By Rahul Mehta, senior vice president and head of data management proficiency, CitiusTech.
The sheer volume and variety of data, such as claims, EMRs, lab systems, and IoT now available to healthcare organizations is mind-boggling. The potential to pull data from these myriad sources to work for real-time care intervention, clinical quality improvement, and value-based payment models is unfolding fast.
Yet, as organizations seek to aggregate, normalize and draw insights from large and diverse data sets, the importance of data quality becomes apparent. Consider an activity as fundamental as identifying the correct patient. According to Black Book Research, roughly 33 percent of denied claims can be attributed to inaccurate patient identification, costing the average hospital $1.5 million in 2017.
For example, the average cost of repeated medical care due to inaccurate patient identification with a duplicate record is roughly $1,950 per inpatient stay and more than $800 per emergency department visit.
As data quality become more important, healthcare organizations need to understand the key characteristics that affect quality: accuracy, completeness, consistency, uniqueness and timeliness. However, data reliability and integrity also depend on other key factors, including data governance, de-duplication, metadata management, auditability and data quality rules.
With a strategic approach, healthcare organizations can employ a unified data strategy with strong governance for data quality across all data types, sources and use cases, giving them the ability to scale and extend to new platforms, systems and healthcare standards. The result is an approach that uses a combination of industry best-practices and technology tools to overcome common challenges and assure data quality for the long term.
Understanding Data Quality Challenges
Historically, providers and payers alike treated data quality as a peripheral issue, but that is no longer viable in today’s complex data ecosystems. First, there are a diversity and multiplicity of data sources and formats: EHRs, clinical systems, claims, consumer applications, and medical devices. Add to that, challenges associated with legacy applications, automation needs, interoperability, data standards and scalability.
Lastly, there are increasing numbers of use cases for clinical quality, utilization, risk management, regulatory submission, population health, and claims management that need to be supported.
Considering the current data environment, the downstream effects of data quality issues can be significant and costly. For example, in the case of patient matching as referenced above, something as common as two hospitals merging into the same health system, but following different data-entry protocols, can lead to duplicate and mis-matched patient records. It can also lead to critical patient data elements, such as date of birth, being documented differently by different facilities and then made available across multiple systems, in varying formats.
It still seems magical that Spotify creates a personalized music track for my life. Similarly, I now get personalized suggestions of what books to read, what recipes to cook, and even where to travel. This is the way we’re living our lives except for healthcare. It represents almost 20 percent of the U.S. economy and has a huge impact on my life, but I don’t have the ability to personalize my healthcare experience, personalize my medical treatments, or personalize how I’m treated as I move through the system.
What’s the missing piece? Data. We need to break data out of silos, exchange it, share it, leverage it, use it — all types of data — claims, clinical, new, and old. We can’t build personalized health without piecing together each patient’s individual experience to tell the full story. We cannot leverage the positive power of technology, including machine learning and AI, without data. Unlocking this information is difficult. But it’s critical work. And we need to democratize access to data, not treat it like a competitive asset, to bring the power of personalized medicine to every clinician and patient.
Data signals help patients personalize their choices
A nurse friend of mine has stage four breast cancer. Her clinicians gave her a treatment plan. But she took a close look at her health, her data, and the evidence and determined that in her particular case there was no evidence that the treatment options would extend her life, and they would probably cause her a lot of pain and suffering in the form of adverse effects. She decided not to get treatment and has lived a quite incredible life since then. Her doctors were surprised. But to her, it was simple — she didn’t want treatment because there was no evidence that it would work for her.
Data signals help care teams see the hidden patterns
We work with a care manager who follows up with patients after they have been in the hospital to help them get the care they need. Recently, she noticed a patient was getting treated at multiple emergency departments for falls. No one had noticed the pattern. But the care manager had access to the patient’s community health record from Manifest MedEx (MX) and could see the trend: The patient needed a walker. It did not take a huge amount of information or technology to deliver dramatically more effective and personalized care. It took data and someone to notice.
That’s the care we all want. We want healthcare that’s responsive to our needs, to our preferences, and to the simple things that make a difference.
