NURS-6051N Module 3: Week 5: Discussion BIG DATA RISKS AND REWARDS

Big Data Risk and Rewards

Big data in healthcare describes the massive amounts of health information that is collected through the use of digital technologies. Big data not only offers promise in several sectors but has also changed how data is analyzed, managed, and leveraged across sectors, and healthcare is looking at big data to transform public health, clinical care, and personal care (Wang, Kung & Byrd 2018). However, as much as various benefits have been associated with the use of big data in healthcare, there are also certain risks that come with the application of big data in healthcare.

One potential benefit of using big data is a clinical system is the identification of patterns of care. According to Wang, Kung & Byrd (2018), big data analytics can be used to identify care patterns and discover associations from massive patient records to offer a wider view for evidence-based practice (EBP) in clinical area. For instance, in a hospital clinical system, big data can be used to discover patterns related to the rates of re-hospitalization. Consequently, there would be efforts to find appropriate measures to address the issues leading to re-hospitalization, which would benefit patients, improve patient outcomes, and impact reimbursement from insurance. Besides, big data can be used in the clinical system to provide insights into the causes and outcomes of illnesses.

One potential challenge of using big data is a clinical system relates to the security and confidentiality of patient information. Pastorino et al. (2019) note that the use of big data in healthcare carries new legal and ethical changes due to the personal or private nature of the information it contains. With the use of big data in clinical systems, chances are that personal autonomy and privacy can be compromised. There is also the risk to compromise the effects on public demand for fairness, trust, and transparency with the use of big data.

As such, there is need for effective strategies to mitigate these risk and challenges so as to realize maximum potential from the use of big data in clinical systems. One of such strategies is the formulation and implementation of appropriate and affirmative policies to safeguard individuals’ health data, in terms of security, privacy, and confidentiality. These policies must also ensure that technological advancements can take advantage of the open use of data for the health and well-being of individuals and communities. As suggested by ComplianceBridge & Procedures Team (2021), the policies should be realistic and accessible to everyone, and should be communicated accordingly to the medical staff to ensure their compliance with the policies.

References

ComplianceBridge & Procedures Team. (2021, June 21). How to Ensure Employees Comply with Policies and Procedures. Retrieved from https://compliancebridge.com/how-to-ensure-employees-comply-with-policies-and-procedures/Links to an external site.

Pastorino, R., De Vito, C., Migliara, G., Glocker, K., Binenbaum, I., Ricciardi, W., & Boccia, S. (2019). Benefits and challenges of Big Data in healthcare: an overview of the European initiatives. European journal of public health, 29(Supplement_3), 23-27. doi: 10.1093/eurpub/ckz168Links to an external site.

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, 126, 3-13. https://doi.org/10.1016/j.techfore.2015.12.019Links to an external site.

       Big Data refers to “a large complex data set that yields more information when it is analyzed as a fully integrated data set” (Thew, 2016). In other words, it is information that is so huge in volume and size, it is condensed in order to be efficiently used as it relates to healthcare. This helps us as healthcare providers be able to utilize the knowledge and skills, we already have in conjunction with these informatic programs to provide our patients with the best and safest quality of care we can. One benefit of using big data is providing advanced real time care. It is noted that this can provide a “clear audit trail of clinical data” documented with dates and times through examinations and evaluations of the patient by healthcare professionals.

Another example of this is deciding if a patient should go to the emergency room or urgent care for treatment. Through the use of mobile healthcare apps, an individual or family member is able to submit data to be analyzed to be able to guide the patient in the best way possible (Branch,2022). One challenge with using big data involves security and privacy of the data and information being collected. Nowadays we must all be careful and not fall for a lot of these phishing attacks where personal and medical history becomes compromised (Shanthagiri, 2014).

One strategy that I have experienced/observed that may decrease the worry in big data has been with the Kaiser  Permanente’s mobile app. In helping to prevent security attacks, they have encouraged members to utilize the two-way authentication step as well as the face recognition method of logging into the app. Although there is still and always a chance of personal information getting into the wrong hands, I believe it still adds an extra layer of protection for those of us who may worry about our information being misused.

