Current status of artificial intelligence methods for skin cancer survival analysis: a scoping review.

Skin cancer mortality rates continue to rise, and survival analysis is increasingly needed to understand who is at risk and what interventions improve outcomes. However, current statistical methods are limited by inability to synthesize multiple data types, such as patient genetics, clinical history, demographics, and pathology and reveal significant multimodal relationships through predictive algorithms. Advances in computing power and data science enabled the rise of artificial intelligence (AI), which synthesizes vast amounts of data and applies algorithms that enable personalized diagnostic approaches. Here, we analyze AI methods used in skin cancer survival analysis, focusing on supervised learning, unsupervised learning, deep learning, and natural language processing. We illustrate strengths and weaknesses of these approaches with examples. Our PubMed search yielded 14 publications meeting inclusion criteria for this scoping review. Most publications focused on melanoma, particularly histopathologic interpretation with deep learning. Such concentration on a single type of skin cancer amid increasing focus on deep learning highlight growing areas for innovation; however, it also demonstrates opportunity for additional analysis that addresses other types of cutaneous malignancies and expands the scope of prognostication to combine both genetic, histopathologic, and clinical data. Moreover, researchers may leverage multiple AI methods for enhanced benefit in analyses. Expanding AI to this arena may enable improved survival analysis, targeted treatments, and outcomes.

Long term impact of PositiveLinks: Clinic-deployed mobile technology to improve engagement with HIV care.

BACKGROUND: PositiveLinks (PL) is a smartphone-based platform designed in partnership with people living with HIV (PLWH) to improve engagement in care. PL provides daily medication reminders, check-ins about mood and stress, educational resources, a community message board, and an ability to message providers. The objective of this study was to evaluate the impact of up to 24 months of PL use on HIV viral suppression and engagement in care and to examine whether greater PL use was associated with improved outcomes. SETTING: This study occurred between September 2013 and March 2017 at a university-based Ryan White HIV clinic. METHODS: We assessed engagement in care and viral suppression from study baseline to the 6-, 12-, 18- and 24-month follow-up time periods and compared trends among high vs. low PL users. We compared time to viral suppression, proportion of days virally suppressed, and time to engagement in care in patients with high vs. low PL use. RESULTS: 127 patients enrolled in PL. Engagement in care and viral suppression improved significantly after 6 months of PL use and remained significantly improved after 24 months. Patients with high PL use were 2.09 (95% CI 0.64-6.88) times more likely to achieve viral suppression and 1.52 (95% CI 0.89-2.57) times more likely to become engaged in care compared to those with low PL use. CONCLUSION: Mobile technology, such as PL, can improve engagement in care and clinical outcomes for PLWH. This study demonstrates long-term acceptability of PL over two years and provides evidence for long-term improvement in engagement in care and viral suppression associated with PL use.

Development of PositiveLinks: A Mobile Phone App to Promote Linkage and Retention in Care for People With HIV.

BACKGROUND: Linkage to and retention in HIV care are challenging, especially in the Southeastern United States. The rise in mobile phone app use and the potential for an app to deliver just in time messaging provides a new opportunity to improve linkage and retention among people living with HIV (PLWH). OBJECTIVE: This study aimed to develop an app to engage, link, and retain people in care. We evaluated the acceptability, feasibility, and impact of the app among users. METHODS: App development was informed by principles of chronic disease self-management and formative interviews with PLWH. Once developed, the app was distributed among participants, and usability feedback was incorporated in subsequent iterations. We interviewed app users after 3 weeks to identify usability issues, need for training on the phone or app, and to assess acceptability. We tracked and analyzed usage of app features for the cohort over 2 years. RESULTS: A total of 77 participants used the app during the pilot study. The query response rate for the first 2 years was 47.7%. Query response declined at a rate of 0.67% per month. The community message board was the most popular feature, and 77.9% (60/77) of users posted on the board at least once during the 2 years. CONCLUSIONS: The PositiveLinks app was feasible and acceptable among nonurban PLWH. High participation on the community message board suggests that social support from peers is important for people recently diagnosed with or returning to care for HIV.

