Sistema de apoyo al diagnóstico médico de COVID-19 mediante mapa cognitivo difuso / Support system to Covid-19 medical diagnosis via diffuse cognitive map

Introducción: Los escenarios de convivencia de las diversas poblaciones son muy complejos, lo que contribuye con la propagación de enfermedades. Diagnosticar tempranamente enfermedades infecciosas representa una tarea fundamental para disminuir su propagación y evitar epidemias. Sin embargo, la inconsistencia en los datos de poblaciones y la imposibilidad de contar con un diagnóstico oportuno en muchos casos trae como consecuencia la proliferación de pandemias tales como la COVID-19. Objetivo: Desarrollar un sistema de apoyo al diagnóstico médico para COVID-19 a partir de la modelación de las relaciones causales de los criterios de diagnóstico, para conformar el mapa cognitivo difuso. Métodos: Para el desarrollo de la investigación se utilizaron métodos teóricos, empíricos y estadísticos, tales como: analítico-sintético, inductivo-deductivo, hipotético-deductivo, modelación. Como método empírico se utilizó la entrevista semiestructurada con la intención de recoger información que permitiera incluir contenidos no prescritos y precisar el conocimiento de los expertos sobre los principales indicadores para la toma de decisiones en el diagnóstico médico de la COVID-19. Resultados: El sistema funciona a través de un mapa cognitivo difuso para modelar las relaciones causales que representan la base de la inferencia. Se utilizan técnicas de inteligencia artificial como base al diagnóstico médico. Se presenta un ejemplo demostrativo para el diagnóstico médico de la COVID-19 en el que se modelan las relaciones causales de los diferentes conceptos que describen la enfermedad provocada. Conclusiones: El sistema diseñado constituye una herramienta viable de apoyo a la toma de decisiones en el diagnóstico médico de la COVID-19, que permite obtener criterios evaluativos a partir de la modelación de las relaciones causales, esto lo hace extensible a otros tipos de situaciones de emergencias sanitarias(AU)

Introduction: Different populations coexistence scenarios are very complex, which contributes to the spread of diseases. Diagnosing infectious diseases early is a critical task in reducing its spread and preventing epidemics. However, inconsistency in population data and the inability to have timely diagnosis in many cases result in the proliferation of pandemics such as COVID-19. Objective: Develop a support system for COVID-19 medical diagnostic from modeling causal relations of diagnostic criteria, to form the diffuse cognitive map. Methods: Theoretical, empirical and statistical methods were used for the development of the research, such as: analytical-synthetic, inductive-deductive, hypothetical-deductive, modeling. As an empirical method, the semi-structured interview was used with the intention of collecting information that would include unprescribed contents and require expert knowledge of the main indicators for decision-making in COVID-19 medical diagnosis. Results: The system works through a diffuse cognitive map to model causal relationships that represent the inference´s basis. Artificial intelligence techniques are used as a basis for medical diagnosis. A demonstrative example is presented for COVID-19 medical diagnosis in which are modelled the causal relations of the different concepts that the disease describes. Conclusions: The designed system is a viable support tool for decision-making in COVID-19 medical diagnosis, which allows to obtain evaluative criteria from the modelling of causal relations, and this makes it extendable to other types of health emergencies situations(AU)

Value-based medicine in oncology: the importance of perspective in the emerging value frameworks

Recently, professional and healthcare-related entities have launched frameworks designed to assess the value of cancer innovations in multistakeholder decision processes. Among the most visible entities that propose and implement value frameworks in oncology are the European Society of Medical Oncology (ESMO), the American Society of Clinical Oncology (ASCO), the Memorial Sloan Kettering Cancer Center (MSKCC) and the National Comprehensive Cancer Network (NCCN). However, these value frameworks have been criticized for conceptual inconsistencies, inability to include a greater variety of value criteria, and inadequate explanation of the uncertainty approach used in the modeling process. On the other hand, Multi-Criteria Decision Analysis (MCDA) is a set of methods and processes that allow the multiple criteria involved in a decision to be explicitly addressed. This approach allows the identification of relevant decision criteria, gathering of evidence based on scientific literature, attribution of weights to the criteria and scores to the evidence raised, and aggregation of the weighted scores to constitute a global metric of value. The purpose of this article is to review the main features of these value frameworks in oncology and the importance of perspective for framework readiness to support healthcare decision-making based on MCDA methodology.

