RESUMO

INTRODUCTION AND OBJECTIVES: Despite the huge clinical burden of MASLD, validated tools for early risk stratification are lacking, and heterogeneous disease expression and a highly variable rate of progression to clinical outcomes result in prognostic uncertainty. We aimed to investigate longitudinal electronic health record-based outcome prediction in MASLD using a state-of-the-art machine learning model. PATIENTS AND METHODS: n = 940 patients with histologically-defined MASLD were used to develop a deep-learning model for all-cause mortality prediction. Patient timelines, spanning 12 years, were fully-annotated with demographic/clinical characteristics, ICD-9 and -10 codes, blood test results, prescribing data, and secondary care activity. A Transformer neural network (TNN) was trained to output concomitant probabilities of 12-, 24-, and 36-month all-cause mortality. In-sample performance was assessed using 5-fold cross-validation. Out-of-sample performance was assessed in an independent set of n = 528 MASLD patients. RESULTS: In-sample model performance achieved AUROC curve 0.74-0.90 (95 % CI: 0.72-0.94), sensitivity 64 %-82 %, specificity 75 %-92 % and Positive Predictive Value (PPV) 94 %-98 %. Out-of-sample model validation had AUROC 0.70-0.86 (95 % CI: 0.67-0.90), sensitivity 69 %-70 %, specificity 96 %-97 % and PPV 75 %-77 %. Key predictive factors, identified using coefficients of determination, were age, presence of type 2 diabetes, and history of hospital admissions with length of stay >14 days. CONCLUSIONS: A TNN, applied to routinely-collected longitudinal electronic health records, achieved good performance in prediction of 12-, 24-, and 36-month all-cause mortality in patients with MASLD. Extrapolation of our technique to population-level data will enable scalable and accurate risk stratification to identify people most likely to benefit from anticipatory health care and personalized interventions.

Assuntos

RESUMO

This study aimed to validate and refine an information model on pain management in a Brazilian hospital, considering the institutional culture, using an expert consensus approach. The first stage took place through a computerized questionnaire and Content Validity Index calculation. Pain management attributes were considered validated with 75% consensus among 19 experts. The second stage validated and refined the information model by three experts via an online meeting. Results showed that out of 11 evaluated attributes, five were validated. In the second stage, the inclusion of new attributes was suggested to address institutional culture. The final information model resulted from 23 sets of revised attributes: 12 validated, seven suggested and four not validated. The resulting Brazilian model has the potential to support the implementation of interventions and propose improvements to the institution's electronic system, which can be reused in other institutions.

Assuntos

RESUMO

Objective: Long COVID, marked by persistent, recurring, or new symptoms post-COVID-19 infection, impacts children's well-being yet lacks a unified clinical definition. This study evaluates the performance of an empirically derived Long COVID case identification algorithm, or computable phenotype, with manual chart review in a pediatric sample. This approach aims to facilitate large-scale research efforts to understand this condition better. Methods: The algorithm, composed of diagnostic codes empirically associated with Long COVID, was applied to a cohort of pediatric patients with SARS-CoV-2 infection in the RECOVER PCORnet EHR database. The algorithm classified 31,781 patients with conclusive, probable, or possible Long COVID and 307,686 patients without evidence of Long COVID. A chart review was performed on a subset of patients (n=651) to determine the overlap between the two methods. Instances of discordance were reviewed to understand the reasons for differences. Results: The sample comprised 651 pediatric patients (339 females, M age = 10.10 years) across 16 hospital systems. Results showed moderate overlap between phenotype and chart review Long COVID identification (accuracy = 0.62, PPV = 0.49, NPV = 0.75); however, there were also numerous cases of disagreement. No notable differences were found when the analyses were stratified by age at infection or era of infection. Further examination of the discordant cases revealed that the most common cause of disagreement was the clinician reviewers' tendency to attribute Long COVID-like symptoms to prior medical conditions. The performance of the phenotype improved when prior medical conditions were considered (accuracy = 0.71, PPV = 0.65, NPV = 0.74). Conclusions: Although there was moderate overlap between the two methods, the discrepancies between the two sources are likely attributed to the lack of consensus on a Long COVID clinical definition. It is essential to consider the strengths and limitations of each method when developing Long COVID classification algorithms.