Addressing Stigma Through a Virtual Community for People Living with HIV: A Mixed Methods Study of the PositiveLinks Mobile Health Intervention.

Stigma has negative consequences for quality of life and HIV care outcomes. PositiveLinks is a mobile health intervention that includes a secure anonymous community message board (CMB). We investigated discussion of stigma and changes in stigma scores. Of 77 participants in our pilot, 63% were male, 49% Black, and 72% had incomes below the federal poverty level. Twenty-one percent of CMB posts (394/1834) contained stigma-related content including negative (experiencing stigma) and positive (overcoming stigma) posts addressing intrapersonal and interpersonal stigma. Higher baseline stigma was positively correlated with stress and negatively correlated with HIV care self-efficacy. 12-month data showed a trend toward more improved stigma scores for posters on the CMB versus non-posters (- 4.5 vs - 0.63) and for posters of stigma-related content versus other content (- 5.1 vs - 3.3). Preliminary evidence suggests that a supportive virtual community, accessed through a clinic-affiliated smartphone app, can help people living with HIV to address stigma.

PositiveLinks: A Mobile Health Intervention for Retention in HIV Care and Clinical Outcomes with 12-Month Follow-Up.

Mobile health interventions may help People Living with HIV (PLWH) improve engagement in care. We designed and piloted PositiveLinks, a clinic-affiliated mobile intervention for PLWH, and assessed longitudinal impact on retention in care and viral suppression. The program was based at an academic Ryan White Clinic serving a nonurban population in Central Virginia. The PL intervention included a smartphone app that connected participants to clinic staff and provided educational resources, daily queries of stress, mood and medication adherence, weekly quizzes, appointment reminders, and a virtual support group. Outcomes were analyzed using McNemar's tests for HRSA-1, visit constancy, and viral suppression and nonparametric Wilcoxon signed-rank tests for CD4 counts and viral loads. Of 77 participants, 63% were male, 49% black non-Hispanic, and 72% below the federal poverty level. Participants' achievement of a retention in care benchmark (HRSA-1) increased from 51% at baseline to 88% at 6 months (p < 0.0001) and 81% at 12 months (p = 0.0003). Visit constancy improved from baseline to 6 months (p = 0.016) and 12 months (p = 0.0004). Participants' mean CD4 counts increased from baseline to 6 months (p = 0.0007) and 12 months (p = 0.0005). The percentage of participants with suppressed viral loads increased from 47% at baseline to 87% at 6 months (p < 0.0001) and 79% at 12 months (p = 0.0007). This study is one of the first to demonstrate that a mobile health intervention can have a positive impact on retention in care and clinical outcomes for vulnerable PLWH. Next steps include integration with clinical practice and dissemination.

Social Support in a Virtual Community: Analysis of a Clinic-Affiliated Online Support Group for Persons Living with HIV/AIDS.

Social support can improve outcomes for people living with HIV (PLWH) and could be provided through online support groups. The Positive Links smartphone app is a multicomponent intervention that allows users to interact in a clinic-affiliated anonymous online support group. We investigated how social support was exchanged in a group of 55 participants over 8 months, using an adaptation of the Social Support Behavior Code. Participant interviews assessed their experiences and perceptions of the app. Of 840 posts analyzed, 115 (14 %) were coded as eliciting social support and 433 (52 %) as providing social support. Messages providing support were predominantly emotional (41 %), followed by network (27 %), esteem (24 %), informational (18 %), and instrumental (2 %) support. Participants perceived connection and support as key benefits of the app. Technical issues and interpersonal barriers limited some participants in fully using the app. Mobile technology offers a useful tool to reach populations with barriers to in-person support and may improve care for PLWH.

