Early warning systems and end-user decision-making: A risk formalism tool to aid communication and understanding.

In this work, we introduce a formalism to highlight the role of decision-making implicit in the setup of early warning systems (EWSs) and its consequences with respect to loss avoidance for end users. The formalism, a close relative of the cost/loss approach, combines EWS verification scores with traditional expressions of risk from the point of view of the user. This formalism articulates in mathematical format many well-known issues surrounding EWS usage, offering a conceptual anchor for concepts that otherwise may seem to wobble among the multidisciplinary perspectives participating in the EWS chain. This decision model is visually represented in a variation of the popular "performance diagram" used in forecast and warning verification. Our diagram adds to this the perspective of a generic user, in an effort to gain insight into how choices made regarding EWS settings may determine which users benefit from warnings and which do not. Although these results are based on a conceptual model, they are useful to better understand the actual benefits experienced by users and to highlight aspects that may temper unrealistic expectations on EWSs. The recent United Nations initiative to extend EWSs for natural hazards to all nations within 5 years will make EWSs more common and more public. The approach proposed here can be a tool to promote greater transparency and improve the necessary dialog between warning issuers and users in order to reduce loss.

Design of early warning system for mental health problems based on data mining and database / Projeto de sistema de alerta precoce para problemas de saúde mental com base na mineração de dados e banco de dados / Diseño de un sistema de alerta temprana de problemas de salud mental basado en la minería de datos y en la base de datos

ABSTRACT Introduction: Data mining technology is mainly employed in the era of big data to evaluate the acquired information. Subsequently, reasoning about the data inductively is fully automated to discover possible patterns. Objective: Recently, data mining technology in the national mental health database has deepened and can be effectively used to solve various mental health early warning problems. Methods: For example, it can be applied to mine psychological data and extract the most important features and information. Results: This paper presents the design of an early warning system for mental health problems based on data mining techniques to offer some thoughts on early warning of mental health problems, including data preparation, data mining, results in analysis, and decision tree algorithm. Conclusion: The experimental results indicate that the results of the early warning system in this paper can achieve an accuracy rate of more than 96% with a high accuracy rate. Level of evidence II; Therapeutic studies - investigating treatment outcomes.

RESUMO Introdução: A tecnologia de mineração de dados é empregada principalmente na era da big data para avaliar as informações adquiridas. Posteriormente, raciocinar indutivamente sobre os dados de forma totalmente automatizada para descobrir possíveis padrões. Objetivo: Recentemente, a tecnologia de mineração de dados no banco de dados nacional de saúde mental tem se aprofundado e pode ser efetivamente utilizada para resolver vários problemas de alerta precoce da saúde mental. Métodos: Por exemplo, ela pode ser aplicada para a mineração de dados psicológicos e extrair as características e informações mais importantes. Resultados: Este documento apresenta o projeto de um sistema de alerta precoce para problemas de saúde mental baseado em técnicas de mineração de dados, com o objetivo de oferecer algumas reflexões sobre alerta precoce de problemas de saúde mental, incluindo preparação de dados, mineração de dados, análise de resultados e algoritmo de árvore de decisão. Conclusão: Os resultados experimentais indicam que os resultados do sistema de alerta precoce neste trabalho podem alcançar uma taxa de precisão de mais de 96% com uma alta taxa de precisão. Nível de evidência II; Estudos terapêuticos - investigação dos resultados do tratamento.

