Samara Rosenfeld 

Personal digital health profiles show promise in a step-wise approach to chronic disease prevention, according to research published in the journal BMC Public Health.
Of the 22% of patients advised to get a health check at their general practitioner, almost all of them (19%) did. And of the nearly 25% of patients advised to schedule an appointment for behavior-change counseling at their municipal health center, 21% took the advice.
Participants who had fair or poor self-rated health, a body mass index above 30, low self-efficacy, were female, non-smokers or who led a sedentary lifestyle were more likely to attend targeted preventive programs.
A Danish research team implemented a step-wise approach in the Danish primary care sector for the systematic and targeted prevention of chronic disease.
The researchers designed an early detection and prevention intervention for Type 2 diabetes mellitus, cardiovascular disease and chronic obstructive pulmonary disease (COPD). The intervention had two elements:

  1. General intervention. This involved the creation of a personal digital health profile for each individual in the study population.
  2. Targeted intervention. This intervention included a health check at the general practitioner or behavior-change counseling at a municipal health center. The targeted interventions were for patients who were deemed likely to benefit from such interventions due to their high overall risk of the chronic conditions or because they regularly engaged in health-risk behaviors.

More than 8,800 patients between the ages of 29 and 60 from 47 general practitioners participated in the study.
Participants received a digital invitation and consent form prior to the study.
The aims of the digital health profiles were centered on four key ideas:

  1.  To motivate and enable patients who otherwise would not have taken up a targeted intervention like the one offered.
  2. To motivate and enable patients with poor self-management skills to take up the targeted intervention.
  3. To guide patients with good self-management skills to change their own behavior.
  4. To keep the healthy and low-risk population from demanding unnecessary health checks from their general practitioner. 

Digital health profiles contained clear and concise personalized health information and recommendations for further action. Recommendations included advice to take up a targeted preventive program, facts about health-risk behavior, information about the positive impact of behavior-change and a personalized list of available and relevant behavior-change interventions.
Researchers created the digital health profiles based on the patients’ electronic health records and questionnaire information, which included health-risk behaviors, family history of disease, early symptoms of COPD and osteoarthritis.
Participants were then stratified into one of four groups.

The first group consisted of patients who had treatment for hypertension, hyperlipidemia, Type 2 diabetes mellitus, cardiovascular disease and/or COPD at their general practitioner. The patients in this group did not have any additional intervention beyond usual care.

 Patients in the second group were those would likely benefit from a health check at their general practitioner determined by three risk algorithms for the chronic conditions. These patients were advised to schedule a check with their practitioner, which included a medical examination and subsequent health counseling session.

In the third group were patients who were not flagged by the risk algorithms but had a body mass index above 35 and/or reported they regularly engaged in health-risk behavior. Risky behaviors included daily smoking, high-risk alcohol consumption, unhealthy dietary habits and sedentary leisure time activities. Patients in this group were advised to schedule a 15-minute telephone-based counseling session. These could be requested online through the digital health profile.

 Patients with a healthy lifestyle and no need for further intervention made up the fourth group.

Deciphering the Findings

Women and participants with sedentary leisure behavior were more likely to attend a health check at their general practitioner. General practitioner attendance rates revealed that physical activity was the strongest predictor of attendance. The attendance for those with sedentary behavior was 28%, while those who exercised during down time was 17%.
Of those who had fair or poor self-related health, 20% of smokers attended the telephone-based counseling session and 42% of the non-smokers attended.
Overall, the attendance rate for patients who were advised to schedule a health check and for those who were advised to schedule a counseling session was near 20%.
“This study suggests that a personal digital health profile may help foster a more equitable uptake of preventive programs in the primary care sector — especially among patients with lower self-efficacy and fair to poor self-related health,” the authors wrote.
The researchers suggest that further research is needed on personal digital health profiles.

Jared Kaltwasser

The premise of clinical decision support (CDS) software is clear: Use technology to leverage the power of big data to improve patient care and, theoretically, drive down costs. But the technology is, in many ways, still at the starting gate, in part due to technical and bureaucratic hurdles and a lack of scientific data surrounding its use.

Now, a major academic medical center, the University of Virginia Health System, is launching a concerted effort to find ways to integrate CDS into its organization. The evaluation is part of a larger effort at the health system to boost value-based care. It could prove to be a model to help other medical centers take the leap.

Joseph Wiencek, Ph.D., an assistant professor of pathology at UVA, said the health system is looking at products developed in house and elsewhere.

“We have several rules built from our internal analytics/informatics teams but would like to see if there is any value in external support that is becoming more widely available,” he told Inside Digital Health™. “These decision support tools would likely target high-volume, low-cost tests as well as high cost, low volume.”

The team remains in the evaluation and “data-crunching” phase, but he said one important element of the evaluation will be to get buy-in from the health system stakeholders.

“Since we are an academic teaching hospital, it is important to research and strategically partner with service lines and department leads to make sure we achieve lateral buy-in from our colleagues,” he said.

He and teammate Andrew Parsons, M.D., MPH, an assistant professor of medicine at UVA, recently wrote about how reduce laboratory costs, noting that “low-value care” — care that could be eliminated without harming patient safety — costs the U.S. healthcare system an estimated $800 billion each year.

They wrote that integrating decision support tools into electronic health record software could help reduce unnecessary costs. However, given the relative novelty of these types of products, health systems should evaluate them carefully before integration.

Wiencek told Inside Digital Health™ that there simply isn’t much in the way of scientific literature when it comes to the effects of CDS.

“I think the lack of peer-reviewed literature is an enormous impact,” he said.

While the technical work that’s required to implement the systems can be difficult, Wiencek said scientific evaluation will also be key.

“It truly is a multi-modal approach, and support from your colleagues and evidence-based literature will really be the only way these tools will succeed,” he said.

