API adoption can streamline patient access to data, promote the use of clinical decision support tools, and boost both interoperability and patient data exchange between providers.
Application programming interface (API) adoption in healthcare will give clinicians and patients access to patient data and allow third-party applications access patient information and boost patient care, according to Ben Moscovitch, project director of Health Information Technology at Pew Charitable Trusts.
Although EHR adoption is becoming more widespread throughout the healthcare industry, interoperability and patient data sharing still pose challenges to providers.
As a result, a portion of the ONC final rule calls on medical providers and device developers to promote patient data access using third-party apps and APIs.
ONC proposed to adopt the HL7 Fast Healthcare Interoperability Resources (FHIR) standard as a foundational standard and requested comment on four options to determine the best version of FHIR to adopt.
Ultimately, ONC adopted FHIR Release 4.
Moscovitch said to address interoperability and patient data exchange challenges, the healthcare industry can adopt similar a technological approach that industries, such as finance and travel, have adopted. For example, APIs allow travel services to compare flights from separate airlines without the user visiting each website.
“If standard APIs were broadly adopted in health care, patients could access and compile their data from multiple providers while clinicians could process complicated information and make care recommendations,” Moscovitch said. “APIs would also offer other benefits, such as facilitating the exchange of clinical data among health care providers.”
BENEFITS OF API ADOPTION
Moscovitch gave three key healthcare benefits for API adoption, which include patient access to data, the incorporation of clinical decision support (CDS) tools for prescribing antibiotics, and patient data exchange between providers.
API adoption can give patients access to data. Patients can utilize APIs to track and manage their healthcare outside of the doctor’s office on their smartphone or computer.
Using APIs, providers can integrate applications into the EHR to give users a broader range of CDS tools that would allow the user to pick one that works best.
APIs can allow clinicians to pick and choose the needed or important patient information to exchange, rather than sending full clinical history
CURRENT API ADOPTION CHALLENGES
Although APIs can be beneficial, health IT professionals still face integration and usability challenges.
First, health IT developers could increase API adoption if they code them differently for each EHR system. But this approach would be limited because it would only allow adoption on one EHR system or application, Moscovitch said.
“But standards—such as the industry-developed Fast Healthcare Interoperability Resources (FHIR), which is a standard for exchanging health care information electronically—ensure easier use of APIs,” explained Moscovitch. “FHIR can offer access to individual pieces of information—such as a list of medications—instead of a broader document containing more data, some of which might be unnecessary or patients may not wish to share.”
Additionally, not all APIs can read EHR data and most do not have write access functions to input information back into the EHR. Moscovitch said once APIs receive write access functions, clinicians and patients could utilize CDS tools to edit portions of the EHR, such as changing an address, correcting errors, or updating symptoms.
“Federal regulations finalized in 2020 require the use of FHIR and expand the dataset that must be available for exchange via APIs, but the rules did not address write access,” Moscovitch explained.
“Those regulations are scheduled to take effect in 2022. Although these regulations are critical, they do not mitigate the need for significant additional policy and technology developments in order to successfully integrate and prioritize APIs within health care. Policymakers can take additional measures to promote the use of APIs and incentivize new capabilities through both legislation and additional regulation,” Moscovitch continued.
FUTURE OF API ADOPTION
Pew partnered with RTI International, a research institute, to analyze and evaluate the current and future API uses by interviewing health IT professionals.
Respondents said they most commonly utilized APIs for patient access and CDS. Some respondents even said they have not utilized APIs for other use cases, such as patient data exchange.
Next, respondents said health IT vendors vary on the permitted data elements for patient data exchange. This variance impacts the type and amount of patient information that clinicians can exchange.
Pew learned many of the terms and conditions from providers, EHR vendors, and third-party app developers were incomplete and did not have critical details, such as costs. Because of this, those three groups of individuals can dictate costs and these costs vary.
Last, the respondents said API use could improve by enabling EHR data entry, integrating applications into clinician workflow, and implementing standardized data elements.
