Scientific and technological mapping of big data architectures in healthcare
Abstract
Context: The growth of data in healthcare brings both challenges and opportunities. The term Big Data refers to the handling of large volumes of data using advanced techniques and scalable infrastructure. Distributed processing and parallel computing accelerate data processing and necessitate a robust architecture. A Big Data architecture requires distributed systems, security, data storage, processing, analysis, and visualization. Crucially, in a Public Health context, such architectures must also incorporate strict data integrity and epidemiological validation to prevent the rapid processing of biased data.
Objective: This work aims to identify and characterize the approaches, concepts, and software tools used in constructing a general Big Data architecture for healthcare, exploring how these generalized frameworks can be adapted for specific unmet needs, such as health auditing environments, with a focus on performance, scalability, and structural data validity.
Method: A systematic mapping was conducted to identify primary studies in the literature and collect evidence to guide future research and technological adaptations.
Results: A total of 234 articles were analyzed, with Scopus and ACM Digital Library being the most relevant databases. A total of 22 articles were selected after applying inclusion and exclusion criteria and conducting a quality assessment. The most addressed layers were data storage, processing, ingestion, analysis, and visualization. However, a…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.