 

References:

Branch, T. (2022, June 10). Top Advantages of Big Data in The Healthcare Industry. Dimensional Insight. https://www.dimins.com/blog/2022/06/13/big-data-healthcare/

Thew, J. (2016, April 19). Big data means big potential, challenges for nurse execs Links to an external site.Links to an external site.. Retrieved from https://www.healthleadersmedia.com/nursing/big-data-means-big-potential-challenges-nurse-execs

Vinay Shanthagiri. (2014). Big Data in Health Informatics Links to an external site.Links to an external site. [Video file]. Retrieved from https://www.youtube.com/watch?v=4W6zGmH_pOw

 

Today data is being collected at unfathomable rate. Yet just because we’re collecting this data doesn’t necessarily mean we’re gaining much from it. Medynska (2020), reports that modern technologies are no longer able to manage large volumes of information which can lead to lost revenues, poor performance, and wasted time. This is why it has become crucial for companies to figure out their focal point and go from there to help sort data. Although recently there have been issues revolving around data mining there have still been many positive results around data. The reason data is collected is to enhance our knowledge and benefit from it. Medynska (2020), stated that a benefit of data is allowing for well-informed decisions, with the help of data collecting instruments, clinicians can now quickly and effectively collect and evaluate results.

While big data has its benefits, currently it is running into several challenges. This is because we are in an era that is still learning what it means to collect big data and what to do with it. Dealing with its current challenges will allow for reform and changes to mitigate risks and additional challenges. A challenge that is being brought forth is simply not all healthcare systems are on the same page. Norwich University (2020) states that a large challenge to data is that in the U.S. many systems are digital but other small organizations are paper based. This makes it difficult to develop a complete picture of our healthcare system and scenarios.

A time consuming but necessary solution to the gaps from small organizations are to introduce electronic health records. Allowing for all health organizations to be digital will let the collection of data to assimilate and therefore be a more accurate pool of data to analyze. The National Coordinator for Health Information Technology (2019) reported “Electronic health records (EHRs) can improve public and population health outcomes. By efficiently collecting data in a form that can be shared across multiple health care organizations and leveraged for quality improvement and prevention activities” (para 1). Although the introduction of electronic health records will be timely and costly it is crucial that our healthcare system continues to move towards all systems being interlinked. This will allow for data analysts to see the full picture and use important, high-quality data.

References

Medynska, O. (2020, September 2). The importance of data collection in healthcare. KeyUA. https://keyua.org/blog/the-importance-of-data-collection-in-healthcare/Links to an external site.

Norwich University. (2020, May 27). Current big data challenges in hospitals and healthcare. https://online.norwich.edu/academic-programs/resources/data-challenges-in-healthcareLinks to an external site.

The National Coordinator for Health Information Technology. (2019, May 21). Improving public and population health outcomes. HealthIT.gov. https://www.healthit.gov/faq/how-can-electronic-health-records-improve-public-and-population-health-outcomes#:~:text=Electronic%20health%20records%20%28EHR%20s%29%20can%20improve%20public,s%20can%3A%20Improve%20public%20health%20reporting%20and%20surveillanceLinks to an external site..

                                                                                 Big Data Systems and Healthcare

Initial Post

 

The digital era has been a useful time not only for consumers but also for the healthcare industry, the use of EHRs has led to interoperability initiatives and a definite increase in use of technology in order to store healthcare data, the use of big data at times seems like a lot but it has been helpful in organizations to keep track of useful information for the outcome of patients and research on evidence-based practices. The use of data mining according to McGonigle and Mastrian has been used to visualized relationships in data and mechanize the discovery of predictive information in massive databases.  Massive databases in healthcare have been responsible in generating new knowledge by utilizing real time information in order to gather data in the treatment of patient with multiple co-morbidities.