Ultimately, the success of any decision support technology will be about more than just cost. For some institutions, that could be the benchmark. But for others, victory might resemble patients receiving the right test at the right time, he said.

In fact, a recent study by researchers at the Massachusetts Institute of Technology found that CDS helped providers make more appropriate decisions but didn’t result in cost savings, in part because sometimes the most appropriate decision was a high-cost test.

Wiencek said while cost is a major issue in healthcare generally, he doesn’t think people should overemphasize its importance. Besides, he said, the cost implications of better decisions might not appear in the short term.

“Doing the right test for the right patient will lead to better clinical decisions, and patients will get the care that they need or be diagnosed faster,” he said. “If this happens, costs will fall, too. I’d like to see these types of tools lead us in that direction.”

Wiencek offered no timeline as to when UVA will complete its evaluations, though he said the team is proceeding at a “steady pace.” The health system is currently working with a single external vendor, though he said they have been approached by several others.

Samara Rosenfeld

The U.S. Food and Drug Administration (FDA) has released a letter in support of open data sharing through efforts like the Patient Safety Movement Foundation’s Open Data Pledge, according to an announcement today.

While the FDA did not sign the Open Data Pledge, which is meant for companies, it supports the principles of it.

“We encourage policymakers, healthcare entities including hospitals, digital health technology companies, medical device manufacturers and others to share data to support patient safety,” Jeffrey Shuren, M.D., J.D., director of the FDA Center for Devices and Radiological Health, wrote in a letter to Joe Kiani, founder of the Patient Safety Movement Foundation, which aims to eliminate preventable deaths.
The Center for Devices and Radiological Health supports data sharing to protect patients and promote public health, Shuren noted. He wrote that openly sharing data with patients, providers and researchers could:

  • Empower patients to participate in the development and evaluation of medical devices that meet their needs
  • Facilitate medical device surveillance and help identify and prevent adverse effects
  • Increase the FDA’s knowledge of the benefits and risks of technologies, which could enhance patient safety

When individuals and companies sign the Open Data Pledge, they agree to allow anyone who wants to improve patient safety to interact with their products and access the data that are collected. The agreement is subject to privacy laws.
“We are grateful for FDA’s recognition of our work and thank the nearly 100 enlightened companies that have signed the Open Data Pledge,” Kiani said. “Patient harm can be avoided with predictive algorithms and decision support using data from the myriad of products that touch the patient.”

Jay Haughton, RN

All across the United States, the delivery of care is stressful for both patients and doctors. Patients want better access to their information and to be actively engaged in their own care. Doctors want to spend more time with patients but face intense time pressures.

According to a 2018 survey, 60 percent of doctors report they spend between 13 to 24 minutes on average with each patient. During some of these precious minutes, they are struggling to follow electronic health record (EHR) requirements and processes. Current EHRs are not work-flow confluent as the patient is asked the same questions multiple times. Providers struggle with fragmented systems that require separate log-ins, and many of the processes are simply not clinically useful.

Click fatigue and multitasking can lead to mistakes. It’s estimated that multitasking immediately decreases productivity and accuracy by 40 percent. Additionally:

  • 70 percent of doctors using EHRs attribute the bulk of their administrative burden to the software, according to a 2017 study. However, doctors’ opinion of EHRs improved when their medical institutions made efforts to optimize how the software is used.
  • 92 percent of clinicians say lengthy prior authorization protocols have impeded timely patient access to care and harmed patient clinical outcomes, according to an American Medical Association survey.
  • 89 percent of senior patients (age 55 and older) surveyed said they want to manage their own healthcare—and will require better health technology access to do so.

A more thoughtful EHR can deliver a better experience for both sides. What’s needed is a tool that leverages cutting edge technology to deliver better usability, flexibility, and value, designed by clinicians who truly understand the healthcare workflow. For patients, an EHR should provide a patient portal that integrates data into a clinical registry, allowing access to all of their data in a single location.

Electronic enterprise-wide data is essential to manage the patients doctors care for every day. Unfortunately, current EHRs typically do not deliver the insights or tools providers need to manage their high-risk patients when they are not in the hospital. Even if the specific EHR does offer such population health management capabilities, it again requires excessive amounts of manual data access and manipulation, leading to time wasted and higher costs.

With the introduction of Medicare Access and CHIP Reauthorization Act (MACRA) and the 2015 Merit-based Incentive Payment System (MIPS), along with APMs, providers are being reimbursed by performance versus fee-for-service. One of the performance measurements is Promoting Interoperability (formerly Advancing Care Information), and new CEHRT qualified EHR systems are ready to meet this new requirement.

To improve outcomes via improved data sharing and automation, the next generation of EHRs offer these four improvements:

Usability: Make key clinical data easily available by streamlining workflows and navigation with fewer clicks and a common patient banner, which puts certain patient information in the same location regardless of application. This empowers providers to focus on the work that matters most. The EHR should integrate and aggregate data into a clinical registry, allowing patients to access all of their data from a single portal.

Flexibility: Care organizations have numerous regulatory requirements and certification standards. A better EHR allows organizations to create additional fields to meet the unique needs of their workflow. Organizations can define and link fields to medical code sets to stay current with ever-changing regulatory requirements and advancements in healthcare information technology.

Technology: Leverage the latest technology for a scalable and portable solution that meets doctor and patient needs today, while avoiding vendor lock and enabling constant improvements.  Solutions that use cloud-based infrastructure can do this while keeping patient data secure and up- to-date.

Value: Next generation  EHR solutions do not need to be costly. They can provide greater value—including all implementation and support costs—without sacrificing functionality. Cloud-based infrastructure eliminates the demand for large in-house IT staffs and data storage, allowing outsourced IT to handle the heavy lifting.

