Using machine learning to identify patient characteristics to predict mortality of in-patients with COVID-19 in south Florida.

Introduction: The SARS-CoV-2 (COVID-19) pandemic has created substantial health and economic burdens in the US and worldwide. As new variants continuously emerge, predicting critical clinical events in the context of relevant individual risks is a promising option for reducing the overall burden of COVID-19. This study aims to train an AI-driven decision support system that helps build a model to understand the most important features that predict the "mortality" of patients hospitalized with COVID-19. Methods: We conducted a retrospective analysis of "5,371" patients hospitalized for COVID-19-related symptoms from the South Florida Memorial Health Care System between March 14th, 2020, and January 16th, 2021. A data set comprising patients' sociodemographic characteristics, pre-existing health information, and medication was analyzed. We trained Random Forest classifier to predict "mortality" for patients hospitalized with COVID-19. Results: Based on the interpretability of the model, age emerged as the primary predictor of "mortality", followed by diarrhea, diabetes, hypertension, BMI, early stages of kidney disease, smoking status, sex, pneumonia, and race in descending order of importance. Notably, individuals aged over 65 years (referred to as "older adults"), males, Whites, Hispanics, and current smokers were identified as being at higher risk of death. Additionally, BMI, specifically in the overweight and obese categories, significantly predicted "mortality". These findings indicated that the model effectively learned from various categories, such as patients' sociodemographic characteristics, pre-hospital comorbidities, and medications, with a predominant focus on characterizing pre-hospital comorbidities. Consequently, the model demonstrated the ability to predict "mortality" with transparency and reliability. Conclusion: AI can potentially provide healthcare workers with the ability to stratify patients and streamline optimal care solutions when time is of the essence and resources are limited. This work sets the platform for future work that forecasts patient responses to treatments at various levels of disease severity and assesses health disparities and patient conditions that promote improved health care in a broader context. This study contributed to one of the first predictive analyses applying AI/ML techniques to COVID-19 data using a vast sample from South Florida.

Social and Psychological Factors Associated With Health Care Transition for Young Adults Living With Sickle Cell Disease.

Introduction: Due to advances in disease management, mortality rates in children with sickle cell disease (SCD) have decreased. However, mortality rates for young adults (YA) increased, and understanding of social and psychological factors is critical. The aim of this study was to explore factors associated with health care transition experiences for YA with SCD. Method: This was a qualitative descriptive study. A 45-minute semistructured interview was conducted with 13 YA (M = 21.5 years, SD = 1.73). Results: Results suggest that social and psychological factors and self-management experiences influence health care transition. Eight themes emerged: "need for accessible support"; "early assistance with goal setting"; "incongruence among expectations, experiences, and preparation"; "spiritual distress"; "stigma"; "need for collaboration"; "appreciation for caring providers"; and "feeling isolated." Discussion: Consideration of cultural contexts will guide nurses in supporting health care transition. Designing culturally relevant interventions that address unique needs for YA living with SCD is warranted.

Depression and Intimate Partner Violence Among African American Women Living in Impoverished Inner-City Neighborhoods.

Mental health correlates of intimate partner violence (IPV) victimization including negative physical and mental health outcomes are well documented. However, certain subgroups of African American women, such as those living in impoverished, urban communities, are underrepresented in most studies and may experience IPV at higher rates. Furthermore, the circumstances of this women including poverty makes them at risk to IPV and its consequences. The present study estimated the prevalence of IPV victimization and its association with depression in a sample of low-income African American women participating in the Mobile Youth and Poverty Study. Participants in this study were caregivers of adolescents living in extremely impoverished conditions and were part of the Mobile Youth Survey, a community-based, longitudinal, multiple cohort survey conducted between the years 1998 and 2011. Data for the current study were collected between the years 2001 and 2010. The dependent variable was depressive symptoms as measured by the Center for Epidemiological Studies-Depression Scale (CES-D). The independent variable was IPV measured using a subsample of items from the Conflict Tactics Scale. Nearly three quarters (73.6%, n = 489) of the sample experienced some form of IPV and 49.1% (n = 326) had a CES-D depression score of 16 or greater indicating mild to severe depression symptoms. The highest proportion of women who met the CES-D criteria for depression were those experiencing the most severe IPV irrespective of category (i.e., physical, psychological, or combined). Logistic regression analyses showed that women reporting the most severe abuse, irrespective of category, were significantly more likely to meet the CES-D criteria for depression. In addition, low education and receipt of economic assistance were significantly associated with depressive symptoms. The combination of poor economic conditions and IPV may predispose African American women living in impoverished, urban communities to mental health outcomes such as depression.

