RESUMO

BACKGROUND: Stroke management requires a coordinated strategy, adhering to clinical pathways (CP) and value-based healthcare (VBHC) principles from onset to rehabilitation. However, the discrepancies between these pathways and actual patient experiences highlight the need for ongoing monitoring and addressing interoperability issues across multiple institutions in stroke care. To address this, the Fast Healthcare Interoperability Resource (FHIR) Implementation Guide (IG) standardizes the information exchange among these systems, considering a specific context of use. OBJECTIVE: Develop an FHIR IG for stroke care rooted in established stroke CP and VBHC principles. METHOD: We represented the stroke patient journey by considering the core stroke CP, the International Consortium for Health Outcomes Measurement (ICHOM) dataset for stroke, and a Brazilian case study using the Business Process Model and Notation (BPMN). Next, we developed a data dictionary that aligns variables with existing FHIR resources and adapts profiling from the Brazilian National Health Data Network (BNHDN). RESULTS: Our BPMN model encompassed three critical phases that represent the entire patient journey from symptom onset to rehabilitation. The stroke data dictionary included 81 variables, which were expressed as questionnaires, profiles, and extensions. The FHIR IG comprised nine pages: Home, Stroke-CP, Data Dictionary, FHIR, ICHOM, Artifacts, Examples, Downloads, and Security. We developed 96 artifacts, including 7 questionnaires, 27 profiles with corresponding example instances, 3 extensions, 18 value sets, and 14 code systems pertinent to ICHOM outcome measures. CONCLUSION: The FHIR IG for stroke in this study represents a significant advancement in healthcare interoperability, streamlining the tracking of patient outcomes for quality enhancement, facilitating informed treatment choices, and enabling the development of dashboards to promote collaborative excellence in patient care.

Assuntos

RESUMO

Introduction: Leprosy reactions (LR) are severe episodes of intense activation of the host inflammatory response of uncertain etiology, today the leading cause of permanent nerve damage in leprosy patients. Several genetic and non-genetic risk factors for LR have been described; however, there are limited attempts to combine this information to estimate the risk of a leprosy patient developing LR. Here we present an artificial intelligence (AI)-based system that can assess LR risk using clinical, demographic, and genetic data. Methods: The study includes four datasets from different regions of Brazil, totalizing 1,450 leprosy patients followed prospectively for at least 2 years to assess the occurrence of LR. Data mining using WEKA software was performed following a two-step protocol to select the variables included in the AI system, based on Bayesian Networks, and developed using the NETICA software. Results: Analysis of the complete database resulted in a system able to estimate LR risk with 82.7% accuracy, 79.3% sensitivity, and 86.2% specificity. When using only databases for which host genetic information associated with LR was included, the performance increased to 87.7% accuracy, 85.7% sensitivity, and 89.4% specificity. Conclusion: We produced an easy-to-use, online, free-access system that identifies leprosy patients at risk of developing LR. Risk assessment of LR for individual patients may detect candidates for close monitoring, with a potentially positive impact on the prevention of permanent disabilities, the quality of life of the patients, and upon leprosy control programs.

RESUMO

Introduction: Leprosy reactions (LR) are severe episodes of intense activation of the host inflammatory response of uncertain etiology, today the leading cause of permanent nerve damage in leprosy patients. Several genetic and non-genetic risk factors for LR have been described; however, there are limited attempts to combine this information to estimate the risk of a leprosy patient developing LR. Here we present an artificial intelligence (AI)-based system that can assess LR risk using clinical, demographic, and genetic data. Methods: The study includes four datasets from different regions of Brazil, totalizing 1,450 leprosy patients followed prospectively for at least 2 years to assess the occurrence of LR. Data mining using WEKA software was performed following a two-step protocol to select the variables included in the AI system, based on Bayesian Networks, and developed using the NETICA software. Results: Analysis of the complete database resulted in a system able to estimate LR risk with 82.7% accuracy, 79.3% sensitivity, and 86.2% specificity. When using only databases for which host genetic information associated with LR was included, the performance increased to 87.7% accuracy, 85.7% sensitivity, and 89.4% specificity. Conclusion: We produced an easy-to-use, online, free-access system that identifies leprosy patients at risk of developing LR. Risk assessment of LR for individual patients may detect candidates for close monitoring, with a potentially positive impact on the prevention of permanent disabilities, the quality of life of the patients, and upon leprosy control programs.

