RESUMO
This study quantifies health outcome disparities in invasive Methicillin-Resistant Staphylococcus aureus (MRSA) infections by leveraging a novel artificial intelligence (AI) fairness algorithm, the Fairness-Aware Causal paThs (FACTS) decomposition, and applying it to real-world electronic health record (EHR) data. We spatiotemporally linked 9 years of EHRs from a large healthcare provider in Florida, USA, with contextual social determinants of health (SDoH). We first created a causal structure graph connecting SDoH with individual clinical measurements before/upon diagnosis of invasive MRSA infection, treatments, side effects, and outcomes; then, we applied FACTS to quantify outcome potential disparities of different causal pathways including SDoH, clinical and demographic variables. We found moderate disparity with respect to demographics and SDoH, and all the top ranked pathways that led to outcome disparities in age, gender, race, and income, included comorbidity. Prior kidney impairment, vancomycin use, and timing were associated with racial disparity, while income, rurality, and available healthcare facilities contributed to gender disparity. From an intervention standpoint, our results highlight the necessity of devising policies that consider both clinical factors and SDoH. In conclusion, this work demonstrates a practical utility of fairness AI methods in public health settings.
Assuntos
Infecções Comunitárias Adquiridas , Staphylococcus aureus Resistente à Meticilina , Infecções Estafilocócicas , Humanos , Infecções Estafilocócicas/tratamento farmacológico , Infecções Estafilocócicas/diagnóstico , Inteligência Artificial , Infecções Comunitárias Adquiridas/tratamento farmacológico , Biologia Computacional , Algoritmos , Avaliação de Resultados em Cuidados de Saúde , Antibacterianos/uso terapêuticoRESUMO
Structure-guided image completion aims to inpaint a local region of an image according to an input guidance map from users. While such a task enables many practical applications for interactive editing, existing methods often struggle to hallucinate realistic object instances in complex natural scenes. Such a limitation is partially due to the lack of semantic-level constraints inside the hole region as well as the lack of a mechanism to enforce realistic object generation. In this work, we propose a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects. Specifically, the semantic discriminators leverage pretrained visual features to improve the realism of the generated visual concepts. Moreover, the object-level discriminators take aligned instances as inputs to enforce the realism of individual objects. Our proposed scheme significantly improves the generation quality and achieves state-of-the-art results on various tasks, including segmentation-guided completion, edge-guided manipulation and panoptically-guided manipulation on Places2 datasets. Furthermore, our trained model is flexible and can support multiple editing use cases, such as object insertion, replacement, removal and standard inpainting. In particular, our trained model combined with a novel automatic image completion pipeline achieves state-of-the-art results on the standard inpainting task.
RESUMO
Background: Despite the prevalence of sexual assault presentations to emergency departments (ED) in the United States, current access to sexual assault nurse examiners (SANE) and emergency contraception (EC) in EDs is unknown. Methods: In this study we employed a "secret shopper," cross-sectional telephonic survey. A team attempted phone contact with a representative sample of EDs and asked respondents about the availability of SANEs and EC in their ED. Reported availability was correlated with variables including region, urban/rural status, hospital size, faith affiliation, academic affiliation, and existence of legislative requirements to offer EC. Results: Over a two-month period in 2019, 1,046 calls to hospitals were attempted and 960 were completed (91.7% response rate). Of the 4,360 eligible hospitals listed in a federal database, 960 (22.0%) were contacted. Access to SANEs and EC were reported to be available in 48.9% (95% confidence interval [CI] 45.5-52.0) and 42.5% (95% CI 39.4-45.7) of hospitals, respectively. Access to EC was positively correlated with SANE availability. The EDs reporting SANE and EC availability were more likely to be large, rural, and affiliated with an academic institution. Those reporting access to EC were more likely to be in the Northeast and in states with legislative requirements to offer EC. Conclusion: Our results suggest that perceived access to sexual assault services and emergency contraception in EDs in the United States remains poor with regional and legislative disparities. Results suggest disparities in perceived access to EC and SANE in the ED, which have implications for improving ED practices regarding care of sexual assault victims.
Assuntos
Anticoncepção Pós-Coito , Delitos Sexuais , Humanos , Estados Unidos , Estudos Transversais , Serviço Hospitalar de Emergência , Inquéritos e QuestionáriosRESUMO
Background: There is a paucity of data on long-term outcomes after Fontan palliation in patients with a dominant morphological univentricular right (uRV) vs left (uLV) ventricle. Objectives: The purpose of this study was to compare the incidence of atrial arrhythmias, thromboembolic events, cardiac transplantation, and death following Fontan palliation in patients with uRV vs uLV. Methods: The Alliance for Adult Research in Congenital Cardiology conducted a multicenter retrospective cohort study on patients with total cavopulmonary connection Fontan palliation across 12 centers in North America. All components of the composite outcome, that is, atrial arrhythmias, thromboembolic events, cardiac transplantation, and death, were reviewed and classified by a blinded adjudicating committee. Time-to-event analyses were performed that accounted for competing risks. Results: A total of 384 patients were followed for 10.5 ± 5.9 years. The composite outcome occurred in 3.7 vs 1.7 cases per 100 person-years for uRV (N = 171) vs uLV (N = 213), respectively (P < 0.001). In multivariable analyses, uRV conferred a >2-fold higher risk of the composite outcome (HR: 2.17, 95% CI: 1.45-3.45, P < 0.001). In secondary analyses of components of the primary outcome, uRV was significantly associated with a greater risk of cardiac transplantation or death (HR: 9.09, 95% CI: 2.17-38.46, P < 0.001) and atrial arrhythmias (HR: 2.17, 95% CI: 1.20-4.00, P = 0.010) but not thromboembolic events (HR: 1.64, 95% CI: 0.86-3.16, P = 0.131). Conclusions: Fontan patients with uRV vs uLV morphology have a higher incidence of adverse cardiovascular events, including atrial arrhythmia, cardiac transplantation, and all-cause mortality.
