The spread of COVID-19 gave health IT experts another reason to implement patient travel history into the EHR.
An EHR extraction system could be the key for translating unstructured text about patient travel history into actionable health data, according to a study published in JMIR Publications.
Without an automatic extraction system, clinicians would have to manually review travel charts, utilize a specific EHR system that imposes travel history documentation, or ignore travel history completely.
The spread of COVID-19 provided urgency to integrate travel history information into the EHR. Implementing travel history into the EHR can help put infectious symptoms into context for clinicians.
If implemented as a vital sign, along with temperature, heart rate, respiratory rate, and blood pressure, travel history can add to detailed patient data, prompt further testing, and spark protective measures for individuals who come into contact with the patient.
EHRs can also integrate with travel history to customize immediate diagnosis for returning travelers, similar to how cardiovascular risk calculators can show the patient a personalized list of potential lifestyle changes.
Although the Department of Veterans Affairs (VA) currently integrates travel history into patient EHRs, the research team evaluated the feasibility of annotating and automatically extracting travel history mentions in clinician notes, which present as unstructured text, across disparate healthcare facilities to respond to public health emergencies.
The researchers created a standard for patient travel history EHR detection through manual patient chart abstraction and developed an automatic text extraction pipeline.
Out of over 4,500 annotated EHRs, 58 percent contained travel history mentions, 34.4 did not contain travel history, and the remaining were undetermined. The research team said automated text processing accuracy and clinician burden levels were acceptable enough to provide rapid screening in the future.
Travel history varied from semi-structured questionnaires, such as “Have you visited a region known for Zika transmission?” to “Has the patient recently returned from Brazil, Mexico, or Miami” to “Went to Europe.”
Several researcher disagreements stemmed from differing attribution of past affirmed travel as opposed to future or hypothetical travel.
For example, one researcher marked “Traveling to visit sister in Hungary in May” as future travel, while another marked this example as past affirmed travel.
Additionally, the study authors expected military deployment locations, but the patient did not always deploy. Some EHRs would display “Service Era: Vietnam” but that does not mean the patient traveled to Vietnam.
“Location agreement was calculated for all annotated location text spans and required an exact match of text offset and negation status,” researchers explained. “Any difference in status was counted as a disagreement and any difference in text span was considered as a separate annotation element. Record agreement combined any annotated location status so that each snippet would be assigned a class of either no travel mentioned, negated locations, positive locations, or mixed.”
The research team identified 561 distinct locations over 8,127 location spans.
“Our findings demonstrate that training an accurate model to extract travel mentions is feasible in an automated system,” wrote the study authors. “Both labeled sets and the modeling approaches were chosen to minimize development time and computational resources necessary to continue surveillance in day-to-day operations. The baseline comparison presented here is a simplified evaluation, but it demonstrates that general-purpose geoparsing solutions alone result in lower precision.”
Because the research team developed the technology three years before COVID-19, its use during the spread of the coronavirus was limited because travel was only a relevant risk factor during the early phases of transmission, the study authors wrote. When researchers developed the tool, its capabilities were primarily concerned with individuals bringing infectious disease into the United States.
“The Centers for Disease Control and Prevention (CDC) guidance for Persons Under Investigation on February 12, 2020, included explicit mention for travel to Wuhan or Hubei Province,” the study authors explained. “By March 4, the CDC removed these criteria and instead encouraged clinicians to use best judgment for virus testing. In some surveillance efforts, travel history was deemed to be less important in risk assessment once community acquisition increased.”
Researchers could leverage the method in the future to prevent and contain another COVID-19 spread and the spread of other infectious diseases.
Over half of acute care hospitals reported engagement in all four domains of EHR interoperability in 2019.
EHR interoperability among acute care hospitals increased from 2018 to 2019, according to the 2019 American Hospital Association IT Supplement published by the Office of the National Coordinator (ONC) for Health IT.
Interoperability continues to be a challenge for health systems across the country. Still, the report found that over half of acute care hospitals participated in all four interoperability domains (send, receive, find, and integrate). This number has steadily increased from 26 percent in 2015, to 29 percent in 2016, to 41 percent in 2017, to 46 percent in 2018, and then to 55 percent in 2019.
Roughly 70 percent of hospital respondents integrated data into the EHR, which was a considerable increase from 2018. Furthermore, 75 percent of hospitals reported finding or querying patient data from outside hospitals.