In order to accelerate API adoption and enhance both security and usability, Moscovitch recommended lawmakers focus on developing policies that:
- Advance privacy and security
- Develop the ability to enter data into EHRs
- Grow API use for data exchange among providers
- Expand more data elements for exchange
- Monitor costs
- Protect health inequities with CDS tools
“Increased use of APIs—particularly those based on common adopted and consistently deployed standards—has the potential to make health care more efficient, lead to better care coordination, and give providers and patients additional tools to access information and ensure high-quality, efficient, safe, and value-based care,” Moscovitch concluded.
“Yet obstacles remain, such as some hospital hesitation to grant patient access to data, lack of bidirectional data exchange, confusion around the process of implementing APIs, and potentially prohibitive fee structures.”
A predictive analytics algorithm can determine which COVID-19 patients are most likely to deteriorate while in the hospital.
Using predictive analytics, researchers were able to accurately identify COVID-19 patients at risk of quickly deteriorating up to 24 hours in advance, a study published in British Journal of Anaesthesia revealed.
Throughout the pandemic, the only constant has been the virus’s wildly different impact on individual patients. While some present with only mild respiratory symptoms, others have severe illness and need supplementary oxygen or ventilators.
Researchers noted that using invasive mechanical ventilation to treat COVID-19 respiratory failure have shown mortality greater than 85 percent. However, there is little information available about which patients admitted to the hospital who don’t require mechanical ventilation will progress to mechanical ventilation. Researchers also have limited data on which clinical factors are associated with that progression.
“You can see large variability in how different patients with COVID-19 do, even among close relatives with similar environments and genetic risk,” said Nicholas J. Douville, of the Department of Anesthesiology, one of the study’s lead authors. “At the peak of the surge, it was very difficult for clinicians to know how to plan and allocate resources.”
To build the predictive analytics algorithm, researchers from Michigan Medicine looked at a set of patients with COVID-19 hospitalized during the first pandemic surge from March to May 2020 and modeled their clinical course.
The team used inputs such as a patient’s age, whether they had underlying medical conditions, what medications they were on when entering the hospital, and variables that changed while hospitalized – including vital signs like blood pressure, heart rate, and oxygenation ratio. The group aimed to discover which of these data points would help best predict which patients would require a mechanical ventilator or die within 24 hours.
Of the 398 patients in the study, 93 required a ventilator or died within two weeks. The model was able to predict mechanical ventilation most accurately based on key vital signs, including oxygen saturation ratio, respiratory rate, heart rate, blood pressure, and blood glucose level.
The team examined data points of interest at four-, eight-, 24-, and 48-hour increments to identify the optimal amount of time necessary to predict and intervene before a patient deteriorates.
While the algorithm worked best at shorter increments, researchers noted that the model maintained accuracy even two days before an adverse event.
“The closer we were to the event, the higher our ability to predict, which we expected. But we were still able to predict the outcomes with good discrimination at 48 hours, giving providers time to make alterations to the patient’s care or to mobilize resources,” said Douville.
For example, the algorithm could quickly identify a patient on a general medical floor who would be a good candidate for transfer to the ICU, before their condition deteriorated to the point where ventilation would be more difficult.
Going forward, the team expect that the algorithm can be integrated into existing clinical decision support tool already used in the ICU. In the short term, the study highlights patient characteristics that clinicians should consider when treating patients with COVID-19.
The study also raises new questions about which COVID-19 therapies, such as anti-coagulants or anti-viral drugs, may or may not alter a patient’s clinical trajectory.
“Our algorithm can be integrated into a clinical support software with the ultimate goal of identifying patients prior to clinical decompensation. Our primary target (24-hour prediction window) was selected to allow appropriate time for interventions, while still providing evidence of deterioration in dynamic features,” researchers said.
The algorithm could help providers better manage patient care and allocate necessary resources.
“While many of our model features are well known to experienced clinicians, the utility of our model is that it performs a more complex calculation than the clinician could perform ‘on the back of the envelope’ – it also distills the overall risk to an easily interpretable value, which can be used to ‘flag’ patients in a way so they are not missed,” said Douville.
At the Alliance for Better Health, an interoperable digital platform is connecting providers and community leaders to effectively address individuals’ social determinants of health.
In care delivery today, it’s well understood that a patient’s social determinants of health have a profound impact on both physical well-being and healthcare spending – sometimes even more so than clinical factors.
