How de-identified data can advance medical research and improve patient care.
De-identified data has become an important tool in medical research and for providers looking to enhance patient care. While data sharing between different organizations could violate the Health Insurance Portability and Accountability Act of 1996 (HIPAA), the de-identification process makes sharing information HIPAA-compliant.
De-identified data sharing can then assist medical researchers in advancing tools and treatments. Additionally, it allows for collaborative efforts from large provides. Overall, de-identifies plays a critical role in improving the patient experience.
WHAT IS DE-IDENTIFIED DATA IN HEALTHCARE?
The process of de-identification removes all direct identifiers from patient data and allows organizations to share it without the potential of violating HIPAA.
Direct identifiers can include a patient’s name, address, medical record information, etc. While direct identifiers are removed from the data to keep a patient’s identity confidential, indirect identifiers can remain untouched to allow researchers to study data trends. Indirect identifiers include gender, race, age, etc.
According to the Department of Health & Human Services, “The process of de-identification, by which identifiers are removed from the health information, mitigates privacy risks to individuals and thereby supports the secondary use of data for comparative effectiveness studies, policy assessment, life sciences research, and other endeavors.”
Data de-identification is crucial to advancing medical research and treatment while also protecting patient privacy.
HOW DO RESEARCHERS USE DE-IDENTIFIED DATA?
De-identified data can be used in medical research and treatment. Once identifying information is removed, the data can provide useful information for advancing healthcare.
In a recent study, researchers used de-identified data to develop an artificial intelligence tool to predict 30-day mortality risks in patients with cancer. Cancer is one of the leading causes of death in the United States each year. With the artificial intelligence tool, medical professionals can discover patients who are at high risk and provide early intervention and resolutions for reversible complications.
Additionally, the tool can identify patients who are approaching end of life (EoL) and refer them to early palliative and hospice care. In this case, the use of de-identified data assists with artificial intelligence and can provide an improved quality of life and symptom management for the patient.
“In contrast, aggressive, life-sustaining EoL care can conflict with patient preference and result in lower quality of life, family perceptions of poorer quality of care, and greater regret about treatment decisions. Earlier referral also represents an opportunity to transform cancer care by reducing the potential for unnecessary, toxic and expensive treatments at EoL,” the study authors wrote.
De-identified data can also be used in developing predictive analytics tools. To address healthcare gaps created by the COVID-19 pandemic, UnitedHealthcare developed a predictive analytics tool that used de-identified data to address social determinants to health.
“Around 80 percent of your health is determined by things that are not your genetics. There are things more such as what’s going on in the rest of your life, what we call social determinants of health — social, economic, gender orientation, and other markers that sometimes can lead to inequality,” Rebecca Madsen, chief consumer officer, UnitedHealthcare said.
To eliminate care gaps, UnitedHealthcare created an advocacy system to assist members who might be struggling due to their social environment. Through predictive analytics and a machine learning model, the advocacy system can evaluate de-identified data from members and determine the need for social services.
Data is then loaded into an agent dashboard used by UnitedHealthcare advocates. When a member calls in, advocates can connect the caller to community resources at low or no cost.
De-identified data allows medical professionals to both develop tools to better serve patients and advance research to produce improved outcomes.
WHAT ARE THE BENEFITS OF DE-IDENTIFIED DATA?
Data sharing allows those in the healthcare field to create better tools and treatments to improve patient care and outcomes. However, according to the Centers for Disease Control & Prevention (CDC), HIPAA law states that patient information must be protected and cannot be shared with other entities without the patient’s knowledge and consent.
By de-identifying data, providers can share information with other organizations to advance medical researcher and treatment. Additionally, de-identifying the data removes some liability regarding HIPAA violations.
Furthermore, the use of de-identified data allows for the collaboration of large data analytic platforms. Earlier this year, fourteen leading healthcare providers partnered to form Truveta, a new company that used big data analytics to enhance care insights.
The providers included AdventHealth, Advocate Aurora Health, Baptist Health of Northeast Florida, Bon Secours Mercy Health, CommonSpirit Health, Hawaii Pacific Health, Henry Ford Health System, Memorial Hermann Health System, Northwell Health, Novant Health, Providence health system, Sentara Healthcare, Tenet Health, and Trinity Health.
By combining the healthcare providers’ tens of millions of patients and from thousands of care facilities across 40 states, Truveta created a large de-identified dataset for their analytic effort.