 

Big data systems work for the healthcare industry, but also has implications that are not extremely favorable, for example they might be data breaches compromising the information of patients. On the other hand it is helpful in keeping a large amount of information that could be disseminated to improve a patient’s outcome, for example data use to track patients with congestive heart failure outcomes after discharge from the hospital, according to the case study noted in the Nursing Informatics and Foundation of knowledge book, patients were followed due to the high rate of readmission so the CNO and the nursing research team device a plan in order to prevent the readmission of this patient population.  They used EHRs for more than 15,000 patients with CHF and used 4 years of data to determine the situation, they discovered patterns and relationships in the data.  They started using this data and developed a plan of following these patients closely by calling them after discharge, and by going to their home for follow up visits, they found that doing this reduced these patients’ readmissions by 40%, thus also providing full reimbursement to the hospital. This is a prime example of how having the knowledge of this data is helpful, however how is it sustainable especially in the shortage of nursing staff, they also needs to be a way to ensure that research like these are continued and funded.

 

Data and having the knowledge to use it for better patient outcome is something that the National Institutes of Health started in 2013 by starting the Big Data to Knowledge (BD2K) initiative in order to support research and to develop new and innovative approaches to medical research, and to making databases FAIR which means findable, accessible, interoperable, and reusable. (McGonigle&Mastrian,2022).  Nursing informaticists have also made this easy for nurses to use these databases to make workflow easier and more user friendly in order to gain knowledge and to improve patient outcomes, which is the ultimate goal of using big data bases.

 

Reference:

McGonigle, D., & Mastrian, K. G. (2022). Nursing informatics and the foundation of knowledge (5th ed.). Jones & Bartlett Learning. Chapter 22. (p 545).

 

Murdoch and Detsky, 2013Links to an external site. T.B. Murdoch, A.S. Detsky The inevitable application of big data to health care J. Am. Med. Assoc., 309 (13) (2013), pp. 1351-135. Retrieved December 26, 2022, from jamanetwork.com

Wang, Y., Kung, L., & Byrd, T. A. (2018). Big data analytics: Understanding its capabilities and potential benefits for healthcare organizations Links to an external site.Links to an external site.. Technological Forecasting and Social Change, 126(1), 3–13.

 

#Main Post

Big Data Risks and Rewards

Benefits of Using Big Data as Part of Clinical System

Big data is a collection of data that is large and complex and continually growing, such that the traditional data management tools are unable to store and process it effectively (McGonigle & Mastrian, 2022). One potential benefit of using big data as part of a clinical system is the ability to identify patterns and trends that may not be apparent from smaller data sets. Hospital systems have data on millions of patients visits, including information on diagnoses, treatment, and other factors. By analyzing this data, it may be possible to identify trends in patient care that could inform clinical decision-making and improve patient outcomes (Glassman, 2017). For example, the data may reveal that a certain treatment is more effective for a particular condition, or that certain risk factors are associated with poor outcomes.

Challenges in Big Data

One potential challenge or risk of suing big data in the clinical system is the possibility of bias in the data. Data may be collected from a population that is not representative of the general population, or some groups may be underrepresented. This could lead to biased conclusions or recommendations based on the data which can worsen the current disparities in the healthcare system (Cahan et al., 2019).

Mitigation

To mitigate the risk of bias in the data, it’s important to ensure that data is collected in a representative and unbiased manner. This could involve the use of strategies such as random sampling and stratified sampling to ensure that different groups are adequately represented in the data. Also consider any potential biases in data, such as data being collected from a single hospital or healthcare system as it may be more biased than data collected from larger and more diverse groups of institutions. Another strategy to mitigate risk of bias is to use a combination of data collected from different sources and types of analysis. For example, combining data from electronic health records and from patient surveys or other sources may provide more accurate results. Using different methods of analysis can also be helpful in reducing the risk of bias.

References

Cahan, E. M., Hernandez-Boussard, T., Thadaney-Israni, S., & Rubin, D. L. (2019). Putting the data before the algorithm in big data addressing personalized healthcare. NPJ Digital Medicine, 2(1), 1-6.

Glassman, K. S. (2017). Using data in nursing practice Links to an external site.Links to an external site.. American Nurse Today, 12(11), 45–47. Retrieved from https://www.americannursetoday.com/wp-content/uploads/2017/11/ant11-Data-1030.pdfLinks to an external site.