Both sides of the healthcare equation are under strain, and it doesn’t have to be this way. Technology has created the challenge, and better technology can provide the solution. It’s past time to fulfill the original promise of EHRs—reducing risk, improving efficiencies, and supporting high quality patient outcomes.

In a clinician survey, researchers found healthcare organizations that invest in EHR training report higher levels of EHR user satisfaction.

Kate Monica 

Administering sufficient EHR training to clinicians may be the key to improving rates of EHR user satisfaction, according to a recent clinician survey by the KLAS Arch Collaborative.

Researchers including Julia Adler-Milstein, Christopher A. Longhurst, and others analyzed survey data from the Arch Collaborative from tens of thousands of EHR users to identify the factors that influence whether a user will report higher levels of EHR satisfaction.

“We as an industry have an opportunity to improve EHR adoption by investing in EHR learning and personalization support for caregivers,” wrote researchers in the study.

“If health care organizations offered higher-quality educational opportunities for their care providers — and if providers were expected to develop greater mastery of EHR functionality — many of the current EHR challenges would be ameliorated,” they stated.

Researchers noted during their review that users of the same EHR system often report significantly different experiences with the software. Less than 20 percent of variation in user experience could be explained by EHR software type, while over 50 percent of variation resulted from differences in the way clinicians interacted with their system, researchers wrote.

“Similarly, within the seven EHR solutions measured, a very unsuccessful provider organization was identified in each customer base, and a successful customer was identified in six of the seven customer bases,” researchers stated.

Healthcare organizations interested in improving rates of EHR satisfaction among clinicians are more likely to see improvements if they invest in EHR training and assist users in becoming more adept at navigating EHR technology rather than investing in a new EHR implementation.

“In the Arch Collaborative large dataset, the single greatest predictor of user experience is not which EHR a provider uses nor what percent of an organization's operating budget is spent on information technology, but how users rate the quality of the EHR-specific training they received,” researchers wrote.

The team found 475 instances in their research in which two physicians in the same specialty used the same EHR system at the same organization and reported very different user experiences.

“In over 89 percent of these instances, the physician who strongly agreed also reported better training, more training efforts, or more effort expended in setting up EHR personalization,” emphasized researchers.

Researchers recommended healthcare industry stakeholders implement standards to ensure clinicians across organizations receive high-quality EHR training.

Recommending healthcare organizations administer at least 4 hours of EHR training may help to improve rates of EHR satisfaction industry-wide.

“Organizations requiring less than 4 hours of education for new providers appear to be creating a frustrating experience for their clinicians,” wrote researchers. “These organizations have lower training satisfaction, lower self-reported proficiency, and are less likely to report that their EHR enables them to deliver quality care.”

Standardizing the way EHR training should be structured would be more challenging. Researchers observed significant variation in the ways different healthcare organizations structure their training and educational programs, and were unable to indicate a single training program structure that achieved better results than every other.

However, researchers did note user personalization features were typically underutilized during EHR training programs.

“One of the most consistent observations seen across the collaborative organizations is how powerful EHR personalization can be and how much adoption is lacking today,” wrote researchers.

Investing resources in ongoing education that assists EHR users with system personalization may help to promote EHR optimization and improve rates of EHR satisfaction.

Looking ahead, researchers recommended healthcare organizations prioritize EHR training so that clinicians fully understand the limits of their systems and are confident in their ability to navigate the technology.

“While the Arch Collaborative research has convinced us that the greatest opportunity for progressing the value of the EHR currently lies in improved user training, this approach clearly needs to be balanced with a parallel focus on better designed and smarter software that can better meet nuanced needs of health care,” noted researchers.

“For EHR software to revolutionize health care, both the software and the use of that complicated software need to progress in parallel,” the team added.

Samara Rosenfeld

Inpatient violence risk assessments can be performed automatically using available clinical notes without sacrificing predictive validity, according to the findings of a study published in JAMA Network Open.
Researchers used machine learning to analyze clinical notes in the electronic health records (EHRs) of two psychiatric institutions to predict inpatient violence. Investigators measured each site’s area under the curve to determine predictive validity. The first site had an area under the curve of 0.797, while the second registered at 0.764, meaning it is possible to use routinely registered clinical notes for automatic violence risk assessment. 

The model performed with a specificity between 0.935 and 0.947 and a sensitivity between 0.334 and 0.336.
“Inpatient violence remains a significant problem despite existing risk assessment methods,” the study authors wrote. “The lack of robustness and the high degree of effort needed to use current methods might be mitigated by using routinely registered clinical notes.”
The research team used the first site, the psychiatry department of the academic medical center in Utrecht, Netherlands, for internal method validation. The data set consisted of 3,201 admissions of 2,211 unique patients. The second site, a general psychiatric hospital that delivers secondary care in Rotterdam, Netherlands, was used for external method validation. This data set consisted of 3,277 admissions of 1,937 unique patients.
Researchers extracted clinical notes written by psychiatrists and nurses from patients’ EHRs. The research team included notes written in the four weeks before admission up to the first 24 hours of admission. They excluded admissions with fewer than 100 words registered after 24 hours.
Reports of violent incidents helped determine the outcome for each admission. Staff members involved in a given incident at either site filled in structured information, a textual description of the incident and the severity of the incident as measured by the Staff Observation Aggression Scale-Revised.
Violent incidents included all threatening and violent behavior of verbal or physical nature directed at another person. This excluded self-harm and inappropriate behavior like substance abuse or vandalism.
Researchers examined predictive power hidden in the notes by extracting the 1,000 most frequent terms. A chi-squared test helped assess the strength of the term’s association with the outcome. The research team selected the top 10% of predictors based on their chi-squared test scores in 1,000 repeated samples.