With de-identified data, providers can share patient data to assist in medical advances while also maintaining patient privacy and complying with HIPAA.
API EHR integrations can support patient centered care by promoting patient reported outcomes data sharing with primary care providers.
Application programming interface (API) EHR integrations can support patient reported outcomes data sharing with primary care providers, according to a study published in JAMIA.
In a prior feasibility study, researchers developed and tested an initial prototype of a remote patient monitoring application for asthma patients in pulmonary subspecialty clinics. The original intervention consisted of a smartphone app that prompted patients to report asthma symptoms every week. The study demonstrated high patient adherence and low provider burden.
Increased access to patient reported outcomes data can aid providers in delivering patient-centered care.
For the current study, researchers adapted the intervention to the primary care setting and gathered patient and PCP feedback on requirements for a successful remote patient monitoring application.
The study’s results are based on analysis of 26 transcripts (21 patients, 5 providers) from the prior study, 21 new design sessions (15 patients, 6 providers), and survey responses from 55 PCPs.
PCP-facing requirements included a clinician-facing dashboard accessible from the EHR and an EHR inbox message preceding the visit. Nurse-facing requirements included callback requests sent as an EHR inbox message.
Patient-facing requirements included the ability to complete a one- or five-item symptom questionnaire each week, depending on asthma control. Patients also called for the option to request a callback, and the ability to enter notes. Additionally, patients suggested that the app push tips prior to a PCP visit. Requirements were consistent for English- and Spanish-speaking patients.
“This study demonstrates how third-party apps can be used for PRO-based between-visit monitoring in a real-world clinical setting with the goal of maximizing use, usability, and scalability in parallel with native EHR functionality and patient portal offerings,” the study authors wrote.
“Although we focused exclusively on asthma, these findings may generalize to other chronic conditions that benefit from routine symptom monitoring using standardized PROs, such as rheumatologic disease, mental health illness, and irritable bowel disease,” they continued.
Additionally, the authors noted that their study’s findings could be applied more broadly to support primary care patient reported outcomes for patients with multiple chronic illnesses.
“Similar requirements elicitation approaches also have the potential to develop scalable interventions for monitoring overall health of patients with multiple chronic conditions, such as captured by global health PROs which measure general physical, mental, and social health,” they wrote.
“With further testing, iterative development, and continued attention to scalability, the rapidly evolving efforts of digital remote monitoring between visits may be achievable at the population level for patients with chronic conditions,” the authors continued.
As care is increasingly delivered remotely, such requirements are likely to become more important.
“Our effort is distinct from other reported efforts at developing clinically integrated remote monitoring interventions, which lack prioritization of requirements, require additional clinical staff, such as care managers, to monitor data, or require a device,” the authors wrote.
These alternate approaches may encounter scalability issues, such as cost challenges for using devices where they aren’t necessary, they explained.
“Furthermore, we provide new knowledge regarding how a third-party application can be integrated into an EHR with patient- and provider-facing components to enable the use of PROs for between-visit monitoring.”
Mayo Clinic researchers found that the population health of those under 45 regarding severe COVID-19 infection is greatly affected by chronic disease.
Mayo Clinic researchers have discovered new risk factors impacting the population health of those under 45 when it comes to severe COVID-19 infection.
Using data from 9,859 COVID-19 infections, researchers found that younger populations had a greater than threefold increased risk of severe infection if they had chronic diseases such as cancer, heart disease, or blood, neurologic, or endocrine disorders.
The team of researchers studied individuals living in a 27-county region of Southeast Minnesota and West Central Wisconsin who were diagnosed with COVID-19 between March and September 2020. The study used the Rochester Epidemiology Project, a linkage of 1.7 million medical records from multiple health care systems that provided significant insight into the risks for the whole geographical region.
"Medical care is really fragmented in our country, so someone diagnosed with COVID-19 at one health care provider might end up at a totally different hospital for their severe case. If those records are not linked together, there's really not a good way for us to understand that that is even the same patient," Jennifer St. Sauver, PhD, a Mayo Clinic epidemiologist and the study's first author, said in a press release.
"By contrast, the Rochester Epidemiology Project allowed us to follow patients from the time they were diagnosed through their use of health care after that diagnosis, even if they were taken care of at different places. In addition, we could look back in their medical records to better understand all of the chronic diseases this population had even before getting diagnosed with COVID-19 and how those diseases might have contributed to more severe infections," Sauver continued.