Resumen Introducción: La tecnología de minería de datos se emplea principalmente en la era de la big data para evaluar la información adquirida. Posteriormente, razonar inductivamente sobre los datos de forma totalmente automatizada para descubrir posibles patrones. Objetivo: Recientemente, la tecnología de minería de datos en la base de datos nacional de salud mental se ha profundizado y puede ser utilizada eficazmente para resolver varios problemas de alerta temprana de salud mental. Métodos: Por ejemplo, puede aplicarse para minar datos psicológicos y extraer las características e información más importantes. Resultados: Este trabajo presenta el diseño de un sistema de alerta temprana de problemas de salud mental basado en técnicas de minería de datos, con el objetivo de ofrecer algunas reflexiones sobre la alerta temprana de problemas de salud mental, incluyendo la preparación de los datos, la minería de datos, el análisis de los resultados y el algoritmo de árbol de decisión. Conclusión: Los resultados experimentales indican que los resultados del sistema de alerta temprana de este documento pueden alcanzar un índice de precisión superior al 96% con un alto índice de precisión. Nivel de evidencia II; Estudios terapéuticos - investigación de los resultados del tratamiento.

National Early Warning Score 2: transcultural adaptation to Brazilian Portuguese / National Early Warning Score 2: adaptación transcultural para el portugués de Brasil / National Early Warning Score 2: adaptação transcultural para o português do Brasil

ABSTRACT Objective: Cross-cultural adaptation of the National Early Warning Score 2 to Brazilian Portuguese. Methods: A methodological study of a cross-cultural adaptation of a scale, based on the Beaton et al. framework, authorized by the Royal College of Physicians. Judges from nine Brazilian states, nurses and physicians evaluated the semantic, idiomatic, cultural, and conceptual equivalence between the original instrument and the translated versions. The nurses, working in inpatient or emergency units, conducted the pilot test, applying the final version to three case studies. Psychometric tests were used for data analysis: Content Validity Index (CVI), Kappa Coefficient, and Cronbach's Alpha. Results: The adaptation showed a mean CVI of 0.98 and perfect/almost perfect inter-rater agreement, with scores above 0.80. The consistency of the scale was 0.712. Conclusion: The process of cross-cultural adaptation of the scale to Brazilian Portuguese was successful, providing Brazilian professionals with an instrument aligned with patient safety.

RESUMEN Objetivo: Adaptación transcultural del National Early Warning Score2 al portugués de Brasil. Métodos: Estudio metodológico de adaptación transcultural de escala, fundamentado en el referencial de Beaton et al, autorizado por el Royal College of Physicians. Jueces de nueve estados brasileños, enfermeros y médicos evaluaron la equivalencia semántica, idiomática, cultural y conceptual entre el instrumento original y las versiones traducidas. Los enfermeros, actuantes en unidades de ingreso o de emergencia, realizaron la prueba piloto, aplicando la versión final a tres estudios de caso. Para el análisis de datos se utilizaron pruebas psicométricas: Índice de Validez de Contenido (IVC), Coeficiente de Kappa, y Alpha de Cronbach. Resultados: La adaptación presentó un IVC promedio de 0,98 y un acuerdo entre evaluadores perfecto/casi perfecto, con puntajes superiores a 0,80. La consistencia de la escala fue de 0,712. Conclusión: El proceso de adaptación transcultural de la escala al portugués de Brasil fue exitoso, proporcionando a los profesionales brasileños un instrumento alineado con la seguridad del paciente.

RESUMO Objetivo: Adaptar transculturalmente o National Early Warning Score2 para o português do Brasil. Método: Estudo metodológico de adaptação transcultural de escala, fundamentado no referencial de Beaton et al, autorizado pelo Royal College of Physicians. Juízes de nove estados brasileiros, enfermeiros e médicos, avaliaram equivalência semântica, idiomática, cultural e conceitual entre o instrumento original e as versões traduzidas. Enfermeiros, atuantes em unidades de internação ou emergência, realizaram o teste piloto, aplicando a versão final em três estudos de caso. Para análise de dados foram utilizados testes psicométricos: Índice de Validade de Conteúdo (IVC), Coeficiente de Kappa e Alpha de Cronbach. Resultados: A adaptação apresentou IVC médio de 0,98 e concordância inter-avaliadores perfeito/quase perfeito, com pontuações superiores a 0,80. A consistência da escala foi igual a 0,712. Conclusão: O processo de adaptação transcultural da escala para o português do Brasil foi exitoso, disponibilizando aos profissionais brasileiros um instrumento alinhado à segurança do paciente.