Terms such as “aggressive,” “angry,” “verbal,” “threatening” and “irritated” can be directly associated with violence. Terms like “reacts,” “walks” and “speaks” describe behavioral cues that can be indirectly associated with violence.
Researchers then used a machine-learning approach to perform a violence risk assessment. Algorithms can detect patterns in historical data, and prediction can help the course of treatment based on those patterns.
The approach transformed clinical notes into a numerical representation and then fed the representations into a classification model.
Researchers trained the model using the internal set of clinical notes.
The risk of violent outcomes for patients with predicted high risk compared to low risk was 5.121 in the first site and 6.297 in the second.
“In the near future, we envision that further advancements towards a data-driven psychiatric practice will be made and that EHR data will become an even more valuable asset in supporting important decisions in the clinical practice,” the authors wrote.

Nathan Eddy

Pre-treatment scans were input into a deep-learning model, which analyzed the scans to create an image signature that predicts treatment outcomes.

Artificial intelligence and machine learning networks could help personalize radiation therapy for lung cancer, according to a new study by the Cleveland Clinic.

The research, published in The Lancet Digital Health, centers around an artificial neural network built with a large dataset of patients receiving lung radiotherapy.

That network, which allows each clinical center to utilize their own CT datasets to customize the framework and tailor it to their specific patient population, was built using CT scans and the electronic health records of nearly a thousand lung cancer patients treated with high-dose radiation.

The company's framework uses probability estimates to select an optimized dose that prevents treatments failures to a set level, for instance a five percent probability of failure.

Pre-treatment scans were input into a deep-learning model, which analyzed the scans to create an image signature that predicts treatment outcomes.

This image signature was combined with data from patient health records, to generate a personalized radiation dose using advanced mathematical modeling.

"AI can learn from imaging and electronic health records and make predictions about the likelihood an individual patient could fail radiation treatments," lead author Dr. Mohamed Abazeed, a radiation oncologist at Cleveland Clinic's Taussig Cancer Institute and a researcher at the Lerner Research Institute, told HealthcareITNews.

"Therefore," he said, "AI can help individualize radiotherapy treatments for patients with cancers in the lung."

Dr. Abazeed explained they will assess the transportability of the model across varied hospital systems via local implementation or using large-scale federated datasets.

In the future AI-models could be optimized based on different target populations based on ethnicities, gender or age, medical settings (community hospital or academic center) geographical locales  or even include temporally distinct populations.

"We will also test the putative supremacy of iGray--individualized dose--recommendations head-to-head with standard of care recommendations in a prospective clinical trial," Dr. Abazeed said.

In reference to those who believe AI technology still has much farther to go before it has practical applications for the medical and healthcare sectors Dr. Abazeed noted a prerequisite for scientific progress is the willful suspension of disbelief.

"In large part driven by this work, we are on the precipice for practical and innovative implementations in the highly standardized and data-replete discipline of radiation oncology," he said. 

The study follows news that French biopharmaceutical company Sanofi and tech giant Google are partnering to leverage machine learning, AI and deep analytics technologies across data sets to better understand major diseases.

Meanwhile, a new study from Innovaccer explores the ways its AI algorithms could be put to work to improve risk scoring and stratification and enhance value-based care initiatives.

Benjamin Harris

Many illnesses are easy to treat if caught in time. New EHR studies show how optimizing data can spot problems clinicians might overlook.

Early detection is a mantra in hospitals: Find a nascent condition before it can morph into something serious and you can alleviate suffering, improve care and save lives.

Symptoms can be hidden in plain sight or can be masked by other known illnesses. In these manners, thousands of patients a year fall through the cracks and become seriously ill.


Two new early detection algorithms that integrate with electronic health record data are looking to make the odds more favorable.

Johns Hopkins has developed an algorithm called TREWS that can detect sepsis in patients far more reliably than a clinician alone, and the American Medical Association has published guidelines on optimizing EHRs to identify patients at risk of diabetes.


In the case of both type 2 diabetes and sepsis, the at-risk population is broad and the conditions for both diseases are widespread: Accurately targeting those most likely to be affected takes more detailed hunting than many clinicians can do.

Johns Hopkins researchers note that one in 10 sepsis alerts from a “dumb” EHR system are true – their algorithm brings that down to one in two. Similarly, the AMA says that while many Americans are at risk of type 2 diabetes, optimizing an EHR to monitor relevant test results and make it easy for clinicians to order additional testing – both steps that empower providers to better manage their population health.

“One of the challenges traditionally with sepsis has been making sure the patient gets all of the interventions within the first three hours,” says computer science graduate student Katharine Henry, who worked on the Johns Hopkins TREWS program.


Artificial intelligence-assisted detection technologies are helping clinicians find needles in haystacks in every specialty.

When a disease like sepsis can present through very common symptoms like elevated heart rate or temperature, a doctor can’t be sure of a false positive based on a few metrics. Relying on an optimized EHR algorithm that monitors more data points than a clinician alone could, however, means the EHR does the heavy lifting on the data end and frees a provider up to take action when needed.

Similarly, much like a disease like type 2 diabetes can be brought under control through management of lifestyle, a healthcare provider can nip many instances in the bud when they manage the health of their patient population well. Providing monitoring tools and predefined courses of action through an EHR makes identifying patients and taking appropriate action that much easier.

Samara Rosenfeld 

Ordering gamma glutamyl transferase tests through the search engine function of an electronic health record (EHR) reduced orders from 36,000 to about 1,000 per month, according to the findings of a study published in the American Journal of Managed Care.

The research team found that ordering tests through the search engine function, rather than from two other lists that appear on the main screen of the EHR, led to a dramatic reduction in orders. The team returned the gamma glutamyl transferase test option to one of its original places on the main screen, which caused the numbers to spike to 18,000. When the test option returned to its original place in all the lists, the numbers jumped to more than 35,000.

The solution could lead to a reduction in costs.

Researchers set out to evaluate if changes in how laboratory requests are presented in the EHR would lead to less testing.