McGonigle, D., & Mastrian, K. G. (2022). Nursing informatics and the foundation of knowledge (5th ed.). Jones & Bartlett Learning.

 

McGonigle and Mastrian (2022) describe big data as a large collection of information whose inter-relationship may only be apparent by using data mining techniques to discover the knowledge and trends that the information holds. This collection of information is further described by Wang et al (2018) as a “flood” of information. The term “Big Data” describes so much digital information that it is impossible to make heads or tails of it and to find meaningful knowledge within its sheer volume without the proper data mining tools, which is software that can sift through this enormous amount of data and find information that is meaningful to nurse leaders and managers.

The benefit, though, of working with big data is that there are likely many unknown relationships between the existing data a facility may have and better outcomes for that facility if the knowledge hidden in the data can be discovered. Walden University, LLC (2012) describes this process as a “continuum” where knowledge is extracted from information that is, in turn, extracted from data. The benefit of using this Big Data is that unused, it is an untapped storehouse of Data that can be transformed into workable information and then knowledge. For instance, Dao et al., (2008) describe the benefit of extracting information on emerging infections and infection trends from all the data a hospital may have on microbial infections. By attaching another program to their database to enable a data mining function, they can take the data about infections in their hospital database and create knowledge about what is going on and why, with regard to infections. This type of benefit is what Wang et al.,(2108) refer to as an “Operational Benefit” or the use of Big Data to help an organization or system improve its operating capabilities.

A common barrier to reaping the benefit of using big data is that many nurses need to gain the competency to data mine. Per Topaz and Pruinelli (2017) the use of Big data is important for the future of nursing, and the ability of nurses to extract knowledge from data is a key competency. Still, many nurses need training and knowledge to accomplish this.

And the strategy to overcome this challenge is better training to ensure that nurses do possess this competency. Wang et al. (2018) suggest that a facility provide training in data analytical skills and hire people who have these skills in the first place as a strategy to ensure nurses have these abilities.

 

References

Dao, T. K., Zabaneh, F., Holmes, J., Disrude, L., Price, M., & Gentry, L. (2008). A

practical data mining method to link hospital microbiology and an infection control

database. AJIC: American Journal of Infection Control, 36(3), S18–S20.

https://doi.org/10.1016/j.ajic.2007.05.010Links to an external site.

 

McGonigle, D., & Mastrian, K. G. (2022). Nursing informatics and the foundation of

      knowledge (5th ed.). Jones & Bartlett Learning.

 

TOPAZ, M., & PRUINELLI, L. (2017). Big Data and Nursing: Implications for the

Future…NI 2016, Switzerland. Studies in Health Technology & Informatics, 232,

165–171. https://doi.org/10.3233/978-1-61499-738-2-165

 

Walden University, LLC. (Executive Producer). (2012). Data information, knowledge and

     wisdom Continuum [Multimedia file]. Baltimore, MD: Author. Retrieved

from http://cdn-

media.waldenu.edu/2dett4d/Walden/NURS/6051/03/mm/continuum/index.html

 

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, 126(1), 3–13.

             Big data is a massive volume of datasets beyond the capacity of typical software that is utilized to capture, store, analyze and manage information assets. Its definition is not measured by its parameter but rather by its enormous capacity to focus on the insights that turn high volumes of data into meaningful information. Its potential usefulness significantly impacts the transformation of the healthcare system. It enables evidence-based decision-making that produces an efficient software analysis that is characterized by fourth dimensions called integrity, quality, authenticity, and trustworthiness of data (Pastorino et al., 2019). The medical industry generates a high volume of data, such as clinical records, which causes data streams to expand constantly. However, big data analytics has security and data integrity challenges. The proper software application allows healthcare providers to treat the disease in a personalized patient treatment management approach. The adoption of big data strategies will enable the implementation of real-time patient care interventions, with an enhanced clinical method of comparing prevention, diagnostic, and treatment options (Batko & Slezak, 2022).

 

Big data and analysis have numerous benefits that significantly impact the optimization of the functionality of the healthcare industry. The big data software system’s trends and patterns allow health service providers and stakeholders in the health sector to offer more accurate and insightful diagnoses, personalized treatment, preventative interventions, and better-quality treatment services while reducing healthcare costs. It enables doctors and healthcare administrations to make effective informed decisions about their patient’s individualized treatment and clinical services. For example, doctors easily detect early warning signs of cancer before it becomes terminal if the healthcare provider has a big data sample to draw based on the patient’s medical history and previous treatments. The physician’s response to this is to treat the disease in an early stage before it can progress to a serious illness that requires extensive treatment that is expected to be costly. Big data could bring enormous advantages in the coming years, including advanced and reliable clinical diagnostic tools, early detection of chronic diseases, prognosis, disease process, and how it spreads. In addition, the benefits expected from the application of big data include improving patient care, developing protocols to prevent re-hospitalization, optimizing clinical staffing ratio and hospital equipment, forecasting the need for hospital beds, operating rooms, treatments, and a developing drug supply chain (Batko & Slezak, 2022). There are strict laws governing the application of electronic health records; however, particularly in the U.S., data regulations are less forceful. According to Tulane University (2022), one of the vast concerns of big data is the ongoing cybersecurity breaches that most healthcare organizations need to prioritize protecting their patient’s confidential information. The fear of the inappropriate use of personal data, particularly linking through multiple sources, can be the primary source of hacking and ransomware episodes, in which healthcare data is subject to an array of vulnerabilities. Eisenhower’s organization follows strict regulations regarding HIPPA Security Rules in storing protected health information, integrity, auditing, transmission security, controls over access, and authentication protocols. Using up-date-virus software, encrypting sensitive data, and applying multi-factor authentication that helps safeguards translate data into common-sense security procedures. A recommendation for healthcare organizations to prevent security breaches is to frequently remind staff members about the critical nature of the data security protocols and to regulate and review staff who has access to high-value data assets to prevent malicious parties from causing damage (Bresnick, 2017).

 

HIPPA offers a list of safeguards for healthcare organizations to secure protected health information (PHI). Data practices include adopting authentication protocols, managing data access, and integrity controls, ensuring transmission security, and scheduling regular data security audits. In a recent report regarding the largest healthcare data breaches in 2022, more than 550 organizations impacted upwards of a total of 48 million individuals. Health IT Security has compiled a list of the ten most significant data breaches from third-party vendors with access to protected health information (PHI). Databases that were compromised contained patient names, addresses, birth dates, driver’s license numbers, health insurance information, medical record numbers, social security number, and medical information related to their treatment. Healthcare organizations affected revived and altered their policies, procedures, and network security of systems and services, placing restrictions on their data management and storage (Health IT Security, 2022). In addressing concerns with big data in healthcare, HIPPA Security Rules should be observed by institutions to prevent privacy security concerns. In its strict rule application, the assurance of safeguarding and encrypting sensitive data is feasible. Furthermore, the advantages of the HIPPA Security rule involve the implementation of multi-factor authentication, enabling firewalls, and up-to-date anti-virus software that most of the healthcare industry is trying to maintain to protect their patients’ information. Healthcare staff should coordinate with their employers to prioritize their patient’s data security by complying with software updates, security checks, and data access constraints. Also, organizations should constantly review and follow data protocols and regulate access to confidential data (Tulane University, 2022).

 

 

 

                                                                             References:

Batko, K., Slezak, A. (2022). The Use of Big Data Analytics in Healthcare.

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8733917/Links to an external site.

Bresnick, J. (2017). Top 10 Challenges of Big Data Analytics in Healthcare.

https://healthitanalytics.com/news/top-10-challenges-of-big-data-analytics-in-healthcareLinks to an external site.

Health IT Security. (2022). This Year’s Largest Healthcare Data Breaches.

https://healthitsecurity.com/features/this-years-largest-healthcare-data-breachesLinks to an external site.

