User Feedback on the Use of a Natural Language Processing Application to Screen for Suicide Risk in the Emergency Department.

Suicide is the 10th leading cause of death in the USA and globally. Despite decades of research, the ability to predict who will die by suicide is still no better than 50%. Traditional screening instruments have helped identify risk factors for suicide, but they have not provided accurate predictive power for reducing death rates. Over the past decade, natural language processing (NLP), a form of machine learning (ML), has been used to identify suicide risk by analyzing language data. Recent work has demonstrated the successful integration of a suicide risk screening interview to collect language data for NLP analysis from patients in two emergency departments (ED) of a large healthcare system. Results indicated that ML/NLP models performed well identifying patients that came to the ED for suicide risk. However, little is known about the clinician's perspective of how a qualitative brief interview suicide risk screening tool to collect language data for NLP integrates into an ED workflow. This report highlights the feedback and observations of patient experiences obtained from clinicians using brief suicide screening interviews. The investigator used an open-ended, narrative interview approach to inquire about the qualitative interview process. Three overarching themes were identified: behavioral health workflow, clinical implications of interview probes, and integration of an application into provider patient experience. Results suggest a brief, qualitative interview method was feasible, person-centered, and useful as a suicide risk detection approach.

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions.

BACKGROUND: As adolescent suicide rates continue to rise, innovation in risk identification is warranted. Machine learning can identify suicidal individuals based on their language samples. This feasibility pilot was conducted to explore this technology's use in adolescent therapy sessions and assess machine learning model performance. METHOD: Natural language processing machine learning models to identify level of suicide risk using a smartphone app were tested in outpatient therapy sessions. Data collection included language samples, depression and suicidality standardized scale scores, and therapist impression of the client's mental state. Previously developed models were used to predict suicidal risk. RESULTS: 267 interviews were collected from 60 students in eight schools by ten therapists, with 29 students indicating suicide or self-harm risk. During external validation, models were trained on suicidal speech samples collected from two separate studies. We found that support vector machines (AUC: 0.75; 95% CI: 0.69-0.81) and logistic regression (AUC: 0.76; 95% CI: 0.70-0.82) lead to good discriminative ability, with an extreme gradient boosting model performing the best (AUC: 0.78; 95% CI: 0.72-0.84). CONCLUSION: Voice collection technology and associated procedures can be integrated into mental health therapists' workflow. Collected language samples could be classified with good discrimination using machine learning methods.

Cluster Randomized Trial of a Church-Based Peer Counselor and Tailored Newsletter Intervention to Promote Colorectal Cancer Screening and Physical Activity Among Older African Americans.

Action Through Churches in Time to Save Lives (ACTS) of Wellness was a cluster randomized controlled trial developed to promote colorectal cancer screening and physical activity (PA) within urban African American churches. Churches were recruited from North Carolina (n = 12) and Michigan (n = 7) and were randomized to intervention (n = 10) or comparison (n = 9). Intervention participants received three mailed tailored newsletters addressing colorectal cancer screening and PA behaviors over approximately 6 months. Individuals who were not up-to-date for screening at baseline could also receive motivational calls from a peer counselor. The main outcomes were up-to-date colorectal cancer screening and Metabolic Equivalency Task (MET)-hours/week of moderate-vigorous PA. Multivariate analyses examined changes in the main outcomes controlling for church cluster, gender, marital status, weight, and baseline values. Baseline screening was high in both intervention (75.9%, n = 374) and comparison groups (73.7%, n = 338). Screening increased at follow-up: +6.4 and +4.7 percentage points for intervention and comparison, respectively (p = .25). Baseline MET-hours/week of PA was 7.8 (95% confidence interval [6.8, 8.7]) for intervention and 8.7 (95% confidence interval [7.6, 9.8]) for the comparison group. There were no significant changes (p = .15) in PA for intervention (-0.30 MET-hours/week) compared with the comparison (-0.05 MET-hours/week). Among intervention participants, PA increased more for those who participated in church exercise programs, and screening improved more for those who spoke with a peer counselor or recalled the newsletters. Overall, the intervention did not improve PA or screening in an urban church population. These findings support previous research indicating that structured PA opportunities are necessary to promote change in PA and churches need more support to initiate effective peer counselor programs.