Sistema de suporte à decisão clínica para um programa para profilaxia de tromboembolia venosa em um hospital geral de um país de renda média / A clinical decision support system for venous thromboembolism prophylaxis at a general hospital in a middle-income country

OBJETIVO: Determinar o impacto da implantação de um sistema informatizado de suporte à decisão clínica combinado com seminários instrucionais na utilização de profilaxia para tromboembolia venosa (TEV) de forma adequada. MÉTODOS: Estudo transversal em duas fases (antes e depois da implantação de um novo protocolo de profilaxia para TEV) para avaliar o impacto que a estratégia combinada teve na utilização adequada da profilaxia para TEV. O estudo foi conduzido no Hospital Nossa Senhora da Conceição, um hospital geral localizado em Porto Alegre (RS). Foram incluídos pacientes clínicos e cirúrgicos com mais de 18 anos com tempo de hospitalização > 48 h. Nas fases pré e pós-implantação, foram incluídos 262 e 261 pacientes, respectivamente. RESULTADOS: As características de base das duas amostras foram semelhantes, inclusive em relação à distribuição dos pacientes por nível de risco. Comparando-se os períodos pré e pós-implantação, verificou-se que a adequação da profilaxia para TEV aumentou de 46,2% para 57,9% (p = 0,01). Ao se observar populações específicas de pacientes, o uso adequado da profilaxia para TVE aumentou dramaticamente em pacientes com câncer (de 18,1% para 44,1%; p = 0,002) e em pacientes com três ou mais fatores de risco (de 25,0% para 42,9%; p = 0,008), populações essas que mais se beneficiam da profilaxia. CONCLUSÕES: É possível aumentar o uso de profilaxia adequada para TEV em cenários economicamente desfavoráveis através do uso de protocolos informatizados e de profissionais treinados. A subutilização da profilaxia permanece como um problema importante, destacando a necessidade da melhora continuada na qualidade da assistência hospitalar.

OBJECTIVE: To determine the impact that implementing a combination of a computer-based clinical decision support system and a program of training seminars has on the use of appropriate prophylaxis for venous thromboembolism (VTE). METHODS: We conducted a cross-sectional study in two phases (prior to and after the implementation of the new VTE prophylaxis protocol) in order to evaluate the impact that the combined strategy had on the use of appropriate VTE prophylaxis. The study was conducted at Nossa Senhora da Conceição Hospital, a general hospital in the city of Porto Alegre, Brazil. We included clinical and surgical patients over 18 years of age who were hospitalized for > 48 h. The pre-implementation and post-implementation phase samples comprised 262 and 261 patients, respectively. RESULTS: The baseline characteristics of the two samples were similar, including the distribution of patients by risk level. Comparing the pre-implementation and post-implementation periods, we found that the overall use of appropriate VTE prophylaxis increased from 46.2% to 57.9% (p = 0.01). Looking at specific patient populations, we observed that the use of appropriate VTE prophylaxis increased more dramatically among cancer patients (from 18.1% to 44.1%; p = 0.002) and among patients with three or more risk factors (from 25.0% to 42.9%; p = 0.008), two populations that benefit most from prophylaxis. CONCLUSIONS: It is possible to increase the use of appropriate VTE prophylaxis in economically constrained settings through the use of a computerized protocol adhered to by trained professionals. The underutilization of prophylaxis continues to be a major problem, indicative of the need for ongoing improvement in the quality of inpatient care.