The number of small and medium to large hospitals with 2015 Edition Certified EHR technology increased from 2018 to 2019.
The national average of US non-federal acute care hospitals jumped from 83 percent in 2018 to 91 percent in 2019. Nearly 90 percent of small hospitals had certified EHR technology in 2019, while 95 percent of medium to large hospitals adopted certified EHR technology. The latter was at 67 percent just two years ago.
Health information exchanges (HIEs) are crucial for connecting communities and ensuring patient medical records are available at all times. While interoperability remains a major issue for HIE implementation, HIE connectivity is becoming more prevalent across the country.
According to the survey, there was nearly a 40 percent increase in the proportion of hospitals that used a national network to find patient data between 2018 and 2019.
On the other hand, state, regional, or local HIEs were the most common method utilized by hospitals to find patient data from outside providers. This percentage increased from 46 percent in 2018 to 53 percent in 2019.
A little over four in 10 hospitals utilized an interface connection, such as an HL7 interface, between EHR systems. A similar percentage used provider portals or national networks to find patient data in 2019.
Hospitals reported a 4 percent decrease from using other healthcare organization HER logins credentials. This percentage fell from 31 percent in 2018 to 27 percent in 2019.
National network participation dramatically rose from 2018 to 2019.
Nearly 70 percent of hospitals participated in any national network, and almost 50 percent of hospitals participated in more than one national network. These percentages increased from 57 percent and 33 percent, respectively.
DirectTrust and Sequoia Project’s Carequality connections both increased more than 10 percent.
The report found that 80 percent of medium to large hospitals participated in either a state, regional, or local HIE network. This compared to only 68 percent of small, rural hospitals that participated in HIE networks. Less than 50 percent of small, rural, and critical access hospitals (CAHs) participated in national as well as state, regional, or local HIE networks.
Small, rural, and CAHs reported participating in neither a national HIE, a state, regional, or local HIE compared to larger or more suburban hospitals.
Hospitals reported patient data exchange barriers in 2019. Roughly 70 percent of hospitals noted information blocking barriers, such as exchanging patient data across separate EHR vendor platforms and attempting to exchange patient data with outside providers.
In March 2020, ONC released the next phase of the 21st Century Cures Act, the interoperability rule, which primarily focused on interoperability and patient information blocking. The published rule aims to drive patient access and sharing of patient electronic health information, allowing individuals to coordinate their own healthcare.
“ONC is working to improve the flow of EHI between patients, health care providers, and health information networks,” concluded ONC.
eHealth Exchange users reported high customer satisfaction across multiple areas, including patient data exchange and interoperability.
eHealth Exchange customers said the health information exchange (HIE) enables patient data exchange across state and regional HIEs and public health agencies, according to a recent KLAS First Look report.
Although a few respondents reported a lack of consistent support and platform navigation, all respondents said they would purchase the product again in the future.
eHealth Exchange, the nation’s largest HIE, connects to 75 percent of all US hospitals, over 60 regional or state HIEs, and four government agencies, including Veterans Affairs (VA) and Department of Defense (DoD). KLAS interviewed 19 individuals from 19 unique organizations, made up of HIEs, clinics, hospitals, and various health systems to assess client satisfaction and use.
Nearly every respondent said the HIE supported integration goals, promoted needed functionality, and would recommend the service to a friend.
Sixty-seven percent of respondents said they were highly satisfied with the HIE overall, and 28 percent said they were satisfied. Meanwhile, only 5 percent of eHealth Exchange customers reported dissatisfaction with the HIE.
Following integration, 46 percent of respondents said they saw immediate results and an equal percentage saw results within six months. Less than 10 percent said they saw results between six and 12 months.
Over 60 percent of respondents said eHealth Exchange is easy to scale, while only 7 percent said it was not scalable. A little over 30 percent of customers reported it was scalable with effort.
When it comes to connectivity, 92 percent of respondents said they could connect with VA and DoD, 69 percent said they could connect with the Social Security Administration (SSA), 69 percent reported connectivity with 60 state and regional HIEs. In comparison, only 38 percent of respondents reported connectivity with public health agencies, and 23 percent said they could connect with the Indian Health Service (IHS).
The respondents reported several strengths, but most agreed that interoperability, especially with SSA and VA connections, was most beneficial. Customers also reported seeing value with the organization and most said the HIE works as well as expected and promoted.