You can’t personalize patient care without data
Exciting technology is in the pipeline to make the vision of personalized medicine a reality, but we don’t have a reliable health data infrastructure in place to power this future. It’s like saying you’re going to create self-driving cars, but there’s no GPS network.
Ten years ago, most data in healthcare was trapped on paper. Now, most — but not all — of it is digital. It’s huge that in just a decade we’ve been able to transition from paper to electronic data. And we are also getting better at sharing it.
But if we don’t have platforms to integrate it, match it to each patient, and identify signal, the data is just more noise for overburdened clinicians. If we want a future of personalized health, we’re going to have to make meaning from data. And this meaning needs to be available to everyone treating a patient.
By Karen Way, global practice lead for data and intelligence, NTT DATA Services.
A recent study conducted by NTT DATA Services and Oxford Economics highlighted the top three challenges identified by healthcare executives and consumers: standardizing and sharing of data across the healthcare spectrum, preparing for and adapting to regulatory changes and recruiting or retaining the right resources. It’s understandable that these challenges rise to the top of the list, as trying to meet rising consumer demands for access to their healthcare data while maintaining regulatory compliance with limited resources is a bit like juggling raw eggs. If your timing or skills are just a bit off, you end up with egg on your face.
How can a healthcare organization address these challenges? First, it’s important to understand exactly which challenges are present within your own organization, and how they are impacting the patient experience.
Study results showed that only 24 percent of healthcare organizations share data across the business. Why? There are several reasons:
Interoperability – Even though this concern has been expressed since the inception of the EHR/EMRs, there are still barriers to being able to communicate data between different systems in a consumable, usable format. For example, several years ago, I had a CT scan due to the sudden onset of a continuous migraine headache. After the scan, I was referred to a neurologist that practiced out of another hospital system. I took a copy of the scan (on a DVD) to my specialist appointment, but the doctor was unable to view it on her system. As a result, I had to have another CT scan for the neurologist to see what may have been happening. Data already collected could not be used due to lack of standardization across systems. As noted in Dr. Eric Topol’s book Deep Medicine, “Your ATM card works in Outer Mongolia, but your electronic health record can’t be used in a different hospital across the street.”
Data Volume – The volume of data being generated daily in the healthcare industry has been estimated to be approximately 30 percent of the world-wide total. With the estimates of data generation rates of at approximately 2.5 quintillion (that’s 1, followed by 30 zeros) bytes/day, that’s a lot of healthcare related data. Healthcare organizations aren’t even beginning to tap the depths of this data, simply due to the data volume.
Disparate Data – Like patients, healthcare data comes in many different shapes, sizes and languages. Even if interoperability issues didn’t exist, sharing of data across the healthcare business is hard because of these differences. Data can be an image, a PDF, a written note, a prescription label, etc. Historically, each type of data requires different mechanisms for managing it, often using different tools or systems.
These three factors combined can be overwhelming for healthcare organizations whose main goal is to provide the best healthcare possible.
Another leading challenge identified in the study is that of recruiting and retaining skilled resources. Of the healthcare executives surveyed, only 51 percent stated that they were able to recruit and retain resources with the required skills and knowledge. There are two components to this issue:
Upskilling resources – With the continual advancements in technology, it is important to ensure that resources can take advantage of training opportunities and professional growth. This is often a delicate balance for organizations; time spent in training is often seen as time away from projects with deadlines.
Healthcare experience – While there may be a pool of qualified resources with the required technical skills, it can be hard to find resources with knowledge and/or experience in the healthcare sector. For example, several years ago, a client brought in resources to support their enterprise data warehouse that had extensive experience in data warehousing. There were high expectations of new and improved functionality due to the technical depth of these resources. Unfortunately, the project did not deliver as expected. Why? None of the resources had knowledge of healthcare data or business processes. One resource posed the question to the client: “what is a healthcare claim?”
Just as important as reviewing the patient experience for ways technology can solve the problem, it helps to treat your workforce like your customer and improve the experience of transforming the organization into a digital-first enterprise. A recent article in the Wall Street Journal highlights the difficulty in recruiting resources and approaches to solving this challenge. The article also reinforces that in today’s data economy, it is no longer enough that a resource be technically skilled, they must also have knowledge of the business environment in which they are applying the technology.