Physical activity in young adults: a signal detection analysis of Health Information National Trends Survey (HINTS) 2007 data.

Many young adults are insufficiently active to achieve the health benefits of regular physical activity. Using signal detection analysis of data from the 2007 Health Information National Trends Survey, the authors examined distinct subgroups of 18-39 year-old adults who vary in their likelihood of not meeting physical activity recommendations. We randomly split the sample and conducted signal detection analysis on the exploratory half to identify subgroups and interactions among sociodemographic and health communication variables that predicted engaging in less than 150 minutes per week of moderate-intensity physical activity (low physical activity). We compared rates of low physical activity among subgroups with similarly defined subgroups in the validation sample. Overall, 62% of participants did not meet physical activity recommendations. Among 8 subgroups identified, low physical activity rates ranged from 31% to 90%. Predictors of low physical activity were general health, body mass index (BMI), perceived cancer risk, health-related Internet use, and trust in information sources. The least active subgroup (90% low physical activity) included young adults in poor to good health with a BMI of 30.8 or more (obese). The most active subgroup (31% low physical activity) comprised those in very good to excellent health, who used a website to help with diet, weight, or physical activity, and had little to no trust in health information on television. Findings suggest potential intervention communication channels and can inform targeted physical activity interventions for young adults.

Information processing versus social cognitive mediators of weight loss in a podcast-delivered health intervention.

Podcasting is an emerging technology, and previous interventions have shown promising results using theory-based podcast for weight loss among overweight and obese individuals. This study investigated whether constructs of social cognitive theory and information processing theories (IPTs) mediate the effect of a podcast intervention on weight loss among overweight individuals. Data are from Pounds off Digitally, a study testing the efficacy of two weight loss podcast interventions (control podcast and theory-based podcast). Path models were constructed (n = 66). The IPTs, elaboration likelihood model, information control theory, and cognitive load theory mediated the effect of a theory-based podcast on weight loss. The intervention was significantly associated with all IPTs. Information control theory and cognitive load theory were related to elaboration, and elaboration was associated with weight loss. Social cognitive theory constructs did not mediate weight loss. Future podcast interventions grounded in theory may be effective in promoting weight loss.

Process of diffusing cancer survivorship care into oncology practice.

The LIVESTRONG Centers of Excellence were funded to increase the effectiveness of survivorship care in oncology practice. This study describes the ongoing process of adopting and implementing survivorship care using the framework of the diffusion of innovation theory of change. Primary data collection included telephone interviews with 39 members from the eight centers and site visits. Organizational characteristics, overall progress, and challenges for implementation were collected from proposals and annual reports. Creating an awareness of cancer survivorship care was a major accomplishment (relative advantage). Adoption depended on the fit within the cancer center (compatibility), and changed over time based on trial and error (trialability). Implementing survivorship care within the existing culture of oncology and breaking down resistance to change was a lengthy process (complexity). Survivorship care became sustainable as it became reimbursed, and more new patients were seen (observability). Innovators and early adopters were crucial to success. Diffusion of innovation theory can provide a strategy to evaluate adoption and implementation of cancer survivorship programs into clinical practice.

Primary care providers' self-efficacy and outcome expectations for childhood obesity counseling.

BACKGROUND: Primary care providers have a role in the prevention and management of childhood obesity. We explored the relationship of providers' self-efficacy, outcome expectations, and practice level support with childhood obesity counseling frequency. METHODS: Providers (n=123) completed a survey that assessed their self-efficacy, outcome expectations, and reported obesity counseling frequency. A practice level assessment tool was used to characterize the practices. We analyzed data using frequencies and proportional odds modeling. RESULTS: Providers were confident or very confident (78.5-93.5%) in their ability to counsel about healthy eating, physical activity, and weight and agreed or strongly agreed (64.2-86.2%) that their counseling would result in actual changes. Providers with higher outcome expectations were more likely [odds ratio (OR)=3.4] to report providing obesity counseling. Female providers were more likely to report counseling about obesity (OR=2.3) than males. Providers in practices with resources for healthy eating and physical activity reported higher levels of self-efficacy and counseling frequency. CONCLUSIONS: In our study, providers were confident in their ability to provide obesity counseling and expected changes from their efforts, suggesting that future studies should build on the high level of outcome expectations as well as self-efficacy. The gender difference found regarding obesity counseling may need further exploration.

