Health Care Data An intangible Asset
An introductory note on healthcare as a transforming domain:
In the contemporary era of data revolution, healthcare is transforming and being redefined is as a clinical science with mutual collaboration and conversation with data science. Today’s health care revolution is mainly built on the power of patient data. The evolution in the field is mainly influenced by unravelling the insights contained in patient phenotypic and genomic data which is collected in the care context. Different stakeholders in the health care ecosystem such as patients, care providers, policy makers, payers, and medical/health researchers can profit from well-structured curated and consolidated patient data that incites an improved patient care through innovation in medical research. In this context it is not an overstatement to represent the patient data as a treasured source of information and a valuable intangible asset desired by multiple stakeholders. Three main forces advancing this exponential growth and trigger an upsurge in digitized health care data include technology, health care reform, and the movement toward patient-centered care. These forces incite the institutions to capture, manage, and share health information as a series of ongoing data elements, not a collection of documents filed in a folder. Through-out the last 30 years a large amount of data has been generated through health care providers and health care industry. The accessibility and amount of data has exponentially increased with implementation of electronic and digital infrastructure of collection and storage of health data which was generally in paper form.
Value of health care data:
There are increasing evidence concerning the economic possibilities related to use of big data and their wider implications. Indeed, the case can be made for the major useful economic role of the health care data that is related to the implementation of strategies and actionable intelligence that will illustrate and quantify the benefit related to the big data. in a study conducted by Price Waterhouse Coopers, more than three-quarters of the health care executives surveyed stated that information contained in their electronic health record (EHR) could become their most valuable asset over the next 5 years as “secondary use” of data takes off [1]. To inform this discussion, we must examine the potential value that big data can create for health care organizations and seek to illustrate and quantify the value. Secondary use of the data coming from the EHRs has the potential to predict public health trends, improve patient care, and reduce health care costs. A recent report from UK NHS indicates “We estimate that the value of the curated NHS data set could be as much as £5bn per annum, delivering around £4.6bn worth of benefit to patients per annum, if this effort is undertaken. The value to patients would come from potential operational savings for the NHS, enhanced patient outcomes and the generation of wider economic benefits to the UK.” [2]. There will be a significant process and technology costs associated with aggregation, cleaning, curating, hosting, analysing and protecting the transformation of these raw data records into a consolidated longitudinal patient-level data set. Moreover, challenges around interoperability and diverse data contents/sources need to be addressed. When wrangled, consolidated, and curated into a structured longitudinal data set, patient-level records will trace a complete story of a patient’s health, wellness, diagnosis, treatments, medical procedures and outcomes. For instance, treatment of chronic diseases is a crucial issue that can be addressed through the use of a well-curated patent dataset includes factors such as medical history, demographic or socioeconomic profiles and comorbidities that influence the risk of developing chronic diseases using traditional analytics and modern machine-learning models. Therefore, by aggregating data related to these factors, predictive analytics can help identify those individuals who are at risk of chronic conditions.
Enabling Al-Enabled learning health-care settings:
Above we have underlined that consolidated patient data provide multiple opportunities such as deeper disease understanding through an increased level of the quality of care, through faster and early diagnosis as well as the observation of real-world patient outcomes, which is a clinical pathway to treatment effectiveness that might result in an improved patient access to therapies. In terms of innovation and development/targeting new treatments and medicines, curated patient data can provide evidence of cost-effectiveness and outcomes to inform value-based payments and evaluation of safety through quantitative pharmacovigilance. More specifically, in line with recent developments in application of machine learning and computational statistics in the domain of health, big data can enable personalised medicine and implementation of right treatments for the right patients. In other words, accessibility of such a data provides the possibility of implementation of advanced data mining and predictive modelling procedures to reveal trends and patterns that improve diagnoses, treatments and operational effectiveness. Along the same lines, and in the current context of COVID pandemics the use of apps and remote health-care solutions is on the rise. AI-enabled systems are a crucial element to enable a comprehensive understanding of patient’s data that has the potential to offer effective, accurate and actionable advice to all stakeholders. Such solutions are designed and optimized for high volume and velocity of health care data, the same characteristics which make gaining actionable insight difficult to obtain from other traditional data mining and statistical technics. Such initiatives facilitate the day-to-day clinical workflows, for care providers as better workflows can be established and effectively communicated with the patient, leading to better outcomes. In other words, patient data along with AI-driven solutions provide the link between underlying genomic attributes, diagnostic and interventional procedures, and the actual clinical outcomes people experience.
Another vision for the secondary use of healthcare data is to promote the development of a learning health care system. The potential to use Health IT (Health Information Technology) as a vehicle to reduce health care costs, improve efficiency, and enhance quality of patient care/safety has been explored by some of the pioneer in health informatics. A learning health care system latter refers to a system where the natural delivery of best care practices and the real-time generation of new evidence is guided and engineered by information systems and processes used throughout the healthcare providing institutes. This also can be coupled with the use of computational methods and artificial intelligence to enhance decision making by capitalizing on large amounts of data to identify variables that affect the patient or institution level outcomes. Within this context, health IT is transforming to a crucial solution to ever evolving care management and rapid patient turnover. More specifically, in a learning health system where they benefit from diagnostic and treatment decisions supported by data-driven guidance they can access, intelligence-driven and personalised digital health services via apps and online systems which in their place reduce the burden of care on providers and save time. Because of the intelligence-driven pathways that inform diagnostic, treatment, and post treatment care, even patients with complex co-morbidities and chronic conditions who have better outcomes.
Concluding remarks:
The essence of informatics revolution in healthcare is to realize the necessity of right set of tools to properly abstract, collate, and synthesis data and the fact that data per se is not the solution. Clinical, financial, and operational visions can be gained from the vast volumes of data that coming from the care providing procedures. The right approach to secondary data analytics and implementation of a learning healthcare context can be the key to knowledge that advance health care systems ahead of competitors. Even mountains of data without proper tools, expertise and culture could not acquire propre information and knowledge. Technical and governance issues such as format and architecture do matter. Along the same lines, well-adjusted technologies that are adapted for big data applications (such as cloud computing) can foster balanced performance and long-term scalability system for real- time decision making processing power require. However, there are several problems surrounding sharing and building infrastructure around the health care data including incomplete standards, access, transparency, technology, and ethical guidelines. It is critical that the analyses and innovations adhere with medical ethics and research regulations. Patients have to be informed and need to be confident that their data is being used for their own and public good, and that their privacy and rights are safeguarded. Although the health care industry has already resolved some of the security and privacy concerns there is still another significant issue concerning the standardization of disparate health data from the health care organizations and providers.
References
[1] Manca, D. P. (2015). Do electronic medical records improve quality of care?: Yes. Canadian Family Physician, 61(10), 846.
[2] National Health Service–NHS (2019) Realising the value of healthcare data: a framework for the future.