Search

The growing challenges of healthcare systems pose a unique opportunity to leverage evidence-based digital health interventions. The WHO's SMART (Standards-based, Machine-readable, Adaptive, Requirements-based, and Testable) guidelines represent a significant advancement in this domain. This paper aims to summarize SMART guidelines authoring and implementation process, drawing on a comprehensive literature analysis. Our findings highlight critical success factors for national implementation, including stakeholder engagement, customization to local contexts, and leveraging international standards and digital technologies. We conclude with recommendations for countries aiming to implement WHO SMART guidelines, underscoring the need for a multi-disciplinary approach and the potential challenges to be navigated.

This is an exploratory study on different variables known to be associated with epidemiological outbreaks of lower respiratory tract infections in children under 2 years raised to identify patterns and potential predictors for making strategic decisions in terms of strengthening health teams in periods of greatest demand.

Background: documentation of aspirin consumption is usually not complete and clear, probably because it's a cheap drug that can be easily acquired., Objective: To evaluate the quality of the record of aspirin consumption documented in the electronic medical records (EMRs) of a Private University Hospital of Argentina., Design: Qualitative and quantitative descriptive exploratory study., Results: principal findings were that 86 % of the notes mentioned aspirin as a chronic prescription. 12% mentioned its temporary suspension. Numerous EMRs mentioned the use of an "antiplatelet" drug without specifying which, and didn't specify abbreviations, consumed dose or when to start or stop aspirin., Conclusions: overall quality of aspirin related information registration in EMRs was poor. This is concerning since it's a frequently prescribed drug, not exempt from adverse events.

The implementation of an Electronic Medical Record (EMR) in the public healthcare system of Buenos Aires City began in June 2016. AGISE is a government department that assists in health decision-making processes by providing timely and quality data. In this study we designed a professional development program to improve organizational capacities for health analytics.

Through the development of a dashboard with participative methodology we present a centralized strategy to analyze and visualize EMRs data for the management of 15 public hospitals from Buenos Aires City. This approach could constitute an efficient option for public health systems from developing countries.

Despite recommendations for the routine HIV testing of all sexually active individuals, a significant percentage of HIV-positive adults are unaware of their HIV status. Therefore, a number of strategies have been implemented to expand HIV testing, which in turn makes it necessary to develop tools for identifying patients with unknown HIV status. This study presents the results of an external validation of an electronic phenotyping algorithm for identifying HIV status and its application on a retrospective cohort in order to explore temporal trends of HIV knowledge status and associated factors.

By the implementation of the EMR in the Primary Care Centers of the City of Buenos Aires, it has been claimed that there is a need to obtain systematic and accurate information about the assessment that patients have about such incorporation. A qualitative research has been carried out in order to answer this query.

The influence of social relationships on mortality is comparable with that of standard clinical factors. In order to extract this information via supervised NLP algorithms, clinical notes have to be annotated manually. At present we did not find any systematic annotation standards to extract social support. In this work, we developed a systematic text annotation standard to detect social support in couples from electronic medical records.

Depression is frequently underdiagnosed or the diagnosis occurs in late stages, mainly because it usually presents as a paucisymptmatic diseorder. Electronic health records (EHRs) are a very useful tool to capture the longitudinal medical history of the patient which may help in diagnosing these patients earlier. We aimed to understand how these patients' consultation patterns are represented in the EHR up until depression diagnosis.

This paper describes how an Electronic Health Records (EHR) allowed for the implementation of a strategy to reduce maternal and child morbidity and mortality in outpatient settings of hospitals in the public healthcare system of Buenos Aires City.

Physical activity has been associated with many positive health outcomes. In this study we explored clinical notes to better understand how physicians record information on this topic.

Determining the cause of death of hospitalized patients with cardiovascular disease is of the utmost importance. This is usually recorded in free text form. In this study we aimed to develop a series of supervised natural language processing algorithms to extract cardiovascular causes of hospitalization and final causes of death.

On October 2018, Buenos Aires hosted the Youth Olympic Games. The organization asked the Health Information System Office to provide the health stations and clinics with an Electronic Health Record (EHR) and bring support during the duration of the games. Four hundred and fifty healthcare professionals from different disciplines were trained in the use of the EHR.

The continuity of care is the relationship between a physician and a patient that extends throughout different episodes of illness. This care includes that in some opportunities the patient must consult a medical specialist. In this qualitative study, we set out to explore and describe the different requests for referral authorization to a specialist by patients affiliated with private health insurance, in order to understand the different patterns of interaction between general practitioners (GP) and their patients. The conversation analysis let us identify categories (structural and functional) after a critical reading of messages between GPs and their patients through an Electronic Health Records (EHR) messaging system. This work allowed us to know more in depth the process of continuity of care. In most cases, the doctor answered affirmatively to the request for a new referral to a specialist.

The availability of statistical information is usually associated with 'better decision making', fundamentally within the paradigm of evidence-based decisions. Thus, it is interesting to understand the demands and expectations, interpretations and effective use of statistical information by decision-makers at the primary health care level, considering the implications of the recently implemented Information System in Public Health (Buenos Aires, Argentina).

During the implementation of an electronic health record (EHR) system in the public system of the city of Buenos Aires, Argentina, different patient indexing strategies were devised and implemented. We sought to assess the association between these strategies and effective indexing (proportion of patients who are indexed and have a consultation registered in the EHR). Strategies were grouped into three modalities (High, Intermediate, and Low intensity). We estimated hazard ratios (HR) comparing the High and Low intensity to the Intermediate strategies. The crude analyses showed a significant difference between the curves (p < 0.0001). In the multivariate analysis, the HRs of High and Low intensity interventions showed on average, values above 1 from 0 to 90 days compared to the Intermediate intensity strategy (High: 2.08 (1.65, 2.52); Low: 2.59 (2.29, 2.9)). From that point on, the HRs of both strategies were not different from 1.

Precision medicine requires extremely large samples. Electronic health records (EHR) are thought to be a cost-effective source of data for that purpose. Phenotyping algorithms help reduce classification errors, making EHR a more reliable source of information for research. Four algorithm development strategies for classifying patients according to their diabetes status (diabetics; non-diabetics; inconclusive) were tested (one codes-only algorithm; one boolean algorithm, four statistical learning algorithms and six stacked generalization meta-learners). The best performing algorithms within each strategy were tested on the validation set. The stacked generalization algorithm yielded the highest Kappa coefficient value in the validation set (0.95 95% CI 0.91, 0.98). The implementation of these algorithms allows for the exploitation of data from thousands of patients accurately, greatly reducing the costs of constructing retrospective cohorts for research.