AI-Driven Decision Support for Early Detection of Cardiac Events: Unveiling Patterns and Predicting Myocardial Ischemia.

Cardiovascular diseases (CVDs) account for a significant portion of global mortality, emphasizing the need for effective strategies. This study focuses on myocardial infarction, pulmonary thromboembolism, and aortic stenosis, aiming to empower medical practitioners with tools for informed decision making and timely interventions. Drawing from data at Hospital Santa Maria, our approach combines exploratory data analysis (EDA) and predictive machine learning (ML) models, guided by the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. EDA reveals intricate patterns and relationships specific to cardiovascular diseases. ML models achieve accuracies above 80%, providing a 13 min window to predict myocardial ischemia incidents and intervene proactively. This paper presents a Proof of Concept for real-time data and predictive capabilities in enhancing medical strategies.

[Risk Factors for Delayed Discharge Due to Social Factors: A Retrospective Study]. / Factores de Risco para Alta Prorrogada por Motivos Sociais: Um Estudo Retrospectivo.

INTRODUCTION: The hospital setting faces a rate of bed occupation by patients whose discharge is limited by other factors apart from clinical needs. This urges the need for an early identification of the patients at risk of delayed discharge due to social factors in order to reduce expenses and to add value that converts itself into the patient health. The aim of this study was to identify the demographic and clinical factors that may be associated with delayed discharge. MATERIAL AND METHODS: Demographic and clinical comorbidity data on 582 patients of an internal medicine ward from a tertiary hospital center during the years 2018 and 2019 was analyzed. A binomial logistic regression model was used, adjusted for sex, age, and length of clinical stay, in order to identify potential risk factors associated with delayed discharge. RESULTS: A total of 473 patients admitted in the internal medicine ward throughout the two years of study were included. Ninety-four (19%) of these patients had their discharge delayed beyond their clinical needs; sixty-four (68%) of these were females. The most representative age was between 75 - 89 years old (45.7%). The characteristics that significantly differed between both non-delayed and delayed discharge were female sex (OR 2.84, 95% CI 1.65 - 4.90, p-value < 0.05), prolonged clinical stay (OR 2.64, 95% CI 1.60 - 4.937, p-value < 0.05) and diabetes mellitus (OR 1.87, 95% CI 1.08 - 3.23, p-value < 0.05). Besides these, the presence of heart failure (OR 0.52, 95% CI 0.27 - 0.99, p-value < 0.05) and chronic kidney disease (OR 0.34, 95% CI 0.14 - 0.86, p-value < 0.05) were associated with a lower risk of delayed discharge. CONCLUSION: Female sex, a prolonged clinical stay and diabetes mellitus were associated with a higher risk of delayed discharge, while heart failure and chronic kidney disease were associated with a reduced risk. These findings create a basis for a possible future multicentre study aimed at creating a clinical prediction rule to stratify the risk of delayed hospital discharge in the Portuguese population.

Introdução: Os hospitais deparam-se com uma percentagem das suas camas ocupadas por doentes cuja alta hospitalar está limitada não pela alta clínica, mas por outros fatores. Cria-se a necessidade da identificação precoce dos indivíduos que estão em risco de uma alta prorrogada por motivos sociais (internamentos sociais - IS), de forma a reduzir gastos e a acrescentar valor que se traduza em saúde dos utentes. O objetivo deste estudo foi identificar os fatores de risco demográficos e clínicos que condicionam risco de internamento social. Material e Métodos: Foram analisados 582 internamentos referentes a um serviço de Medicina Interna de hospital terciário nos anos de 2018 e 2019, e consideradas as características demográficas e comorbidades clínicas dos doentes. Foi feita uma regressão logística binominal ajustada ao sexo, idade e internamento clínico prolongado, para identificação de potenciais fatores de risco associados a alta prorrogada. Resultados: Foram incluídos neste estudo um total de 473 doentes admitido no serviço no período de dois anos em estudo. Noventa e quatro (19%) doentes tiveram a sua alta prorrogada, dos quais 64 (68%) eram do sexo feminino. As principais características estatisticamente significativas associadas a maior risco de prorrogação da alta foram o sexo feminino (OR 2,84, 95% IC 1,65 ­ 4,90, p-value < 0,05), o internamento clínico prolongado (OR 2,64, 95% IC 1,60 ­ 4,937, p-value < 0,05) e a diabetes mellitus (OR 1,87, 95% IC 1,08 ­ 3,23, p-value < 0,05); para além destes, a presença de insuficiência cardíaca (OR 0,52, 95% IC 0,27 ­ 0,99, p-value < 0,05) e de doença renal crónica (OR 0,34, 95% IC 0,14 ­ 0,86, p-value < 0,05) associaram-se a um risco inferior de prorrogação de alta. Conclusão: O sexo feminino, os internamentos clínicos prolongados e diabetes mellitus associaram-se a um maior risco de internamento social, enquanto a insuficiência cardíaca e a doença renal crónica se associaram a um risco inferior de IS. Estes achados servem de base de construção para um futuro estudo multicêntrico para criação de uma regra de predição clínica para estratificação do risco de internamento social na população portuguesa.