Use of the Spiritual Development Framework in Conducting Spirituality and Health Research with Adolescents.

Spirituality is considered a universal phenomenon, but research addressing the spiritual needs of adolescents in the context of health and illness is limited. The aim of this article is to provide a description of how the spiritual development framework (SDF) was used in conducting research with adolescents. An exemplar of a qualitative descriptive study is provided to demonstrate applicability of the SDF. The SDF was used as a guiding theoretical framework in conducting research with adolescents living with sickle cell disease. The SDF is culturally applicable and methodologically appropriate. Additional research applying the SDF is warranted.

The Psychosocial and Clinical Well-Being of Women Living with Human Immunodeficiency Virus/AIDS.

This study examined factors impacting the psychological well-being of women living with human immunodeficiency virus/AIDS and the impact of depression on clinical outcomes. Nearly two-thirds of participants in this cross-sectional study reported significant depressive symptoms. Compared with women living with human immunodeficiency virus/AIDS without depressive symptoms, those with depression reported significantly poorer health outcomes. Health care providers should regularly screen these women for and adequately treat depression, and must collaborate with mental health providers and pastoral care counselors to address the mental health needs of women living with human immunodeficiency virus/AIDS to optimize their human immunodeficiency virus-related outcomes.

The interrelationships among pain interference, depressive symptoms, loneliness, and employment status: a moderated mediation study.

OBJECTIVE: To explore the mediating effect of loneliness on the relationship between pain interference and depressive symptoms and to determine whether this mechanism is contingent on employment status. DESIGN: Cross-sectional study. SUBJECTS: A total of 876 adult caregivers of adolescents living in extremely impoverished conditions. ANALYSIS: Mediation and moderated mediation analyses using standard path-analytic approaches. RESULTS: The mean age of the sample was 39.0 (SD = 12.8) years and 80.7% ( n = 707) identified as female. Almost half (48.9%, n = 425) of the participants did not report any pain, while 32.5% ( n = 285) reported non-disabling pain, and 19.0% ( n = 166) reported disabling pain. The mean depressive symptoms score was 16.20 (SD = 10.6), and the mean loneliness score was 40.09 (SD = 10.5). Loneliness mediated the effect of both non-disabling and disabling pain on depressive symptoms. However, the indirect effect of pain interference on depressive symptoms through loneliness was more pronounced among participants reporting disabling pain (coefficient, 2.11; Boot 95% confidence interval (CI) (1.25-3.01)) than non-disabling pain (coefficient, 0.99; Boot 95% CI (0.25-1.76)). Moderated mediation results showed that the indirect effect of pain interference on depressive symptoms, via loneliness varied in magnitude as a function of employment status among participants reporting disabling pain but not those reporting non-disabling pain. CONCLUSION: Loneliness provides an important link in the relationship between depressive symptoms and pain interference. Furthermore, employment status is an important factor to consider, especially among individuals reporting disabling pain with comorbid depressive symptoms.

Sexual Risk Behaviors of African American Adolescent Females: The Role of Cognitive and Religious Factors.

INTRODUCTION: African American (AA) high school-age girls are more likely to have had sex before age 13 years and have higher rates of all sexually transmitted infections. Cognition and religion/spirituality are associated with adolescent sexuality, therefore, the purpose of this study was to identify cognitive and religious substrates of AA girls' risky sexual behaviors. METHOD: A descriptive study was conducted with 65 AA girls aged 15 to 20 years using computerized questionnaires and cognitive function tasks. RESULTS: Average age was 17.8 ± 1.9 years and average sexual initiation age was 15.5 ± 2.6 years. Overall, 57.6% reported a history of vaginal sex. Girls who reported low/moderate religious importance were significantly younger at vaginal sex initiation than girls for whom religion was very/extremely important. Girls who attended church infrequently reported significantly more sexual partners. IMPLICATIONS: Health care providers can use these findings to deliver culturally congruent health care by assessing and addressing these psychosocial factors in this population.

When It Is Not Postpartum Depression: Understanding the Postpartum Mental Health Needs of Mothers and How They Are Being Met.

Although often overlooked, subclinical symptoms of postpartum depression, anxiety, or other mental health symptoms among new mothers increase the risk of more severe problems and can adversely affect maternal and infant health. We conducted focus groups with 92 new mothers and interviews with 20 healthcare providers to elucidate perceptions of mental health needs among first-time mothers and how healthcare providers address these needs. Our findings suggest that a tradition of focusing exclusively on severe presentations of mental health issues may limit maternal and provider ability to address the full spectrum of mental health needs.