In today’s generation with the advancements in IoT, machine learning, cloud etc. the way the healthcare system is being functioned is also massively changing. There are advancements in several cutting-edge treatments and myriad of minimally invasive procedures that results in quicker healing and less pain. This paper discusses the latest technologies like big data analytics, cloud, machine learning and how they have transformed the health care delivery. It explains about the relationship between the technology and the costs involved. Additionally, it describes the future scope of technology in transforming health care.
Digitization of health care data is rapidly increasing these days with the adoption of Electronic Health Records (EHRs). Proper systematic analysis of these large data sets obtained, definitely has the key to improve the efficiency, quality of care and reduce costs of health care delivery (Gonzalez-Alonso et al. 284). As healthcare data is being generated from various heterogenous stakeholders like physicians with diverse specialties, pathologists, nurses, radiologists etc. and because of huge volumes, diversity and the complexity of data being generated, the health care organizations are responsible to adopt the advanced technologies like big data analytics along with the traditional tools and techniques like Data Warehouses, OLAP analysis etc. to efficiently analyze the data. As per the Harvard business review, the usage of big data analytics led to the improvised preventive care, patient satisfaction and personalized treatment (Olaronke and Oluwaseun 1152-1156).
If you need assistance with writing your nursing essay, our professional nursing essay writing service is here to help!Find out more
One of the key aspects of improvised health care delivery is the requirement for continuous monitoring of patients. Most of the patients require continuous monitoring of various biological parameters like heart rate, oxygen saturation level in blood, blood pressure and temperature which usually requires the presence of healthcare professional at regular intervals to monitor them. But this can be achieved using IoT -driven monitoring (Tripathi and Shakeel 153-154). This technology implements sensors to collect the detailed required data and then makes use of the gateways and the cloud to analyze and store the information. The analyzed information is then sent to further analysis and review wirelessly.
This paper discusses the introduction to the concept of big data analytics, how some of the machine learning techniques can be applied to the data in health care along with its benefits and challenges and how remote monitoring and controlling can be done using the sensors and the cloud.
Big data Analytics in health care:
The term big data in health care refers to the large volumes of electronic health data that is being generated by the health care industry. What is more important is not the volume of data but how this data is being analyzed. This data is being generated from various sources like machine generated data, biometric data, human generated data, transactional data, behavioral data, epidemiological data, publication data etc. Big data is characterized by 5 properties mainly which are volume, velocity, variability, variety and veracity. Volume refers to the huge amount of data being generated from various health care sources. Velocity refers to the rate or speed at which this data is being generated, stored, shared, visualized etc. Variability refers to the various ways and the formats the data can be stored. Variety refers to the diversification of data. Finally, veracity refers to the quality of the data that is being generated. Some of the advanced tools and techniques can be employed to analyze the big data are Google big query that uses its cloud infrastructure to store and query the large data sets within few seconds. Map Reduce which is framework for distributed processing of massive data in large clusters. Jagl is functional and declarative query language which facilitates parallel processing and makes use of Map reduce tasks in order to convert the high-level queries into lower level. Hadoop is an open source distributed processing framework which processes massive volumes of data across scalable clusters of computer servers. Cloud based services which includes software-as-a-service (SaaS), platform-as-a-service (PaaS) and infrastructure-as-a-service (IaaS) (Olaronke and Oluwaseun 1152-1156).
How big data Analytics helps to transform the health care (Kayyali et al. 1-4):
Prior to the introduction of big data analytics, physicians generally used their judgement to make the decisions for treatments, but now big data analytics provides with evidence-based medicine, by aggregating data from various sources. Hence this process involves the systematic review of clinical data and taking the decisions based on the patterns and trends of the available data.
With the ready access to the information, the healthcare delivery costs have been decreased as the information can be accessed from anywhere, anytime and any number of times. According to Priyanka and Kulennavar (5865-5868), “Analyzing data with innovative tools and techniques would result in the savings of $300 billion per year in the United States of America”. It is about 8% of the total national healthcare expenditures.
