Alcohol use and violent behaviors among youth are associated with morbidity and mortality. An emergency department (ED) visit provides an opportunity to initiate prevention efforts. Despite promising findings from our single session SafERteens brief intervention (BI), impact is limited by modest effect sizes, with data lacking on optimal boosters to enhance effects. This paper describes the protocol for a sequential, multiple assignment, randomized trial (SMART). Adolescents and emerging adults (ages 14-20) in the ED screening positive for alcohol use and violent behaviors (physical aggression) were randomly assigned to: 1) SafERteens BI + Text Messaging (TM), or 2) SafERteens BI + remote Health Coach (HC). Participants completed weekly surveys over 8 weeks after the ED visit to tailor intervention content and measure mechanisms of change. At one-month, intervention response/non-response is determined (e.g., binge drinking or violent behaviors). Responders are re-randomized to continued intervention condition (e.g., maintenance) or minimized condition (e.g., stepped down). Non-responders are re-randomized to continued condition (e.g., maintenance), or intensified condition (e.g., stepped up). Outcomes were measured at 4 and 8 months, including primary outcomes of alcohol consumption and violence, with secondary outcomes of alcohol consequences and violence consequences. Although the original goal was to enroll 700 participants, COVID-19 impacts on research diminished recruitment in this trial (enrolled n = 400). Nonetheless, the proposed SMART is highly innovative by blending real-time assessment methodologies with adaptive intervention delivery among teens with comorbid alcohol misuse and violent behaviors. Findings will inform the content and timing booster interventions to alter risk behavior trajectories. Trial Registration:ClinicalTrials.govNCT03344666. University of Michigan # HUM00109156.

Recently, empathetic dialogue systems have received significant attention. While some researchers have noted limitations, e.g., that these systems tend to generate generic utterances, no study has systematically verified these issues. We survey 21 systems, asking what progress has been made on the task. We observe multiple limitations of current evaluation procedures. Most critically, studies tend to rely on a single non-reproducible empathy score, which inadequately reflects the multidimensional nature of empathy. To better understand the differences between systems, we comprehensively analyze each system with automated methods that are grounded in a variety of aspects of empathy. We find that recent systems lack three important aspects of empathy: specificity, reflection levels, and diversity. Based on our results, we discuss problematic behaviors that may have gone undetected in prior evaluations, and offer guidance for developing future systems.(1)

Understanding empathy in text dialogue data is a difficult, yet critical, skill for effective human-machine interaction. In this work, we ask whether systems are making meaningful progress on this challenge. We consider a simple model that checks if an input utterance is similar to a small set of empathetic examples. Crucially, the model does not look at what the utterance is a response to, i.e., the dialogue context. This model performs comparably to other work on standard benchmarks and even outperforms state-of-the-art models for empathetic rationale extraction by 16.7 points on T-F1 and 4.3 on IOU-F1. This indicates that current systems rely on the surface form of the response, rather than whether it is suitable in context. To confirm this, we create examples with dialogue contexts that change the interpretation of the response and show that current systems continue to label utterances as empathetic. We discuss the implications of our findings, including improvements for empathetic benchmarks and how our model can be an informative baseline.

BackgroundTelehealth is being adopted by health systems across the country and many barriers to the expansion of video visit programs have been identified. Our study focused on the usability of video visit technology by examining technical challenges faced by patients over the course of a video visit.MethodsWe conducted a survey of patients who received care from the Michigan Medicine video visit program from January 31, 2019 to July 31, 2019. The video visit program includes more than 1,300 visits a year across more than 30 specialties. Following the completion of their video visit, all patients were invited to participate in our online survey through the patient portal. The survey included questions on patient satisfaction, motivation and technical challenges.ResultsWe received responses from 180 patients (response rate of 26%). Overall patient satisfaction was high; 90% of respondents agreed that their video visit experience was similar to that of in-person visits and 93.3% of respondents would recommend video visits. Despite this high satisfaction rate, 36 out of 180 (20.0%) respondents cited technical issues during their video visit: video issues (n=11), audio issues (n=5), video and audio issues (n=2), slow/dropped connection (n=7), initial set-up issues (n=4), long wait time (n=3), and other (n=4).ConclusionsWhile most patients report a high degree of satisfaction with their video visit, a meaningful subset of patients continue to experience technical challenges.

