Big Data Analytics in Healthcare: Comments by Students
objectives:- To describe the promise and potential of big analytics in healthcare.
Solution.
Big Data Analytics in Healthcare: Comments by Students
Comment by 1st Student
Introduction
Big data can be defined as a collection of complex and huge data elements that require the adoption of new software and hardware mechanisms to store, analyze and process the data. The dramatic growth of healthcare data in the U.S has led to the need for much more advanced data management tools and methods to store and analyze these large amounts of data. Digitization of these massive amounts of data contributes to the reduction in healthcare costs, improvement in the quality of healthcare and compliance with regulatory requirements. The biggest problem with the massive healthcare data is that it can be really overwhelming because of the different data types and the speed with which they need to be arranged.
Purpose of big data analytics in healthcare
The main argument behind big data analytics in healthcare is that it contributes towards saving lives, improvement in the quality of healthcare and lowering of health costs. Basically, the modern data management tools and software help in understanding trends and patterns within the data, as well as discovering associations. Such platforms are capable of processing megabytes and terabytes of data which simplifies data analysis. The big data analytics applications can, therefore, help stakeholders and healthcare providers make more informed decisions in regards to treatment and diagnoses of diseases. Effectively using big data can help in detecting diseases earlier which makes treatment more easy and effective. Big data analytics can also help in detecting fraud in health care more quickly.
Application of evidence from the article
The concept of big data analytics can be applied in different areas of health care management and medicine research. Medical imaging gives vital information on body organs which helps in detecting diseases like tumors, deformities in the spinal cord, and determining the presence and location of carotid artery stenosis. Advanced computer-aided data management tools and techniques are therefore needed as the size and dimensionality of the data increases. Medical images are prone to different types of noise/artifacts and missing data. Sophisticated storage mechanisms are therefore imperative to facilitate rapid data storage and retrieval of important patient information.
Developments in big data analytics can also assist in genome sequencing and effective analysis of genome-scale data. The human genome is made up of between 30000 and 35000 genes which make it even difficult to analyze traits of a population and timely delivery of health care. Development of high-throughput sequencing technology can, therefore, assist in the reliable and timely analysis of genome-scale big data thereby facilitating quick delivery of health care and recommendations for public health policies. They also help in reduction of the inherent costs involved which is crucial in health care management.
Relevance of the article
The healthcare industry is currently grappling with the technological issues in regards to the increasingly expanding volumes of massive data. This article, therefore, highlights the importance of modernizing the infrastructure in the healthcare industry. Big data analytics change the way data is managed, analyzed and leveraged in health care management. The analytics can help in the prediction of outbreaks of epidemics, reduction in treatment costs, and avoidance of preventable diseases thereby leading to overall improvement in the quality of lives. Big data analytics in healthcare helps the health care professionals and providers to make the best use of the massive amounts of patient data collected.
However, this article has not addressed
one of the main hurdles derailing application of big data analytics.
Integration of medical data from the different sources governed by different
states, administrative departments and hospitals is a major challenge that
should be considered besides implementing new data analysis techniques and
procedures. Necessary infrastructures should be developed where all big data
providers collaborate and share information with each other.
Comment by the 2nd Student
Critique of Big Data Analytics
Raghupathi & Raghupathi (2014) in their article Big data analytics in healthcare: promise and potential, have highlighted the evolution of data analytics in the health sector. The healthcare sector generates junks of data as a result of patient care, regulatory and compliance requirements and record keeping. The upsurge to digitize the health sector in line with the changing trends with the intent of improving healthcare provision require transfer of traditionally hard copy data to be digitized. The article illuminates the importance of digitizing the healthcare records such as being able to support a wide range of healthcare and medical functions, disease surveillance, clinical decision support, and the management of population health. The article further brings forth the challenges of managing the high volumes of data such as the diversity of health records as well as the speed at which they are expected to be analysed to be of use to the healthcare system.
The article highlights the advantages of big data analytics that are geared towards healthcare provision improvement. Big data synthesis and analysis offers healthcare providers in the system a platform in which insightful and thorough diagnoses as well as treatments in better outcomes, higher quality and at lower costs. This is possible through analysis of patient characteristics outcome of the provided care, and the costs to identify the most cost effective and clinically effective as well as offering analysis and tools. Such a process will influence the provider behavior, application of advanced analytics such as predictive modeling and segmentation to patient profiles. The application will proactively identify patients who might benefit from lifestyle changes or preventive care; disease profiling in broad scale for identification of predictive events and prevention initiative support; collection and publishing of data based on medical procedures. This is meant to assist patients to determine care protocols that are suited for better value through identification, prediction, and minimization of fraud by implementation of advanced analytical systems geared towards accuracy checking, fraud detection, consistency of claims, claim authorization, nearer to real time implementation, new revenue stream creation through synthesizing and aggregation of patient records; for instance data licensing to help pharmaceutical firms to identify patients for clinical trials inclusion. The whole process can also monitor drug adherence and treatment regimens to detect trends of individual and whole population wellness benefits.
Digitization as brought out in this article can be of importance to the healthcare system through the combination and effectiveness using healthcare organizations, and big data for care organizations that will realize significant benefits. Other benefits include early disease detection when they are treatable easily and effectively, individual and population health management through quick detection of healthcare fraud. The historical data available through big data management can offer developments and outcomes that are predictable or estimated based on the available patient data such as elective surgery patients, length of stay, non-beneficial surgery patients, patients prone to medical complications, sepsis risk patients, disease progression, hospital acquired illness, disease causal factors, disease stage advancement risks, and possibility of morbid conditions.
Predictive modeling will lower attrition which will in turn produce faster, leaner, target oriented drugs and services. This will improve research and development. Trial failures will be eliminated through algorithms and statistical tool that will improve patient recruitment and trial design to match treatment to specific patients and speeding marketing of new treatments.
The
article is beneficial to the healthcare sector since it provides a clear-cut
solution to the increasingly huge data due to the efficiency in the health
systems. Big data management will make healthcare tasks easier for physicians
and insurance firms. However, the article has only focused on the situation in
the United States of America health sector and thus making its recommendations
and applicability limited in other countries that have different health systems
from the one in the US.
Comment by the 3rd Student
Comments about Big Data Analytics in Healthcare
Data records in the healthcare system are essential for the provision of quality services. For instance personal health records lead to better healthcare management for the patient and healthcare givers through easy availability of important health information such as lab reports, immunization records, history of alcohol abuse or smoking, admittance and discharge report, prescriptions and screening due dates. Such information is essential but at times lucking due to manual or traditional storage that takes time to retrieve and use. Therefore the Raghupathi & Raghupathi (2014)’s article; big data analytics in healthcare: promise and potential offers practical solutions that can better the healthcare system through digitization of the health records. For instance the healthcare system in the United States alone has overstretched to over 150 exabytes and still growing with the advent of Obamacare. Therefore the article brings to the attention of the health sector the challenge that big data poses and the need to get a technological solution that can handle big data that is beyond the traditional hardware and software that manage small data in healthcare systems.
The evolution of the world to a global village has enhanced the movement of people around the globe. Healthcare givers therefore encounter people and health challenges that are not similar in their work locality. The big data management will take into consideration all healthcare systems across the globe so that healthcare givers in Riyadh can effectively attend to an individual fro United Kingdom or the United States who has fallen sick during Hajji by accessing any leads on the patient’s health records in the hoe country. The article is insightful to the health records improvement needs.
Through big data analytics will be beneficial to clinical operations through comparative effectiveness that can determine cost effective and clinically relevant way to diagnose and treat a patient. The analytics of big data will offer evidence based medicine as presented in the article. Combination and analysis of unstructured and structured varieties of EMRS data, operational and financial data, genomic data, clinical data, prediction of patients at risk or readmission will lead to provision of efficient care.
The article highlights the pre-adjudication of fraud analysis through rapidly analyzing of large claim request numbers to reduce cases of waste, fraud and abuse in the healthcare sector. The article further brings forth the possibility of remote monitoring through big data analytics; large volumes of data from in-home and in-hospital devices are captured and analyzed in real-time for safe monitoring and prediction of adverse events.
Patient profile analytics through big data analytics such as predictive modeling and modeling can be used to identify patients who are set to benefit from lifestyle changes and proactive care. For instance individuals at risk of developing diabetes would be assisted through preventive care. Pin-pointing patients at great risk of adverse outcomes or great health resource consumers will provide essential information needed to make informed decisions and effective management of health individually. The patient can identify treatment, processes and management that are cost effective, reduce readmissions through identification of the lifestyle factors that enhance the risky adverse events. Population health can be managed through detection of vulnerabilities during disease outbreak within patient populations. Clinical, operational and financial data combination can offer an analysis of resource utilization in real time and productively.
The article is of essential to the
health sector through its proposed big data analytics that will make the health
provision exercise easier and cost effective.
However, the authors have not taken into consideration the possibility
of the analytics information finding its way to the wrong hands or malicious
people through hacking which will affect the patient privacy policy.
References
Raghupathi, V., & Raghupathi, W. (2014). Big Data analytics in healthcare: promise and potential. Health Information Science and Systems, 2, 1-10.