Application of Artificial Neural Networks for Dengue Fever Outbreak Predictions in the Northwest Coast of Yucatan, Mexico and San Juan, Puerto Rico.

Modelling dengue fever in endemic areas is important to mitigate and improve vector-borne disease control to reduce outbreaks. This study applied artificial neural networks (ANNs) to predict dengue fever outbreak occurrences in San Juan, Puerto Rico (USA), and in several coastal municipalities of the state of Yucatan, Mexico, based on specific thresholds. The models were trained with 19 years of dengue fever data for Puerto Rico and six years for Mexico. Environmental and demographic data included in the predictive models were sea surface temperature (SST), precipitation, air temperature (i.e., minimum, maximum, and average), humidity, previous dengue cases, and population size. Two models were applied for each study area. One predicted dengue incidence rates based on population at risk (i.e., numbers of people younger than 24 years), and the other on the size of the vulnerable population (i.e., number of people younger than five years and older than 65 years). The predictive power was above 70% for all four model runs. The ANNs were able to successfully model dengue fever outbreak occurrences in both study areas. The variables with the most influence on predicting dengue fever outbreak occurrences for San Juan, Puerto Rico, included population size, previous dengue cases, maximum air temperature, and date. In Yucatan, Mexico, the most important variables were population size, previous dengue cases, minimum air temperature, and date. These models have predictive skills and should help dengue fever mitigation and management to aid specific population segments in the Caribbean region and around the Gulf of Mexico.

Sistemas de alerta temprana con enfoque participativo: un desafío para la gestión del riesgo en colombia / Early warning systems with a participative approach: a challenge for risk management in colombia

La mayor parte de la población colombiana está en condiciones de riesgo debido a factores hidroclimatológicos, fuertemente influenciados por la variabilidad (VC) y el cambio climático (CC). A esto se suma el aumento de la vulnerabilidad por la inadecuada planificación y ocupación del territorio, propia de países en desarrollo. En este sentido, los sistemas de alerta temprana (SAT) facilitan los procesos de adaptación y mitigación de impactos, por lo que se constituyen en uno de los ejes transversales de la gestión del riesgo. En este trabajo se presenta una reflexión de diversos enfoques y experiencias nacionales e internacionales en SAT. A partir de lo anterior, se identificó que muchos SAT no llegan a ser implementados; y una vez en funcionamiento, existe desequilibrio entre sus componentes. Por otro lado, no se ajustan a las necesidades de los territorios como consecuencia de la escasa participación comunitaria, tanto en la etapa de diseño como en la de operación. Por ello, se considera que para obtener resultados eficaces, que promuevan la construcción de resiliencia, son necesarios SAT con enfoque participativo, que fortalezcan las capacidades de las comunidades para enfrentar las condiciones de riesgo de su entorno.

Most of the Colombian population is facing risks due to hydroclimatological factors, strongly influenced by the climate variability (CV) and climate change (CC). Likewise, vulnerability is continuously increasing because of inadequate land planning and occupation, common in developing countries. Therefore, early warning systems (EWS) facilitate the processes of adaptation and mitigation of impacts, which is why they constitute one of the transverse axes in risk management. This study aimed to review approaches to and field experiences with EWS throughout the world, including Colombia. We identified that many EWS are unimplemented; and once in operation, there exists an imbalance among components. On the other hand, some EWS fail to meet the territory needs as a result of poor community participation, both at design and operation stages. Hence, a participative approach in EWS to tackling risks and building up the capacities of the communities should be promoted for obtaining effective results.