A comparative study of the quality and availability of health information used to facilitate cost burden analysis of diabetes and hypertension in the Caribbean / Estudio comparativo de la calidad y disponibilidad de la información sobre la salud usada para facilitar el análisis del nivel de costos de la diabetes y la hipertensión en el Caribe

OBJECTIVE: Non-communicable Diseases (NCDs) are leading threats to health and well-being in the Caribbean. A study was undertaken in the latter part of 2005 to compute the economic burden of diabetes mellitus and hypertension within the Caribbean Community and Common Market (CARICOM). This report critiques the quality and availability of health information which can be used to facilitate cost burden analysis of diabetes mellitus and hypertension. METHODS: A form was developed and disseminated to obtain epidemiological and health service utilization data. Subsequent visits were made to seven CARICOM member countries to collect the data. RESULTS: The results revealed (i) a number of deficiencies in the reliability and validity of the data received, in particular, those needed to facilitate the analysis of cost-specific complications such as ischaemic heart disease, cerebrovascular disease, chronic renal failure, hypertensive and diabetic retinopathy and peripheral circulatory complications; (ii) data management systems in hospitals were not linked to facilitate generation of cost-effectiveness estimates and other information required to compare options for health investment; (iii) despite repeated attempts by regional governments to develop/strengthen Health Information Systems within the Caribbean, sustainability has been significantly hampered by human, material and financial resource constraints and ongoing monitoring and evaluation is generally poor. CONCLUSION: There are deficiencies in the quality and availability of health information to facilitate cost burden analysis of hypertension and diabetes mellitus in the Caribbean. Strong commitment from CARICOM governments will be necessary to address these concerns if economic evaluations are to be undertaken more frequently as part of the effort to reduce the morbidity and mortality from these diseases.

OBJETIVO: Las enfermedades no comunicables (ENC) se cuentan entre las principales amenazas a la salud y el bienestar en el Caribe. Se llevó a cabo un estudio hacia finales de 2005, con el fin de computar la carga económica de la diabetes mellitus y la hipertensión dentro de la Comunidad y el Mercado Común del Caribe (CARICOM). Este reporte constituye un análisis crítico de la calidad y disponibilidad de información sobre la salud, que puede ser usada para facilitar el análisis del nivel de costos de la diabetes mellitus y la hipertensión. MÉTODOS: Se desarrolló y distribuyó un formulario para obtener datos acerca de la utilización de servicios de salud y servicios epidemiológicos. Posteriormente se realizaron visitas a siete países miembros de CARICOM con el propósito de recoger datos. RESULTADOS: Los resultados revelaron (i) algunas deficiencias en cuanto a la confiabilidad y la validez de los datos recibidos, en particular los necesarios para facilitar el análisis de las complicaciones costo-específicas, tales como la enfermedad cardíaca isquémica, la enfermedad cerebrovascular, el fallo renal crónico, la retinopatía hipertensiva y diabética, y las complicaciones circulatorias periféricas; (ii) los sistemas de administración de datos en los hospitales no estaban conectados para facilitar la producción de estimados de costo-efectividad y otras informaciones requeridas para comparar las opciones de inversión para la salud; (iii) a pesar de reiterados intentos de los gobiernos regionales por desarrollar y fortalecer los sistemas de información de salud en el área del Caribe, su sostenimiento ha sido obstaculizado significativamente a causa de restricciones en cuanto a recursos humanos, materiales y financieros, y por el hecho de que el monitoreo y la evaluación actuales son generalmente pobres. CONCLUSIÓN: Existen deficiencias en la calidad y disponibilidad de información sobre la salud, en cuanto a facilitar el análisis del nivel de la magnitud del costo de la hipertensión y la diabetes mellitus en el Caribe. Será necesario un fuerte compromiso por parte de los gobiernos del CARICOM para abordar estos problemas, si se ha de emprender evaluaciones económicas con mayor frecuencia, como parte del esfuerzo por reducir la morbilidad y la mortalidad por estas enfermedades.