There are several benefits as well as challenges associated with the use of Big Data Analytics in the e-Healthcare industry. Identify the challenges associated with each of the Catagories below:
- Data Gathering
- Storage and Integration
- Data Analysis
- Knowledge Discovery and Information Interpretation
Note:
Part 1: One page of an answer to the question
Part 2: 100-word replies to each of the files attached(can attach them only when part 1 is completed and attached).
Data Gathering
Big data is challenging to deal with due to the challenges in collection, representation, and transmission. Big data presents with complex structures and various dimensions that make it challenging to represent (Dash, et al., 2019). Also, transmitting large volumes of data to the storage infrastructures is inefficient because of high bandwidth consumptions and energy efficiency associated with big data, making the data gathering difficult.
Storage and Integration
The storage of large volumes of data poses a primary challenge in organizations, where the onsite server’s maintenance is difficult and expensive. The organization is required to implement cloud-based storage following the decreased cost and increased reliability of cloud storage. However, it may not be a flexible and workable approach in some organizations. Also, the integration of big data is challenging due to the variety of data; important information is obtained from various sources, including enterprise applications, social media, systems of email, and documents created by employees, among other relevant sources (Dash, et al., 2019).
Data Analysis
Increased data growth has negative implications when it comes to analyzing all the information. Considerably, the information in the digital universe in IT systems is doubling within two years, making it difficult to explain the data. For a successful big data analytics, the organizations must overcome all the other challenges associated with big data. However, dealing with such problems is costly to the organization in terms of time, finance, and commitments (Dash, et al., 2019). Believably, implementing the big data analytic in healthcare settings reduces costs by about 25% per year.
Knowledge Discovery and Information Interpretation
The big data in health care industries come with possession of massive sets of data originating from heterogeneous sources. Unfortunately, conventional analytics hardly manage the vast volumes of data. Therefore designing a high-performance platform for computing that can handle big data analytics is a challenge. The big data, as a result, remains unhelpful since no information is translated, not knowledge discovered.
Reference
Dash, S., Shakyawar, S. K., Sharma, M., & Kaushik, S. (2019). Big data in healthcare: management, analysis and future prospects. Journal of Big Data, 6(1), 54.
By definition, Big Data analytics is the use of advanced tools to collect, clean, store, and retrieve data to derive insights from large volumes of data that help to support healthcare professionals to make better and informed decisions. The ultimate aim here is to draw correlations and conclusions from data that were previously unmanageable and incomprehensible when using traditional tools like spreadsheets or file storage format. But, despite the enormous benefits of Big Data analytics and its associate platforms, the road towards drawing meaningful insights from Big Data Analytics is filled with some challenges. As a consequence, the complexity of Big Data requires a close look at the methods and approaches when it comes to collecting, storing, analyzing, visualizing, and presenting the data to stakeholders. In this regard, data gathering is one of the typical challenges that face health organizations. Usually, capturing quality data that is clean, consistent, accurate, and formatted correctly is an ever-ending process for health organizations. In some cases, clinical data are captured in various systems and often not well integrated (Adibuzzaman et al., 2017). Similarly, poor collection of data may lead to poor EHR usability, hinder workflows, and eventually contribute to quality issues throughout the life cycle of data. A typical example of constraints that associate with gathering Big Data include missing data attributes or incorrect data records, ambiguous, puzzling, or contradictory variables (Ayani et al., 2019).
The second challenge entails the storage and integration of biomedical and healthcare data. As the volume of Big Data continues to pile up at an exponential rate, the costs of storage of Electronic Health Record (EHR) data also continue to increase (McDonald, 2016). For example, an on-site server network or data center can be expensive to manage and maintain. This accumulation of data over time may cause the central data storage to serve as data silos, thus affecting the interoperability of data across the healthcare organization while preventing analytics tools from accessing and retrieving the primary database.
The third challenge is that the voluminous and highly heterogeneous nature of big data in healthcare may be rendered relatively less informative, especially when using a low manual intervention approach to process and analyzed the data. Therefore, common platforms such as Hadoop and Apache Spark, as well as advanced algorithms of Artificial Intelligence (AI), Machine learning is required to assist in the analysis of Big Data analysis in healthcare (Dash et al., 2019).
In regard to knowledge discovery in healthcare, however, Big Data analytics plays a major role in managing and finding potentially useful patterns of information. Data mining techniques such as classification can be used in knowledge discovery to uncover the hidden patterns and relationships that buried within the Big Data. However, the success of such mining technique sometimes faces many challenges (Baitharu & Pani, 2016). To name a few, developing a unified framework of data mining in healthcare require algorithms with high accuracy. In part, this is because knowledge discovery in healthcare deals with diverse and complex issues of life or death. Plus, knowledge in healthcare discipline keeps changing continuously, which means previous research knowledge experience must be taken into account when searching for new Knowledge discovery in databases (KDD).
References:
Adibuzzaman, M., DeLaurentis, P., Hill, J., & Benneyworth, B. D. (2017). Big data in healthcare–the promises, challenges and opportunities from a research perspective: A case study with a model database. In AMIA Annual Symposium Proceedings (Vol. 2017, p. 384). American Medical Informatics Association.
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977694/
Ayani, S., Moulaei, K., Khanehsari, S. D., Jahanbakhsh, M., & Sadeghi, F. (2019). A Systematic Review of big data potential to make synergies between sciences for achieving sustainable health: Challenges and solutions. Applied Medical Informatics., 41(2), 53-64.
https://ami.info.umfcluj.ro/index.php/AMI/article/view/642/638
McDonald, C.(2016). The motivation for big data
https://mapr.com/blog/reduce-costs-and-improve-health-care-with-big-data/
Dash, S., Shakyawar, S. K., Sharma, M., & Kaushik, S. (2019). Big data in healthcare: Management, analysis and future prospects. Journal of Big Data, 6(1), 54.
https://link.springer.com/article/10.1186/s40537-019-0217-0
Baitharu, T. R., & Pani, S. K. (2016). Analysis of data mining techniques for healthcare decision support system using liver disorder dataset. Procedia Computer Science, 85, 862-870.
https://www.sciencedirect.com/science/article/pii/S1877050916306263