Desenvolvimento de software para vigilância e alerta de deterioração clínica e disfunções orgânicas / Software development for surveillance and alert of clinical deterioration and organic dysfunctions

OBJETIVOS: Desenvolvimento de um software para auxiliar no gerenciamento médico para casos traumáticos e não traumáticos com recursos de vigilância e alerta de deterioração clínica baseado nos sinais vitais e disfunções orgânicas baseadas nos resultados de exames laboratoriais. MÉTODOS: Desenvolvimento de um módulo de software para sistemas web. Resultados: Este estudo mostra o desenvolvimento de um sistema capaz de reunir informações clínicas e laboratoriais para criar alertas visuais sobre a evolução do quadro clínico do paciente. CONCLUSÃO: Através de resultados preliminares com 32 variáveis fisiológicas (25 resultados de exames laboratoriais e sete sinais vitais) foi possível desenvolver uma interface que reúne todos os dados de uma maneira clara e de fácil entendimento. Utilizando o desvio de normalidade de cada parâmetro fisiológico, foi criado um alerta visual guiado por cores, indicando melhora ou deterioração do quadro clínico.

OBJECTIVES: To develop software to support medical management of traumatic and non-traumatic cases, using surveillance resources in addition to a clinical deterioration alert system based on vital signs and organ dysfunction, with the latter being dependent on the results of laboratory analysis. METHODS: Development of modular software for web systems. RESULTS: The study demonstrated the development of a system capable of assembling clinical and laboratory data in order to create visual alerts from tracking a patient`s clinical progress. CONCLUSION: From the preliminary results using 32 physiologic variables (25 results from laboratory exams and 7 from vital signs), it was possible to develop an interface that assembled data in a clear and comprehensible way. From the physiological parameters, acolour-coded visual alert system was created, which was able to indicate the improvement or deterioration in the patient`s condition.

Influencia de la variabilidad climática en las enfermedades respiratorias agudas en Bogotá / Influence of the climate variability on acute respiratory infections in the city of Bogotá

Introducción. La enfermedad respiratoria es una de las principales causas de morbilidad en Bogotá y los efectos de la variabilidad climática se han reflejado en un aumento del número de casos. Objetivo. En el presente estudio se analizó el comportamiento semanal de la enfermedad respiratoria aguda en Bogotá y se asoció con las variables climatológicas de temperatura, humedad relativa y precipitación, analizando su impacto en la aparición de casos en la ciudad. Materiales y métodos. El análisis se llevó a cabo mediante la estimación de modelos de regresión de Poisson, con datos epidemiológicos de 104 semanas correspondientes a los años 2011 y 2012. La variabilidad climática temporal se analizó considerando los efectos de las variables en semanas anteriores y, para el análisis de la variabilidad espacial, la ciudad se dividió en cuatro zonas: norte, sur, oriente y occidente. Resultados. Los resultados de las correlaciones cruzadas demostraron que en tres de las cuatro zonas la humedad relativa tenía un mayor impacto sobre los casos de enfermedad respiratoria aguda y su efecto persistía hasta por ocho y diez semanas. La precipitación, por el contrario, tuvo impacto únicamente en la zona oriente, mientras que la temperatura tuvo efectos moderados en todas las zonas. Conclusión. Debido al componente dinámico de estos modelos, los resultados son un primer paso para el diseño de un sistema de alerta temprana en salud que tome en cuenta la variabilidad climática.

Introduction: Acute respiratory infection is one of the most significant causes of morbidity in Bogota, and its burden of disease has increased in association with climate variability . Objective: The aim of the study was to evaluate weekly trends of acute respiratory infection in relation to meteorological variables (temperature, relative humidity and cumulative rainfall) in Bogota during 2011 and 2012. Materials and methods: Epidemiological and meteorological data from 104 weeks were gathered. Temporal variability was taken into account including previous weeks and spatial variability was considered by studying each zone of the city separately (north, south, east, west). Statistical analysis was performed through Poisson dynamic regression models. Results: The relative humidity had the greater impact on acute respiratory infection and its effects lasted between 8 to 10 weeks. Cumulative rainfall had effects only in the east zone, while the temperature presented mild effects across the four different zones of the city. Conclusion: Such results are the first step for the design of health-related early warning systems associated with climate variability.