaction terms (α = 0.05).We found evidence of a nonlinear J-curve association between BMI and likelihood of hospitalization and mortality. BMI was associated with increased odds for hospitalization, ICU admission, and mortality among patients with BMI 30 to 39 but decreased odds of hospitalization and mortality for patients with BMI 23 to 30. Patients under age 75 with BMI between 30 and 39 had increased odds for mortality with increasing BMI.Odds for severe outcomes with COVID-19 infection increased with increasing BMI for people with, but not without, obesity. This nonlinear relationship should be tested in future research. COVID-19 public health messages in VHA, and broadly, should incorporate information about risks associated with all classes of obesity, particularly for those under age 75.

A revised stratigraphy is presented for the late Miocene–early Pliocene sedimentary rocks of the northern Aorangi Range, Wairarapa. Despite major differences in lithology, the Clay Creek Limestone ...

This study describes a randomized controlled trial called "Operation Worth Living" (OWL) which compared the use of the Collaborative Assessment and Management of Suicidality (CAMS) to enhanced care as usual (E-CAU). We hypothesized that CAMS would be more effective than E-CAU for reducing suicidal ideation (SI) and suicide attempts (SA), along with secondary behavioral health and health care utilization markers for U.S. Army Soldier outpatients with significant SI (i.e.,13 on Beck's Scale for Suicide Ideation).Study participants were 148 Soldiers who presented to a military outpatient behavioral health clinic. There were 73 Soldiers in the experimental arm of the trial who received adherent CAMS; 75 Soldiers received E-CAU. Nine a-priori treatment outcomes (SI, past year SA, suicide-related emergency department (ED) admits, behavioral health-related ED admits, suicide-related inpatient psychiatric unit (IPU) days, behavioral health-related IPU days, mental health, psychiatric distress, resiliency) were measured through assessments at Baseline and at 1, 3, 6, and 12 months post-Baseline (with a 78% retention of intent-to-treat participants at 12 months).Soldiers in both arms of the trial responded to study treatments in terms of all primary and secondary outcomes (effect sizes ranged from 0.63 to 12.04). CAMS participants were significantly less likely to have any suicidal thoughts by 3 months in comparison to those in E-CAU (Cohen's d = 0.93, p=.028).Soldiers receiving CAMS and E-CAU significantly improved post-treatment. Those who received CAMS were less likely to report SI at 3 months; further group differences were not otherwise seen.

We present a Southwest Pacific Ocean paleothermometry transect using new and existing foraminiferal Mg/Ca data from six Eocene locations from eastern New Zealand to southwestern Campbell Plateau, spanning 10° of paleolatitude (43° to 53°S). Sea surface and seafloor temperatures (SST and SFT) have been calculated taking into account the partition coefficients of calcite and Paleogene Mg/Ca sw ratios, and used to determine values for the power component ( H ) of this relationship in foraminiferal calcite from paired proxy (δ 18 O and Mg/Ca) records from Canterbury Basin. This study presents the first Eocene paleotemperature record for the East Coast Basin and, in so doing, shows the absence of a meridional temperature gradient over 10° of latitude during the Early Eocene Climatic Optimum (EECO) and provides evidence for a very weak to absent gradient from the equatorial Pacific to 53°S at this time of extreme global warmth. The application of a new subsurface TEX 86 calibration correlates remarkably well with Mg/Ca seafloor temperature trends from the continental slope setting ( 86 is recording an upper ocean subsurface temperature record, rather than simply SST values. SST-SFT gradients demonstrate a notable reduction, decreasing to 3–5 °C across the EECO. The comparable ocean temperatures of the East Coast Basin, Canterbury Basin and DSDP Site 277 during this time support the intensification of a proto-East Australian Current (EAC), explaining the distribution of tropical sea temperatures extending into the high-latitude Southwest Pacific Ocean during the EECO. Seafloor temperatures (~ 1000 m paleodepth) likely correspond to a northern, intermediate water source during the early Eocene, before switching to a cooler southern-derived source in the middle to late Eocene.