RESUMO

Objectives: Describe the current legislation on electronic medical records (EMR) and telehealth in Latin American countries and analyze the treatment of confidentiality and professional secrecy. Methods: Between March and September 2022, a survey of the regulations in force in 21 Latin American countries was conducted at two levels: the existence of legislation on EMR and telehealth, and the treatment of confidentiality and professional secrecy in EMR and telehealth. A data extraction form was prepared for each country. Data were collected from official on-line sources. The information was analyzed qualitatively and synthesized in tables when possible. Results: The use of EMR is legally regulated in 16 countries. Nineteen countries have legislation on telehealth. All the countries analyzed safeguard confidentiality and professional secrecy through regulations. However, confidentiality and professional secrecy are mentioned in 11 countries in the context of telehealth, and in only nine countries in the context of EMR. Conclusions: Since the start of this century, Latin America has made progress in the legislation of digital tools for health care, such as EMR and telehealth. There is also interest in ethical issues related to the use of EMR and telehealth, particularly confidentiality and professional secrecy, aspects that should be strengthened in digital health.

Objetivo: Descrever a legislação vigente sobre prontuários eletrônicos e telessaúde nos países da América Latina e analisar o tratamento da confidencialidade e do sigilo profissional. Métodos: Entre março e setembro de 2022, realizou-se um levantamento sobre a regulamentação vigente nos 21 países latino-americanos incluídos no estudo, em dois níveis: i) existência de legislação sobre prontuários eletrônicos e telessaúde; e ii) tratamento da confidencialidade e do sigilo profissional em prontuários eletrônicos e telessaúde. Uma planilha para extração de dados foi elaborada para cada país. Os dados foram coletados de fontes oficiais disponíveis on-line. Foi realizada uma análise qualitativa das informações, que foram resumidas em tabelas, quando possível. Resultados: O uso dos prontuários eletrônicos é legalmente regulamentado em 16 países. Quanto à telessaúde, 19 países têm legislação sobre essa ferramenta. Todos os países analisados protegem a confidencialidade e o sigilo profissional por meio de regulamentação. No entanto, no contexto da telessaúde, eles são mencionados em 11 países; já no contexto dos prontuários eletrônicos, em apenas 9 países. Conclusões: Desde o início dos anos 2000, a América Latina vem avançando em relação à legislação sobre ferramentas digitais na atenção à saúde, como prontuários eletrônicos e telessaúde. Há também interesse nas questões éticas relacionadas ao uso de prontuários eletrônicos e telessaúde, especialmente em relação à confidencialidade e ao sigilo profissional, embora esses aspectos precisem ser reforçados na saúde digital.

RESUMO

Objective: Postpartum hemorrhage (PPH) is the leading cause of maternal death globally. Therefore, prevention strategies have been created. The study aimed to evaluate the occurrence of PPH and its risk factors after implementing a risk stratification at admission in a teaching hospital. Methods: A retrospective cohort involving a database of SISMATER® electronic medical record. Classification in low, medium, or high risk for PPH was performed through data filled out by the obstetrician-assistant. PPH frequency was calculated, compared among these groups and associated with the risk factors. Results: The prevalence of PPH was 6.8%, 131 among 1,936 women. Sixty-eight (51.9%) of them occurred in the high-risk group, 30 (22.9%) in the medium-risk and 33 (25.2%) in the low-risk group. The adjusted-odds ratio (OR) for PPH were analyzed using a confidence interval (95% CI) and was significantly higher in who presented multiple pregnancy (OR 2.88, 95% CI 1.28 to 6.49), active bleeding on admission (OR 6.12, 95% CI 1.20 to 4.65), non-cephalic presentation (OR 2.36, 95% CI 1.20 to 4.65), retained placenta (OR 9.39, 95% CI 2.90 to 30.46) and placental abruption (OR 6.95, 95% CI 2.06 to 23.48). Vaginal delivery figured out as a protective factor (OR 0.58, 95% CI 0.34 to 0.98). Conclusion: Prediction of PPH is still a challenge since its unpredictable factor arrangements. The fact that the analysis did not demonstrate a relationship between risk category and frequency of PPH could be attributable to the efficacy of the strategy: Women classified as "high-risk" received adequate medical care, consequently.

Assuntos

RESUMO

AIM(S): To demonstrate how interoperable nursing care data can be used by nurses to create a more holistic understanding of the healthcare needs of multiple traumas patients with Impaired Physical Mobility. By proposing and validating linkages for the nursing diagnosis of Impaired Physical Mobility in multiple trauma patients by mapping to the Nursing Outcomes Classification (NOC) and Nursing Interventions Classification (NIC) equivalent terms using free-text nursing documentation. DESIGN: A descriptive cross-sectional design, combining quantitative analysis of interoperable data sets and the Kappa's coefficient score with qualitative insights from cross-mapping methodology and nursing professionals' consensus. METHODS: Cross-mapping methodology was conducted in a Brazilian Level 1 Trauma Center using de-identified records of adult patients with a confirmed medical diagnosis of multiple traumas and Impaired Physical Mobility (a nursing diagnosis). The hospital nursing free-text records were mapped to NANDA-I, NIC, NOC and NNN linkages were identified. The data records were retrieved for admissions from September to October 2020 and involved medical and nursing records. Three expert nurses evaluated the cross-mapping and linkage results using a 4-point Likert-type scale and Kappa's coefficient. RESULTS: The de-identified records of 44 patients were evaluated and then were mapped to three NOCs related to nurses care planning: (0001) Endurance; (0204) Immobility Consequences: Physiological, and (0208) Mobility and 13 interventions and 32 interrelated activities: (6486) Environmental Management: Safety; (0840) Positioning; (3200) Aspiration Precautions; (1400) Pain Management; (0940) Traction/Immobilization Care; (3540) Pressure Ulcer Prevention; (3584) Skincare: Topical Treatment; (1100) Nutrition Management; (3660) Wound Care; (1804) Self-Care Assistance: Toileting; (1801) Self-Care Assistance: Bathing/Hygiene; (4130) Fluid Monitoring; and (4200) Intravenous Therapy. The final version of the constructed NNN Linkages identified 37 NOCs and 41 NICs. CONCLUSION: These valid NNN linkages for patients with multiple traumas can serve as a valuable resource that enables nurses, who face multiple time constraints, to make informed decisions efficiently. This approach of using evidence-based linkages like the one developed in this research holds high potential for improving patient's safety and outcomes. NO PATIENT OR PUBLIC CONTRIBUTION: In this study, there was no direct involvement of patients, service users, caregivers or public members in the design, conduct, analysis and interpretation of data or preparation of the manuscript. The study focused solely on analysing existing de-identified medical and nursing records to propose and validate linkages for nursing diagnoses.

Assuntos

RESUMO

The target trial framework has emerged as a powerful tool for addressing causal questions in clinical practice and in public health. In the healthcare sector, where decision-making is increasingly data-driven, transactional databases, such as electronic health records (EHR) and insurance claims, present an untapped potential for answering complex causal questions. This narrative review explores the potential of the integration of the target trial framework with real-world data to enhance healthcare decision-making processes. We outline essential elements of the target trial framework, and identify pertinent challenges in data quality, privacy concerns, and methodological limitations, proposing solutions to overcome these obstacles and optimize the framework's application.

Assuntos

RESUMO

Creating notes in the EHR is one of the most problematic aspects for health professionals. The main challenges are the time spent on this task and the quality of the records. Automatic speech recognition technologies aim to facilitate clinical documentation for users, optimizing their workflow. In our hospital, we internally developed an automatic speech recognition system (ASR) to record progress notes in a mobile EHR. The objective of this article is to describe the pilot study carried out to evaluate the implementation of ASR to record progress notes in a mobile EHR application. As a result, the specialty that used ASR the most was Home Medicine. The lack of access to a computer at the time of care and the need to perform short and fast evolutions were the main reasons for users to use the system.

Assuntos

RESUMO

ABSTRACT Objective: To reflect on the contributions of representing nursing practice elements in the ISO 18.104:2023 standard. Method: This is a theoretical study with standard analysis. Categorical structures were described to represent nursing practice in terminological systems and contributions identified in the parts of the version were analyzed. Results: There is innovation in the inclusion of nurse sensitive outcomes, nursing action, nursing diagnosis explanation as an indicator of nursing service demand and complexity of care, representation of concepts through mental maps and suggestion of use of restriction models for nursing actions. It describes that the Nursing Process is constituted by nursing diagnosis, nursing action and nurse sensitive outcomes. Final considerations: Indicating a nursing diagnosis as an indicator will bring benefits for knowledge production and decision-making. Although care outcomes are not exclusive responses to nursing action, the modifiable attributes of a nursing diagnosis generate knowledge about clinical practice, nursing action effectiveness and subjects of care' health state. There is coherence in understanding the Nursing Process concept evolution.

RESUMO Objetivo: Refletir sobre as contribuições da representação dos elementos da prática de enfermagem na norma ISO 18.104:2023. Método: Estudo teórico com análise da norma. Foram descritas estruturas categoriais para representação da prática da enfermagem nos sistemas terminológicos e analisadas as contribuições identificadas nas partes da versão. Resultados: Há inovação na inclusão do resultado sensível à ação da enfermeira, explicitação do diagnóstico de enfermagem como indicador da demanda de serviços e complexidade de assistência, representação dos conceitos por mapas mentais e sugestão do uso de modelos de restrição para ações de enfermagem. Descreve que o Processo de Enfermagem é constituído pelo diagnóstico, ação e resultado sensível à ação da enfermeira. Considerações finais: A indicação do diagnóstico de enfermagem como um indicador trará benefícios para produção de conhecimento e tomada de decisão. Embora os resultados do cuidado não sejam respostas exclusivas a uma ação da enfermeira, os atributos modificáveis de um diagnóstico de enfermagem geram conhecimentos sobre a prática clínica, a eficácia das ações de enfermagem e o estado de saúde dos sujeitos de cuidado. Há coerência na compreensão da evolução do conceito de Processo de Enfermagem.

RESUMEN Objetivo: Reflexionar sobre los aportes de representar los elementos de la práctica de enfermería en la norma ISO 18.104:2023. Método: Estudio teórico con análisis de la norma. Se describieron estructuras categóricas para representar la práctica de enfermería en sistemas terminológicos y se analizaron las contribuciones identificadas en las partes de la versión. Resultados: Hay innovación en la inclusión del resultado sensible a la acción del enfermero, explicación del diagnóstico de enfermería como indicador de demanda de servicios y complejidad del cuidado, representación de conceptos a través de mapas mentales y sugerencia del uso de modelos de restricción para las acciones de enfermería. Describe que el Proceso de Enfermería está constituido por el diagnóstico, la acción y el resultado sensible a la acción del enfermero. Consideraciones finales: La indicación del diagnóstico de enfermería como indicador traerá beneficios para la producción de conocimiento y la toma de decisiones. Aunque los resultados del cuidado no son respuestas exclusivas a la acción del enfermero, los atributos modificables de un diagnóstico de enfermería generan conocimiento sobre la práctica clínica, la efectividad de las acciones de enfermería y el estado de salud de los sujetos del cuidado. Hay coherencia en la comprensión de la evolución del concepto de Proceso de Enfermería.

Assuntos

RESUMO

Abstract Objective: Postpartum hemorrhage (PPH) is the leading cause of maternal death globally. Therefore, prevention strategies have been created. The study aimed to evaluate the occurrence of PPH and its risk factors after implementing a risk stratification at admission in a teaching hospital. Methods: A retrospective cohort involving a database of SISMATER® electronic medical record. Classification in low, medium, or high risk for PPH was performed through data filled out by the obstetrician-assistant. PPH frequency was calculated, compared among these groups and associated with the risk factors. Results: The prevalence of PPH was 6.8%, 131 among 1,936 women. Sixty-eight (51.9%) of them occurred in the high-risk group, 30 (22.9%) in the medium-risk and 33 (25.2%) in the low-risk group. The adjusted-odds ratio (OR) for PPH were analyzed using a confidence interval (95% CI) and was significantly higher in who presented multiple pregnancy (OR 2.88, 95% CI 1.28 to 6.49), active bleeding on admission (OR 6.12, 95% CI 1.20 to 4.65), non-cephalic presentation (OR 2.36, 95% CI 1.20 to 4.65), retained placenta (OR 9.39, 95% CI 2.90 to 30.46) and placental abruption (OR 6.95, 95% CI 2.06 to 23.48). Vaginal delivery figured out as a protective factor (OR 0.58, 95% CI 0.34 to 0.98). Conclusion: Prediction of PPH is still a challenge since its unpredictable factor arrangements. The fact that the analysis did not demonstrate a relationship between risk category and frequency of PPH could be attributable to the efficacy of the strategy: Women classified as "high-risk" received adequate medical care, consequently.

Assuntos