RESUMO
BACKGROUND: Fenestrating a Fontan baffle has been associated with improved perioperative outcomes in patients with univentricular hearts. However, longer-term potential adverse effects remain debated. We sought to assess the impact of a fenestrated Fontan baffle on adverse cardiovascular events including all-cause mortality, cardiac transplantation, atrial arrhythmias, and thromboemboli. METHODS: A multicentre North American retrospective cohort study was conducted on patients with total cavopulmonary connection Fontan baffle, with and without fenestration. All components of the composite outcome were independently adjudicated. Potential static and time-varying confounders were taken into consideration, along with competing risks. RESULTS: A total of 407 patients were followed for 10.4 (7.1-14.4) years; 70.0% had fenestration of their Fontan baffle. The fenestration spontaneously closed or was deliberately sealed in 79.9% of patients a median of 2.0 years after Fontan completion. In multivariable analysis in which a persistent fenestration was modelled as a time-dependent variable, an open fenestration did not confer a higher risk of the composite outcome (hazard ratio, 1.18; 95% confidence interval, 0.71-1.97; P = 0.521). In secondary analyses, an open fenestration was not significantly associated with components of the primary outcome: that is, mortality or transplantation, atrial arrhythmias, or thromboemboli. However, sensitivity analyses to assess the possible range of error resulting from imprecise dates for spontaneous fenestration closures could not rule out significant associations between an open fenestration and atrial arrhythmias or thromboemboli. CONCLUSIONS: In this multicentre study, no significant association was identified between an open fenestration in the Fontan baffle and major adverse cardiovascular events.
RESUMO
Background: Preprocedural anxiety may have detrimental effects both cognitively and physiologically. Objectives: The objective of this study was to determine the association between state (situational) and trait (persistent in everyday life) anxiety and differences between the adult congenital heart disease (ACHD) and acquired heart disease populations. Methods: The State-Trait Anxiety Inventory and financial stress scale were administered to adults with acquired and CHD at 4 tertiary referral centers in the United States prior to cardiac catheterization. Student's t-test and least absolute shrinkage and selection operator regression analyses were used to assess differences in anxiety between groups and identify the optimal model of predictors of anxiety. Results: Of the 291 patients enrolled, those with CHD (n = 91) were younger (age 41.3 ± 16.3 years vs 64.7 ± 11.3 years, P < 0.001), underwent more cardiac surgeries (P < 0.001), and had higher levels of trait anxiety (t[171] = 2.62, P = 0.001, d = 0.33). There was no difference in state anxiety between groups (t[158.65] = 1.37, P = 0.17, d = 0.18). State anxiety was singularly associated with trait anxiety. Trait anxiety was negatively associated with age and positively associated with state anxiety and financial stress. Patients with CHD of great complexity were more trait (F[2,88] = 4.21, P = 0.02) and state anxious (F[2,87] = 4.59, P = 0.01), though with relatively small effect size. Conclusions: Trait anxiety levels are higher in the ACHD population and directly associated with state anxiety. Specialists caring for ACHD patients should not only recognize the frequency of trait anxiety but also high-risk subgroups that may benefit from psychological or social interventions to reduce preprocedural anxiety.
RESUMO
Underserved regions in the developing world are challenging areas to provide emergency medical care. As populations in these often remote or isolated districts may have minimal access to regular health care, contacts with medical providers are frequently episodic and driven by an acute condition. Health promoterspractitioners who provide basic medical care and promote public health in numerous countries across Central and South America, Asia and Africahelp to fill this void. Typically, health promoters are certified through a formal training program in their country and come from the same population as the clients they serve, which helps them form a link between their community and the dominant health care system in the region (1-2). Access to health and social services in regions served by health promoters is usually minimal, resulting in high morbidity and mortality associated with preventable diseases. Health promoters strive to improve the overall health of these communities by supplementing and improving the curative, preventive, and promotional aspects of the existing health system.
Assuntos
Humanos , Serviços Médicos de Emergência/tendências , América Central , Tratamento de Emergência/tendências , América do Sul , Atenção à Saúde , Enfermeiros Obstétricos/educação , Atenção Primária à Saúde/métodos , Países em DesenvolvimentoRESUMO
Los promotores de salud, las parteras y otros proveedores de cuidados médicos básicos trabajan en comunidades locales de todo el mundo para mejorar y facilitar la atención sanitaria. No hay suficiente información que describa los programas educacionales dirigidos a mejorar los conocimientos y las habilidades de los promotores de salud y sobre su impacto sanitario a largo plazo. Muchas iniciativas educacionales dirigidas a los promotores de salud consisten en intervenciones aisladas que permiten evaluar sus conocimientos inmediatamente después de la intervención, pero no miden los progresos a largo plazo en la base de conocimientos o la atención sanitaria. La Alianza Pediátrica Global -una organización sin ánimo de lucro basada en los EE.UU. que trabaja con personal médico y sanitario local- creó un programa educacional para promotores sanitarios y parteras en Ecuador, Guatemala, México y Nicaragua con un enfoque centrado en reducir la mortalidad materna e infantil y en mejorar la atención primaria y de urgencias. En este artículo se describen estas iniciativas educacionales diseñadas para mejorar las habilidades de los promotores de salud y las parteras mediante un entrenamiento médico avanzado y sostenible, ajustadas a las necesidades específicas de cada comunidad.