Question

What is the challenge of transforming medical knowledge into usable data?

Think of a healthcare situation you’ve worked in. Or, only if you’r e comfortable doing so and have no professional experience to share, discuss one you have or a family member has been in. Please do this without naming anyone and being as anonymous as possible. Very briefly discuss what this experience and what it has taught you about sources of information. Explain the distinct sources of the information involved (pages 11-12 of Taylor) and how some part of it might fit into the each of the stages of the “virtuous circle of heath knowledge management.”

Answer 1

Data Analytics is the process of examining raw data, using analytical and logical reasoning to draw conclusions about the information they contain. Data analytics can be used on all sorts of data both structured and unstructured, for example on numbers, texts and images. It can be used to handle vast amounts of data as well as data from a number of different sources that could be very time-consuming or even impossible for human beings to analyse.

Data Analytics covers the collection and analysis of structured and unstructured data from a variety of different sources. The fields of application for data analytics in healthcare are many, covering areas within diagnostics, prevention and treatment. This makes a good starting point for large scale data analytics. There are, however, ethical, technical and legal challenges related to using and sharing data in healthcare. Companies should develop data analytics solutions and services in strong collaboration with users and other experts, and they should build an architecture that supports transparency, a high degree of security and interoperability.

Big data in healthcare is important as it can be used in the prediction of outcome of diseases prevention of co-morbidities, mortality and saving the cost of medical treatment. In many countries, big data has becoming an important database where information generated could be used for treatment and management of diseases. Massive quantities of health care data accumulating from patients and populations and the advanced analytics that can give it meaning, hold the prospect of becoming an engine for the knowledge generation that is necessary to address the extensive unmet information needs of patients, clinicians, administrators, researchers, and health policy makers. The integration of new approaches will require new thinking on the part of medical authorities regarding the ways in which this type of health and health care research can best contribute to the productivity of the research enterprise.

Analysis of healthcare data has been used to improve care delivery and to prevent hospitalisation. Data analytics holds the potential to take previous advancements to a whole new level. We have seen the first glimpses of it when it comes to image recognition and decision support but we are just starting to scratch the surface. We are starting to understand on the one hand the future potential within the field of advanced predictive measures, personalised medicine and behavioural pattern analysis, and on the other hand the negative consequences such as automated inaccurate decisions carried out based on data analytics, which forces a potential distrust and public resistance towards adopting the technology.

The ‘precision medicine (systems medicine)’ concept promises to achieve a shift to future healthcare systems with a more proactive and predictive approach to medicine, where the emphasis is on disease prevention rather than the treatment of symptoms. The individualization of treatment for each patient will be at the center of this approach, with all of a patient’s medical data being computationally integrated and accessible. Precision medicine is being rapidly embraced by biomedical researchers, pioneering clinicians and scientific funding programmes. Precision medicine promises to revolutionize patient care and treatment decisions. However, the participants in precision medicine are faced with a considerable central challenge. Greater volumes of data from a wider variety of sources are being generated and analysed than ever before; yet, this heterogeneous information must be integrated and incorporated into personalized predictive models, the output of which must be intelligible to non-computationally trained clinicians. Drawing primarily from the field of ‘oncology’, this article will introduce key concepts and challenges of precision medicine and some of the approaches currently being implemented to overcome these challenges.

“Big data in healthcare” refers to the abundant health data amassed from numerous sources including electronic health records (EHRs), medical imaging, genomic sequencing, payor records, pharmaceutical research, wearables, and medical devices, to name a few. Three characteristics distinguish it from traditional electronic medical and human health data used for decision-making: It is available in extraordinarily high volume; it moves at high velocity and spans the health industry’s massive digital universe; and, because it derives from many sources, it is highly variable in structure and nature. This is known as the 3Vs of Big Data.

The Usefulness and Challenges of Big Data in Healthcare
Big data in health informatics can be used to predict outcome of diseases and epidemics, improve treatment and quality of life, and prevent premature deaths and disease development. Big data also provide information about diseases and warning signs for treatment to be administered. This will help not only to prevent co-morbidities and mortality but also assists government to save the cost of medical treatment. It is very useful not only in clinical medicine for diagnosis/detection but also in epidemiological research as the big data will provide huge amount of data. The government, non-governmental organization and/ or pharmaceutical companies can use the data to formulate policies, strategies, intervention or medical treatment such as drugs development. Big data has implications on healthcare on patients, providers, researchers, health professionals. Nowadays, there is an increasing demand for more information by the patients about their healthcare options or choices, and want participation in their health decision-making. The big data will help to provide patients with up-to-date information to assist them to make the best decision and to comply with the medical treatment.