Evidence has shown that industrialized nations that dedicate more resources to social services than healthcare tend to have better health outcomes.
A 2019 report from the National Academies of Sciences, Engineering, and Medicine revealed that for every $1 the US spends on healthcare services, it spends about 90 cents on social services. In comparison, other industrialized countries spend $2 on social services for every $1 they spend on healthcare.
Although the importance of addressing individuals’ social needs is widely known, many providers still struggle to identify and document the non-medical factors affecting patients’ health. And even if they can, clinicians then have to clear the next difficult hurdle: referring patients to the right services that will meet their needs.
“When I was a family doctor and a patient would tell me about a need that our organization didn't address – such as housing instability, food insecurity, or transportation challenges – often I would look something up quickly on the internet and then scribble the number of some kind of service on a yellow sticky note,” Jacob Reider, MD, CEO of the Alliance for Better Health, told HealthITAnalytics.
While better than nothing, this method was not exactly effective, Reider said. There was no way for providers to tell whether a person actually received the services that were recommended to them. Clinicians also had no way of knowing if the referred organization could adequately meet a patient’s needs.
To help clinicians communicate more easily with social service entities, Reider and his team partnered with digital referral platform Unite Us, implementing their platform to develop Healthy Together, a closed-loop network that connects physicians, organizations, and community members in one platform. The tool allows Alliance to quickly identify and address social determinants of health, eliminating silos between each party.
“Healthy Together solves a problem that many communities have – and are our community was certainly one of those many,” said Reider.
“At Alliance, we recognized the gap between services needed and services provided. A referral is open forever because we were never tracking whether or how the loop was closed. Our platform makes sure that the loop does get closed.”
The first step in developing the platform was to find social organizations that would pledge to respond to requests for services, Reider noted.
“Healthy Together is a commitment from all participating organizations to send referrals and to receive referrals. If a referral is received and the services provided, the organization needs to document that in the system so that we know the referral was closed,” he stated.
“And if the referral wasn't closed for any reason, we want them to say the service wasn't provided. Either that individual didn't appear, or they were hard to reach, or perhaps that's not the right organization. We did this so we could make sure that people receive the services they need, when they need them.”
The platform also ensures that the people who administer these services can easily access and update relevant information.
“There are clinicians who access it, but more often it’s care coordinators or social workers who work in either hospitals or medical practices,” Reider said.
“Community organizations access the platform as well, including food pantries, homeless shelters, job assistance providers, and substance use disorder treatment facilities. They all have logins and they can both send and receive referrals through the system.”
With all of these different players accessing and updating the tool, interoperability is a critical part in the successful design and deployment of these platforms, Reider said.
“In communities where we need to communicate both the need and the services, you need a common infrastructure and interoperable systems to make all of that work,” he said.
Industry-wide standards are also necessary to help organizations address patients’ social determinants – a refrain that has been echoed by leaders in all sectors of healthcare.
“Step two is implementing standards so that the systems can talk to each other. Without standards, it’s really hard to make that happen,” Reider explained.
“If you're looking into a solution like this, you need to ask the question, are we using industry standards? How interoperable is the system? And that's very different from how integrated the system is. Integrations don't use industry standards, whereas interoperable components do and are much easier to maintain.”
In addition to establishing a common infrastructure and standards, leaders will need to determine how they want to measure the value of this kind of platform.
“The first step was defining success, and one definition of success is that the loop is closed and the service was provided. When we started, we were seeing service provision rates under 50 percent. That means that if I refer a hundred people for services, less than 50 of them got those services,” Reider said.
“We are now measuring that rate on a daily, weekly, and monthly basis. We're now in the upper seventies of percentages, which is significant when compared to other communities.”
Alliance decided to use another measure of success as well: the health of the community.
“We’ve started measuring how frequently individuals have to go to the emergency department for things that generally would not warrant an ER visit. An easy example is asthma exacerbation in a child. Kids shouldn't ever have to go to the hospital for asthma. If they have to go to the hospital for asthma, that means that their asthma is not controlled,” said Reider.