Gari Blumberg, M.D., from the family medicine department at Tel Aviv University, and the research team compared the numbers of gamma glutamyl transferase tests ordered at different times. The researchers changed the parameters on the main laboratory screen of the EHR.

Researchers at the laboratory at Leumit Health Services in Israel removed the testing option from the main screen in 2014. With the option removed, physicians could only order the test if it was specifically searched for.

After two months, the main screen option partially returned, then it went back to its original status.

When the gamma glutamyl transferase tests could only be ordered through the search engine function, Blumberg and the research team saw a 97.3% reduction in the number of orders.

While the number of test orders has increased since July 2015, less are ordered now compared to before the intervention. As of 2018, physicians ordered about 25 to 34 tests per 1,000 health maintenance organization members. Prior to the intervention, physicians ordered 51 tests per 1,000 members.

The study authors noted that there is a slight inconvenience when the test cannot be ordered on the main screen of the EHR. But using the search engine led to a dramatic decrease in the number of tests sent.

“Because the doctors are still able to choose the test should they feel it necessary by actively searching for it, it follows that the increased convenience was the most likely cause of the overordering, facilitated by the use of shortcuts,” the authors wrote.

The researchers wrote that while convenience is positive when it saves time, if it leads to overtesting, physicians do not gain much and are wasting money.

Kate Monica

Amidst concerns that EHR technology worsens provider burnout, one study showed 64 percent of clinicians say the systems have a positive effect on satisfaction levels.

New research suggests EHR technology may have a relatively positive reputation among healthcare professionals, with nearly 70 percent of surveyed providers reporting that EHR systems improve care quality.

This insight comes from a recent Future Health Index 2019 report commissioned by Philips.

Researchers surveyed 3,100 healthcare professionals and 15,000 healthcare consumers across 15 countries to gauge opinions of EHR technology in the current digitized care system.

While researchers found many healthcare professionals see the benefits of EHR technology and other health IT tools in clinical care, providers in most countries are not using health IT to its fullest potential.

For example, 80 percent of providers have engaged in health data exchange with other providers within their own care facility. However, only 32 percent of surveyed clinicians have shared patient health data with providers outside their facility.

Fifty-six percent of providers who do not share patient health data with outside hospitals and health systems lack the health IT infrastructure to do so. The lack of EHR interoperability between different provider systems restricts the scope of health data exchange for half of clinicians.

Fifty percent of providers also cited concerns over data privacy and security as an impediment to health data exchange with care facilities outside their health system.

In addition to this general lag in advanced health IT use among care professionals, many clinicians also struggle with EHR implementation and administrative burden.

“Many countries experience challenges with the implementation of digital health records and there is a common assumption that healthcare professionals feel these records can simply add administrative tasks to their workload,” wrote researchers in the report.

Health data exchange between patients and providers is similarly low. Only 36 percent of surveyed patients who use patient portals or other health IT regularly share their health information with their provider. Meanwhile, 26 percent of patients share health data with providers when they have a specific concern.

Despite these drawbacks, most surveyed healthcare providers agree EHR technology has had an overall positive impact on care quality.

Furthermore, 64 percent of surveyed providers said EHR technology has had a positive impact on provider satisfaction. Fifty-nine percent reported that EHR use has helped to boost patient health outcomes.

“Additionally, 57 percent of healthcare professionals report that, in the past five years, their experience has been positively impacted by having access to patients’ full medical history,” wrote researchers.

Patients who engage patient portals and other technologies to access and share their data also generally report higher levels of satisfaction.

“Those with access to their digital health record report better personal experiences in healthcare and better quality of care available to them than those who do not have access,” stated researchers.

Specifically, 82 percent of patients with access to their EHRs rate their experience with their providers as good, very good, or excellent. Comparatively, 66 percent of patients without access to their EHRs reported having a positive experience with their provider.

“The data suggests that there could be greater potential for individuals’ uptake of digital health technology and mobile health apps if usage of these technologies was more frequently recommended by healthcare professionals,” authors wrote in the report.

“There is also evidence to suggest that individuals will be more likely to use digital health technology if it’s easier to share data with their healthcare professional,” they added.

Overall, patients who access and exchange their own digital health information are more likely to have a positive perception of care quality.

“The challenge, now, is to encourage more individuals to share data with their healthcare professional, giving healthcare professionals access to more up-to-date and complete information that will allow for more coordinated patient care,” suggested researchers.

Mike Miliard

Even five years after go-live, many health systems aren't realizing the full value of their electronic health records, says a new Chartis Group report. Gaining clinical and financial ROI depends on a "sustained, organized approach."

Why aren't more hospitals realizing the benefits of their electronic health records? And what are the organizations that are capitalizing on their EHRs doing well that others should try?

Those are questions asked and answered in a new report from the Chartis Group, which surveyed some leading health systems that are leveraging their IT systems to enable big improvements in length of stay, reductions of adverse drug events, boosts in nursing efficiency, fewer unnecessary lab tests, speedier cash collections, better preventative care and more.

The report, by Douglas Thompson and Tonya Edwards, MD, shows that even five years after attaining Stage 4 on the HIMSS EMR Adoption Model, where the benefits of improved clinical decision support should begin to show up system-wide, most hospitals still haven't fully realized them.

Moreover, "increased costs of operating more sophisticated EHRs leave some further behind financially, leading critics to claim that EHRs have been a huge waste of time and money."

But it doesn't have to be that way. Indeed, the report shows how many leading health systems have realized big ROI on their EHR investments with improved patient outcomes and cost efficiencies.

"Texas Health Resources  saved an estimated $10 million from a greater than 60 percent reduction in adverse drug events at three hospitals one year after EHR go-live," for instance. "Sentara realized $57 million in annual EHR-driven savings, net of expenses, and a 50 percent reduction in hospital mortality ratio. And Memorial Hermann saved over $2 million annually from increased use of just six standardized electronic order sets."

