Article Preview
TopResearch Background And Motivations
Yee et al. (2020) discussed the implications of big data on healthcare and its future steps with uses for clinical decision-making, research and development, population health and surveillance, detecting fraud, prediction capabilities, Google Trends, and preventive measures. They referred to Chen et al. (2016), describing a cognitive computing tool developed by IBM. The tool, named Watson, has been applied to big data challenges in life sciences research by integrating and analyzing big data that includes medical literature, patents, genomics, and chemical and pharmacological data. Chen et al. (2016) specifically discussed the application of IBM Watson to explore big data for cancer kinases.
Healthcare applications that have used big data include those for cancer research, disease detection, and population health. Big data has changed how researchers understand diseases, providing access to patient information, trends, and patterns that were not accessible before. Companies that use big data in healthcare applications include:
- •
Cancer research carried out by Tempus in Chicago, Illinois (USA) and Flatiron Health in New York City (USA)
- •
Early disease detection by Pieces in Irving, Texas (USA) and Prognos in New York City (USA)
- •
Population health research conducted by Amitech in Creve Coeur, Missouri (USA), Linguamatics in Marlborough, Massachusetts, and Socially Determined in Washington, DC (USA). (Schroer, 2023)
Pramanik et al. (2022) provided a comprehensive overview of healthcare big data that extends the traditional 5 V’s to 10 V’s for healthcare big data: Volume, Velocity, Variety, Veracity, Validity, Viability, Volatility, Vulnerability, Visualization, and Value. Each of these are defined as below in Table 1 where the traditional 5 V’s are listed as the first five.