BackgroundRegional networking between services that provide mental health care in Brazil’s decentralized public health system is challenging, partly due to the simultaneous existence of services managed by municipal and state authorities and a lack of efficient and transparent mechanisms for continuous and updated communication between them. Since 2011, the Ribeirao Preto Medical School and the XIII Regional Health Department of the Sao Paulo state, Brazil, have been developing and implementing a web-based information system to facilitate an integrated care throughout a public regional mental health care network.Case presentationAfter a profound on-site analysis, the structure of the network was identified and a web-based information system for psychiatric admissions and discharges was developed and implemented using a socio-technical approach. An information technology team liaised with mental health professionals, health-service managers, municipal and state health secretariats and judicial authorities. Primary care, specialized community services, general emergency and psychiatric wards services, that comprise the regional mental healthcare network, were identified and the system flow was delineated. The web-based system overcame the fragmentation of the healthcare system and addressed service specific needs, enabling: detailed patient information sharing; active coordination of the processes of psychiatric admissions and discharges; real-time monitoring; the patients’ status reports; the evaluation of the performance of each service and the whole network. During a 2-year period of operation, it registered 137 services, 480 health care professionals and 4271 patients, with a mean number of 2835 accesses per month. To date the system is successfully operating and further expanding.ConclusionWe have successfully developed and implemented an acceptable, useful and transparent web-based information system for a regional mental healthcare service network in a medium-income country with a decentralized public health system. Systematic collaboration between an information technology team and a wide range of stakeholders is essential for the system development and implementation.

O objetivo deste relato é apresentar, dentro da proposta do Programa Nacional de Reorientação da Formação Profissional em Saúde (Pró-Saúde), uma parte do projeto da Faculdade de Medicina de Ribeirão Preto (USP). Trata-se da estratégia de inserção das Tecnologias de Informação e Comunicação (TIC) no ensino de graduação extramuros da FMRP, que visa definir e implantar recursos tecnológicos de Aprendizado Eletrônico para apoiar atividades discentes e docentes, gestão da informação, educação continuada e segunda opinião formativa. A trajetória metodológica delineou tanto o processo de atendimento de parte das ações do eixo Cenário de Prática em Atenção Básica de saúde relativa ao processo de ampliação da rede de malha ótica, essencial para suporte às atividades de desenvolvimento do uso das TIC, quanto a abordagem qualitativa de um estudo exploratório sobre a utilização do Teleduc no primeiro ano do eixo de Atenção à Saúde da Comunidade (ASC) do curso de Medicina. Nesta investigação foram realizados dois grupos focais com aplicação de questionário estruturado a discentes e docentes.

The state of the art for monitoring hypertension relies on measuring blood pressure (BP) using uncomfortable cuff-based devices. Hence, for increased adherence in monitoring, a better way of measuring BP is needed. That could be achieved through comfortable wearables that contain photoplethysmography (PPG) sensors. There have been several studies showing the possibility of statistically estimating systolic and diastolic BP (SBP/DBP) from PPG signals. However, they are either based on measurements of healthy subjects or on patients on intensive care units (ICUs). Thus, there is a lack of studies with patients out of the normal range of BP and with daily life monitoring out of the ICUs. To address this, we created a dataset (HYPE) composed of data from hypertensive subjects that executed a stress test and had 24-hours monitoring. We then trained and compared machine learning (ML) models to predict BP. We evaluated handcrafted feature extraction approaches vs image representation ones and compared different ML algorithms for both. Moreover, in order to evaluate the models in a different scenario, we used an openly available set from a stress test with healthy subjects (EVAL). The best results for our HYPE dataset were in the stress test and had a mean absolute error (MAE) in mmHg of 8.79 (SD 3.17) for SBP and 6.37 (SD 2.62) for DBP; for our EVAL dataset it was 14.74 (SD 4.06) and 7.12 (SD 2.32) respectively. Although having tested a range of signal processing and ML techniques, we were not able to reproduce the small error ranges claimed in the literature. The mixed results suggest a need for more comparative studies with subjects out of the intensive care and across all ranges of blood pressure. Until then, the clinical relevance of PPG-based predictions in daily life should remain an open question.

Background Recently, the COMPASS trial demonstrated that dual therapy reduced cardiovascular outcomes compared with aspirin alone in patients with stable atherosclerotic disease. Methods and Results We sought to assess the proportion of patients eligible for the COMPASS trial and to compare the epidemiology and outcome of these patients with those without COMPASS inclusion or with any exclusion criteria in a contemporary, nationwide cohort of patients with stable coronary artery disease (CAD). Among the 4068 patients with detailed information allowing evaluation of eligibility, 1416 (34.8%) did not fulfill the inclusion criteria (COMPASS-Not-Included), 841 (20.7%) had exclusion criteria (COMPASS-Excluded) and the remaining 1811 (44.5%) were classified as COMPASS-Like. At 1 year, the incidence of major adverse cardiovascular event (MACE), a composite of cardiovascular death, myocardial infarction and stroke, was 0.9% in the COMPASS-Not-Included and 2.0% in the COMPASS-Like (p = 0.01), and 5.0% in the COMPASS-Excluded group (p < 0.0001 for all comparisons). Among the COMPASS-Like population, patients with multiple COMPASS enrichment criteria presented a significant increase in the risk of MACE (from 1.0% to 3.3% in those with 1 and ≥3 criteria, respectively; p = 0.012), and a modest absolute increase in major bleeding risk (from 0.2% to 0.4%, respectively; p = 0.46). Conclusions In a contemporary real-world cohort registry of stable CAD, most patients resulted as eligible for the COMPASS. These patients presented a considerable annual risk of MACE that consistently increases in the presence of multiple risk factors.

Objectives The development of clinical predictive models hinges upon the availability of comprehensive clinical data. Tapping into such resources requires considerable effort from clinicians, data scientists, and engineers. Specifically, these efforts are focused on data extraction and preprocessing steps required prior to modeling, including complex database queries. A handful of software libraries exist that can reduce this complexity by building upon data standards. However, a gap remains concerning electronic health records (EHRs) stored in star schema clinical data warehouses, an approach often adopted in practice. In this article, we introduce the FlexIBle EHR Retrieval (FIBER) tool: a Python library built on top of a star schema (i2b2) clinical data warehouse that enables flexible generation of modeling-ready cohorts as data frames. Materials and Methods FIBER was developed on top of a large-scale star schema EHR database which contains data from 8 million patients and over 120 million encounters. To illustrate FIBER’s capabilities, we present its application by building a heart surgery patient cohort with subsequent prediction of acute kidney injury (AKI) with various machine learning models. Results Using FIBER, we were able to build the heart surgery cohort (n = 12 061), identify the patients that developed AKI (n = 1005), and automatically extract relevant features (n = 774). Finally, we trained machine learning models that achieved area under the curve values of up to 0.77 for this exemplary use case. Conclusion FIBER is an open-source Python library developed for extracting information from star schema clinical data warehouses and reduces time-to-modeling, helping to streamline the clinical modeling process.

No abstract

Objective Hypertension has long been recognized as one of the most important predisposing factors for cardiovascular diseases and mortality. In recent years, machine learning methods have shown potential in diagnostic and predictive approaches in chronic diseases. Electronic health records (EHRs) have emerged as a reliable source of longitudinal data. The aim of this study is to predict the onset of hypertension using modern deep learning (DL) architectures, specifically long short-term memory (LSTM) networks, and longitudinal EHRs. Materials and Methods We compare this approach to the best performing models reported from previous works, particularly XGboost, applied to aggregated features. Our work is based on data from 233 895 adult patients from a large health system in the United States. We divided our population into 2 distinct longitudinal datasets based on the diagnosis date. To ensure generalization to unseen data, we trained our models on the first dataset (dataset A “train and validation”) using cross-validation, and then applied the models to a second dataset (dataset B “test”) to assess their performance. We also experimented with 2 different time-windows before the onset of hypertension and evaluated the impact on model performance. Results With the LSTM network, we were able to achieve an area under the receiver operating characteristic curve value of 0.98 in the “train and validation” dataset A and 0.94 in the “test” dataset B for a prediction time window of 1 year. Lipid disorders, type 2 diabetes, and renal disorders are found to be associated with incident hypertension. Conclusion These findings show that DL models based on temporal EHR data can improve the identification of patients at high risk of hypertension and corresponding driving factors. In the long term, this work may support identifying individuals who are at high risk for developing hypertension and facilitate earlier intervention to prevent the future development of hypertension.

No abstract