The ongoing COVID-19 pandemic has raised concerns for many regarding personal and public health implications, financial security and economic stability. Alongside many other unprecedented challenges, there are increasing concerns over social isolation and mental health. We introduce \textit{Expressive Interviewing}--an interview-style conversational system that draws on ideas from motivational interviewing and expressive writing. Expressive Interviewing seeks to encourage users to express their thoughts and feelings through writing by asking them questions about how COVID-19 has impacted their lives. We present relevant aspects of the system's design and implementation as well as quantitative and qualitative analyses of user interactions with the system. In addition, we conduct a comparative evaluation with a general purpose dialogue system for mental health that shows our system potential in helping users to cope with COVID-19 issues.

Background Management guidelines have identified unmet educational needs in gout patients. Our objective was to develop and pilot test MyGoutCare (MGC©)—a web-based, interactive educational resource for gout patients, tailored to improve knowledge. Methods The website was developed with input from patients and experts. A health informatics expert tailored content areas so the patient could walk through a journey to learn various aspects of gout. During the pilot study, patients completed baseline demographics and a 10-item validated gout knowledge questionnaire. After reviewing the website, patients completed a post-survey within 2 weeks of their physician visit. Data were analyzed using paired t-tests and effect size (ES) was calculated for the changed scores. Results Gout patients and experts agreed on these content areas—triggers of flares, comorbidities, pharmacologic and non-pharmacologic treatment, healthy gout diet, and lifestyle choices. In the pilot study, 50 patients (mean age of 54 years, mean disease duration of 9.5 years, and mean 3–5 flares/year) were recruited. Their post-survey scores (0–10) on knowledge questions improved significantly when compared to pre-survey scores with mean (SD) of 1.95 (1.76) p < 0.0001, ES = 0.95. Patients identified actionable changes moving forward after reviewing the website—decision to continue lifelong urate-lowering therapy, complying with periodic monitoring of serum urate, and making dietary changes. Conclusions Web-based platforms that offer patient-focused materials can serve as a practical tool to address ongoing educational needs of gout patients. Additional studies are needed to evaluate if the website can improve patient–physician communication and lead to better long-term outcomes.

