The Quintuple Aim seeks to improve healthcare by addressing social determinants of health (SDOHs), which are responsible for 70-80% of medical outcomes. SDOH-related concerns have traditionally been addressed through referrals to social workers and community-based organizations (CBOs), but these pathways have had limited success in connecting patients with resources. Given that health inequity is expected to cost the United States nearly USD 300 billion by 2050, new artificial intelligence (AI) technology may aid providers in addressing SDOH. In this commentary, we present our experience with using ChatGPT to obtain SDOH management recommendations for archetypal patients in Philadelphia, PA. ChatGPT identified relevant SDOH resources and provided contact information for local organizations. Future exploration could improve AI prompts and integrate AI into electronic medical records to provide healthcare providers with real-time SDOH recommendations during appointments.

BACKGROUND: Public health guidance recommended that children who are 6 months or older be vaccinated against COVID-19 in June of 2022. In the U.S., 56% of children under 17 had not received the COVID-19 vaccination in 2023. We examine parents\' willingness to vaccinate their children against COVID-19 using the theory of planned behavior in order to design effective strategies to promote vaccine uptake.
METHODS: The Philadelphia Community Engagement Alliance is part of an NIH community-engaged consortium focused on addressing COVID-19 disparities across the U.S. We surveyed 1,008 Philadelphia parents (mean age 36.86, SD 6.55; 42.3% racial/ethnic minorities) between September 2021 and February 2022, a period when guidance for child vaccination was anticipated. Structural Equation Modeling analysis examined associations between parental willingness and vaccine-related attitudes, norms, and perceived control. Covariates included parents\' COVID-19 vaccination status, race/ethnicity, gender, and survey completion post-CDC pediatric COVID-19 vaccination guidelines. Subgroup analyses by race/ethnicity and gender were conducted.
RESULTS: Our model demonstrated good fit (χ2 = 907.37, df = 419, p<0.001; comparative fit index [CFI] = 0.951; non-normed fit index [NNFI] = 0.946; root mean square error of approximation [RMSEA] = 0.034 with 95% CI = 0.030-0.038). Attitudes ([Formula: see text] = 0.447, p<0.001) and subjective norms ([Formula: see text] = 0.309, p = 0.002) were predictors of intention. Racial/ethnic minority parents exhibited weaker vaccination intentions ([Formula: see text] = -0.053, p = 0.028) than non-Hispanic White parents.
CONCLUSIONS: Parents\' attitudes and norms influence their vaccination intentions. Despite the survey predating widespread child vaccine availability, findings are pertinent given the need to increase and sustain pediatric vaccinations against COVID-19. Interventions promoting positive vaccine attitudes and prosocial norms are warranted. Tailored interventions and diverse communication strategies for parental subgroups may be useful to ensure comprehensive and effective vaccination initiatives.

BACKGROUND: Cooling towers containing Legionella spp are a high-risk source of Legionnaires\' disease outbreaks. Manually locating cooling towers from aerial imagery during outbreak investigations requires expertise, is labour intensive, and can be prone to errors. We aimed to train a deep learning computer vision model to automatically detect cooling towers that are aerially visible.
METHODS: Between Jan 1 and 31, 2021, we extracted satellite view images of Philadelphia (PN, USA) and New York state (NY, USA) from Google Maps and annotated cooling towers to create training datasets. We augmented training data with synthetic data and model-assisted labelling of additional cities. Using 2051 images containing 7292 cooling towers, we trained a two-stage model using YOLOv5, a model that detects objects in images, and EfficientNet-b5, a model that classifies images. We assessed the primary outcomes of sensitivity and positive predictive value (PPV) of the model against manual labelling on test datasets of 548 images, including from two cities not seen in training (Boston [MA, USA] and Athens [GA, USA]). We compared the search speed of the model with that of manual searching by four epidemiologists.
RESULTS: The model identified visible cooling towers with 95·1% sensitivity (95% CI 94·0-96·1) and a PPV of 90·1% (95% CI 90·0-90·2) in New York City and Philadelphia. In Boston, sensitivity was 91·6% (89·2-93·7) and PPV was 80·8% (80·5-81·2). In Athens, sensitivity was 86·9% (75·8-94·2) and PPV was 85·5% (84·2-86·7). For an area of New York City encompassing 45 blocks (0·26 square miles), the model searched more than 600 times faster (7·6 s; 351 potential cooling towers identified) than did human investigators (mean 83·75 min [SD 29·5]; mean 310·8 cooling towers [42·2]).
CONCLUSIONS: The model could be used to accelerate investigation and source control during outbreaks of Legionnaires\' disease through the identification of cooling towers from aerial imagery, potentially preventing additional disease spread. The model has already been used by public health teams for outbreak investigations and to initialise cooling tower registries, which are considered best practice for preventing and responding to outbreaks of Legionnaires\' disease.
BACKGROUND: None.