Researchers identified cancer to be the biggest difference in risk when comparing study participants younger than 45 to those older. For those under 45, cancer was a strong risk factor. However, it was not as significant for the older age group.
Additionally, patients with developmental disorders, personality disorders, schizophrenia, and other psychoses have the highest adjusted risk for severe COVID-19 compared to all chronic conditions.
Researchers also discovered risk factors among races and ethnicities. According to the study, Asian Americans had the highest risk of developing severe COVID-19, followed by Black Americans and Latino populations.
"The Rochester Epidemiology Project allows us to study diseases, such as COVID-19, in a defined population, which provides the ability to translate our results to all people with COVID-19, not just those with the most severe disease requiring medical care," senior author Celine Vachon, PhD, Chair of the Mayo Clinic Division of Epidemiology said.
"This type of infrastructure will allow us to follow patients who had COVID-19 in the 27-county region over time to better understand any future links to disease."
For the COVID-19 HotSpotting Score, investigators use a combination of indicators to help predict upticks of cases and potential hospital admissions – with up to six weeks' lead time.
In a study published this week in BMJ Open, Kaiser Permanente researchers put forth a method to predict upcoming COVID-19 surges up to six weeks in advance.
By examining electronic health record data from Kaiser Permanente in Northern California, the team was able to zero in on ten indicators that, they say, can help effectively forecast an upcoming surge when combined.
"This current COVID-19 surge has shown us how challenging it is to have a reliable, long-range forecast of COVID’s impact on hospitals," said Dr. Vincent Liu, lead author on the study, in an email to Healthcare IT News.
"By knitting together diverse streams of health system data, we can identify the earliest signals of renewed COVID activity impacting our patients and contextualize our findings against other prediction tools," said Liu, who is a research scientist with the Kaiser Permanente Division of Research, as well as being a practicing intensivist with the Permanente Medical Group and regional director of hospital advanced analytics for Kaiser Permanente in Northern California.
WHY IT MATTERS
Based on 35 million data elements, the investigators ultimately incorporated 10 indicators into "the COVID-19 HotSpotting Score," or CHOTS.
They identified four major indicators:
- Patient calls that activated regional "cough and cold" protocols.
- Patient-initiated "influenza-like illness" email communications.
- New positive COVID-19 tests.
- COVID-19 hospital census numbers.
The also noted another six minor ones:
- Patient calls that activated regional COVID-19 protocols.
- Respiratory infection visits (routine).
- Respiratory infection visits (urgent care).
- COVID-19 visits (routine).
- COVID-19 visits (urgent care).
- Respiratory viral testing.
Although many of the individual indicators signaled an upcoming surge within one to three weeks, the combined CHOTS significantly increased the lead time to as far as six weeks prior to a surge, said the Kaiser team.
"Over the course of 2020, COVID-19 surprised us at nearly every turn, making longer-term predictions of its impact on our patients, health system, and communities extremely challenging," said Liu in a statement.
"At the same time, shorter-term predictions – looking only one to three weeks out – left little time to respond adequately,” he said.
After CHOTS went live in June 2020, the team evaluated it against actual COVID-19 hospital activity through the end of the year.
"The correlation of the regional CHOTS with hospital census was very strong, peaking with a 28- to 35-day lead time, but with continued correlation when tested out to six weeks," said Kaiser representatives in a press release.
Researchers note that public health officials and individual health systems could use the forecasting information to help prepare for increased patient numbers – and know when relief is on the way.
They also flag a few of the study's limitations, such as the fact that the tool's generalizability could vary across settings and geographies.
In addition, they mention that they developed CHOTS during a time of "great uncertainty" following the first wave of COVID-19 in California.
"As a result of the extreme urgency to prepare our health system, we depended on clinical judgment and heuristics, in addition to prior health-system influenza patterns, to develop our score," they wrote in the study.
"With the luxury of time, more advanced machine learning or statistical techniques may have produced different calculations," they added.
THE LARGER TREND
Given the immense strain on resources that COVID-19 has continued to put on hospitals, multiple teams of researchers have tried to develop predictive tools that can help health systems prepare for the different factors affecting demand – such as length of hospitalization, respiratory failure likelihood, clinical severity and patient outcomes.