You have accessJournal of UrologySexual Function/Dysfunction: Medical, Hormonal & Non-surgical Therapy II (PD28)1 Apr 2019PD28-02 TRUENTH SEXUAL RECOVERY INTERVENTION FOR COUPLES COPING WITH PROSTATE CANCER: RANDOMIZED CONTROLLED TRIAL RESULTS Daniela Wittmann*, Akanksha Mehta, Sharon Bober, Rodney Dunn, Ziwei Zhu, Thomas Braun, Caroline Carter, Ashley Duby, Kellie Paich, Ted Skolarus, Larry An, Christian Nelson, Christopher Saigal, Ronald Chen, and Craig Pollack Daniela Wittmann*Daniela Wittmann* More articles by this author , Akanksha MehtaAkanksha Mehta More articles by this author , Sharon BoberSharon Bober More articles by this author , Rodney DunnRodney Dunn More articles by this author , Ziwei ZhuZiwei Zhu More articles by this author , Thomas BraunThomas Braun More articles by this author , Caroline CarterCaroline Carter More articles by this author , Ashley DubyAshley Duby More articles by this author , Kellie PaichKellie Paich More articles by this author , Ted SkolarusTed Skolarus More articles by this author , Larry AnLarry An More articles by this author , Christian NelsonChristian Nelson More articles by this author , Christopher SaigalChristopher Saigal More articles by this author , Ronald ChenRonald Chen More articles by this author , and Craig PollackCraig Pollack More articles by this author View All Author Informationhttps://doi.org/10.1097/01.JU.0000555907.62685.8bAboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVES: Despite high levels of sexual dysfunction and distress following the treatment of localized prostate cancer, usual care offers only physiologic management focused on erectile function. We performed a randomized controlled trial to test the effectiveness of an online intervention to address the psychosexual needs of men and their partners. METHODS: An online intervention for couples’ sexual recovery was developed using mixed methods research with prostate cancer patients and their partners, tailored to treatment type and sexual orientation. The intervention consisted of modules addressing expectations for sexual and emotional sequelae of treatment, rehabilitation and guidance towards recovery of sexual intimacy and included videos, psychoeducation, couple-oriented activities, and coping strategies. Control subjects accessed the American Cancer Society’s website. Couples recruited from 6 sites nationally completed validated measures at baseline and 3 and 6 months post-treatment. Group differences were assessed with t-tests for individual outcomes and the Actor-Partner Interaction Model for dyadic outcomes. RESULTS: 142 patients treated with surgery or radiation and their partners were randomized. All couples showed an expected post-treatment decline in PROMIS Satisfaction with Sex Life, with similar declines for the intervention and control groups. Both patients and partners in the intervention arm showed increased knowledge about sexual issues at 3-months post-treatment vs baseline. Patients more engaged in the intervention evidenced improved ability to communicate about sex with their partners than those less engaged. Dyadic analysis showed that higher complicated grief scores and negative coping by partner were associated with both patients’ and partners’ lower satisfaction with sex life. Subjects generally had high satisfaction levels with the module content (65-85%). Qualitative analysis found five satisfaction themes: managing expectations, couple communication, fostering couple coping and intimacy, increasing knowledge about rehabilitation, and not being alone. CONCLUSIONS: Online psychosexual support for couples can succeed in impacting knowledge, sexual communication, loss and grief, and negative coping; more engaged couples experience the greatest benefits. Further refinements to the content and format may lead to larger impacts as the intervention is made available to a national audience giving patients and providers an important resource. Source of Funding: Movember Foundation Ann Arbor, MI; Atlanta, GA; Boston, MA; Ann Arbor, MI; Culver City, CA; Ann Arbor, MI; Ann Arbor, MI; New York, NY; Los Angeles, CA; Chapel Hill, NC; Baltimore, MD© 2019 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 201Issue Supplement 4April 2019Page: e486-e486 Advertisement Copyright & Permissions© 2019 by American Urological Association Education and Research, Inc.MetricsAuthor Information Daniela Wittmann* More articles by this author Akanksha Mehta More articles by this author Sharon Bober More articles by this author Rodney Dunn More articles by this author Ziwei Zhu More articles by this author Thomas Braun More articles by this author Caroline Carter More articles by this author Ashley Duby More articles by this author Kellie Paich More articles by this author Ted Skolarus More articles by this author Larry An More articles by this author Christian Nelson More articles by this author Christopher Saigal More articles by this author Ronald Chen More articles by this author Craig Pollack More articles by this author Expand All Advertisement PDF downloadLoading ...

We introduce a new dataset consisting of natural language interactions annotated with medical family histories, obtained during interactions with a genetic counselor and through crowdsourcing, following a questionnaire created by experts in the domain. We describe the data collection process and the annotations performed by medical professionals, including illness and personal attributes (name, age, gender, family relationships) for the patient and their family members. An initial system that performs argument identification and relation extraction shows promising results - average F-score of 0.87 on complex sentences on the targeted relations.

225 Background: Decision making for adjuvant chemotherapy is increasingly complicated for women with a new diagnosis of early stage breast cancer. Few decision tools are designed to help support informed systemic treatment decision-making, by improving knowledge and decision quality. Methods: We conducted a randomized controlled trial (RCT) of a tailored, comprehensive (locoregional and systemic treatment) and interactive decision tool (iCanDecide), compared with static online information. 537 newly diagnosed, early stage breast cancer patients were enrolled from 22 surgical practices. Participants were surveyed 5 weeks (N = 496; RR 92%) and those eligible for systemic treatment (N = 358) again at 9 months (N = 307; RR 88%). The main outcome for this analysis was knowledge about systemic treatment using 4 true/false items, categorized into high (3- 4 correct) vs. low (0-2 correct). We also assessed subjective decision quality (SDQ) for chemotherapy on a 5-point scale and dichotomized into high (4-5) vs. low (1-3) We evaluated the distribution of participants in each arm, and assessed the association between the study arm and the outcomes using bivariate and multivariable approaches. Results: Of the 358 respondents, 201 did not receive or intend to have chemotherapy. Significantly more intervention than control patients had high knowledge about systemic treatment (52.9% vs. 39.9%, p = 0.012). Overall SDQ for chemotherapy was slightly higher in intervention than control subjects (mean 4.8 vs. 4.6, p = 0.08). However, among women who did not receive chemotherapy, significantly more intervention subjects reported high SDQ than controls (87.1% vs. 75.2%, p = 0.06). Values significantly related to chemotherapy use included avoiding side effects, continuing to work, and being most extensive possible. Conclusions: We found that the interactive decision tool contributed significantly to higher knowledge about systemic treatment among eligible patients. We further found the tool shows promise for improving subjective decision quality, particularly in patients who choose not to have chemotherapy. Further work to integrate tools into the oncology clinical setting is needed. Clinical trial information: NCT01840163.