“We wanted to be able to exchange the information and utilize the system to exchange with our state reporting agency,” an anonymous manager told KLAS. “The system allows us to do that work easily and successfully. With the SSA, we have been hugely successful with our information exchange. There is a fast turnaround on the disability claims because the SSA can electronically obtain the information from us quickly.”
However, some respondents said the HIE sometimes lacks health IT support and the platform can be difficult to navigate.
“eHealth Exchange’s support is confusing. Sometimes when I try to seek out information, I feel like there are a couple of different steps to take before I can find out whether I have all of the information that I need,” described an anonymous application manager.
Mike Davis of the KLAS Research Arch Collaborative said eHealth Exchange could address a few key interoperability areas.
“Land mines for interoperability include the ability to provide positive patient identification when exchanging patient information,” Davis said. “How many Tom Smiths are there? The other challenge is creating an effective minimum discrete data set that can be used to improve care management and analytics. CDA information helps, but discrete patient data would be more useful.”
Overall, Davis said eHealth Exchange has long-term viability across the healthcare sector.
“Promoting interoperability is a key focus of CMS to drive higher levels of patient care quality and safety,” Davis explained. “The pandemic exposed the need for better information sharing between care providers. eHealth Exchange’s ability to provide an interoperability solution that can be quickly implemented with standard exchange protocols and partners sets them up for long-term success.”
Researchers found a 10.1 percent transmission risk percentage with EHR data, which was on par with traditional contact tracing methods.
Extracting household patient EHR data proved to be as effective at tracking transmission as COVID-19 contact tracing, according to a research letter published in JAMA Network Open.
Because COVID-19 is primarily transferred by person-to-person contact through respiratory droplets in households, researchers aimed to find out if healthcare professionals could leverage EHR home address data to identify COVID-19 risk factors and estimate transmission risk.
Researchers analyzed EHR COVID-19 data between exposed children and adults from Mass General Brigham between March and May 2020. Researchers compiled data from all patients registered at the addresses of index cases but excluded patients who did not have at least one health system visit within the last 60 months.
Overall, researchers evaluated 7,762 index cases between 17,917 at-risk individuals. Using EHR data, researchers found a 10.1 percent overall household infection risk, or 1,809 COVID diagnoses. This transmission risk percentage was consistent with traditional contact tracing, the study authors wrote.
“Independent factors significantly associated with higher transmission risk included age greater than 18 years and multiple comorbid conditions,” the study authors wrote. “In sensitivity analyses limiting the maximum size of the household to as small as 2 persons, the calculated transmission risk increased to only 13.8%.”
Although EHRs proved to be useful to track COVID-19 patients, relying on home address EHR data was also a major limitation, wrote the research team. The study authors said leveraging home address data could lead to undercounting and overcounting household members.
There currently isn’t a great fix for that issue, but nevertheless, the researchers contended the EHR-based strategy was effective.
“Although we acknowledge that contact investigations are the standard approach for estimating household transmission risk, we believe that the consistency of our results with these approaches suggests that our approach may provide a more efficient method for risk estimation and household contact identification,” the study authors explained. “Moreover, our sensitivity analysis indicated that the results were qualitatively similar when restricted to smaller households.”
Overall, EHR data could support COVID-19 control efforts, so as long as adequate infrastructure is in place to put this to scale.
Developing, implementing, and assessing a plan for EHR systems and public health information systems require a boost in health IT, governance, and overall strategy, according to a separate study published in The Journal of the American Medical Informatics Association (JAMIA).
COVID-19 response efforts have included the collection and analysis of individual and community EHR data from healthcare organizations, public health departments, and socioeconomic indicators. But those resources haven’t been deployed the same way in all healthcare organizations, the researchers stated.
An analysis of COVID-19 response efforts from 15 healthcare organizations that saw delays in correctly understanding, predicting, and mitigating the COVID-19 spread highlighted some pitfalls.
The research team determined a number of steps that could help organizations in the current and future steps to mitigate the pandemic. The researchers’ recommendations may also help in future public health crises.
Health IT infrastructure needs to support public health that leverages EHR systems and associated patient data, but it cannot be developed and implemented right away, the researchers wrote.
Additionally, having better control of the timeliness of data analysis will be essential. Because analytic methods do not always give real-time results, it is easy to overlook or underuse EHR data.
Researchers also found public health information infrastructure does not currently support larger-scale integration. Due to this issue, health organizations have been largely unable to gather information during the pandemic because it requires multiple data submissions to a number of agencies.