What are they doing right that other health systems aren't?

Illustrated by a series of anecdotes from those organizations and others, Thompson and Edwards show that too few hospitals understand that extracting lasting value from IT implementations requires a "sustained, organized approach," bolstered by a "firm commitment from business leaders."

And beyond mere technology, effective deployments depend on those health systems understanding the enterprise-wider cultural shift and specific process changes that will be necessary from clinicians and staff.

It's key, they said, to stay focused on "benefits realization amid the distractions of the design, build and implementation process," not just until go-live day, but aftward, "when the next big change initiative comes along."

Based on its experience with and review of several hundred hospitals nationwide, Chartis found that the most successful ones share some EHR best practices in common.

The health systems gaining the most from their technology investments are those who have bought their EHRs with an eye toward using them for specific strategic outcomes – and know how important it is to steer system implementation and optimization toward those goals.

Those hospitals also know that the most beneficial aspects of an EHR don't happen just by flipping a switch and running the system, but when the new tool is used to help change how day-to-day work is done. It's the difference between "automation" and "innovation," said Thompson and Edwards.

They also said that "without a formal structure, benefits realization is left to chance – and benefits don’t happen by accident," pointing to the value of "dedicated resources, well-defined roles and robust governance."

It's also critical to measure the system's benefit after go-live through quality indicators, financial data and other key performance indicators, to ensure its value is manifesting itself, they said. "If you don’t measure it, you won’t achieve it."

The value of a properly deployed electronic health record system is hard to argue with. And even if some hospitals are struggling to show ROI after Stage 4 of the HIMSS EMRAM, the advantages that can be gained by pushing higher up that ladder can be substantial.

We've shown, for instance, how Los Angeles-based Martin Luther King Jr. Community Hospital joined just 6.4 percent of other American hospitals at Stage 7 by treating that goal as a formal project, with a prep team and a designated project manager to lead the charge. By optimizing its EHR, the hospital was able to make big gains on an array of clinical use cases.

The Chartis Group report shows the value of approaching EHR rollouts strategically, and part of that is a robust and clinician-focused training program. As we showed this week, physician dissatisfaction and poor user experience have less to do with software design and much more to do with the quality of system training. The better the training, the better the care delivered and the outcomes reported.

"Health system leaders should be satisfied with nothing less than achievement of the strategic clinical and business objectives of their technology investments," said Thompson and Edwards in the Chartis Group report.

"While the majority of health system EHRs have not delivered on that promise, there is ample evidence that with clear goals, careful planning, good governance, and ongoing measurement and commitment, any organization can expect real, substantial benefits from EHR use," they added. "Organizations that have already implemented or upgraded their EHRs can use the principles and methods described above to optimize their EHRs to deliver measurable benefits."

Nathan Eddy

Humanwide pilot collects data with mobile monitoring devices then pulls it into an EHR so the care team can help patients manage conditions.

A clinical trial program initiated by Stanford Medicine has deployed a data-driven, integrated team approach to predict and prevent disease and better detect overlooked health conditions and risks.


The Humanwide pilot project uses science and technology to understand each patient, from lifestyle to DNA, and apply that knowledge to transform their health.

The organization’s model combines tools of biomedicine with a data-driven, team-based approach to focus on predicting and preventing disease before it strikes.

As part of the pilot, Humanwide patients used mobile monitoring devices, including a glucometer, pedometer, scale and blood pressure cuff, to regularly measure key health metrics.

The data automatically uploaded to their electronic health records for remote monitoring by their health care team, and the care team then helps the patient manage current health conditions and address future risks through a plan aligned with his or her personal goals.


“With Humanwide, we’re able to focus on the whole human: who they are when they’re working, who they are when they’re playing, who they are when they’re at home,” Mahoney said in a statement. “This program demonstrates how we can zero in on what matters to a patient, to craft the entire care plan around their goals.”


In a paper in the Annals of Family Medicine, she and co-author Steven Asch outlined the early lessons of the year-long project, which involved 50 patients.

The paper noted encouraging the use of wearable devices in a healthy population helped identify multiple patients with early diabetes or hypertension, prompting early intervention and self-management.

The pilot participants underwent genetic assessments that gauged their risk for cancer and other diseases, and a pharmacogenomic evaluation that determined which types of drugs are most effective for their individual biology and cause the fewest side effects.

The patients also tracked key health metrics, such as blood glucose levels and blood pressure, using portable digital devices that beamed their readings back to their electronic health records for remote monitoring by care teams.

The teams, which included a primary care physician, nutritionist, behavioral health specialist and clinical pharmacist, used this data to inform each patient's care.

They also considered other factors, such as social and environmental determinants, and succeeded in identifying several previously overlooked health conditions and risks for different participants, from hypertension to heightened risk for breast cancer.

“Looking at genomic data and other factors that actually predict patient health allows us to be proactive instead of waiting for something to happen and having to react to that,” David Entwistle, president and CEO of Stanford Health Care, said in a statement. “Humanwide is an opportunity to build a deep understanding of each patient in a unique way.”

Joseph Goedert

Computer algorithms were used to analyze 29 clinical variables in UPMC’s electronic health record systems, and were able to recognize patients with sepsis within six hours of arrival.

But it took a lot of learning to reach this stage and be able to spot the signs of sepsis and the hidden subtypes of sepsis, say researchers at Pitt Health Sciences, part of University of Pittsburgh Medical Center.

“For over a decade there have been no major breakthroughs in the treatment of sepsis; the largest improvements we’ve seen involve the enforcing of ‘one size fits all’ protocols,” says study lead author Christopher Seymour, MD, an associate professor in Pitt’s department of critical care medicine. But these protocols ignore that sepsis patients are not all the same.”