Aims The aim was to systematically review published articles that reported the incidence of chronic kidney disease among people with diabetes. Methods A systematic literature search was performed using MEDLINE, Embase and CINAHL databases. The titles and abstracts of all publications identified by the search were reviewed and 10 047 studies were retrieved. Results A total of 71 studies from 30 different countries with sample sizes ranging from 505 to 211 132 met the inclusion criteria. The annual incidence of microalbuminuria and albuminuria ranged from 1.3% to 3.8% for Type 1 diabetes. For Type 2 diabetes and studies combining both diabetes types, the range was from 3.8% to 12.7%, with four of six studies reporting annual rates between 7.4% and 8.6%. In studies reporting the incidence of eGFR < 60 ml/min/1.73 m2 using the Modification of Diet on Renal Disease (MDRD) equation, apart from one study which reported an annual incidence of 8.9%, the annual incidence ranged from 1.9% to 4.3%. The annual incidence of end-stage renal disease ranged from 0.04% to 1.8%. Conclusions The annual incidence of microalbuminuria and albuminuria is ~ 2–3% in Type 1 diabetes, and ~ 8% in Type 2 diabetes or mixed diabetes type. The incidence of developing eGFR < 60 ml/min/1.73 m2 is ~ 2–4% per year. Despite the wide variation in methods and study design, within a particular category of kidney disease, there was only modest variation in incidence rates. These findings may be useful in clinical settings to help understand the risk of developing kidney disease among those with diabetes.

Weight management medications (WMM) are underutilized as an adjunct to behavioral and lifestyle interventions. In fiscal years 2014-2015, a total of approximately 2500 veterans-a mere 2% of veterans receiving care from the Veterans Health Administration (VHA)-eligible for a WMM received a prescription for one. A State of the Art Conference on Weight Management workgroup, focused on pharmacotherapy, developed evidence-based recommendations and strategies to foster the appropriate use of WMM in the VHA. The workgroup identified patient, prescriber, and health system barriers to and facilitators for prescribing WMM. Barriers included patient and provider concerns about medication safety and efficacy, limited involvement of primary care, restrictive medication criteria for use (CFU), and skepticism among providers regarding the safety and efficacy of WMM and the perception of obesity as a disease. Potential facilitators for removing barriers included patient and provider education about WMM and the health benefits of weight loss, increased engagement of primary care providers in weight management, relaxation of the CFU, and creation of a system to help patients navigate through weight management treatment options. Several research questions were framed with regard to WMM in general, and specifically to the care of obese veterans. While some of the workgroup's conclusions reflect issues specific to the VHA, many are likely to be applicable to other health organizations.

Background Suicide is a major public health concern, particularly among people who use illicit substances and/or non-prescribed medications. Methods The present study prospectively assessed the incidence and predictors of suicidal ideation (SI) and suicide attempt (SA) among 868 substance-using patients over 12 months after receiving primary care within seven public primary care clinics. Results Participants reported a high incidence of SI (25.9%) and SA (7.1%) over the year following primary care visits. Suicidality was elevated in patients who were female; lacked a high school diploma; were unemployed; reported depression, anxiety, hallucinations, concentration difficulty, or violent behavior; used nicotine or stimulants; used the emergency department or mental health services in the past 90 days; reported current quality-of-life impairment in mobility or usual activities; or reported recent SI or lifetime SA at baseline. In multiple regression analyses, only past 30-day SI, any lifetime SA, past 90-day violent behavior, and current impairment due to anxiety or depression at baseline uniquely predicted SI or SA beyond other variables. Conclusions Results support the need for screening for suicidality among primary care patients who use illicit substances and identify key of these patients who are at particularly elevated risk for suicidality.

Psychotherapy represents a broad class of medical interventions received by millions of patients each year. Unlike most medical treatments, its primary mechanisms are linguistic; i.e., the treatment relies directly on a conversation between a patient and provider. However, the evaluation of patient-provider conversation suffers from critical shortcomings, including intensive labor requirements, coder error, non-standardized coding systems, and inability to scale up to larger data sets. To overcome these shortcomings, psychotherapy analysis needs a reliable and scalable method for summarizing the content of treatment encounters. We used a publicly-available psychotherapy corpus from Alexander Street press comprising a large collection of transcripts of patient-provider conversations to compare coding performance for two machine learning methods. We used the Labeled Latent Dirichlet Allocation (L-LDA) model to learn associations between text and codes, to predict codes in psychotherapy sessions, and to localize specific passages of within-session text representative of a session code. We compared the L-LDA model to a baseline lasso regression model using predictive accuracy and model generalizability (measured by calculating the area under the curve (AUC) from the receiver operating characteristic (ROC) curve). The L-LDA model outperforms the lasso logistic regression model at predicting session-level codes with average AUC scores of .79, and .70, respectively. For fine-grained level coding, L-LDA and logistic regression are able to identify specific talk-turns representative of symptom codes. However, model performance for talk-turn identification is not yet as reliable as human coders. We conclude that the L-LDA model has the potential to be an objective, scaleable method for accurate automated coding of psychotherapy sessions that performs better than comparable discriminative methods at session-level coding and can also predict fine-grained codes.