暂无摘要。

BACKGROUND: Adolescent substance use poses a critical public health challenge, intertwined with risk-taking behavior, criminality, functional impairment, and comorbid mental and physical health issues. Adolescents with bipolar spectrum disorders (BSD) exhibit heightened susceptibility to substance use, necessitating a nuanced exploration of the bipolar-substance use relationship.
METHODS: This study addressed gaps in the literature by employing a prospective, longitudinal design with 443 Philadelphia-area adolescents, tracking BSD symptoms and substance use. We predicted that BSD symptoms would be associated with increases in substance use, and that these effects would be more pronounced for individuals with a BSD and those with high reward sensitivity.
RESULTS: Hypomanic symptoms predicted subsequent substance use, with a stronger association observed in individuals diagnosed with BSD. Contrary to expectations, depressive symptoms did not exhibit a similar relationship. Although the hypothesized moderating role of reward sensitivity was not supported, higher reward sensitivity predicted increased substance use.
CONCLUSIONS: Symptoms and substance use are only captured for the month prior to each session due to the assessment timeline. This highlights the benefits of frequent assessments over a shorter time frame to monitor real-time changes. Alternative classification methods for reward sensitivity, such as brain or behavior-based assessments, might yield different results.
CONCLUSIONS: This study\'s contributions include evaluating substance use broadly, utilizing a longitudinal design for temporal clarity, and shifting the focus from substance use predicting mood symptoms to the inverse. The findings underscore the need for continued exploration of mood symptom predictors of substance use, emphasizing the role of reward sensitivity.

Parks can provide a low-cost setting for safe physical activity, but older adults are underrepresented among park users in the United States. Using data from a population-representative survey in 2015 and 2018 among adults aged 60 years and older living in Philadelphia, we tested whether perceived access was a mechanism by which objectively-measured park access predicted self-reported physical activity. After controlling for individual-level factors and neighborhood characteristics, we found a statistically significant pathway from overall park area and within-park tree canopy to increased physical activity, mediated by perceived park access. These results highlight the importance of tree canopy for older adult park access and physical activity.

UNASSIGNED: While disparities in consent rates for research have been reported in multiple adult and pediatric settings, limited data informing enrollment in pediatric intensive care unit (PICU) research are available. Acute care settings such as the PICU present unique challenges for study enrollment, given the highly stressful and emotional environment for caregivers and the time-sensitive nature of the studies.
UNASSIGNED: To determine whether race and ethnicity, language, religion, and Social Deprivation Index (SDI) were associated with disparate approach and consent rates in PICU research.
UNASSIGNED: This retrospective cohort study was performed at the Children\'s Hospital of Philadelphia PICU between July 1, 2011, and December 31, 2021. Participants included patients eligible for studies requiring prospective consent. Data were analyzed from February 2 to July 26, 2022.
UNASSIGNED: Exposures included race and ethnicity (Black, Hispanic, White, and other), language (Arabic, English, Spanish, and other), religion (Christian, Jewish, Muslim, none, and other), and SDI (composite of multiple socioeconomic indicators).
UNASSIGNED: Multivariable regressions separately tested associations between the 4 exposures (race and ethnicity, language, religion, and SDI) and 3 outcomes (rates of approach among eligible patients, consent among eligible patients, and consent among those approached). The degree to which reduced rates of approach mediated the association between lower consent in Black children was also assessed.
UNASSIGNED: Of 3154 children included in the study (median age, 6 [IQR, 1.9-12.5] years; 1691 [53.6%] male), rates of approach and consent were lower for Black and Hispanic families and those of other races, speakers of Arabic and other languages, Muslim families, and those with worse SDI. Among children approached for research, lower consent odds persisted for those of Black race (unadjusted odds ratio [OR], 0.73 [95% CI, 0.55-0.97]; adjusted OR, 0.68 [95% CI, 0.49-0.93]) relative to White race. Mediation analysis revealed that 51.0% (95% CI, 11.8%-90.2%) of the reduced odds of consent for Black individuals was mediated by lower probability of approach.
UNASSIGNED: In this cohort study of consent rates for PICU research, multiple sociodemographic factors were associated with lower rates of consent, partly attributable to disparate rates of approach. These findings suggest opportunities for reducing disparities in PICU research participation.