In fact, use of algorithms have found four distinct sepsis types:

  • Alpha: the most common type (33 percent), comprising patients with the fewest abnormal laboratory test results, least organ dysfunction and lowest in-hospital death rate at 2 percent.
  • Beta: older patients comprising 27 percent with the most chronic illnesses and kidney dysfunction.
  • Gamma: similar frequency to beta but with elevated levels of inflammation and primarily pulmonary dysfunction.
  • Delta: the least common at 13 percent, but the most deadly type, often with liver dysfunction and shock, and the highest in-hospital death rate at 32 percent.

Having analyzed the clinical variables of 20,000 patients, researchers then studied the electronic health records of 43,000 other UPMC sepsis patients and the four findings held. The findings held again when the team studied rich clinical data and immune response biomarkers from about 500 pneumonia patients enrolled at 28 hospitals across the nation.

The next step was to apply their findings to recently completed international clinical trials that tested promising therapies, but results were unremarkable.

Sepsis recognition can be tricky, says Derek Angus, MD, senior author of the study and an associate professor in Pitts’ department of critical care medicine. Most doctors are not confused about a classic case of sepsis, but those are only a very small portion of all cases, meaning that in most other cases the recognition of sepsis is known only when it has become obvious and is too late to make the first correct treatment moves, Angus notes.

In an “early goal-directed therapy (EGDT),” an aggressive resuscitation protocol that includes placing a catheter to monitor blood pressure and oxygen levels, delivery of drugs fluids and blood transfusions was found to have no benefit following a five-year $8.4 million study. But when Seymour’s team-reexamined the results, they found that EGDT was beneficial for patients with the Alpha type of sepsis, but EGDT resulted in worse outcomes for those with the Delta subtype.

“Intuitively, this makes sense as you would not give all breast cancer patients the same treatment,” Angus explains. “Some breast cancers are more invasive and must be treated aggressively. Some are positive or negative for different biomarkers and respond to different medications. The next step is to do the same for sepsis that we have for cancer—to find therapies that apply to the specific types of sepsis and then new clinical trials to test them.”

That’s why it is imperative that patients have their vitals and labs captured upon arrival at the hospital, Seymour says. Sepsis requires the presence of organ disruption and six organs can be effected by the disease. Consequently, early treatment intervention should be done within 6 hours of suspected sepsis as the time window for capturing data at hospital presentation is 6 hours.

Capturing the vitals and labs early, with additional information available in the electronic health record, quickly helps physicians at the bedside to wrap their minds around the patient’s physiology. But now, physicians have another powerful tool at their disposal—machine learning technology.

Machine learning can find patterns that doctors cannot—much more than the three to four variables that doctors usually use. Data in the EHR can help doctors select variables to consider and then run machine learning models in collaboration with biostatisticians and computer scientists, says Seymour.

“We rely on doctors to find sepsis and quickly get patients on antibiotics, and we have machine learning and the EHR to parse out the type of sepsis,” he adds.

Samyukta Mullangi, John P. Pollak, Said Ibrahim

Health systems do not systematically collect information on social determinants of health (SDH) — the conditions in which people are born, live, grow, and age — despite knowing that they have a big impact on individual and population health. But the shift from reimbursing providers for the volume of services they deliver (fee for service) to the quality of patient outcomes relative to cost (value) is causing them to focus more on maintaining patients health and not just curing disease. This shift is causing providers to start investing in population health management strategies, which require them to better understand the local population and identify unmet needs.

The challenge is that the SDH information that physicians collect from patients and enter into their electronic medical records (EMRs) is pretty limited. Even though 83% of family physicians agree that the Institute of Medicine’s 2014 recommendation that they collect sociodemographic, psychological, and behavioral information from patients and put it into their EMRs, only 20% say they have the time to do so. But alternative means of collecting such information are emerging: smartphones, credit card transactions, and social media.

Smartphones. The Pew Research Center estimates that more than three-fourths of Americans now own smartphones. One example of how these devices could be used to collect SDH information involves the mobile applications that health systems offer to allow patients to easily book appointments or contact medical providers. These apps can also access information on patients’ location, which can be cross-referenced with rich databases like Foursquare’s book of local businesses or city-level heat maps on crime/domestic violence to understand a patient’s experience of his or her neighborhood — e.g., the availability of fresh food via local grocers or bodegas and the ability to exercise outside in relative safety. In a research setting, this type of location sharing has yielded startling insights.

In one interesting study on smoking cessation and relapses, patients’ location data, along with their self-reporting on their craving levels and smoking status, was overlaid on a point-of-sale tobacco outlet geodatabase to demonstrate that an individuals’ daily exposure to these retail outlets was significantly associated with lapses even when cravings were low. This real-time quantification about an individual’s interactions with her local environment unearthed novel influences on health behaviors that were likely invisible to the patient herself. This type of geolocation data is currently still being developed and tested in the research setting, but one day it may be used to make patients more aware of these triggers and resist unhealthy temptations.

Credit-card transactions. These are another goldmine of information that can help round out the medical record. For instance, a Gates Foundation- and United Nations Foundation-funded investigation into the economic, social, and health status of women in developing countries combined credit card records with records on their phone calls to identify patterns in people’s socioeconomic behaviors. The analysis resulted in six distinct lifestyle clusters in terms of expenditure patterns, age, mobility, and social networks. One can imagine that this type of aggregation can be useful as health systems increasingly work to tailor community and outreach programs to patients.

Credit-card statements do not contain the details necessary to generate insights ( i.e., what actual items make up a bill from the grocery store). That level of granular detail would go a long way into understanding whether patients fill their prescriptions, purchase cigarettes, or order salads. Some digital grocers (e.g., Instacart, Peapod), drug retailers (e.g., CVS, Walgreens), and payment kiosks (e.g., Square) are now emailing itemized receipts to consumers (with their consent). One group at Cornell Tech has created software tools that scrape these receipts and analyze purchases against a patient’s personal nutritional goals, a research effort with commercial potential. Such approaches not only collect information on SDH but also raise the patients’ level of awareness of the relationship between healthy behaviors and health itself.