Pastorino, R., De Vito, C., Glocker, K., Binenebaum, K., Ricciardi, W., Boccia, S. (2019). Benefits and Challenges of Big Date in Healthcare: An Overview of the European Initiatives.

https://pubmed.ncbi.nlm.nih.gov/31738444/Links to an external site.

Tulane University. (2022). Big Data in Health Care and Patient Outcomes.

https://publichealth.tulane.edu/blog/big-data-in-healthcare/Links to an external site.

 

 

 

 

Big Data is an enormous collection of data sets that cannot be handled, stored, or examined with conventional technologies. Health information is gathered from various sources, including patient portals, medical devices, pharmaceutical research, medical imaging, and electronic health records. Its structure and nature are extremely erratic. The clinical sector faces several difficulties, including preventing the spread of new diseases and ensuring maximum operating effectiveness. The inability to search for and analyze such data due to the lack of a clearly defined schema necessitates the use of a particular technology and procedure to turn the data into value (Batko&Ślęzak,2022). 

Potential benefits 

Big Data Analytics can give insights into clinical data and help with the diagnosis and management of diseases, the prevention of illnesses, and other decisions by enabling informed decision-making. Based on the patterns, clinicians can more precisely determine patients’ treatment needs. Some of these patterns may be found in data gathered over a long time and that shows medical history, diagnostic testing, or other aspects of health that would not otherwise be accessible. Big data contributes to increased operational effectiveness. It is used by healthcare organizations to investigate historical patient admittance rates and assess staff productivity as part of their business intelligence strategy. With the aid of predictive analytics, healthcare organizations may lower healthcare costs while improving treatment. By enhancing financial and administrative performance and lowering readmissions, big data also contributes to a decrease in medication errors. Realizing the data’s value through big data analytics can help healthcare organizations become more efficient. From a clinical perspective, the analysis of big data aims to enhance patient health and condition, enable long-term projections of their health status, and implement appropriate therapeutic methods. Data analysis in medicine enables customization of a patient’s treatment, or customized medicine. Being able to predict morbidity accurately is ideal from an epidemiological perspective since it allows for the early implementation of preventive measures (Batko&Ślęzak,2022). 

Potential challenges 

Security Concerns is a major concern with big data. Due to the enactment of the Health Insurance Portability and Accountability Act (HIPAA) legislation, there are significant privacy concerns around the use of big data analytics, particularly in healthcare. Open source data is made available for free, making it extremely susceptible. Furthermore, there are serious worries about confidentiality due to the sensitivity of health care data. Additionally, because this data is centralized, it is extremely vulnerable to attacks. These factors make it crucial to enabling privacy and security. Consequentialist worries arise from unfavorable effects on the individual whose privacy has been invaded. These can include real-world negative outcomes, such as an increase in long-term care insurance costs because of added information made accessible due to a privacy violation, employment discrimination, or learning that people in one’s social circle are aware of one’s HIV status. Having confidential medical information available and potentially being used by others can be upsetting, which can lead to emotional distress (Price &Cohen,2019). Another difficulty with big data is the problems with data standardization. Even while Electronic Health Record(EHR) inside the same organization share data, intra-organizational EHR platforms are at best disjointed. Data is kept in formats that are incompatible with some technology and apps. The transfer of that data encounters issues from the lack of data standardization. It makes data collection and cleaning more difficult (Kruse et al.,2016). 

Solutions 

At my place of employment, resistance to change or learning new things is typical. Every time innovative technology was used, I heard complaints from nurses and doctors. Most of the time, nurses and doctors were not fully involved in the introduction of recent technology, despite them being the ones using it. Successful big data analytics implementation requires the target healthcare organizations to promote an information sharing culture. This is crucial for minimizing any resistance from doctors and nurses to current information management systems. Lack of an information sharing culture will limit data gathering and delivery, which will have a negative influence on the effectiveness of big data analytical and predictive skills. Healthcare organizations should adopt rules that promote and compensate data providers for gathering data and satisfying standards for data delivery to address this issue. This should happen from the very beginning of the big data transition process. The accuracy of analysis and prediction, and data quality, will be improved. Employee development of the big data analytical abilities they will require is also vital, and mentoring, cross-functional team-based training, and self-study are helpful training options. As an alternative, healthcare firms might modify their hiring criteria to target candidates who already possess the required analytical abilities (Wang et al.,2022). Involving nursing leadership in and educating them about the use of technology in their organization is another strategy to overcome the difficulties of using big data in more effective ways. Nurse informaticists training and employment can be particularly beneficial as collaborative team members to support administrative and management activities in helping organizations handle the obstacles posed by modern technology. 