Research documents increased and problematic alcohol use during study abroad experiences for college students yet no research documents effective preventive programs with these students. The present randomized controlled trial was designed to prevent increased and problematic alcohol use abroad by correcting misperceptions of peer drinking norms abroad and by promoting positive and healthy adjustment into the host culture (i.e., sojourner adjustment) through brief online personalized feedback interventions. A sample of 343 study abroad college students was randomly assigned to 1 of 4 conditions including a personalized normative feedback intervention (PNF), a sojourner adjustment feedback intervention (SAF), a combined PNF + SAF intervention, and an assessment-only control condition. Generalized estimated equation analyses accounting for baseline drinking and consequences revealed an intervention effect for PNF that was mitigated by baseline drinking level, such that PNF was best for those with lighter baseline drinking, but heavier baseline drinkers receiving PNF alone or PNF + SAF drank comparatively similar or more heavily abroad to those in the control condition. However, PNF + SAF condition participants with greater baseline levels of consequences reported comparatively less consequences abroad than their control participants. Thus, PNF alone may be helpful for lighter drinkers at predeparture and the addition of SAF to PNF may help prevent consequences abroad for those reporting more consequences prior to departure abroad. This research represents an important first step in designing and implementing efficacious interventions with at-risk study abroad college students, for which no current empirically based programs exist. (PsycINFO Database Record

AIMS Uncertainties about the role of cystatin C-based estimated glomerular filtration rate (eGFR) in the prediction of cardiovascular disease (CVD) beyond traditional CVD risk factors remain. We assessed contributions of eGFR to CVD and mortality in the general population. METHODS Using 14 year follow-up data on 9353 adults without a reported history of CVD from the Australian Diabetes, Obesity and Lifestyle study, we assessed the contributions of eGFR (assessed by cystatin C (eGFRcysC ) and serum creatinine (eGFRcr ) and albuminuria (uACR) to total and CVD mortality. RESULTS After adjusting for age, sex, CVD risk factors and uACR, compared with an eGFRcysC >90 mL/min per 1.73 m2 , eGFRcysC

Objective The challenges posed by people living with multiple chronic conditions are unique for people with dementia and other significant cognitive impairment. There have been recent calls to action to review the existing literature on co-occurring chronic conditions and dementia in order to better understand the effect of cognitive impairment on disease management, mobility, and mortality. Methods This systematic literature review searched PubMed databases through 2011 (updated in 2016) using key constructs of older adults, moderate-to-severe cognitive impairment (both diagnosed and undiagnosed dementia), and chronic conditions. Reviewers assessed papers for eligibility and extracted key data from each included manuscript. An independent expert panel rated the strength and quality of evidence and prioritized gaps for future study. Results Four thousand thirty-three articles were identified, of which 147 met criteria for review. We found that moderate-to-severe cognitive impairment increased risks of mortality, was associated with prolonged institutional stays, and decreased function in persons with multiple chronic conditions. There was no relationship between significant cognitive impairment and use of cardiovascular or hypertensive medications for persons with these comorbidities. Prioritized areas for future research include hospitalizations, disease-specific outcomes, diabetes, chronic pain, cardiovascular disease, depression, falls, stroke, and multiple chronic conditions. Conclusions This review summarizes that living with significant cognitive impairment or dementia negatively impacts mortality, institutionalization, and functional outcomes for people living with multiple chronic conditions. Our findings suggest that chronic-disease management interventions will need to address co-occurring cognitive impairment. Copyright © 2017 John Wiley & Sons, Ltd.