Social media. Leveraging the willingness of people to divulge personal details on social media is yet another emerging frontierin the effort to collect SDH data. It is being used to successfully access populations that have historically been considered hard to reach: younger people, females, and low-income individuals. New features on popular sites like Facebook that allow individuals to mark themselves safe during natural disasters represent an initial foray to using this medium for gathering more SDH data. Health systems that engage patients via social media can elicit answers to questions around food insecurity, employment status, physical activity, and so on. In fact, new research suggests that many adult Facebook and Twitter users are willing to share their social media and medical data and link it with EMR data for research purposes.

Certainly, several pragmatic issues might create barriers to applying these approaches. An obvious one is privacy. More research will need to be done to ascertain patients’ comfort with novel ideas such as giving physicians access to their purchase histories or locations. It is also critical that the information gathered through these novel mechanisms not be used in a punitive manner but rather to inform clinician counseling and to support patients in their efforts to pursue healthy behaviors. Patients are not likely to share credit card or social media data, for example, if they perceive there to be a link between the information gathered and punitive responses such as the denial of insurance coverage or increased co-pays.

Another obstacle lies in the very act of obtaining consent from a large number of patients to participate in such information-gathering programs. One notable effort at Parkland Hospital in Dallas, which linked data about patients’ usage of food pantries, homeless shelters, and other social services with their medical records, found that patients were more willing to be enrolled into a digital database when asked to do so by community partners that had earned their trust rather than in the emergency room. Discouragingly, privacy concerns over the Trump administration’s policies tying social services usage with legal status has caused many undocumented immigrants to ask to be erased from social services’ IT systems.

Finally, it may be difficult to obtain buy-in from physicians who are already suffering from information overload. To overcome it, data will need to be turned into intelligent summaries with clear visuals and actionable takeaways. Additionally, clinics need to invest in support staff and ancillary services that help at-risk patients. For example, clinics can be outfitted with connections to community-based resources (housing programs, job training centers, and nutritional supplement programs). These investments will go a long way to ensuring that physicians are receptive to the work of monitoring additional data about SDH.

With these elements in place, health care systems will be able to harness digital technologies to identify the needs and interventions required to create healthier communities.

The authors wish to acknowledge Jessica Ancker for her critical review of this manuscript.

Heather Landi

An artificial intelligence tool can help diagnose post-traumatic stress disorder in veterans by analyzing their voices, a new study found.

Medical researchers and engineers designed an AI tool that can distinguish, with 89% accuracy, between the voices of those with or without PTSD, according to their study published Monday in Depression and Anxiety. The findings open up the possibility of using the AI-based voice analysis tool to diagnose PTSD more rapidly or through telemedicine.

“Our findings suggest that speech-based characteristics can be used to diagnose this disease, and with further refinement and validation, may be employed in the clinic in the near future,” senior study author Charles Marmar, M.D., from the department of psychiatry at NYU School of Medicine, said in a statement. A division of the U.S. Army supported the study.

The U.S. Department of Veterans Affairs reports that between 11% and 20% of veterans who served in operations in Iraq and Afghanistan have PTSD, while about 12% of Gulf War veterans have PTSD. Additionally, it is estimated that 30% of Vietnam veterans have had PTSD in their lifetimes.

The ability to improve PTSD diagnosis has wider implications, as more than 70% of adults worldwide experience a traumatic event at some point in their lives, with up to 12% of people in some struggling countries suffering from PTSD, according to the Sidran Institute.

According to researchers, the ability to accurately screen for and diagnose PTSD remains challenging. The diagnosis is usually based on clinical interviews or self-report measures. The gold standard for diagnosing the condition is the clinician-administered PTSD scale, a structured clinical interview to assess the frequency and severity of PTSD symptoms and related functional impairments. However, even that assessment is subject to biases. The interviews also require a lengthy visit to a clinician’s office, which some patients may be unwilling or unable to do.

An objective test is lacking, according to the researchers, who developed a classifier of PTSD based on objective speech-marker features that discriminate PTSD cases from controls. The research team included psychiatrists from New York University School of Medicine, Steven and Alexandra Cohen Veterans Center for the Study of Post-Traumatic Stress and Traumatic Brain Injury and engineers from SRI International, the institute that also invented Apple’s Siri feature.

For the study, researchers used speech samples from war zone-exposed veterans, 53 cases with PTSD and 78 controls, assessed with the clinician-administered PTSD Scale. Audio recordings of clinical interviews were used to obtain 40,526 speech features, which the team’s AI program sifted through for patterns.

The program linked patterns of specific voice features with PTSD, including less clear speech and a lifeless, metallic tone, both of which had long been reported anecdotally as helpful in diagnosis. 

The theory is that traumatic events change brain circuits that process emotion and muscle tone, which affects a person’s voice, according to researchers.

“We believe that our panel of voice markers represents a rich, multidimensional set of features which with further validation holds promise for developing an objective, low cost, noninvasive, and, given the ubiquity of smartphones, widely accessible tool for assessing PTSD in veteran, military, and civilian contexts,” the researchers said.

Other healthcare researchers are also exploring the use of voice analysis to detect and diagnose disease. A team at Mayo Clinic is exploring how to use AI-supported voice analysis as a noninvasive diagnostic tool to identify changes in tone or cadence that could potentially be predictive of an outcome, such as high blood pressure, stroke or heart attack.

The research team behind this latest study plans to train the AI voice tool with more data, further validate it on an independent sample and apply for government approval to use the tool clinically.