Content Analysis and User Characteristics of a Smartphone-Based Online Support Group for People Living with HIV.

BACKGROUND: Although there is growing interest in mobile applications and online support groups to enhance chronic disease self-management, little is known about their potential impact for people living with HIV (PLWH). INTRODUCTION: We developed an innovative online support group delivered through a community message board (CMB) within a clinic-affiliated smartphone application Positive Links (PL). We analyzed characteristics of posters and nonposters to the CMB and evaluated content posted to the CMB. MATERIALS AND METHODS: For this study, 38 HIV-infected patients received cell phones with the PL application that included the opportunity to interact with other users on a CMB. Logistic regressions investigated associations between participant characteristics and posting. CMB messages were downloaded and analyzed qualitatively. RESULTS: 24 participants posted to the CMB; 14 did not. Participants had lower odds of posting if they were white (p = 0.028) and had private insurance (p = 0.003). Participants had higher odds of posting if they had unsuppressed viral loads (p = 0.034). Of the 840 CMB messages over 8 months, 62% had psychosocial content, followed by community chat (29%), and biomedical content (10%). DISCUSSION: Psychosocial content was most prevalent on this CMB, in contrast to other online forums dominated by informational content. Participants who posted expressed support for each other, appreciation for the community, and a perception that the app played a positive role in their HIV self-management. CONCLUSIONS: This CMB on a clinic-affiliated mobile application may reach vulnerable populations, including racial/ethnic minorities and those of lower socioeconomic status, and provide psychosocial support to PLWH.

Pilot RCT of bidirectional text messaging for ART adherence among nonurban substance users with HIV.

OBJECTIVE: This pilot study tested the preliminary efficacy of a theory-based bidirectional text messaging intervention (TEXT) on antiretroviral (ART) adherence, missed care visits, and substance use among people with HIV. METHOD: Participants with recent substance use and ART nonadherence from 2 nonurban HIV clinics were randomized to TEXT or to usual care (UC). The TEXT intervention included daily queries of ART adherence, mood, and substance use. The system sent contingent intervention messages created by participants for reports of adherence/nonadherence, good mood/poor mood, and no substance use/use. Assessments were at preintervention, postintervention, and 3-month postintervention follow-up. Objective primary outcomes were adherence, measured by past 3-month pharmacy refill rate, and proportion of missed visits (PMV), measured by medical records. The rate of substance-using days from the timeline follow-back was a secondary outcome. RESULTS: Sixty-three patients participated, with 33 randomized to TEXT and 30 to UC. At preintervention, adherence was 64.0%, PMV was 26.9%, and proportion of days using substances was 53.0%. At postintervention, adherence in the TEXT condition improved from 66% to 85%, compared with 62% to 71% in UC participants (p = .04). PMV improved from 23% to 9% for TEXT participants and 31% to 28% in UC participants (p = .12). There were no significant differences between conditions in substance-using days at postintervention. At 3-month follow-up, differences were not significant. CONCLUSIONS: Personalized bidirectional text messaging improved adherence and shows promise to improve visit attendance, but did not reduce substance using days. This intervention merits further testing and may be cost-efficient given its automation.

Smartphone preventive health care: parental use of an immunization reminder system.

INTRODUCTION: This study examined the feasibility of using a smartphone application recall/reminder system for immunizations given in pediatric primary care. METHOD: The study used a typical descriptive study design. A convenience sample of parents and caregivers was recruited from a primary care pediatric office in a middle-class suburban area. Participants used an Android smartphone application ("Call the Shots") that served as a reminder/recall system for vaccinations and offered an embedded tool kit to obtain reliable information about vaccines. RESULTS: A total of 262 persons accessed the application's Web site. The application was downloaded and used by 45 of those persons during the study; six persons completed the survey. DISCUSSION: Data are insufficient to fully evaluate the usefulness of the "Call the Shots" smartphone application. However, initial results and feedback have been positive, and the application should be launched in Apple's platform to reach a wider test audience.