Integrative analysis reveals the divergence and speciation between sister Sooty Copper butterflies Lycaena bleusei and L. tityrus.

The comparison of closely related taxa is cornerstone in biology, as understanding mechanisms leading up to differentiation in relation to extant shared characters are powerful tools in interpreting the evolutionary process. Hotspots of biodiversity such as the west-Mediterranean, where many lineages meet are ideal grounds to study these processes. We set to explore the interesting example of Sooty Copper butterflies: widespread Eurasian Lycaena tityrus (Poda, 1761) comes into contact in Iberia with closely related and local endemic, L. bleusei (Oberthür, 1884), which hasn't always been considered a distinct species. An integrative analysis was designed, combining the use of extensive molecular data (five genes), geometric morphometrics analyses, verified and up-to-date distribution data, and environmental niche modelling, aimed at deciphering their true relationship, their placement within European Lycaena and trace their evolutionary history. We revealed several levels of differentiation: L. bleusei and L. tityrus appear to be reciprocally monophyletic independent gene-pools, distinct in all genes analysed, having mutually diverged 4.8 Ma ago. L. tityrus but not L. bleusei, further displays a genetic structure compatible with several glacial refugia, where populations assignable to infraspecific taxa surface. Conversely, L. bleusei shows a loss in mtDNA diversity in relation to nuDNA. Morphological analyses differentiate both species according to size and shape but also discriminate strong seasonal and sexual traits and a geographical phenotype segregation in L. tityrus. Finally, updated distribution and its modelling for current and glacial timeframes reveal both species respond differently to environmental variables, defining a mostly parapatric distribution and an overlapping belt where sympatry was recovered. During the last glacial maximum, a wider expansion in L. bleusei distribution explains current isolated populations. Our study highlights the importance of gathering several lines of evidence when deciphering the relationships between closely related populations in the fringe of cryptic species realm.

Barriers to knowledge sharing in Chinese healthcare referral services: an emergent theoretical model.

BACKGROUND: This paper reports on a research study that aims to identify and explain barriers to knowledge sharing (KS) in the provision of healthcare referral services in Chinese healthcare organisations. DESIGN: An inductive case study approach was employed, in which 24 healthcare professionals and workers from four healthcare organisations in the province of Hubei, Central China, were interviewed using semi-structured scripts. RESULTS: Through data analysis, 14 KS barriers emerged in four main themes: interpersonal trust barriers, communication barriers, management and leadership barriers, and inter-institutional barriers. A cause-consequence analysis of the identified barriers revealed that three of them are at the core of the majority of problems, namely, the absence of national and local policies for inter-hospital KS, lack of a specific hospital KS requirement, and lack of mutual acquaintance. CONCLUSIONS: To resolve KS problems, it is of great importance that healthcare governance agencies, both at the national and regional levels, take leadership in the process of KS implementation by establishing specific and strong policies for inter-institutional KS in the referral process. This paper raises important issues that exceed academic interests and are important to healthcare professionals, hospital managers, and Information communication technology (ICT) managers in hospitals, as well as healthcare politicians and policy makers.