Promoting fruit and vegetable consumption among members of black churches, Michigan and North Carolina, 2008-2010.

INTRODUCTION: Evidence-based health promotion programs that are disseminated in community settings can improve population health. However, little is known about how effective such programs are when they are implemented in communities. We examined community implementation of an evidence-based program, Body and Soul, to promote consumption of fruits and vegetables. METHODS: We randomly assigned 19 churches to 1 of 2 arms, a colon cancer screening intervention or Body and Soul. We conducted our study from 2008 through 2010. We used the RE-AIM (reach, effectiveness, adoption, implementation, and maintenance) framework to evaluate the program and collected data via participant surveys, on-site observations, and interviews with church coordinators and pastors. RESULTS: Members of 8 churches in Michigan and North Carolina participated in the Body and Soul program. Mean fruit and vegetable consumption increased from baseline (3.9 servings/d) to follow-up (+0.35, P = .04). The program reached 41.4% of the eligible congregation. Six of the 8 churches partially or fully completed at least 3 of the 4 program components. Six churches expressed intention to maintain the program. Church coordinators reported limited time and help to plan and implement activities, competing church events, and lack of motivation among congregation members as barriers to implementation. CONCLUSIONS: The RE-AIM framework provided an effective approach to evaluating the dissemination of an evidence-based program to promote health. Stronger emphasis should be placed on providing technical assistance as a way to improve other community-based translational efforts.

Delivering health information via podcast or web: media effects on psychosocial and physiological responses.

This study explored differences in psychosocial and physiological variables in response to being presented with information on weight loss through either reading text on a website or listening to the same information via podcast. Participants were randomized to receive a weight loss website (n = 20) or podcast (n = 20). Participants had skin conductance levels measured and completed questionnaire items assessing demographic characteristics, user control, novelty, and knowledge. Participants in the podcast group exhibited greater levels of physiological arousal and reported the intervention to be more novel than those in the Web group; however, the Web group reported greater user control. There was no difference in knowledge between the groups. This study presents the first step in examining the role that novelty and user control may play in two different weight-loss electronic media, as well as differences in knowledge acquisition. Future research should explore adding additional media features, such as video content, to the podcasts and websites in order to optimize fully the different mediums and to examine whether user control and novelty are potential mediators of weight loss outcomes.

The use of motivational interviewing to promote peer-to-peer support for cancer survivors.

Motivational interviewing (MI) as a counseling approach has gained empirical support for its use in a number of settings and for a variety of behaviors. However, the majority of practitioners trained to use MI have been professionals rather than laypeople. This article presents the rationale, design, and evaluation of an MI-based training for cancer survivors and caregivers to deliver peer support. The training and evaluation of the peers ("guides") to encourage practice and increase research knowledge for using MI-based peer support models for cancer care are discussed. Thirteen cancer survivors and two caregivers received two-day DVD-based MI training, as well as supplemental monthly sessions for six months. The guides demonstrated MI proficiency as assessed by the MI Treatment Integrity scale and other process evaluation assessments. MI can be adapted to train laypeople to provide support for groups such as cancer survivors.

Colorectal cancer screening and physical activity promotion among obese women: an online evaluation of targeted messages.

Obese women are at higher risk for several cancers, but are less likely than normal weight women to engage in cancer prevention behaviors such as screening and physical activity. Targeted health messages may help increase healthy behaviors among vulnerable groups such as obese women. Using findings from focus groups with obese women, the authors created targeted messages to promote colorectal cancer screening and physical activity among obese women. The messages addressed psychosocial constructs, such as benefits and barriers to colorectal cancer screening and exercise, which were relevant to the target population. Messages were tested online with women age 50 years and older (N = 181). Participants were stratified by weight (obese vs. nonobese) and randomized to review either 10 targeted (intervention) or 10 generic (control) messages. Study outcomes included elaboration about the messages, message relevance and trustworthiness, and behavioral intentions. The authors used moderation and subgroup analyses to determine whether the intervention messages were better received by certain women. They found no differences in elaboration, behavioral intentions, relevance, or trustworthiness between intervention and control for either weight group. However, exercise intentions increased more (p = .06) among inactive obese women who received intervention messages (+2.9) compared with those who were in the control group (+1.2). Intervention messages also produced more elaboration among women who viewed their weight as a barrier to screening or exercise. Tailoring intervention messages for obese women on the basis of behavior and barriers may improve outcomes more than giving the same messages to all obese women.

Associations between dietary patterns and head and neck cancer: the Carolina head and neck cancer epidemiology study.

Few studies have examined the associations between dietary patterns and head and neck squamous cell carcinoma (SCC) or whether they differ by race. This was evaluated using data from a population-based case-control study (2002-2006) including 1,176 cases of head and neck SCC and 1,317 age-, race-, and gender-matched controls from central and eastern North Carolina whose diets had been assessed by food frequency questionnaire. Factor analysis identified 2 patterns of intake: 1) high consumption of fruits, vegetables, and lean protein and 2) high consumption of fried foods, high-fat and processed meats, and sweets. Associations were estimated using logistic regression, adjusting for matching factors and confounders. Heterogeneity by tumor site (oral/pharyngeal vs. laryngeal) and effect-measure modification were also evaluated. Reduced odds of head and neck SCC were found for the fruit, vegetable, and lean protein pattern (for highest quartile vs. lowest, odds ratio = 0.53, 95% confidence interval: 0.39, 0.71). The fried foods, high-fat and processed meats, and sweets pattern was positively associated only with laryngeal cancer (odds ratio = 2.12, 95% confidence interval: 1.21, 3.72). These findings underline the importance of a dietary pattern rich in fruits and vegetables and low in high-fat and processed meats and sweets for prevention of head and neck cancer.

Evaluating the dissemination of Body & Soul, an evidence-based fruit and vegetable intake intervention: challenges for dissemination and implementation research.

OBJECTIVE: To evaluate whether the evidence-based Body & Soul program, when disseminated and implemented without researcher or agency involvement and support, would achieve results similar to those of earlier efficacy and effectiveness trials. DESIGN: Prospective group randomized trial. SETTING: Churches with predominantly African American membership. PARTICIPANTS: A total of 1,033 members from the 15 churches completed baseline surveys. Of these participants, 562 (54.4%) completed the follow-up survey 6 months later. INTERVENTION: Church-based nutrition program for African Americans that included pastoral involvement, educational activities, church environmental changes, and peer counseling. MAIN OUTCOME MEASURE: Daily fruit and vegetable (FV) intake was assessed at pre- and posttest. ANALYSIS: Mixed-effects linear models. RESULTS: At posttest, there was no statistically significant difference in daily servings of FVs between the early intervention group participants compared to control group participants (4.7 vs 4.4, P = .38). Process evaluation suggested that added resources such as technical assistance could improve program implementation. CONCLUSIONS AND IMPLICATIONS: The disseminated program may not produce improvements in FV intake equal to those in the earlier efficacy and effectiveness trials, primarily because of a lack of program implementation. Program dissemination may not achieve public health impact unless support systems are strengthened for adequate implementation at the church level.

A computerized intervention to promote colorectal cancer screening for underserved populations: theoretical background and algorithm development.

OBJECTIVE: The aim of this exploratory study was to assess factors deemed by patients as "important" as they planned and considered undergoing colorectal cancer (CRC) screening, and to use this data to design a computer-delivered intervention to promote screening. METHODS: Fifty participants 50 years or older, not up-to-date with current recommended CRC screening guidelines, were recruited from a primary care clinic. A semi-structured interview focused on aspects of preparing for colorectal cancer screening was administered; after transcription, researchers used triangulation and consensus to identify relevant themes and concepts. RESULTS: Four main themes were identified that dealt with issues important for both FOBT and colonoscopy planning: personal concerns, reminders, communication with healthcare providers and obtaining test results. FOBT specific themes included: sample collection and return. For colonoscopy screening, themes included: scheduling, intervention questions, colonoscopy preparation, and transportation. These can be classified as barrier, process and accessory themes. The developed computer-administered implementation intentions algorithm addressed all the identified concerns in a planned and sequential manner, in order to facilitate planning for CRC screening. CONCLUSIONS: The results of this study suggest that appropriate reminders, explanations of procedures, and patient understanding of temporary life disruptions, help patients develop and accept a detailed screening plan.

A culturally adapted telecommunication system to improve physical activity, diet quality, and medication adherence among hypertensive African-Americans: a randomized controlled trial.

BACKGROUND: Hypertension is more prevalent and clinically severe among African-Americans than whites. Several health behaviors influence blood pressure (BP) control, but effective, accessible, culturally sensitive interventions that target multiple behaviors are lacking. PURPOSE: We evaluated a culturally adapted, automated telephone system to help hypertensive, urban African-American adults improve their adherence to their antihypertensive medication regimen and to evidence-based guidelines for dietary behavior and physical activity. METHODS: We randomized 337 hypertensive primary care patients to an 8-month automated, multi-behavior intervention or to an education-only control. Medication adherence, diet, physical activity, and BP were assessed at baseline and every 4 months for 1 year. Data were analyzed using longitudinal modeling. RESULTS: The intervention was associated with improvements in a measure of overall diet quality (+3.5 points, p < 0.03) and in energy expenditure (+80 kcal/day, p < 0.03). A decrease in systolic BP between groups was not statistically significant (-2.3 mmHg, p = 0.25). CONCLUSIONS: Given their convenience, scalability, and ability to deliver tailored messages, automated telecommunications systems can promote self-management of diet and energy balance in urban African-Americans.

Implementing the MOVE! weight-management program in the Veterans Health Administration, 2007-2010: a qualitative study.

INTRODUCTION: One-third of US veterans receiving care at Veterans Health Administration (VHA) medical facilities are obese and, therefore, at higher risk for developing multiple chronic diseases. To address this problem, the VHA designed and nationally disseminated an evidence-based weight-management program (MOVE!). The objective of this study was to examine the organizational factors that aided or inhibited the implementation of MOVE! in 10 VHA medical facilities. METHODS: Using a multiple, holistic case study design, we conducted 68 interviews with medical center program coordinators, physicians formally appointed as program champions, managers directly responsible for overseeing the program, clinicians from the program's multidisciplinary team, and primary care physicians identified by program coordinators as local opinion leaders. Qualitative data analysis involved coding, memorandum writing, and construction of data displays. RESULTS: Organizational readiness for change and having an innovation champion were most consistently the 2 factors associated with MOVE! implementation. Other organizational factors, such as management support and resource availability, were barriers to implementation or exerted mixed effects on implementation. Barriers did not prevent facilities from implementing MOVE! However, they were obstacles that had to be overcome, worked around, or accepted as limits on the program's scope or scale. CONCLUSION: Policy-directed implementation of clinical weight-management programs in health care facilities is challenging, especially when no new resources are available. Instituting powerful, mutually reinforcing organizational policies and practices may be necessary for consistent, high-quality implementation.

Cancer screening patterns by weight group and gender for urban African American church members.

Obese white women have lower rates of cancer screening compared to non-obese women. This study will determine if a relationship exists between weight and adherence to cancer screening guidelines among African Americans. We used multivariate logistic regression to examine the relationship between being up-to-date with cancer screening (colorectal, breast, cervical, and prostate) and weight group (normal, overweight, obese I, obese II+) using data from older (age 50+) members (N = 955) of 20 African American churches in Michigan and North Carolina. CRC testing rates were examined using multiple definitions to account for differences in screening rates vs. polyp surveillance rates. After adjusting for confounders, we found relationships between weight group and up-to-date CRC (P = 0.04) and PSA (P = 0.004) testing for men and mammography (P = 0.03) for women. Compared to normal-weight men, obese I men were more likely to be up-to-date with CRC (OR 2.35, 95%CI 1.02-5.40) and PSA (OR 4.24 95%CI 1.77-10.17) testing. CRC screening rates were lower when individuals with polyps were excluded from the analysis; however, patterns by weight remained the same. Contrary to previous research, we did not find lower rates of cancer screening among obese African Americans. Instead, we found that normal-weight African American men had lower screening rates than any other group. As we did not consistently find lower screening rates among obese African Americans, targeting this group for increased screening promotion may not be the most effective way to reduce weight-related cancer disparities.

An examination of sociodemographic, health, psychological factors, and fruit and vegetable consumption among overweight and obese U.S. veterans.

A diet high in fruits and vegetables (F&Vs) is associated with decreased risk for cardiovascular disease, diabetes, and cancer. This study investigated the relationship between sociodemographic, health, and psychosocial factors and F&V consumption among overweight and obese U.S. veterans. Participants were recruited from two Veterans Affairs medical center sites in 2005. Two hundred eighty-nine participants completed a self-administered survey. Bivariate and multivariate linear regression models were built to examine the association between sociodemographic, health, and psychosocial variables and F&V consumption. Older age (B = 0.01; p < 0.001) and being Black (B = -0.18; p < 0.05) were related to increased F&V consumption. Reported tobacco use was inversely associated with F&V consumption (B = -0.30; p < 0.01). Greater self-efficacy (B = 0.07; p < 0.05), fewer perceived barriers (B = -0.14; p < 0.01), and correct knowledge of recommended daily F&V intake (B = 0.12; p <0.05) were related to eating more F&Vs. U.S. veterans disproportionately experience overweight and obese conditions. Age, race, tobacco use, and psychosocial factors should be considered carefully when developing dietary interventionsamong overweight ana obese U.S. veterans.

How confident are young adult cancer survivors in managing their survivorship care? A report from the LIVESTRONG™ Survivorship Center of Excellence Network.

INTRODUCTION: This study examined the association between sociodemographic, cancer treatment, and care delivery factors on young adult cancer survivors' confidence in managing their survivorship care. METHODS: Survivors aged 18-39 years (n = 376) recruited from the LIVESTRONG™ Survivorship Center of Excellence Network sites completed a survey assessing self-reported receipt of survivorship care planning, expectations of their providers, and confidence in managing their survivorship care. Multivariate logistic regression identified characteristics of those reporting low confidence in managing their survivorship care. RESULTS: Mean age was 28 years; mean interval from diagnosis was 9 ± 8 years. Seventy-one percent reported currently attending an oncology survivorship clinic. Regarding survivorship care planning, 33% did not have copies of their cancer-related medical records, 48% did not have a treatment summary, and 55% had not received a survivorship care plan. Seventy percent identified the oncologist as the most important health care provider for decisions regarding test and treatment decisions while 10% reported using a "shared-care model" involving both primary care providers and oncologists. Forty-one percent were classified as having low confidence in managing survivorship care. In multivariate analysis, low confidence was associated with non-white ethnicity and lack of a survivorship care plan (both p < 0.05). DISCUSSION/CONCLUSIONS: Findings suggest that provision of survivorship care plans for young adult cancer survivors can be used to improve confidence in managing survivorship care, particularly for ethnic minorities. IMPLICATIONS FOR CANCER SURVIVORS: Survivors should consider advocating for receipt of a survivorship care plan as it may facilitate confidence as a consumer of survivorship care.

Survivorship care planning after the institute of medicine recommendations: how are we faring?

INTRODUCTION: This study evaluates the concordance of treatment summaries (TSs) and survivorship care plans (SCPs) delivered to breast cancer survivors within the LIVESTRONG™ Network of Survivorship Centers of Excellence with Institute of Medicine (IOM) recommendations and describes additional structure/process variables. METHOD: Seven NCI-designated comprehensive cancer centers and six community-based centers participated. TS/SCPs for 65 patients were rated against IOM recommendations using a study-derived checklist, and surveys were administered to better understand the structure and process of delivering TSs/SCPs. RESULTS: On average, fewer than half of IOM content recommendations were met for TSs (M = 46%) and less than two thirds for SCPs (M = 59%). No sites achieved ≥75% overall concordance with IOM recommendations for TSs and only two of 13 met this criterion for SCPs. Content domain scores across sites varied widely, as did the number of sites addressing domain content with ≥75% concordance. Nonetheless, resources required for document preparation and delivery were substantial. DISCUSSION: Gaps in concordance with IOM recommendations exist even in dedicated survivorship centers. A substantial time burden was also noted. Further research is needed to determine which informational elements are essential, to develop and test strategies for improving efficiency and reach, and to determine if outcomes of survivorship care planning warrant the resources required in their preparation and delivery. IMPLICATIONS FOR SURVIVORS: TSs and SCPs have been recommended for all cancer survivors. Essential elements must be determined, approaches made more efficient, outcome improvements demonstrated, and cost-benefit analyses determined before survivors should expect widespread implementation of this recommendation for survivorship care.