BACKGROUND: Postpartum hemorrhage (PPH) is a leading cause of maternity mortality in the United States. The Code Crimson project aimed to enhance PPH management by implementing a standardized intervention bundle to mitigate morbidity and mortality associated with PPH.
OBJECTIVE: At a large Philadelphia tertiary hospital, health disparities existed for severe maternal morbidity and mortality, and PPH was a significant factor.
METHODS: A quality improvement design, using Plan-Do-Study-Act cycles and interrupted time series analysis, was undertaken.
METHODS: The Code Crimson project implemented a standardized bundle to manage PPH, including blood product administration and massive transfusion protocol activation.
RESULTS: After implementing the Code Crimson bundle, there was a significant decrease in blood product use ( P < .001), with minor reductions in packed red blood cell administration over 4 units and mean blood loss.
CONCLUSIONS: The Code Crimson bundle effectively reduced blood product utilization for PPH treatment.

While menstruation is a physiologic process, it remains highly stigmatized. Despite the sheer number of menstruators, menstruation is a highly individualized experience, with wide variation in duration, symptoms, and management. This wide variability lends itself to large disparities in access to menstruation management products and subsequently the lived experience of menstruators.
The research team sought to understand lived menstrual experiences, symptoms, management tactics, and commonly used and desired resources among 20 cisgendered women aged 18-45 years in Philadelphia.
This project was a qualitative research study.
We used a collaborative, community-based participatory research approach with No More Secrets, a Philadelphia-based grassroots sexuality awareness and menstrual health hub. Semi-structured telephone interviews were used to gain insight into general menstruation-related experiences, communication, worries, and concerns, with subsequent thematic analysis via Key Words in Context approach.
Four themes emerged following analysis: cycle characteristics, menstruation management, coping resources, and future resources. Participants largely spoke about their menses as a negative experience, asked for more comprehensive, verified sources of information and needed greater access to menstrual management supplies.
Menstruation is a highly individualized experience with a large variety in knowledge, menstrual product use, and individual needs. Despite the individuality of menstruation, our community-based research shows that there is a dire need for interventions that promotes knowledge and access to menstrual care.

METHODS: Community-engaged qualitative study using inductive thematic analysis of semistructured interviews.
OBJECTIVE: To understand Latine immigrants\' recent prenatal care experiences and develop community-informed strategies to mitigate policy-related chilling effects on prenatal care utilization.
BACKGROUND: Decreased health care utilization among immigrants due to punitive immigration policies (ie, the \"chilling effect\") has been well-documented among Latine birthing people both pre and postnatally.
METHODS: Currently or recently pregnant immigrant Latine people in greater Philadelphia were recruited from an obstetric clinic, 2 pediatric primary care clinics, and 2 community-based organization client pools. Thematic saturation was achieved with 24 people. Participants\' pregnancy narratives and their perspectives on how health care providers and systems could make prenatal care feel safer and more comfortable for immigrants.
RESULTS: Participants\' recommendations for mitigating the chilling effect during the prenatal period included training prenatal health care providers to sensitively initiate discussions about immigrants\' rights and reaffirm confidentiality around immigration status. Participants suggested that health care systems should expand sources of information for pregnant immigrants, either by partnering with community organizations to disseminate information or by increasing access to trusted individuals knowledgeable about immigrants\' rights to health care. Participants also suggested training non-medical office staff in the use of interpreters.
CONCLUSIONS: Immigrant Latine pregnant and birthing people in greater Philadelphia described ongoing fear and confusion regarding the utilization of prenatal care, as well as experiences of discrimination. Participants\' suggestions for mitigating immigration-related chilling effects can be translated into potential policy and programmatic interventions which could be implemented locally and evaluated for broader applicability.