Turning the deluge of health data into actionable health analytics

0
36


Jon-Michael Smith, Head of Health and Life Sciences Analysis: Data Integration at Qlik

At the time, the HITECH Law 2009 and the introduction of the meaningful use program represented a momentous step in the digital transformation of healthcare. With billions of dollars in investment and government incentives in almost two years, more than 77% of hospitals had reached stage 3 of the Electronic medical record adoption model (EMRAM), or even further, incorporating millions of data points into the newly established EMRs.

Over the next 10 years, as EMRs became a broader, more collaborative snapshot of a patient’s health, the government tried to streamline digitization regulations to further strengthen adoption, and in 2019, despite some challenges, health care data generally flowed more freely. However, by 2020, as a result of the pandemic and health technology record boom, many hospitals were essentially drinking from a data hose.

Amid the ongoing flood of data, health systems are simultaneously facing other institutional challenges related to the COVID-19 pandemic, such as increasing patient volume, depletion of physicians, a nursing shortage, the burden of ensuring cybersecurity and one overwhelming digital health ecosystem. The analysis of health data can and should serve to alleviate some of these operational challenges. To do this, here are four features that data should achieve to be truly useful and valuable.

1. Accessible – Although the collection of more patient data points (clinical, demographic, etc.) and other financial or operational sources (staff, claims, business analysis, etc.) is theoretically good, it has little or no value if cannot be retrieved, downloaded or searched. Collecting or later organizing data sets in standardized formats is the first step in making them more accessible in other ways.

2. Digestible – Depending on the scope of a project, objectives, timing, stakeholders, or any number of factors, teams may require a range of specific data. Quality data analysis tools should be used by employees at different levels of the health system, from support staff to higher level decision makers. Instead of investing in specialized training or data science equipment to make sense of the growing amount of information that hospitals are collecting, the responsibility has really shifted to the market to create tools that meet the needs of IT professionals. health where they find more visual and digestible data tools. While current EMRs have taken a giant step toward better data accessibility, more can be done to centralize and democratize data for non-clinical hospital staff and ultimately for patients themselves.

3. Understandable – While the data may be technically accessible and visually appealing, without improved data literacy, even the largest and most digitally transformed hospitals may not benefit from your data. Critical for Garter’s definition of data literacy as “the ability to read, write, and communicate data in context” is also “the ability to describe the use case, application, and resulting value.” Unfortunately, these deficiencies are especially common in the healthcare community. Also, a recent one poll Philips found that 35 percent of younger health care professionals do not know how to use patient data and analytics to report care. Clearly, skills training and improvement may be required to ensure that each employee is competent in the use of their data.

4. Timely – In addition to being accessible and understandable, the data must also be timely in order to act. Healthcare is already known for its lack of opportunity when it comes to patient interactions and operational efficiency. Delayed operating data can be an inaccurate situation for decision makers, which can lead to poor decision-making that can cost time, money, damage to reputation, decreased employee satisfaction, and poorer quality of care. to the patient.

Between the growing collection of patient data through EMR and other digital health tools over the past decade, as well as new data flows as a result of VOCID, health systems are overflowing. While data flow is a critical first step, more needs to be done to improve data accessibility, visualization, and literacy in order to make it truly useful on a large scale. Fortunately, there are the analytical tools that healthcare workers need, and prioritizing their implementation will lead to a significant improvement in operations, hospital finances, and ultimately patient care.

About Jon-Michael P. Smith

Jon-Michael P. Smith is the head of Healthcare and Life Science Analytics – Data Integration at Click. He is an experienced senior sales leader and certified medical coder with experience in IoT, Big Data, real world evidence, clinical trials, healthcare research, patient reported results (PRO), clinical computing, and patient-centered care. He has decades of experience working with global healthcare delivery systems, pharmaceutical clinical trial sponsors, CROs, biotechnology organizations, and medical devices.



Source link