Advantages of Big Data
Big data could reduce the recency bias or recency effect bias. Recency bias occurs when the recent events are weigh more heavily than earlier events in order to improve the situation, but it may lead to incorrect decisions. The real time information can also be incorporated into big data. Real time big data has many advantages. For example, any errors or trouble shoot in an organization can be identified immediately and the operational problem can be overcome. This will save time, cost and increase the productivity. The services also can be further improved as the real time provides the latest information on the subject matter. For instance, it will provide the complete information on the patients and at the same time able to administer medical intervention without any delay. In healthcare, big data is also used in predictive analysis which is to identify and address the medical issues before it becoming an unmanageable problem. Healthcare professionals are able to reduce the risk and overcome the issue with the information derived from the big data. Apart from that, big data is also able to help identify frauds in healthcare especially on insurance claims. Fraudulent, inconsistency and false claims can be flagged. This will facilitate insurance companies to prevent losses. Big data can also benefit healthcare through data management, electronic medical records and data analysis. The big data will help to find and identify the right population or target group. Big data consists of diverse group of population and certain group can be identified for risk assessment and screenings. The existence of big data will also allow development or modification of a program or intervention to target the health problem. It will enables clinical trials to be initiated immediately. Big data will give a clearer picture on the type of population as well as their medical problem. The pattern of the distribution or disease information will allow quick development of intervention program as well as targeting the affected group as early as possible. Data growth of pharmaceutical industries were derived from patients, caregivers, retailers and Research and Development (R&D). Big data could facilitate the pharmaceutical companies to identify new potential and effective drugs and deliver it to the users more quickly.

Issues with Big Data
There is a huge challenge in big data in terms of data protection, collection and sharing of health data and data usage. Big data analytics with the use of sophisticated technologies has the potential to transform the data repositories and make informed decisions. Issues such as privacy, security, standards and governance to be addressed. Information such as nanoparticulate therapy on cancer treatment could be also be incorporated in big data to provide an overview and best treatment for cancer especially when nanotechnology is important in drug delivery in cancer treatment. Apart from that adverse effects of drugs use could also be determined.

Security
Since the big data contained subject’s personal information and their health history, it is important for the database to be protected from hacking, cyber theft and phishing, where the stolen data can be sold for a huge sum. Apart from the health information and personal information from the health system which can be hacked or stolen, other big data in other commercial organizations such as telecommunications companies (telcos), banks or financial institution are also vulnerable without the knowledge of the clients. Before big data can be implemented, it is necessary to ensure that the administration, privacy, security of the big data are well protected. Protection health information via transmission security, multilayer authentication, using anti-virus software, firewalls, data encryption are indeed vital. As the data becomes more regional and global, it become more complicated and have more serious impact on security, standards, language and terminology. The accessibility of the healthcare data need to be consistently reviewed and monitored.

Data Classification
Big data is a massive, less structured and heterogeneous. As such there is a need to identify and classify the data so that it can be used effectively. However, it is laborious to search for a specific data in the big data. The big data also required to be contextualized or pooled together so that it will become more relevant to specific individuals or groups.

Data Modeling
Although big data is excellent for modelling and simulation, there is a need to identify, structure and pool the proper relevant data so that it can be used to model the problems, which later can be used for intervention. Without the proper structured data, it is challenging to analyse and visualize the output and to extract specific information or data.

Cloud Storage
The cloud storage can be used to upload data or having the whole system designed in the cloud. Thus, the cloud will need to have sufficient space for the storage and sufficient speed for data upload at the same time. The storage apart involving words documentations, it should also able to store graphic type such as X ray, CT or MRI. The system should also be able to generate graphic presentations from the available data so that clinicians are able to visualize and understand quickly and take prompt decision.

Data Accommodation
One simplified big data system is require to accommodate all the data and it has to be compatible and simplified. This is to ensure that the users are able to retrieve the information without any hassle. It is a difficult task to get all the relevant systems to link to each other. There is a culture of dissonance within individual organizations, where some parties may control the data for their own needs rather than for the organization as a whole.

Data Personnel
At this time, it is still an arduous task to find data scientists with expertise in statistics, computer science or information technology (IT). A standard protocol need to be in place for data entry so that all information entered are standardized by data entry person even though there will be changes in the data entry personnel. This is to ensure the continuity and standardized format of data entry.

Miscommunications Gap
The miscommunications or the gap between the users and data scientists is one of the biggest problems in relations to big data. The understanding of the users on data generated by data scientists’ maybe low and this may affect the effective usage of big data.

The health data from all clinics and hospitals need to be pooled together as stored at one-stop center (big data). At the moment, all the information are kept separately. As such, it is difficult to get a clearer picture of the patients due to the incomplete information gathered. Thus, this waste a lot of time as the doctor will need to start all over from the beginning taking the patients history.

Since big data has the ability to predict future medical issues which is a positive thing, big data can also pose risk and undermine doctors. The patients too will rely on the technology rather consulting the healthcare practitioners.

Data Nature
The integration of data will not only involve data within the healthcare system but also external data. Although it gives potential benefits, it is also challenging in terms of privacy, security and legal matters.

The healthcare data usually consists of patients who are seeking treatment in the hospitals or clinics but none on healthy individuals. With the inclusion of healthy individuals in the database, it will help to provide better understanding on the nature of the disease and intervention. As the data becomes more current, it is necessary that the information are passed to the users immediately for clinical decision making and to improve the health outcomes.

Technology Incorporation
Lack of information to support the decision making, policy planning or strategy is one of the problems in big data. The processes of redefining and in adopting of technology is slow and this can impact the healthcare, care delivery and research. Without the technology, big data is unable to generate and disseminate information. Most the time, data are fragmented and dispersed among various stakeholders such as providers, vendors, organizations and payers. The solution to this is to have all the data uploaded in one ‘warehouse’.

Conclusion
Big Data has a great potential changing the healthcare outlook such as in drug discovery, patients personalization care, treatment efficiency, improvement in clinical outcomes, and patients safety management.