Benefits of using Big data analytics in health care ("Benefits of Using Big Data in Healthcare Industry”):
- With the early detection and diagnosis of various diseases, it reduced the mortality rate.
- It helps to provide more accurate and personalized care by minimizing the errors.
- It improved the efficiency of health care by continuous monitoring of the data as patients were able to proactively manage and visualize their data.
- It helps to reduce the medical risks by providing timely attention.
- It helps to simplify the operational tasks by tracking all the essential metrics.
Although there are several advantages of implementing big data analytics in healthcare, there are challenges too. One of the biggest challenges is to secure the data. Some other challenges are (Adibuzzaman et al.):
- As big data deals with massive amount of data, the classification of data really becomes difficult as it has all combinations of unstructured, semi structured and structured data.
- There can be storage and speed issues as the data is stored in the cloud, it is essential that there is required space.
- At times, there can be lack of information to support the decision making as all the data may not be uploaded to a single warehouse.
- There could be communication gap between the users and the data scientists.
Machine learning (ML) in health care (Nithya and Ilango 492-493):
“Machine learning is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead” (“Machine Learning”). There are many machine learning algorithms which can broadly be divided into supervised learners which are basically used for the construction of predictive models. Unsupervised learners which are used to build descriptive models. The typical flow of any machine learning project is to define the problem, prepare the data, evaluate the algorithms, improve the results and finally present them. ML techniques are very much suitable to detect and analyze the complex patterns, therefore these are employed in various diseases detection and diagnosis. It plays key role in many healthcare application areas. With the application of ML techniques to multiple data sources genetic data, personalized treatments for diseases from cancer to depression are being developed. Also, these techniques help to analyze the patient’s data and design personalized treatments. For example, patients with low risk of recurrence receive less aggressive treatments. As ML based techniques incorporate real time data, feedback from previous successful surgeries they aid in performing complex surgeries.
Predictions Using Machine Learning:
- Although pathologists are good at diagnosing cancer, they only have an accuracy of 60% with respect to predicting the development of cancer. Therefore, machine learning the next step to overcome this hurdle and to create a high accuracy pathology system. Using the risk prediction algorithms like Decision Tree (C4.5), Support Vector Machine (SVM), and Artificial Neural Network (ANN) breast cancer diagnosis and recurrence prediction were developed. Also, in the recent times, diseases like Asthma, Tuberculosis (TB) and Blood Pressure Monitoring were also predicted and diagnosed using the ML techniques.
- ML can also use to predict Hepatitis, which is caused due to the inflammation of liver cells. Although it’s usually caused by hepatitis virus, it can also be caused by some other infections and toxic substances. By making use of C4.5 algorithm, ID3 algorithm and CART algorithms this disease can be predicted.
- Diabetes predictions can also be made using the ML techniques. These techniques can also establish the probability of developing diabetes based on individuals eating, sleeping habits, physical activity, type of food etc.
- ML techniques in combination with neural networks are also used to predict cardiovascular diseases.
- It helps in medical image analysis to larger extent.
- It creates a path for new way of medical care, where the patients have accessibility directly to the specific department unlike the general physician as data gets analyzed from the pre stages of medical treatment itself.
- ML plays a key role in drug development, where these techniques can be applied to all stages of drug discovery that is from the design, validation, drug safety to managing clinical trials.
Challenges and problems involved in application of Machine learning techniques to the healthcare (Dou 176-179) (Sendak et al.):
- Huge costs are involved to test newly validated machine learning models. For Duke Health, it almost took $220,000 to develop, validate and integrate a single analytics tool which identifies the patients with high risk of dialysis (Sendak et al.).
- Most of the times during the analysis of data, experts in particular domain are not involved, which leads to not so efficient results. Hence, it’s very important to have the engagement of domain expertise people so that the clinicians and health information leaders wouldn’t struggle with the adoption of ML techniques (Sendak et al.).
- As ML is totally dependent on data, one of the most specific challenges to implement it, is to protect the data from security breaches.
- Although ML plays a key role in medical imaging diagnosis, it is still prone to objective conditions like noises, external conditions etc.
