Malaria-VisAnalytics: a tool for visual exploratory analysis of Brazilian public malaria data.

BACKGROUND: Data integration and visualisation techniques have been widely used in scientific research to allow the exploitation of large volumes of data and support highly complex or long-lasting research questions. Integration allows data from different sources to be aggregated into a single database comprising variables of interest for different types of studies. Visualisation allows large and complex data sets to be manipulated and interpreted in a more intuitive way. METHODS: Integration and visualisation techniques were applied in a malaria surveillance ecosystem to build an integrated database comprising notifications, deaths, vector control and climate data. This database is accessed through Malaria-VisAnalytics, a visual mining platform for descriptive and predictive analysis supporting decision and policy-making by governmental and health agents. RESULTS: Experimental and validation results have proved that the visual exploration and interaction mechanisms allow effective surveillance for rapid action in suspected outbreaks, as well as support a set of different research questions over integrated malaria electronic health records. CONCLUSION: The integrated database and the visual mining platform (Malaria-VisAnalytics) allow different types of users to explore malaria-related data in a user-friendly interface. Summary data and key insights can be obtained through different techniques and dimensions. The case study on Manaus can serve as a reference for future replication in other municipalities. Finally, both the database and the visual mining platform can be extended with new data sources and functionalities to accommodate more complex scenarios (such as real-time data capture and analysis).

Nurturing care indicators for the Brazilian Early Childhood Friendly Municipal Index (IMAPI).

The Nurturing Care Framework (NCF) calls for establishing a global monitoring and accountability systems for early childhood development (ECD). Major gaps to build low-cost and large-scale ECD monitoring systems at the local level remain. In this manuscript, we describe the process of selecting nurturing care indicators at the municipal level from existing routine information systems to develop the Brazilian Early Childhood Friendly Index (IMAPI). Three methodological steps developed through a participatory decision-making process were followed. First, a literature review identified potential indicators to translate the NCF domains. Four technical panels composed of stakeholders from federal, state and municipal levels were consulted to identify data sources, their availability at the municipal level and the strengths and weakness of each potential indicator. Second, national and international ECD experts participated in two surveys to score, following a SMART approach, the expected performance of each nurturing care indicator. This information was used to develop analytical weights for each indicator. Third, informed by strengths and weaknesses pointed out in the previous steps, the IMAPI team reached consensus on 31 nurturing care indicators across the five NCF domains (Good health [n = 14], Adequate nutrition [4], Responsive caregiving [1], Opportunities for early learning [7] and Security and safety [4]). IMAPI represents the first attempt to select nurturing care indicators at the municipal level using data from existing routine information systems.

Sociodemographic inequities in nurturing care for early childhood development across Brazilian municipalities.

Providing an enabling nurturing care environment for early childhood development (ECD) that cuts across the five domains of the Nurturing Care Framework (i.e., good health, adequate nutrition, opportunities for early learning, security and safety and responsive caregiving) has become a global priority. Brazil is home to approximately 18.5 million children under 5 years of age, of which 13% are at risk of poor development due to socio-economic inequalities. We explored whether the Early Childhood Friendly Municipal Index (IMAPI) can detect inequities in nurturing care ECD environments across the 5570 Brazilian municipalities. We examined the validity of the IMAPI scores and conducted descriptive analyses for assessing sociodemographic inequities by nurturing care domains and between and within regions. The strong correlations between school achievement (positive) and socially vulnerable children (negative) confirmed the IMAPI as a multidimensional nurturing care indicator. Low IMAPI scores were more frequent in the North (72.7%) and Northeast (63.3%) regions and in small (47.7%) and medium (43.3%) size municipalities. Conversely, high IMAPI scores were more frequent in the more prosperous South (52.9%) and Southeast (41.2%) regions and in metropolitan areas (41.2%). The security and safety domain had the lowest mean differences (MDs) among Brazilian regions (MD = 5) and population size (MD = 3). Between-region analyses confirmed inequities between the North/Northeast and South/Southeast. The biggest within-region inequity gaps were found in the Northeast (from -22 to 15) and the North (-21 to 19). The IMAPI distinguished the nurturing care ECD environments across Brazilian municipalities and can inform equitable and intersectoral multilevel decision making.

Nurturing care indicators for the Brazilian Early Childhood Friendly Municipal Index (IMAPI)

The Nurturing Care Framework (NCF) calls for establishing a global monitoring and accountability systems for early childhood development (ECD). Major gaps to build low-cost and large-scale ECD monitoring systems at the local level remain. In this manuscript, we describe the process of selecting nurturing care indicators at the municipal level from existing routine information systems to develop the Brazilian Early Childhood Friendly Index (IMAPI). Three methodological steps developed through a participatory decision-making process were followed. First, a literature review identified potential indicators to translate the NCF domains. Four technical panels composed of stakeholders from federal, state and municipal levels were consulted to identify data sources, their availability at the municipal level and the strengths and weakness of each potential indicator. Second, national and international ECD experts participated in two surveys to score, following a SMART approach, the expected performance of each nurturing care indicator. This information was used to develop analytical weights for each indicator. Third, informed by strengths and weaknesses pointed out in the previous steps, the IMAPI team reached consensus on 31 nurturing care indicators across the five NCF domains (Good health [n = 14], Adequate nutrition [4], Responsive caregiving [1], Opportunities for early learning [7] and Security and safety [4]). IMAPI represents the first attempt to select nurturing care indicators at the municipal level using data from existing routine information systems.

On the Accuracy and Scalability of Probabilistic Data Linkage Over the Brazilian 114 Million Cohort.

Data linkage refers to the process of identifying and linking records that refer to the same entity across multiple heterogeneous data sources. This method has been widely utilized across scientific domains, including public health where records from clinical, administrative, and other surveillance databases are aggregated and used for research, decision making, and assessment of public policies. When a common set of unique identifiers does not exist across sources, probabilistic linkage approaches are used to link records using a combination of attributes. These methods require a careful choice of comparison attributes as well as similarity metrics and cutoff values to decide if a given pair of records matches or not and for assessing the accuracy of the results. In large, complex datasets, linking and assessing accuracy can be challenging due to the volume and complexity of the data, the absence of a gold standard, and the challenges associated with manually reviewing a very large number of record matches. In this paper, we present AtyImo, a hybrid probabilistic linkage tool optimized for high accuracy and scalability in massive data sets. We describe the implementation details around anonymization, blocking, deterministic and probabilistic linkage, and accuracy assessment. We present results from linking a large population-based cohort of 114 million individuals in Brazil to public health and administrative databases for research. In controlled and real scenarios, we observed high accuracy of results: 93%-97% true matches. In terms of scalability, we present AtyImo's ability to link the entire cohort in less than nine days using Spark and scaling up to 20 million records in less than 12s over heterogeneous (CPU+GPU) architectures.