References 

Batko, K., & Ślęzak, A. (2022). The use of Big Data Analytics in healthcare. Journal of big data, 9(1), 3. https://doi.org/10.1186/s40537-021-00553-4Links to an external site. 

Kruse, C. S., Goswamy, R., Raval, Y., & Marawi, S. (2016). Challenges and Opportunities of Big Data in Health Care: A Systematic Review. JMIR medical informatics, 4(4), e38. https://doi.org/10.2196/medinform.5359Links to an external site. 

Price, W. N., 2nd, & Cohen, I. G. (2019). Privacy in the age of medical big data. Nature medicine, 25(1), 37–43. https://doi.org/10.1038/s41591-018-0272-7Links to an external site. 

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, 126, 3-13. https://doi.org/10.1016/j.techfore.2015.12.019Links to an external site. 

Main Post

One potential benefit to using big data in healthcare is first understanding what big data means for healthcare professionals. Duquesne University (2022) suggest that Health care professionals need to understand its application to tools like electronic health records (EHRs) and systems like the Internet of Things (IoT). This understanding can empower data-savvy nurses to build care delivery strategies with targeted purpose, resulting in better care today and tomorrow.

In healthcare, we are driven to changes that will improve overall patient care and outcome. Big data impacts the delivery of patient care and can assist in providing patient care more efficiently. Duquesne University (2022) adds that nursing professionals who can harness this data can use it to build a holistic care strategy for a patient, one that takes care of a patient’s needs with greater effectiveness.

Challenges

Overall, the challenges faced by electronic systems are surrounded by syncing schedules and data. Thew (2016) adds to this discussion; for example, the definition of a day may vary from system to system, and how a month is calculated in the finance system may differ from how it is calculated in the payroll system. The lack of data standardization can make it challenging for a CNE to assess how the organization or a particular unit is performing and make well-informed decisions about what to change. Having good data is key to making effective changes.

Information gathered from the electronic medical record stems from the use of the frontline staff, end-users, the business office, the coding department, and the healthcare team members that obtain data for statistical purposes. The compliance officer or data coordinator looks at statistical information for the organization. This includes, but is not limited to, cesarean section rates, outpatient visits, inpatient visits, emergency room visits, and re-admission rates. These statistics assist in the organization’s quality improvement but can create challenges for the person obtaining the information. While data collection is essential, not all yearly, monthly, or even weekly schedules are the same. For example, the budget committee is focused on a fiscal year format of July to June, while the data coordinator uses the January to December format for data collection. When these two departments intertwine, which they often do, the data coordinator must configure their data to reflect that of the fiscal year.

Benefits

The primary example of big data in healthcare is the development of an electronic medical record. An electronic medical record allows users to visualize what other users have entered in the patient’s chart at the click of a button. There is no longer an array of charts sitting around a nurse’s station or nurses trying to search for the chart so they can input diagnostic data results or documents. Using an electronic medical record in healthcare also provides unlimited opportunities for organizations to have direct patient monitoring devices that input data directly into the patient’s chart in real-time. Having these options has eliminated the risk of duplication in most cases. Glassman (2017) suggests that patient care devices (such as cardiac monitors, vital sign monitors, and IV infusion pumps) can be linked with the EHR. Many are essentially mini computers that store and send their discrete data to the EHR (p.46).

Experience with Analysis

Experience obtained as a nurse leader in the surgery department correlates with the data coordinator of the organization. Data collected in surgery is related to infection rates, cesarean section rates compared to vaginal deliveries, and the number of procedures completed from January to December. This data is analyzed and provided to the surgery department’s data coordinator, but the challenge at that point is how they have to interpret that data to match their needs.