While previous studies have examined motivational aspects of self-directed violence, few studies have included specific motivations in predictive models for future suicide attempts. The current study utilized a sample of 160 individuals treated in an acute emergency setting following a suicide attempt who completed an interview battery that included an assessment of functional aspects of the index suicide attempt. A follow-up interview was conducted at 6 months to ascertain subsequent suicide attempts. The functional domains of suicide attempts were labeled as reduction-of-distress, communication, perceived better alternative to living, and self-loathing. Above and beyond other known risk factors, including history and highest lethality of previous self-injury, suicide attempts that served a communication function (OR = 0.18, p = .02, CI = 0.04, 0.73) and higher ratings of clinical dysfunction (OR = 3.41, p = .05, CI = 1.02, 11.36) were associated with a significant reduction in likelihood to engage in a suicide attempt during the 6-month follow-up window. Including the perceived effectiveness of the index suicide attempt in getting one's needs met strengthened the overall model predicting a suicide attempt in the follow-up window and was an independent risk factor above and beyond other variables in the model OR = 1.75, p = .04, CI = 1.02, 3.01). Assessment of functional aspects of suicide attempt is feasible and may improve formulation of risk in a population where typical risk factors for suicide are ubiquitous.

Background: Since 1998, the Veterans Health Administration (VHA) Quality Enhancement Research Initiative (QUERI) has supported more rapid implementation of research into clinical practice. Objectives: With the passage of the Veterans Access, Choice and Accountability Act of 2014 (Choice Act), QUERI further evolved to support VHA’s transformation into a Learning Health Care System by aligning science with clinical priority goals based on a strategic planning process and alignment of funding priorities with updated VHA priority goals in response to the Choice Act. Design: QUERI updated its strategic goals in response to independent assessments mandated by the Choice Act that recommended VHA reduce variation in care by providing a clear path to implement best practices. Specifically, QUERI updated its application process to ensure its centers (Programs) focus on cross-cutting VHA priorities and specify roadmaps for implementation of research-informed practices across different settings. QUERI also increased funding for scientific evaluations of the Choice Act and other policies in response to Commission on Care recommendations. Results: QUERI’s national network of Programs deploys effective practices using implementation strategies across different settings. QUERI Choice Act evaluations informed the law’s further implementation, setting the stage for additional rigorous national evaluations of other VHA programs and policies including community provider networks. Conclusions: Grounded in implementation science and evidence-based policy, QUERI serves as an example of how to operationalize core components of a Learning Health Care System, notably through rigorous evaluation and scientific testing of implementation strategies to ultimately reduce variation in quality and improve overall population health.

Linguistic coordination is a well-established phenomenon in spoken conversations and often associated with positive social behaviors and outcomes. While there have been many attempts to measure lexical coordination or entrainment in literature, only a few have explored coordination in syntactic or semantic space. In this work, we attempt to combine these different aspects of coordination into a single measure by leveraging distances in a neural word representation space. In particular, we adopt the recently proposed Word Mover’s Distance with word2vec embeddings and extend it to measure the dissimilarity in language used in multiple consecutive speaker turns. To validate our approach, we apply this measure for two case studies in the clinical psychology domain. We find that our proposed measure is correlated with the therapist’s empathy towards their patient in Motivational Interviewing and with affective behaviors in Couples Therapy. In both case studies, our proposed metric exhibits higher correlation than previously proposed measures. When applied to the couples with relationship improvement, we also notice a significant decrease in the proposed measure over the course of therapy, indicating higher linguistic coordination.

Psychotherapy, from a narrative perspective, is the process in which a client relates an on-going life-story to a therapist. In each session, a client will recount events from their life, some of which stand out as more significant than others. These significant stories can ultimately shape one’s identity. In this work we study these narratives in the context of therapeutic alliance—a self-reported measure on the perception of a shared bond between client and therapist. We propose that alliance can be predicted from the interactions between certain types of clients with types of therapists. To validate this method, we obtained 1235 transcribed sessions with client-reported alliance to train an unsupervised approach to discover groups of therapists and clients based on common types of narrative characters, or personae. We measure the strength of the relation between personae and alliance in two experiments. Our results show that (1) alliance can be explained by the interactions between the discovered character types, and (2) models trained on therapist and client personae achieve significant performance gains compared to competitive supervised baselines. Finally, exploratory analysis reveals important character traits that lead to an improved perception of alliance.

Objective: Close interpersonal relationships are fundamental to emotion regulation. Clinical theory suggests that one role of therapists in psychotherapy is to help clients regulate emotions, however, if and how clients and therapists serve to regulate each other’s emotions has not been empirically tested. Emotion coregulation – the bidirectional emotional linkage of two people that promotes emotional stability – is a specific, temporal process that provides a framework for testing the way in which therapists’ and clients’ emotions may be related on a moment to moment basis in clinically relevant ways. Method: Utilizing 227 audio recordings from a relationally oriented treatment (Motivational Interviewing), we estimated continuous values of vocally encoded emotional arousal via mean fundamental frequency. We used dynamic systems models to examine emotional coregulation, and tested the hypothesis that each individual’s emotional arousal would be significantly associated with fluctuations in the other’s emotional state over the course of a psychotherapy session. Results: Results indicated that when clients became more emotionally labile over the course of the session, therapists became less so. When changes in therapist arousal increased, the client’s tendency to become more aroused during session slowed. Alternatively, when changes in client arousal increased, the therapist’s tendency to become less aroused slowed.

In April 2017, Victoria University of Wellington launched ICE101X—Antarctica: From Geology to Human History—on the global edX platform. This Massive Open Online Course, or MOOC, attracted 5735 learners from around the world, who engaged with content about Antarctic science, history, geology, and culture, primarily through video lectures filmed in Antarctica. Analysis of feedback from learners in three iterations of the course, offered between 2015 and 2017 and culminating in ICE101X, revealed that learners enjoyed the immersive Antarctic field lectures and learning through a diverse set of disciplinary lenses, had some preconceptions about Antarctica that were challenged by the course content, and completed the course with a new sense of interest in and protection of Antarctica.

Background: Training therapists is both expensive and time-consuming. Degree–based training can require tens of thousands of dollars and hundreds of hours of expert instruction. Counseling skills practice often involves role-plays, standardized patients, or practice with real clients. Performance–based feedback is critical for skill development and expertise, but trainee therapists often receive minimal and subjective feedback, which is distal to their skill practice. Objective: In this study, we developed and evaluated a patient-like neural conversational agent, which provides real-time feedback to trainees via chat–based interaction. Methods: The text–based conversational agent was trained on an archive of 2354 psychotherapy transcripts and provided specific feedback on the use of basic interviewing and counseling skills (ie, open questions and reflections—summary statements of what a client has said). A total of 151 nontherapists were randomized to either (1) immediate feedback on their use of open questions and reflections during practice session with ClientBot or (2) initial education and encouragement on the skills. Results: Participants in the ClientBot condition used 91% (21.4/11.2) more reflections during practice with feedback (P

Automatically analyzing dialogue can help understand and guide behavior in domains such as counseling, where interactions are largely mediated by conversation. In this paper, we study modeling behavioral codes used to asses a psychotherapy treatment style called Motivational Interviewing (MI), which is effective for addressing substance abuse and related problems. Specifically, we address the problem of providing real-time guidance to therapists with a dialogue observer that (1) categorizes therapist and client MI behavioral codes and, (2) forecasts codes for upcoming utterances to help guide the conversation and potentially alert the therapist. For both tasks, we define neural network models that build upon recent successes in dialogue modeling. Our experiments demonstrate that our models can outperform several baselines for both tasks. We also report the results of a careful analysis that reveals the impact of the various network design tradeoffs for modeling therapy dialogue., Accepted to ACL 2019

BackgroundThis paper presents the protocol for the National Institute of Mental Health (NIMH)–funded University of Washington’s ALACRITY (Advanced Laboratories for Accelerating the Reach and Impact of Treatments for Youth and Adults with Mental Illness) Center (UWAC), which uses human-centered design (HCD) methods to improve the implementation of evidence-based psychosocial interventions (EBPIs). We propose that usability—the degree to which interventions and implementation strategies can be used with ease, efficiency, effectiveness, and satisfaction—is a fundamental, yet poorly understood determinant of implementation.ObjectiveWe present a novel Discover, Design/Build, and Test (DDBT) framework to study usability as an implementation determinant. DDBT will be applied across Center projects to develop scalable and efficient implementation strategies (eg, training tools), modify existing EBPIs to enhance usability, and create usable and nonburdensome decision support tools for quality delivery of EBPIs.MethodsStakeholder participants will be implementation practitioners/intermediaries, mental health clinicians, and patients with mental illness in nonspecialty mental health settings in underresourced communities. Three preplanned projects and 12 pilot studies will employ the DDBT model to (1) identify usability challenges in implementing EBPIs in underresourced settings; (2) iteratively design solutions to overcome these challenges; and (3) compare the solution to the original version of the EPBI or implementation strategy on usability, quality of care, and patient-reported outcomes. The final products from the center will be a streamlined modification and redesign model that will improve the usability of EBPIs and implementation strategies (eg, tools to support EBPI education and decision making); a matrix of modification targets (ie, usability issues) that are both common and unique to EBPIs, strategies, settings, and patient populations; and a compilation of redesign strategies and the relative effectiveness of the redesigned solution compared to the original EBPI or strategy.ResultsThe UWAC received institutional review board approval for the three separate studies in March 2018 and was funded in May 2018.ConclusionsThe outcomes from this center will inform the implementation of EBPIs by identifying cross-cutting features of EBPIs and implementation strategies that influence the use and acceptability of these interventions, actively involving stakeholder clinicians and implementation practitioners in the design of the EBPI modification or implementation strategy solution and identifying the impact of HCD-informed modifications and solutions on intervention effectiveness and quality.Trial RegistrationClinicalTrials.gov NCT03515226 (https://clinicaltrials.gov/ct2/show/NCT03515226), NCT03514394 (https://clinicaltrials.gov/ct2/show/NCT03514394), and NCT03516513 (https://clinicaltrials.gov/ct2/show/NCT03516513).International Registered Report Identifier (IRRID)DERR1-10.2196/14990

In this work we address the problem of joint prosodic and lexical behavioral annotation for addiction counseling. We expand on past work that employed Recurrent Neural Networks (RNNs) on multimodal features by grouping and classifying subsets of classes. We propose two implementations: One is hierarchical classification, which uses the behavior confusion matrix to cluster similar classes and makes the prediction based on a tree structure. The second is a graph-based method which uses the result of the original classification just to find a certain subset of the most probable candidate classes, where the candidate sets of different predicted classes are determined by the class confusions. We make a second prediction with simpler classifier to discriminate the candidates. The evaluation shows that the strict hierarchical approach degrades performance, likely due to error propagation, while the graph-based hierarchy provides significant gains.

The language patterns followed by different speakers who play specific roles in conversational interactions provide valuable cues for the task of Speaker Role Recognition (SRR). Given the speech signal, existing algorithms typically try to find such patterns in the output of an Automatic Speech Recognition (ASR) system. In this work we propose an alternative way of revealing role-specific linguistic characteristics, by making use of role-specific ASR outputs, which are built by suitably rescoring the lattice produced after a first pass of ASR decoding. That way, we avoid pruning the lattice too early, eliminating the potential risk of information loss.

People with disabilities constitute 22.2% of the population in the United States, and virtually all physicians have people with disabilities in their clinical practice across a wide range of diagnostic groups. However, studies demonstrate that people with disabilities are inadequately served by the health care system, leading to high costs and poor outcomes. The authors argue that one cause of this discrepancy is that medical students receive limited training in the care of people with disabilities and may therefore not be able to adequately meet the competencies that underlie the Core Entrustable Professional Activities for Entering Residency. To address these gaps, the authors present practical examples of integrating concepts of disability into the curriculum with minimal additional time requirements. A comprehensive disability curriculum is suggested to include active classroom learning, clinical, and community-based experiences. At institutions that do not have a comprehensive curriculum, the authors recommend adding disability-related knowledge and skill acquisition to existing curricula through modifications to current case-based learning, simulated patients, and objective structured clinical examinations. To facilitate curriculum development, they recommend that the World Health Organization International Classification of Functioning, Disability, and Health be used as a tool to build disability concepts into active learning. The goal of these recommended curricular changes is to enhance student performance in the clinical management of people with disabilities and to better train all future physicians in the care of this population.