Assuntos

RESUMO

BACKGROUND: The high volume of research focusing on extracting patient information from electronic health records (EHRs) has led to an increase in the demand for annotated corpora, which are a precious resource for both the development and evaluation of natural language processing (NLP) algorithms. The absence of a multipurpose clinical corpus outside the scope of the English language, especially in Brazilian Portuguese, is glaring and severely impacts scientific progress in the biomedical NLP field. METHODS: In this study, a semantically annotated corpus was developed using clinical text from multiple medical specialties, document types, and institutions. In addition, we present, (1) a survey listing common aspects, differences, and lessons learned from previous research, (2) a fine-grained annotation schema that can be replicated to guide other annotation initiatives, (3) a web-based annotation tool focusing on an annotation suggestion feature, and (4) both intrinsic and extrinsic evaluation of the annotations. RESULTS: This study resulted in SemClinBr, a corpus that has 1000 clinical notes, labeled with 65,117 entities and 11,263 relations. In addition, both negation cues and medical abbreviation dictionaries were generated from the annotations. The average annotator agreement score varied from 0.71 (applying strict match) to 0.92 (considering a relaxed match) while accepting partial overlaps and hierarchically related semantic types. The extrinsic evaluation, when applying the corpus to two downstream NLP tasks, demonstrated the reliability and usefulness of annotations, with the systems achieving results that were consistent with the agreement scores. CONCLUSION: The SemClinBr corpus and other resources produced in this work can support clinical NLP studies, providing a common development and evaluation resource for the research community, boosting the utilization of EHRs in both clinical practice and biomedical research. To the best of our knowledge, SemClinBr is the first available Portuguese clinical corpus.

Assuntos

RESUMO

This theoretical and reflective study aimed to assess the contribution of the ISO/TR 12300:2016 document for the mapping of nursing terminology. The referred document and related articles were used as an empirical framework. The study analyzed the content of the document, highlighting cardinality and equivalence principles. The standard presents conceptual and operational basis for mapping, with cardinality and equivalence as the support for the categorization of cross-terminology mapping in the area of nursing. Cardinality verifies candidate target terms to represent the source term, while the equivalence degree scale checks semantic correspondence. Among the principles included in the ISO/TR 12300:2016, cardinality and equivalence contribute to the accurate representation of the results of the cross-terminology mapping process and its use should decrease inconsistencies.

Assuntos

RESUMO

Abstract This theoretical and reflective study aimed to assess the contribution of the ISO/TR 12300:2016 document for the mapping of nursing terminology. The referred document and related articles were used as an empirical framework. The study analyzed the content of the document, highlighting cardinality and equivalence principles. The standard presents conceptual and operational basis for mapping, with cardinality and equivalence as the support for the categorization of cross-terminology mapping in the area of nursing. Cardinality verifies candidate target terms to represent the source term, while the equivalence degree scale checks semantic correspondence. Among the principles included in the ISO/TR 12300:2016, cardinality and equivalence contribute to the accurate representation of the results of the cross-terminology mapping process and its use should decrease inconsistencies.

Resumen Este estudio teórico reflexivo tiene como fin reflexionar acerca del aporte de la norma ISO/TR 12300:2016 para el mapeo de terminologías en el área de enfermería. Fueron utilizados como base empírica la mencionada norma y artículos relacionados, analizando el contenido de la norma y destacando los principios de cardinalidad y equivalencia. La norma presenta bases conceptuales y operativas para el mapeo, con la cardinalidad y la equivalencia, anclando la categorización de los resultados de los mapeos entre terminologías en el área de enfermería. La cardinalidad verifica los términos meta candidatos para representar el término fuente, mientras que la escala de grado de equivalencia verifica la correspondencia semántica. Entre los principios incluidos en la ISO/TR 12300:2016, la cardinalidad y la equivalencia contribuyen a la representación precisa de los resultados del proceso de mapeo cruzado y su empleo debe de reducir inconsistencias.

Resumo Este estudo teórico-reflexivo teve como objetivo refletir sobre a contribuição da norma ISO/TR 12300:2016 para mapeamento de terminologias na área de enfermagem. Foram utilizados como base empírica a referida norma e artigos relacionados, analisando o conteúdo da norma e destacando os princípios de cardinalidade e equivalência. A norma apresenta bases conceituais e operacionais para o mapeamento, com a cardinalidade e a equivalência, ancorando a categorização dos resultados dos mapeamentos entre terminologias na área de enfermagem. A cardinalidade verifica os termos-alvo candidatos para representar o termo-fonte, enquanto a escala de grau de equivalência verifica a correspondência semântica. Entre os princípios inclusos na ISO/TR 12300:2016, a cardinalidade e a equivalência contribuem para a representação precisa dos resultados do processo de mapeamento cruzado e seu uso deve diminuir inconsistências.