More broadly speaking, chief information officers have spoken to the importance of integrated supply chains, which could respond to fluctuations in need.
ON THE RECORD
"We use machine learning and artificial intelligence every day in our research group to develop predictive models to improve patient care. We applied these tools when we were developing CHOTS, but didn’t find that they improved the tool’s value," said coauthor Patricia Kipnis, principal statistician at Kaiser Permanente's division of research, in a statement.
"Our research group focuses on pairing the right algorithm with the right use case, and, in this case, a simpler tool showed excellent performance and could be readily implemented and shared," she added.
With widespread use and training, electronic prior authorization EHR integrations may cut down on clinician burden and increase patient safety.
As healthcare stakeholders investigate ways to leverage health IT to mitigate clinician burden and improve patient safety, the next frontier for the digital health transformation could be streamlining the arduous prior authorization process through electronic prior authorization.
Automating prior authorization could result in higher quality care by cutting back on clinician burden and providing patients with their medications in a more timely manner.
What is electronic prior authorization?
Prior authorization is a utilization management strategy that payers use to ensure patients access the most cost-effective medication available for their clinical needs.
When a drug has prior authorization requirements, providers must submit certain documents to the payer for permission to prescribe the drug. However, the traditional prior authorization process is time-consuming and can lead to delays in patient care.
A 2019 AMA survey found that 64 percent of providers have to wait a full business day to receive prior authorization feedback from payers; 29 percent reported that they had to wait at least three business days.
This delay can lead to patient care setbacks. The survey found that for 91 percent of providers, prior authorizations delayed patient care; 48 percent reported that prior authorizations often or always have this effect.
Delayed prescriptions due to prior authorization can lead to patient safety issues. Nearly a quarter of providers (24 percent) said that a prior authorization-related delay has resulted in an adverse health event for a patient and 16 percent said that the delay led to hospitalization.
What’s more, the arduous prior authorization process places a sizable administrative workload onto clinicians. Almost nine in ten providers (86 percent) reported that the prior authorization burden was high or extremely high, averaging over 14 hours per week to complete 33 prior authorizations.
However, health IT could alleviate some of the clinician burden while also helping patients receive their medications sooner.
Electronic prior authorization (ePA) aims to speed up the process by sending prior authorization documents digitally instead of via phone or fax. ePA can be integrated into EHR systems to allow providers to easily request prior authorization within their clinical workflows.
Is ePA effective?
To better understand how electronic prior authorization might impact patients and providers, America’s Health Insurance Plans (AHIP) launched the Fast Prior Authorization Technology Highway (Fast PATH) initiative in early 2020.
Six payers—Blue Shield of California, Cambia Health Solutions, Cigna, Florida Blue, Humana, and WellCare (now Centene) participated in the project, which ran for approximately 12 months. Availity and Surescripts served as the program’s health IT partners. RTI International evaluated the results as a third party. Point-of-Care Partners acted as an advisor.
After implementing ePA, the total number of prior authorizations jumped by 34 percent. A third of these transactions took two hours or less, compared to before when 24 percent of prior authorizations took two days or longer to fulfill.
More than 60 percent (62 percent) of prior authorizations were electronic after the health IT solution was implemented, and traditional prior authorizations were cut nearly in half. The report authors noted that ePA had little effect on the rate of approvals.
Most providers who used electronic prior authorization had positive feedback. Six in ten providers who used prior authorization regularly said that ePA made it easier to know whether they needed to request prior authorization.
Approximately the same number of providers (57 percent) who were well-versed in prior authorization said that the ePA requirements were easier to understand, and half of them said that the prior authorization decision was easier to view.
Among less experienced providers, the results were less extreme. Less than half (47 percent) said that it was easier to understand if prior authorization was required with ePA, while 43 percent said they did not observe a difference.
Providers who used ePA for most of their patients reported less administrative work related to prior authorizations; 54 percent had fewer prior authorization-related phone calls and 58 percent had fewer faxes related to prior authorization.
However, across the entire provider population, nearly half of clinicians reported no change in the volume or time spent on phone calls and faxes when using ePA.
Overall, seven in ten respondents who used ePA for most of their patients reported that the tool sped up care delivery. Less than three in ten providers said that the amount of time for care delivery was unchanged (27 percent).