PURPOSE:Health information technology (IT) is an ideal medium to improve the delivery of patient-centered care and increase patient engagement. Health IT interventions should be designed with the end user in mind and be specific to the needs of a given population. Hematopoietic cell transplantation (HCT), commonly referred to as blood and marrow transplantation (BMT), is a prime example of a complex medical procedure where patient-caregiver-provider engagement is central to a safe and successful outcome. We have previously reported on the design and development of an HCT-specific health IT tool, BMT Roadmap.METHODS:This study highlights longitudinal quantitative and qualitative patient-reported outcomes (PROs) in 20 adult patients undergoing allogeneic HCT. Patients completed PROs at three time points (baseline, day 30 post-HTC, and day 100 post-HCT) and provided weekly qualitative data through semistructured interviews while using BMT Roadmap.RESULTS:The mean hospital stay was 23.3 days (range, 17 to 37 days), and patients had access to BMT Roadmap for a mean of 21.3 days (range, 15 to 37 days). The total time spent on BMT Roadmap ranged from 0 to 139 minutes per patient, with a mean of 55 minutes (standard deviation, 47.6 minutes). We found that patients readily engaged with the tool and completed qualitative interviews and quantitative PROs. The Patient Activation Measure, a validated measure of patient engagement, increased for patients from baseline to discharge and day 100. Activation was significantly and negatively correlated with depression and anxiety PROs at discharge, suggesting that this may be an important time point for intervention.CONCLUSION:Given the feasibility and promising results reported in this study, next steps include expanding our current health IT platform and implementing a randomized trial to assess the impact of BMT Roadmap on critical PROs.

Health information technology (HIT) has great potential for increasing patient engagement. Pediatric hematopoietic cell transplantation (HCT) is a setting ripe for using HIT but in which little research exists. "BMT Roadmap" is a web-based application that integrates patient-specific information and includes several domains: laboratory results, medications, clinical trial details, photos of the healthcare team, trajectory of transplant process, and discharge checklist. BMT Roadmap was provided to 10 caregivers of patients undergoing first-time HCT. Research assistants performed weekly qualitative interviews throughout the patient's hospitalization and at discharge and day 100 to assess the impact of BMT Roadmap. Rigorous thematic analysis revealed 5 recurrent themes: emotional impact of the HCT process itself; critical importance of communication among patients, caregivers, and healthcare providers; ways in which BMT Roadmap was helpful during inpatient setting; suggestions for improving BMT Roadmap; and other strategies for organization and management of complex healthcare needs that could be incorporated into BMT Roadmap. Caregivers found the tool useful and easy to use, leading them to want even greater access to information. BMT Roadmap was feasible, with no disruption to inpatient care. Although this initial study is limited by the small sample size and single-institution experience, these initial findings are encouraging and support further investigation.

Health information technology (IT) has opened exciting avenues for capturing, delivering and sharing data, and offers the potential to develop cost-effective, patient-focused applications. In recent years, there has been a proliferation of health IT applications such as outpatient portals. Rigorous evaluation is fundamental to ensure effectiveness and sustainability, as resistance to more widespread adoption of outpatient portals may be due to lack of user friendliness. Health IT applications that integrate with the existing electronic health record and present information in a condensed, user-friendly format could improve coordination of care and communication. Importantly, these applications should be developed systematically with appropriate methodological design and testing to ensure usefulness, adoption, and sustainability. Based on our prior work that identified numerous information needs and challenges of HCT, we developed an experimental prototype of a health IT tool, the BMT Roadmap. Our goal was to develop a tool that could be used in the real-world, daily practice of HCT patients and caregivers (users) in the inpatient setting. Herein, we examined the views, needs, and wants of users in the design and development process of the BMT Roadmap through user-centered Design Groups. Three important themes emerged: 1) perception of core features as beneficial (views), 2) alerting the design team to potential issues with the user interface (needs); and 3) providing a deeper understanding of the user experience in terms of wider psychosocial requirements (wants). These findings resulted in changes that led to an improved, functional BMT Roadmap product, which will be tested as an intervention in the pediatric HCT population in the fall of 2015 (ClinicalTrials.govNCT02409121).