Importance Accessible and cost-effective interventions for suicidality are needed to address high rates of suicidal behavior among military service members. Caring Contacts are brief periodic messages that express unconditional care and concern and have been previously shown to prevent suicide deaths, attempts, ideation, and hospitalizations. Objective To test the effectiveness of augmenting standard military health care with Caring Contacts delivered via text message to reduce suicidal thoughts and behaviors over 12 months. Design, Setting, and Participants This randomized clinical trial was conducted at 3 military installations in the southern and western United States. Soldiers and Marines identified as being at risk of suicide were recruited between April 2013 and September 2016. The final follow-up was in September 2017. Interventions Both groups received standard care, and the Caring Contacts group also received consisted of 11 text messages delivered on day 1, at week 1, at months 1, 2, 3, 4, 6, 8, 10, and 12, and on participants’ birthdays. Main Outcomes and Measures Primary outcomes were current suicidal ideation and suicide risk incidents (hospitalization or medical evacuation). Secondary outcomes were worst-point suicidal ideation, emergency department visits, and suicide attempts. Suicidal ideation was measured by the Scale for Suicide Ideation, suicide risk incidents, and emergency department visits by the Treatment History Interview; attempted suicide was measured by the Suicide Attempt Self-Injury Count. Results Among 658 randomized participants (329 randomizely assigned to each group), data were analyzed for 657 individuals (mean [SD] age, 25.2 [6.1] years; 539 men [82.0%]). All participants reported suicidal ideation at baseline, and 291 (44.3%) had previously attempted suicide. Of the 657 participants, 461 (70.2%) were assessed at 12 months. Primary outcomes were nonsignificant. There was no significant effect on likelihood or severity of current suicidal ideation or likelihood of a suicide risk incident; there was also no effect on emergency department visits. However, participants who received Caring Contacts (172 of 216 participants [79.6%]) had lower odds than those receiving standard care alone (179 of 204 participants [87.7%]) of experiencing any suicidal ideation between baseline and follow-up (odds ratio, 0.56 [95% CI, 0.33-0.95];P = .03) and fewer had attempted suicide since baseline (21 of 233 [9.0%] in the group receiving Caring Contacts vs 34 of 228 [14.9%] in the standard-care group; odds ratio, 0.52 [95% CI, 0.29-0.92];P = .03). Conclusions and Relevance This trial provides inconsistent results on the effectiveness of caring text messages between primary and secondary outcomes, but this inexpensive and scalable intervention offers promise for preventing suicide attempts and ideation in military personnel. Additional research is needed. Trial Registration ClinicalTrials.gov identifier:NCT01829620

BackgroundSmartphones provide a low-cost and efficient means to collect population level data. Several small studies have shown promise in predicting mood variability from smartphone-based sensor and usage data, but have not been generalized to nationally recruited samples. This study used passive smartphone data, demographic characteristics, and baseline depressive symptoms to predict prospective daily mood.MethodDaily phone usage data were collected passively from 271 Android phone users participating in a fully remote randomized controlled trial of depression treatment (BRIGHTEN). Participants completed daily Patient Health Questionnaire-2. A machine learning approach was used to predict daily mood for the entire sample and individual participants.ResultsSample-wide estimates showed a marginally significant association between physical mobility and self-reported daily mood (B=-0.04, P0.50) for 80.6% of participants and very strong prediction in a subset (median AUC>0.80) for 11.8% of participants.ConclusionsPassive smartphone data with current features may not be suited for predicting daily mood at a population level because of the high degree of intra- and interindividual variation in phone usage patterns and daily mood ratings. Personalized models show encouraging early signs for predicting an individual's mood state changes, with GPS-derived mobility being the top most important feature in the present sample.

Speaker Role Recognition (SRR) assigns a specific speaker role to each speaker-homogeneous speech segment in a conversation. Typically, those segments have to be identified first through a diarization step. Additionally, since SRR is usually based on the different linguistic patterns observed between the roles to be recognized, an Automatic Speech Recognition (ASR) system is also indispensable for the task in hand to convert speech to text. In this work we introduce a Role Annotated Speech Recognition (RASR) system which, given a speech signal, outputs a sequence of words annotated with the corresponding speaker roles. Thus, the need of different component modules which are connected in a way that may lead to error propagation is eliminated. We present, analyze, and test our system for the case of two speaker roles to show-case an end-to-end approach for automatic rich transcription with application to clinical dyadic interactions.