Development of a personalized bidirectional text messaging tool for HIV adherence assessment and intervention among substance abusers.

We describe the development of a two-way text messaging intervention tool for substance users who are non-adherent with HIV medications, and examine message flow data for feasibility and acceptability. The assessment and intervention tool, TxText, is fully automated, sending participants mood, substance use, and medication adherence queries by text message. Participants respond, the tool recognizes the category of response, and sends the personalized intervention message that participants designed in return. In 10months, the tool sent 16,547 messages (half initial, half follow-up) to 31 participants assigned to the TxText condition, who sent 6711 messages in response to the initial messages. Response rates to substance use (n=2370), medication (n=2918) and mood (n=4639) queries were 67, 69, and 64%, respectively. Responses indicating medication adherence, abstinence from substances, and good moods were more common than negative responses. The TxText tool can send messages daily over a 3month period, receive responses, and decode them to deliver personalized affirming or intervention messages. While we await the outcomes of a pilot randomized trial, the process analysis shows that TxText is acceptable and feasible for substance abusers with HIV, and may serve as a complement to HIV medical care.

Relative effects of estrogen, age, and visceral fat on pulsatile growth hormone secretion in healthy women.

Growth hormone (GH) secretion is subject to complex regulation. How pre- and postmenopausal age (PRE, POST), estradiol (E(2)) availability, and abdominal visceral fat (AVF) jointly affect peptidyl-secretagogue drive of GH secretion is not known. To this end, healthy PRE (n = 20) and POST (n = 22) women underwent a low- vs. high-E(2) clamp before receiving a continuous intravenous infusion of GH-releasing hormone (GHRH) or GH-releasing peptide (GHRP-2). According to analysis of covariance, PRE and POST women achieved age-independent hypo- and euestrogenemia under respective low- and high-E(2) clamps. All four of age (P < 0.001), E(2) status (P = 0.006), secretagogue type (P < 0.001), and an age x peptide interaction (P = 0.014) controlled pulsatile GH secretion. Independently of E(2) status, POST women had lower GH responses to both GHRH (P = 0.028) and GHRP-2 (P < 0.001) than PRE women. Independently of age, GHRP-2 was more stimulatory than GHRH during low E(2) (P = 0.011) and high E(2) (P < 0.001). Stepwise forward-selection multivariate analysis revealed that computerized tomographic estimates of AVF explained 22% of the variability in GHRH action (P = 0.002), whereas age and E(2) together explained 60% of the variability in GHRP-2 drive (P < 0.001). These data establish that age, estrogen status, and AVF are triple covariates of continuous peptide-secretagogue drive of pulsatile GH secretion in women. Each factor must be controlled for to allow valid comparisons of GH-axis activity.

Alerting strategies in computerized physician order entry: a novel use of a dashboard-style analytics tool in a children's hospital.

Utilizing a commercially available business analytics tool offering dashboard-style graphical indicators and a data warehouse strategy, we have developed an interactive, web-based platform that allows near-real-time analysis of CPOE adoption by hospital area and practitioner specialty. Clinical Decision Support (CDS) metrics include the percentage of alerts that result in a change in clinician decision-making. This tool facilitates adjustments in alert limits in order to reduce alert fatigue.

Twenty-four hour continuous ghrelin infusion augments physiologically pulsatile, nycthemeral, and entropic (feedback-regulated) modes of growth hormone secretion.