Cloud computing in health care
“Cloud computing is the delivery of computing services—including servers, storage, databases, networking, software, analytics, and intelligence—over the Internet (“the cloud”) to offer faster innovation, flexible resources, and economies of scale” (“What Is Cloud Computing? A Beginner's Guide: Microsoft Azure”).
Cloud computing along with IoT enables remote monitoring of the patient. The sensors are attached to the patient that transmits the data continuously to the controlling module which can be viewed on web pages. An email alert is sent to the doctor in case in case the sensed data are above threshold levels (Dhanaliya and Devani 1034-1036). Below diagram illustrates how data is sent from patient to the browser.
(Dhanaliya and Devani 1035)
Advantages of implementing cloud computing in healthcare
- It reduces the infrastructure cost as only subscription fees is paid to make use cloud, which makes easier than to maintain own internal systems which involves huge costs.
- It offers an excellent source for storage of information.
- cloud computing offers a very much scalable and flexible environment as it allows to address the changing requirements with minimal cost and time.
- Cloud computing also ensures reliability and security of the systems which is essential (“What Are the Advantages of Cloud Computing in Healthcare?”)
- It reduces the requirement of human power as monitoring can be done using sensors (Dhilawala).
- It helps to improve collaborative patient care, as storage of data on the cloud rather than personal device helps the doctors, patients, nurses etc. to vie the information from anywhere and anytime thus helps to create a collaborative relationship.
- It allows for faster access of the patient’s data, which is definitely one of the greatest advantages as the instant information can help to diagnose the patient quickly and effectively.
- Accessibility is improved as real time updates on patient information can be obtained from anywhere in the world.
- It helps to ensure privacy as, all of the Cloud services providers are required to comply with many privacy standards such as HIPAA (Health Insurance Portability and Accountability Act)
- Data stored in cloud creates a way for big data applications specifically.
- It helps to enhance patient’s safety using cloud based EMRs
- It helps in clinical researches and drug discoveries because of its high computing power.
- It creates a way for research using the medical data.
- It helps to reduce the burden of managing the data, as healthcare data is obtained from multiple sources. As cloud computing incorporates AI and machine learning techniques, managing the huge data really becomes easier.
- It helps to establish communication among the interconnected devices and effectively maintain the data. Also, clients who make use of same cloud, can easily transfer the data among them.
Although there are many advantages of using cloud computing in healthcare industry, there are also few associated with it. Some of them are (Hein):
- If proper training is not given on how to migrate completely to cloud and how to effectively use it, it may lead to information leakages which is the biggest threat and health data is very much sensitive and confidential.
- Although most of the times cloud is secured, but it not 100 percent as it can be hacked under some exceptional cases. “The U.S. Department of Health and Human Services’ Office for Civil Rights is currently investigating 416 cases involving security breaches of health information. Of those 416 cases, 47% were caused by hacking or an IT incident” (Hein).
- Expertise and regular monitoring are required to maintain compliance with HIPAA, HITECH and other regulations.
- Unexpected costs may occur because of maintenance issues, changing the infrastructure, upgrades etc. (“5 Risks Hospitals Face When Using the Public Cloud”).
- Also, down times are not exceptional in cloud platforms. But accessing data at the right time is much essential in healthcare industry downtime might be one of the biggest risks.
With the advancements in Robotics, AI and augmented reality there is large scope of research in evidence-based approaches which not only leads to reduced costs but also ensures value-based care.
Technology definitely has both positive and negative sides. This paper describes both the benefits and the risks associated with implementing some of the latest technologies. Staying mindful of the risks associated and using the right technology at the right time to serve the right need is the key. It definitely has the capability to transform and drive health care more than any force, enhance the standard of living and achieve improved quality of patient care if used effectively as it provides better solutions than the traditional methods.
- “5 Risks Hospitals Face When Using The Public Cloud.” ClearDATA Business White Paper, https://www.cleardata.com/wp-content/uploads/2016/08/SET-MKTG-WP-34-5-Risks-Hospitals-Face-When-Using-The-Public-Cloud-HIT.pdf.