“If their asthma isn't controlled, then there's a problem. And likely the problem stems from their environment. Maybe they couldn’t make it to the pharmacy and get their medications because there was a snow storm and they had transportation challenges. There are social issues that have medical consequences. When we measure the medical consequences, we can get a broader perspective on whether we are succeeding.”
Through the use of platforms like Healthy Together, healthcare leaders can partner with community organizations to better understand and meet patients’ social needs.
“We developed this platform because we recognized that none of us meets all the needs of an individual. Instead, it takes a whole community to meet all the needs of a patient, and we need to share that responsibility. Healthy Together prompts folks to think more broadly about how we serve people, and then makes it easy for them to act on those expectations,” Reider concluded.
CTHealthLink added Yale New Haven Health and UConn Health to its expanding list of provider connections.
CTHealthLink (CTHL), a physician-led health information exchange (HIE) established in partnership with the Connecticut State Medical Society (CSMS), added two significant health systems to its network, Yale New Haven Health and UConn Health.
“The connections to Yale New Haven and UCONN are important milestones for Connecticut physicians and their patients,” Robert Aseltine, MD, UConn Health professor and chair of CTHL Advisory Board, said in a statement. “These connections allow Connecticut healthcare providers to gain access to critical patient data from hospitals, clinics, and practices, data that are needed to provide safe and comprehensive care to their patients.”
Yale New Haven Health and UConn Health join CVS Health and Minute Clinics, the Veterans Administration (VA), DaVita Health, the Department of Defense (DoD), Fresenius Medical Care, and Premise Health on CTHealthLink’s list of connections. The two organizations also join the state’s public health registries.
Additionally, the HIE has connected to the Carequality interoperability network and is a KONZA National Network member, enabling patient data exchange from across the country.
“Data sharing across providers and facilities is particularly important when patients are transferred from their home communities to receive care, which is becoming more common as COVID-19 strains hospital capacity,” Aseltine continued. “Having immediate access to a patient’s full medical record under these conditions may save lives and significantly improve health care for Connecticut patients.”
Adding two more connections increases patient data exchange and interoperability across the state, triggering a more effective response to certain health emergencies, including the COVID-19 pandemic.
“Connecticut cannot wait any longer for the meaningful exchange of patient data,” said Jeffrey Gordon, MD, chair of the CSMS Council. “In the face of the COVID-19 pandemic, Connecticut physicians are facing unprecedented hurdles to providing quality medical care.”
“Physicians throughout Connecticut must have the ability to coordinate not only COVID -19-related medical care, but also COVID-19 vaccinations. The time for health data exchange to be operational in Connecticut is not tomorrow, but today,” Gordon continued.
The three-year-old HIE enables clinicians, hospitals, and other healthcare providers in the HIE network to exchange patient health records, utilize data analytics tools to improve patient outcomes, and streamline clinical processes. It also grants patients access to their respective health records.
In May, the state of Connecticut signed CTHealthLink as the first member of the state’s health information exchange.
Over the past decade, state leaders found it was not easy to launch a statewide HIE. In fact, the state attempted to launch the HIE four times before adding CTHealthLink, costing the state millions of dollars.
Now established, experts say the HIE will reduce costs and improve care by eliminating the chances of duplicative testing, link several providers without going through the process of establishing a connection with each facility, and identify health trends.
It also presents financial benefits for the state. Health systems utilizing Medicaid and Medicare services can only receive payments if they can show that they are improving the quality of care and reducing hospital readmissions. Better care coordination, enabled by a functional HIE, could help organizations accomplish those clinical quality metrics.
Looking forward, the two organizations plan to improve patient care, boost interoperability throughout the state, and enhance Connecticut’s healthcare delivery system.
Since the HIE is still in its early stages, Aseltine said it will expand upon partnerships with other national exchanges in a way that provides a powerful demonstration of the scale they can achieve together.
“This echoes how important health data exchange is for physicians across the state of Connecticut,” added Layne Gakos, JD, General Counsel of Connecticut State Medical Society.
“We're excited to be where we are right now and to be the first one that's up and running. It's taken a lot of work. But it's been rewarding, and we believe it's going to be rewarding moving forward as the state moves forward in developing its HIE.”