BACKGROUND: Ghrelin is a 28-amino acid acylated peptide that potentiates GHRH stimulation and opposes somatostatin inhibition acutely. Whether prolonged ghrelin administration can sustain physiological patterns of GH secretion remains unknown. HYPOTHESIS: Continuous delivery of ghrelin will amplify physiological patterns of GH secretion over 24 h. SUBJECTS: Men and women ages 29-69 yr, body mass indices 23-52 kg/m2, were included in the study. LOCATION: The study was performed at an academic medical center. METHODS: Twenty-four hour continuous sc infusion of saline vs. ghrelin (1 microg/kg.h) with frequent sampling was examined. Deconvolution and entropy analyses were performed. OUTCOMES: IGF-I concentrations were determined. Basal, pulsatile, nycthemeral, and entropic measures of GH secretion were calculated. RESULTS: Ghrelin infusion compared with saline infusion for 24 h elevated (median) acylated ghrelin, GH, and IGF-I concentrations by 8.1-fold (P < 0.001),11-fold (P < 0.001), and 1.4-fold (P = 0.002). GH secretory-burst mass and frequency increased by 6.6-fold (P = 0.004) and 1.7-fold (P < 0.001), respectively, resulting in a 12-fold increase in pulsatile GH secretion (P < 0.001). Interpulse variability decreased significantly (P = 0.046), whereas GH secretory-burst shape and half-life did not change. The amplitude of the nycthemeral GH rhythm increased by 3.4-fold (P < 0.001), and GH patterns became more irregular (higher approximate entropy P < 0.001). Combining GHRH with ghrelin was not an additive in driving GH secretion. CONCLUSIONS: Continuous ghrelin infusion for 24 h elevates acylated ghrelin, GH and IGF-I concentrations, and stimulates pulsatile, nycthemeral, and entropic modes of GH secretion. The consistency of outcomes in a heterogeneous cohort of adults suggests potentially broad utility of this physiological secretagogue in hyposomatotropic states.

Using mobility technology to improve pharmacist workflow in the PICU rounding process.

Studies have indicated the clinical pharmacist plays a key role in reducing preventable adverse drug events (ADE), as well as decreasing costs and length of stay. Children are particularly at risk for ADEs, primarily due to incorrect dosages. At Children's Hospital in Omaha, Neb., clinical pharmacists are an integral part of the multidisciplinary Pediatric Intensive Care Unit (PICU) team, requiring efficient access to the electronic medical record and other online resources. Children's determined that fixed workstations were not optimal and decided to conduct a comparative workflow study to determine the impact of a mobility computing solution using the Motion C5 mobile clinical assistant. The findings showed solid improvement, increasing pharmacist time with the PICU rounding team to 98.89 percent. Children's also saw a significant decrease in the number of logins and time required to log in to workstations, and a 17 percent increase in pharmacist satisfaction with the rounding workflow.

SUBUNIT COORDINATION IN THE FIREFLY LIGHT ORGAN.

1. Microphotographs were obtained of a firefly (Photuris sp.) light organ on cinema film at 64 frames per second with the aid of an image intensifier. 2. Analysis of the film indicates that the two light organs usually flash simultaneously, but cases of one organ leading by 32-48 msec are seen. 3. Asynchrony is also observed within the light organ during a flash. Submaximal flashes are comprised of small spots of light ("microsources") which turn on at various times throughout the flash. Their durations average 139 ± 3 (S.E.) msec (range 31-360 msec) compared with 300-425 msec for an organ flash. Microsources are of fairly uniform size and shape having an average diameter of 21.6 ± 0.3 µ. (S.E.) and a range of 11-36 µ. Microsources of this size are also seen as time functional unit of uncoordinated emission displays known as scintillation. It is suggested that the microsource is the smallest physiological unit of function in the firefly light organ. 4. Comparisons of glowing organs with histological sections demonstrate that the center portions of the "rosettes" are dark, and the centrifugal elements of the rosettes (the photocytes) emit light. 5. Microsources (21.6 µ in diameters) are somewhat smaller than the measured length of photocytes (34 µ) but larger than the width (8-10 µ). Thus the functional unit is identified as the center portions of 2 or 3 adjacent photocytes. 6. The whole organ flash is the integration of briefer staggered responses of a population of these single units which have activities of variable duration and intensities.