Another example is when an organization does not have an informatics nurse but uses an electronic medical record with frequent updates and go-lives. This challenges frontline staff as other healthcare team members absorb that position, so the frontline staff has support. When a nursing staff member is pulled in many different directions, it is not easy to be efficient in completing the daily tasks associated with their primary position at that organization. On the other hand, frontline staff needs assistance and guidance during electronic medical record updates. With the support, the organization could provide a high level of care to their patients, so nurses are stepping up to fill that gap. Booth et. al. (2021) support this by saying that low progress in some areas has been due to a lack of leadership and investment that supports nurses to champion and lead digital health initiatives. Globally, uncertainty remains regarding the next steps the nursing profession should take to increase and optimize its use of digital technology.

References

Booth, R. G., Strudwick, G., McBride, S., O’Connor, S., & Solano López, A. L. (2021). How the nursing profession should adapt for a digital future. BMJ. https://doi.org/10.1136/bmj.n1190

Duquesne University. (2022, June 2). What is Big Data in healthcare? Duquesne University School of Nursing. Retrieved December 24, 2022, from https://onlinenursing.duq.edu/blog/what-is-big-data-in-healthcare/

Glassman, K. S. (2017). Using data in nursing practice. American Nurse Today, 12(11), 45–47. https://doi.org/https://www.myamericannurse.com/wp-content/uploads/2017/11/ant11-Data-1030.pdf

Main Post

Data, information, knowledge, and wisdom are all a part of nursing informatics and healthcare technology (Walden University, 2018). This continuum helps the largest healthcare profession, nurses, show how they use data to interpret it into information to build knowledge and gain insight or wisdom from all the facts being collected, assessed, and evaluated. (McGonigle & Mastrian, 2022). Big data is exactly how it sounds, a field that uses part of this continuum to collect data and interpret it into information from exceptionally large datasets, databases, and data-processing software (McGonigle & Mastrian, 2022).

This week’s discussion goes perfectly with what I was researching last week for our assignment. Big data can be used to benefit healthcare organizations by improving patient outcomes by using the technology at their disposable. As nurses, we need to know what kind of questions to ask, what data or information we are looking for. I was wondering if improving care coordination between an organizations ED and outpatient behavioral health clinics within the same system could benefit patients and the organization. As I mentioned we have the technology, it is just putting it into action. A care transition alert automated from a patient’s electronic health record could lead to improved patient outreach after discharge (Hewner et al, 2018). Knowing that a high-risk suicidal patient is at least 200% times as likely to attempt to commit suicide within the first week following discharge should be enough knowledge to improve care coordination efforts (Hewner et al, 2018). Improving patient connection, and care coordination is critical for this high risk group.

However, this could lead to a potential risk as well. Behavioral health patients’ records are typically “locked” and in the electronic health record we utilize at this organization you have to “break the glass” to see their psych notes. The reason for this is behavioral health patients are an extremely vulnerable population and alerting their mental health providers or a potential mental health provider about their recent stay in the hospital may not be what the patient wants. In my proposal for this to be implemented this alert would only activate with the patient’s consent. Educating the patient on behavioral health providers and the process of following up with them to help improve their outcomes is one strategy that could be implemented to utilize the big data at our fingertips.

References:

Hewner, S., Sullivan, S., & Yu, G. (2018). Reducing Emergency Room Visits and In-Hospitalization by Implementing Best Practice for Transitional Care Using Innovative Technology and Big Data. Worldviews on Evidence-Based Nursing. 15 (3), 170-177. https://doi.org/10.1111/wvn.12286Links to an external site.

McGonigle, D., & Mastrian, K. G. (2022). Nursing informatics and the foundation of knowledge (5th ed.). Jones & Bartlett Learning

Walden University, LLC. (Executive Producer). (2012). Data, information, knowledge and wisdom continuum Links to an external site.Links to an external site. [Multimedia file]. Baltimore, MD: