Course: Data Science & Big Data Analytics As outlined within this weeks topic, there are several benefits as well as challenges associated with the use of Big Data Analytics in the e-Healthcare in
Substantive replies to the below posts:
Post 1:
8 hours ago
Ritesh kumar
Week 3 Discussion
COLLAPSE
Top of Form
Benefits and Challenges of Data Analysis
Big data is becoming a vital raw material for the healthcare sector, helping the machine learning and AI algorithms as well as the data scientist to use such vital information to enhance different services to different fields of the healthcare industry (Wang et al., 2018). The advantages of data analysis within healthcare aren't known to numerous individuals who are working in the sector.
Advantages of Data Analysis
Enhance operational efficiency – from the healthcare provider's viewpoint, data aids in understanding past discharge and admission rates of patients aiding to analyze the productivity and efficiency of the workers when handling the patients (Basco, & Senthilkumar, 2017). With the help of data analyses, organizations can reduce operational costs and offer quality care to the patients. Moreover, data analysis aids in enhancing accuracy within the administrative and financial performance.
Advanced patient treatment and care – data analysis provide vital insights to the age groups for patients who are vulnerable to ailments, thus allowing them to take preventative measures.
Challenges of Data Analysis
Incomplete data - missing values or even lack of important parts or some sections of data restricts its usability.
Inaccurate data – data collected from surveys are not always collected since some people may provide some false answers. Analyzing such data may result in inaccurate results (Wang et al., 2018).
Data gathered from different sources could different in format and quality – the data gathered from various sources like emails, organization websites, surveys, or EHR (electronic-health-records) will have diverse structures and attributes. Data from different sources might not be compatible with data fields. This data needs a lot of preprocessing before it is ready for analysis.
References
Basco, J. A., & Senthilkumar, N. C. (2017). Real-time analysis of healthcare using big data analytics. In IOP Conference Series: Materials Science and Engineering. IOP Publishing.
Wang, Y., Kung, L., & Byrd, T. A. (2018). Big data analytics: Understanding its capabilities and potential benefits for healthcare organizations. Technological Forecasting and Social Change.
Bottom of Form
Post 2:
3 days ago
Vikas
Week 3 Discussion
COLLAPSE
Top of Form
Data Gathering
There are different medical care data gathering strategies, from surveys and observations to examination reports. Data gathering in medical care permits health systems to make all-encompassing perspectives on patients, customize therapies, advance therapy strategies, improve correspondence among specialists and patients, and upgrade health results (Zink, 2014).
An individual electronic health record (EHR) is a framework that gathers information about the patient's health from various sources. An EHR incorporates test results, clinical observations, analyze, current medical issues, drugs taken by the patient, the systems he/she went through, and so on
The principal advantages of an EHR are security and the thoroughness of patient data.
Challenges
Most medical services suppliers gather information utilizing an assortment of structures, for example, quiet admission structures, assent structures, therapy assessment and health evaluation structures among others. When this data is gathered, it regularly passes through a cycle of manual data section so the information can be accessible in the backend customer relationship management (CRM), electronic health record systems and shared between suppliers.
In any case, this manual cycle leaves a ton of space for mistakes, for example, grammatical errors, incorrect sections, or some unacceptable structures being documented in a patient's records. Likewise, regularly, paper structures don't take into account persistent data to be accessible to all parental figures inside 24-hours, particularly data gathered from outside sources. This may prompt an incoherent consideration climate for the patient.
Data gathering and accumulation networks are similarly divided, making the extraction and combination of information a genuine test. According to Bareinboim (2011), suppliers, payers, general health subject matter experts, managers, interpersonal organization networks and patients all gather information, however there is no push to bind together the data.
References:
Bareinboim, E. (2011). Transportability of causal and statistical relations: A formal approach. In Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference; IEEE, pp. 540–547.
Zink, R. (2014). Using informatics to improve medical device safety and systems thinking. Biomedical Instrumentation Technology, 48(s2):38–43.
Bottom of Form