Across the entire provider population, 43 percent agreed that ePA increased the speed of care delivery, and nearly half reported no change in care delivery speed (49 percent).
“The review of over 40,000 transactions showed the impact electronic prior authorization makes in health care,” said Denise H. Clayton, research economist of Health Economics and Evaluation at RTI International. “Because clinicians and their staff report more benefits from ePA when they use it more often, greater provider adoption of ePA could help further realize its promise.”
Is there an appetite from providers for this?
About 83 percent of physicians surveyed by Surescripts in 2016 reported that ePA is a top priority, and 64 percent agreed that EHR vendors should provide a service for streamlined prior authorization.
EHR vendors also acknowledged the growing importance of adding electronic prior authorization to their systems; 88 percent of vendors stated that they are aware of the demand for this ePA from their customers. Additionally, about 86 percent of EHR vendors said that ePA is a functionality that customers anticipate the systems to provide.
A June 2020 AHIP survey revealed similar findings; almost 85 percent of payers saw prior authorization automation as a key point of collaboration with providers. Approximately 90 percent of plans said that they were streamlining prior authorization processes for prescription medications (91 percent) and medical services (89 percent), primarily relying on ePA in each scenario.
“Many EHR software systems have incorporated electronic prior authorization capabilities, but the functionality may not yet be a standard option, despite vendor acknowledgment that it can improve clinician workflow and quality of care,” explained Joe Delisle, Surescripts senior business management analyst.
“The inefficiency of manual PA processing translates into hours of wasted time, contributes to workflow inefficiency and impedes a practice’s ability to deliver optimal and timely care,” said Delisle. “The time to enable electronic prior authorization is now.”
ePA Implementation, Use Challenges
Despite the promise of ePA, and an appetite from providers to adopt it, there are some challenges. A study published in JAMA Network Open found that misfiring issues and provider education are keeping ePA EHR integrations from achieving success.
Researchers implemented ePA at a large US healthcare system in two phases in September and November 2018, and used the later-implementing sites as controls.
Using EHR and pharmacy data, the study authors matched epA prescriptions with non-ePA prescriptions based on insurance plan, medication, and site, before and after ePA implementation.
Overall, 64.2 percent of ePA prescriptions (24,930) were filled, compared to 68.8 percent of control prescriptions (26,731), a negligible difference.
The researchers suggested several possible reasons for this result.
First, ePA fired for less than two percent of prescriptions, which is less than the nationwide average. This suggests some potential misfiring.
There were no substantial differences for commonly used medications for chronic illnesses. However, there were larger gaps in medication adherence for dermatological agents and lifestyle medication for ePA compared to control prescriptions.
The study authors suggested that ePA may have misfired for medications that did not require prior authorization, such as vaccinations, low-cost topical medications, and glucose supplies.
Additionally, since not all healthcare payers have ePA capability, providers may have been using ePA and traditional prior authorization processes simultaneously. In fact, the study authors noted that approximately 75 percent of providers that use ePA leverage several prior authorization solutions.
Next, the authors noted that upon ePA EHR integration, providers may have faced a learning curve that hindered them from using ePA to its fullest capacity. For instance, prior authorization denial in-basket messages may not have been read immediately.
However, the authors noted that over time, these barriers could diminish with use.
Strategies for improved ePA utilization, integration
The JAMA researchers suggested that reducing fragmentation between payers and ePA could reduce the potential misfiring of medications, especially because payer information may not have been up-to-date.
“This may be increasingly possible as integrated delivery networks and risk-bearing contracts with insurers grow, due to focus on the use of technology to improve care coordination,” they explained.
Additionally, integration of data and processing with pharmacies into the EHR may enhance efficiency.
“These findings offer several broader lessons for health information technology interventions, particularly the importance of testing whether the interventions that are supposed to improve care actually do,” the study authors explained.
“Health information technology represents just one type of tool, and, in this case, computerizing the prior authorization process may not have actually addressed the barriers to efficiency, especially when not all payers participate in the technology,” they continued.
The researchers suggested that future studies investigate whether different ePA implementation processes could improve efficiency.
“This research emphasizes the need for rigorous study of these types of interventions not only to inform effectiveness within healthcare systems but evaluate any issues with implementation,” the authors explained.
ePA could benefit both providers and patients, but like many health IT initiatives, true success will only come from widespread use and sufficient provider training.