- Adibuzzaman, Mohammad, et al. “Big Data in Healthcare - the Promises, Challenges and Opportunities from a Research Perspective: A Case Study with a Model Database.” AMIA ... Annual Symposium Proceedings. AMIA Symposium, American Medical Informatics Association, 16 Apr. 2018, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977694/.
- “Benefits of Using Big Data in Healthcare Industry.” Software Development Company, https://svitla.com/blog/benefits-of-using-big-data-in-healthcare-industry.
- Dhanaliya, Unnati, and Anupam Devani. “Implementation of E-Health Care System Using Web Services and Cloud Computing.” 2016 International Conference on Communication and Signal Processing (ICCSP), 2016, doi:10.1109/iccsp.2016.7754306.
- Dhilawala, Abbas. “9 Benefits of Cloud Computing in Healthcare.” Galen Data, 6 Mar. 2019, https://www.galendata.com/9-benefits-cloud-computing-healthcare/.
- Dou, Hanyue. “Applications of Machine Learning in The Field of Medical Care.” 2019 34rd Youth Academic Annual Conference of Chinese Association of Automation (YAC), 2019, doi:10.1109/yac.2019.8787685.
- Gonzalez-Alonso, P., et al. “Meeting Technology and Methodology into Health Big Data Analytics Scenarios.” 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), 2017, doi:10.1109/cbms.2017.71.
- Hein, Daniel. “8 Benefits and Risks of Cloud Computing in Healthcare.” Best Enterprise Cloud Strategy Tools, Vendors, Managed Service Providers, MSP and Solutions, Best Enterprise Cloud Strategy Tools, Vendors, Managed Service Providers, MSP and Solutions, 9 Apr. 2019, https://solutionsreview.com/cloud-platforms/8-benefits-and-risks-of-cloud-computing-in-healthcare/.
- Kayyali, Basel, et al. “The Big-Data Revolution in US Health Care: Accelerating Value and Innovation.” McKinsey & Company, Apr. 2013, https://www.mckinsey.com/industries/healthcare-systems-and-services/our-insights/the-big-data-revolution-in-us-health-care.
- “Machine Learning.” Wikipedia, Wikimedia Foundation, 29 Nov. 2019, https://en.wikipedia.org/wiki/Machine_learning.
- Nithya, B., and V. Ilango. “Predictive Analytics in Health Care Using Machine Learning Tools and Techniques.” 2017 International Conference on Intelligent Computing and Control Systems (ICICCS), 2017, doi:10.1109/iccons.2017.8250771.
- Olaronke, Iroju, and Ojerinde Oluwaseun. “Big Data in Healthcare: Prospects, Challenges and Resolutions.” 2016 Future Technologies Conference (FTC), 2016, doi:10.1109/ftc.2016.7821747.
- Priyanka, K, and Nagarathna Kulennavar. “a Survey on Big Data Analytics in Health Care.” International Journal of Computer Science and Information Technologies, vol. 5, no. 4, 2014, pp. 5865–5868., http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.436.3892&rep=rep1&type=pdf
- Sendak, Mark, et al. “Machine Learning in Health Care: A Critical Appraisal of Challenges and Opportunities.” EGEMS (Washington, DC), Ubiquity Press, 24 Jan. 2019, https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6354017/.
- Tripathi, Veena, and Faizan Shakeel. “Monitoring Health Care System Using Internet of Things - An Immaculate Pairing.” 2017 International Conference on Next Generation Computing and Information Systems (ICNGCIS), 2017, doi:10.1109/icngcis.2017.26.
- “What Are the Advantages of Cloud Computing in Healthcare?” Afia, 21 Mar. 2019, https://afiahealth.com/advantages-of-cloud-computing-in-healthcare/.
- “What Is Cloud Computing? A Beginner's Guide: Microsoft Azure.” What Is Cloud Computing? A Beginner's Guide | Microsoft Azure, https://azure.microsoft.com/en-us/overview/what-is-cloud-computing/.
Cite This Work
To export a reference to this article please select a referencing stye below:
Related ServicesView all
DMCA / Removal Request
If you are the original writer of this essay and no longer wish to have your work published on the UKDiss.com website then please: