An empirical comparison of the performances of single structure columnar in-memory and disk-resident data storage techniques using healthcare big data

Abstract

Abstract Healthcare data in images, texts and other unstructured formats have continued to grow exponentially while generating storage concerns. Even though there are other complexities, volume complexity is a major challenge for Disk-Resident technique in storage optimization. Hence, this research aimed to empirically compare the efficiency of Disk-Resident and In-Memory single structure database technique (as opposed to multiple structure In-Memory database), using descriptive and inferential big data analytical approaches. The essence was to discover a more cost-effective storage option for healthcare big data. Data from Nigerian Health Insurance Scheme (NHIS) alongside sample patients’ history from Made-in-Nigeria Primary Healthcare Information System (MINPHIS) which included patients’ investigation, patients’ bio-data and patients’ diagnoses were the primary data for this research. An implementation of both Disk-Resident and single structure In-Memory resident data storage was carried out on these big data sources. After storage, each quantity of data items stored for different data items in Disk-Resident was then compared with that of single structure In-Memory resident system using size of items as comparison criteria and different analyses made. The results obtained showed that single structure In-Memory technique conserved up to 90.57% of memory spaces with respect to the traditional (common) Disk-Resident technique for text data items. This shows that with this In-Memory technique, an improved performance in terms of storage was obtained.

Keywords

• Healthcare big data
• Disk-resident database
• Columnar in-memory-resident database
• Big data analytics
• Descriptive analysis
• Big data volume complexity