Assuntos

RESUMO

In this paper, we trained a set of Portuguese clinical word embedding models of different granularities from multi-specialty and multi-institutional clinical narrative datasets. Then, we assessed their impact on a downstream biomedical NLP task of Urinary Tract Infection disease identification. Additionally, we intrinsically evaluated our main model using an adapted version of Bio-SimLex for the Portuguese language. Our empirical results showed that the larger, coarse-grained model achieved a slightly better outcome when compared with the small, fine-grained model in the proposed task. Moreover, we obtained satisfactory results with Bio-SimLex intrinsic evaluation.

Assuntos

RESUMO

Contexto: A amputação e a desarticulação objetivam melhorar a saúde de um indivíduo, mas esses tratamentos apresentam taxas significantes de mortalidade que variam de acordo com os fatores relacionados. Objetivo: Identificar as associações entre os determinantes da mortalidade pós-operatória da amputação. Métodos: Estudo do tipo caso-controle (óbito versus não óbito) em que foi adotada a descoberta de regras de associação (abordagem da mineração de dados) e métricas epidemiológicas sobre 173 registros de pacientes amputados em um hospital público de Santa Catarina em 2014. Resultados: Os principais determinantes foram: idade > 60 anos [ odds ratio (OR) = 3,0], sexo feminino (OR = 2,0), baixa escolaridade, hipertensão (OR = 3,0), diabetes (OR = 1,6) e tabagismo (OR = 1,8). Dos pacientes com idade entre 60 a 69 anos (38%), 87,9% evoluíram para alta, estando o óbito associado a doença vascular periférica. Quando a idade foi > 70 anos, embolia e trombose de artérias dos membros inferiores foram o fator de exceção (óbito). As patologias com maior associação ao óbito foram doença vascular (47,0%), diabetes (29,4%), doença cardíaca (razão de risco = 11,4), doença renal (OR = 10,4) e doença pulmonar (OR = 5,2). As cirurgias proximais estiveram mais associadas ao óbito do que as distais. Entre os pacientes que foram a óbito, 76,0% foram submetidos a raquianestesia e 24,0% a anestesia geral. Conclusão: A mineração de dados permitiu identificar as associações vinculadas ao óbito entre as diferentes variáveis e diagnósticos, como por exemplo, entre idade > 70 anos e diagnóstico de embolia e trombose de artérias dos membros inferiores

Background: The objective of amputation and disarticulation is to improve health. However, these treatments are associated with significant mortality rates that vary in relation to risk factors. Objective: To identify associations between determinants of postoperative mortality after amputation surgery. Methods: Case-control study (death vs. no death) considering data from 173 patients who underwent amputation surgery at a public hospital in Santa Catarina state, Brazil. These data were analyzed using a data mining approach to discover association rules and epidemiologic association metrics. Results: The main determinants were age > 60 years (odds ratio (OR) = 3.0), female sex (OR = 2.0), low education, hypertension (OR = 3.0), diabetes (OR = 1.6), and smoking (OR = 1.8). Among patients aged 60-69 years, 87.9% survived to discharge from hospital. The exceptions occurred when patients in this age range had peripheral vascular disease. The same was true when age was > 70 years, among whom diagnoses of embolism and thrombosis of arteries of the lower extremities were the exception factors (associated with death). The most common pathologies associated with death were vascular disease (47.0%) and diabetes (29.4%), heart disease (relative risk = 11.4), renal disease (OR = 10.4), and lung disease (OR = 5.2). Proximal surgeries were more strongly associated with death than distal ones. Among the deaths, 76.0% had been given spinal anesthesia and 24.0% general anesthesia. Conclusion: Data mining enabled identification of associations between death and a variety of different variables and diagnostic hypotheses; for example, age > 70 years and diagnosis of embolism and thrombosis of arteries of the lower extremities

Assuntos

RESUMO

Studies describing Computer-Interpretable Clinical Guidelines (CIG) with temporal constrains (TC) generally have not addressed issues related to their integration into Electronic Health Record (EHR) systems. This study aimed to represent TCs contained in clinical guidelines by applying archetypes and Guideline Definition Language (GDL) to incorporate decision support into EHRs. An example of each TC class in the clinical guideline for management of Atrial Fibrillation was represented using archetypes and GDL.

Assuntos