Assignment: Data Analytics in Healthcare

Data Analytics in Healthcare
Name:
Institution:
Data Analytics in Healthcare
Part A: Konstanz Information Miner Tool (KNIME)
Using the KNIME Analytics Platform in analyzing Health Care Data
It is without a doubt that biomedical literature is a heap of medical information ranging from diseases, drugs and treatment information, health effects, epidemiology, and medical decisions, among other valuable information. Without proper management of such information, research has shown that many resources go typically to waste with the United States alone, losing close to $5 billion annually (Jain, 2020). With KNIME software, such waste minimizes as the KNIME analytic platform can mining knowledge from various biomedical literature information within a short time. An analytics expert can quickly get to know disease names intuitively when creating a biomedical data workflow in the KNIME Analytics Platform (KNIME, 2021). Additionally, the KNIME tool, through its server, enables researchers to explore further the co-occurring information from the documents examined in the KNIME Analytics Platform.
Benefits of KNIME in Comparison to other ETL tools
Other ETL tools such as Alteryx have more or more minor functionalities and also use KNIME. KNIME software has the edge over other commercial tools due to its effectiveness in data blending. Data blending in KNIME is made more accessible due to its join nodes, which are easy to understand as they can combine datasets even outside a familiar identifier. Being open-source, the KNIME tool has made it easy for different developers to develop various plugins to use in tandem with its already present functionalities. As a result, KNIME software has proven to be the best ETL tool as far as data analysis is concerned, especially when dealing with a large volume of data. Alteryx and other tools can only be efficient in data analysis when processing small quantities of information (KNIME 2021).
The 4 Vs. of Big Data Analytics in Healthcare
Volume
The 4 Vs. of Big Data Analytics are generally the significant characteristics of the higher volume of biomedical information posing a challenge in their management. One of the 4 Vs. is the volume. Work here refers to the ever piling high work of medical data that continue to rise daily (Raghupathi & Raghupathi, 2014). Such a piece of data includes medical records, population data, human genetics, and radiology images. Capturing and storing large volumes of data have fortunately been facilitated thanks to technological advancements such as cloud computing and virtualization (Raghupathi & Raghupathi, 2014. On the contrary, as much as cloud computing has managed to facilitate the capturing and storage of biomedical data, it has influenced more medical data within the server. Most data is now digitally captured.
Velocity
Like in a physics context...