BACKGROUND:Text messages can improve medication adherence and outcomes in several conditions. For this study, experts developed text messages addressing determinants of medication adherence: disease beliefs, medication necessity, medication concerns, and forgetfulness, as well as positive reinforcement messages for patients who were adherent. OBJECTIVES:To validate expert-developed text messages to address medication non-adherence with a group of non-researchers. METHODS:A two-wave, card-sorting activity was conducted with students and staff at the University of Michigan. In the first wave, 40 participants grouped 32 messages addressing barriers for medication adherence (disease beliefs, medication necessity, medication concerns, and forgetfulness) according to their perceived relationship. Messages with poor grouping agreement were deleted or modified. In the second wave, positive reinforcement messages were developed and tested along with the previous categories (36 messages) by 37 participants. Similarity and cluster analyses were used to assess agreement between experts and participants. RESULTS:In the first card-sorting wave, participants grouped messages into between 2 and 13 separate categories. Similarity analysis showed four groupings of messages, however, some had an agreement below 50% and clusters appeared dispersed. In the second wave, and after messages being edited, participants grouped the messages into between 4 and 9 categories. Five groups (now including positive reinforcement messages) were identified with higher agreement in the similarity and cluster analyses. CONCLUSIONS:The structure of expert-developed text messages to address medication adherence key barriers was confirmed. Messages will be used in future research to determine their impact on affecting medication adherence to anti-hypertensive medications using a reinforcement learning controlled text messaging service.

BACKGROUND:Most programs addressing psychosocial concerns of cancer survivors are in-person programs that are expensive to deliver, have limited availability, and seldom deal with caregivers' concerns.OBJECTIVE:This study examined the feasibility of translating an efficacious nurse-delivered program (FOCUS Program) for patients and their caregivers to a tailored, dyadic Web-based format. Specific aims were to (1) test the preliminary effects of the Web-based intervention on patient and caregiver outcomes, (2) examine participants' program satisfaction, and (3) determine the feasibility of using a Web-based delivery format.METHODS:A phase 2 feasibility study was conducted with cancer patients (lung, breast, colorectal, prostate) and their family caregivers (N = 38 dyads). The Web-based intervention provided information and support tailored to the unique characteristics of each patient, caregiver, and their dyadic relationship. Primary outcomes were emotional distress and quality of life. Secondary outcomes were benefits of illness/caregiving, communication, support, and self-efficacy. Analyses included descriptive statistics and repeated-measures analysis of variance.RESULTS:Dyads had a significant decrease in emotional distress, increase in quality of life, and perceived more benefits of illness/caregiving. Caregivers also had significant improvement in self-efficacy. There were no changes in communication. Participants were satisfied with program usability, but recommended additional content.CONCLUSIONS:It was possible to translate a clinician-delivered program to a Web-based format that was easy to use and had positive effects on dyadic outcomes.IMPLICATIONS FOR PRACTICE:The Web-based program is a promising way to provide psychosocial care to more patients and caregivers using fewer personnel. It needs further testing in a larger randomized clinical trial.

Mobile health (mHealth) services cannot easily adapt to users' unique needs.We used simulations of text messaging (SMS) for improving medication adherence to demonstrate benefits of interventions using reinforcement learning (RL).We used Monte Carlo simulations to estimate the relative impact of an intervention using RL to adapt SMS adherence support messages in order to more effectively address each non-adherent patient's adherence barriers, e.g., forgetfulness versus side effect concerns. SMS messages were assumed to improve adherence only when they matched the barriers for that patient. Baseline adherence and the impact of matching messages were estimated from literature review. RL-SMS was compared in common scenarios to simple reminders, random messages, and standard tailoring.RL could produce a 5-14 % absolute improvement in adherence compared to current approaches. When adherence barriers are not accurately reported, RL can recognize which barriers are relevant for which patients. When barriers change, RL can adjust message targeting. RL can detect when messages are sent too frequently causing burnout.RL systems could make mHealth services more effective.