Medical device surveillance with electronic health records

Post-market medical device surveillance is a challenge facing manufacturers, regulatory agencies, and health care providers. Electronic health records are valuable sources of real-world evidence for assessing device safety and tracking device-related patient outcomes over time. However, distilling this evidence remains challenging, as information is fractured across clinical notes and structured records. Modern machine learning methods for machine reading promise to unlock increasingly complex information from text, but face barriers due to their reliance on large and expensive hand-labeled training sets. To address these challenges, we developed and validated state-of-the-art deep learning methods that identify patient outcomes from clinical notes without requiring hand-labeled training data. Using hip replacements—one of the most common implantable devices—as a test case, our methods accurately extracted implant details and reports of complications and pain from electronic health records with up to 96.3% precision, 98.5% recall, and 97.4% F1, improved classification performance by 12.8–53.9% over rule-based methods, and detected over six times as many complication events compared to using structured data alone. Using these additional events to assess complication-free survivorship of different implant systems, we found significant variation between implants, including for risk of revision surgery, which could not be detected using coded data alone. Patients with revision surgeries had more hip pain mentions in the post-hip replacement, pre-revision period compared to patients with no evidence of revision surgery (mean hip pain mentions 4.97 vs. 3.23; t = 5.14; p < 0.001). Some implant models were associated with higher or lower rates of hip pain mentions. Our methods complement existing surveillance mechanisms by requiring orders of magnitude less hand-labeled training data, offering a scalable solution for national medical device surveillance using electronic health records.

The full article can be downloaded below.  

Rural hospital closings reach crisis stage, leaving millions without nearby health care

Presidential candidates and other politicians have talked about the rural health crisis in the U.S., but they are not telling rural Americans anything new. Rural Americans know all too well what it feels like to have no hospital and emergency care when they break a leg, go into early labor, or have progressive chronic diseases, such as diabetes and congestive heart failure.

More than 20% of our nation’s rural hospitals, or 430 hospitals across 43 states, are near collapse. This is despite the fact that rural hospitals are not only crucial for health care but also survival of their small rural communities. Since 2010, 113 rural hospitals across the country have closed, with 18% being in Texas, where we live.

About 41% of rural hospitals nationally operate at a negative margin, meaning they lose more money than they earn from operations. Texas and Mississippi had the highest number of economically vulnerable facilities, according to a national health care finance report in 2016.

As rural health researchers, we’re well aware of the scope of rural hospitals woes’, which span the entire country. Struggling rural hospitals reflect some of the problems with the U.S. health care system overall, in that the poor often struggle to have access to care and there are few obvious solutions to controlling rising costs.

If 20% of America lives in a rural county, why is the nation so slow to address rural health disparities?

The full Salon article can be viewed at this link.  

Data standards may be wonky, but they will transform health care

A Each of us should reasonably expect that health systems invest as much into providing clinicians with insights to make the right diagnosis or choose the right treatment as they currently invest in determining the right ad to display on a webpage. Although that hasn’t been the case so far, there’s now an opportunity to take a quantum leap to meet that expectation.story with enormous implications for the health of all Americans is likely flying below their radar and that of their physicians. In a nutshell, it’s this: A proposed rule that sets data standards will make electronic health information more accessible to patients and doctors through smartphone-style apps and will transform health care.

Most Americans are familiar with this scenario: During the “conversation” parts of a medical appointment, the doctor faces a computer screen and types information into an electronic medical record system. Such systems store data on hundreds of millions of Americans.

Yet even with all of this data entry going on, it is a struggle for patients to get copies of their records, and an even bigger one to get them in useful, digital formats. Even more alarming, despite the vast amount of data collected by electronic medical record systems, little of it is used to help clinicians make decisions about their patients’ care. That’s unacceptable.

Each of us should reasonably expect that health systems invest as much into providing clinicians with insights to make the right diagnosis or choose the right treatment as they currently invest in determining the right ad to display on a webpage. Although that hasn’t been the case so far, there’s now an opportunity to take a quantum leap to meet that expectation.

The full STAT article can be viewed at this link.  

Effect of Organization-Directed Workplace Interventions on Physician Burnout: A Systematic Review

To assess the impact of organization-directed workplace interventions on physician burnout, including stress or job satisfaction in all settings, we conducted a systematic review of the literature published from January 1, 2007, to October 3, 2018, from multiple databases. Manual searches of grey literature and bibliographies were also performed. Of the 633 identified citations, 50 met inclusion criteria. Four unique categories of organization-directed workplace interventions were identified. Teamwork involved initiatives to incorporate scribes or medical assistants into electronic health record (EHR) processes, expand team responsibilities, and improve communication among physicians. Time studies evaluated the impact of schedule adjustments, duty hour restrictions, and time-banking initiatives. Transitions referred to workflow changes such as process improvement initiatives or policy changes within the organization. Technology related to the implementation or improvement of EHRs. Of the 50 included studies, 35 (70.0%) reported interventions that successfully improved the 3 measures of physician burnout, job satisfaction, and/or stress. The largest benefits resulted from interventions that improved processes, promoted teambased care, and incorporated the use of scribes/medical assistants to complete EHR documentation and tasks. Implementation of EHR interventions to improve clinical workflows worsened burnout, but EHR improvements had positive effects. Time interventions had mixed effects on burnout. The results of our study suggest that organization-directed workplace interventions that improve processes, optimize EHRs, reduce clerical burden by the use of scribes, and implement team-based care can lessen physician burnout. Benefits of process changes can enhance physician resiliency, augment care provided by the team, and optimize the coordination and communication of patient care and health information.

The full article can be downloaded below.  

Implementing Real-Time Clinical Decision Support Applications on OpenICE: A Case Study Using the National Early Warning System Algorithm

This paper presents the design and implementation of a software application, called MEWS, that implements the Royal College of Physician’s National Early Warning (scoring) System on the OpenICE interoperable platform. The MEWS app, as a real-time clinical decision support (RT-CDS) application, does not require the use of an Electronic Health Record System to support its operation. Instead, it is able to receive patient vital sign measurements from any patient physiological monitoring device connected to OpenICE, irrespective of the device manufacturer. Based on the received vital signs, MEWS calculates an overall score indicating the monitored patient’s current status and is intended to direct clinicians to patients showing signs of deteriorating conditions and hence needing immediate intervention. The implementation and deployment of the MEWS app on OpenICE presents a preliminary step to understand the challenge of establishing (data) interface protocols to enable medical device interoperability generally, and for RT-CDS applications in particular, and to establish requirements for bridging the gap of current industrial standardization activities in addressing this challenge.

The full article can be downloaded below.  

Looking Through a Different Lens: Patient Satisfaction With Telemedicine in Delivering Pediatric Fracture Care

Telemedicine may transform health care by overcoming geographical and travel-associated barriers to patient care. This study assesses patient satisfaction with telemedicine for fracture care.

Two groups of patients were compared from suburban/ rural Pennsylvania. One group reported to a regional medical center for real-time video consultation with a pediatric orthopaedic surgeon facilitated by a physician’s assistant. The other group underwent conventional outpatient clinic visits at a tertiary care hospital. The distance between the tertiary care hospital and the regional medical center was 69 miles. New or follow-up fracture patients not living in the vicinity of either medical center were included. A satisfaction survey and questionnaire were administered to both groups at the end of their visit.

One hundred sixty-seven patients returned the questionnaires (66 conventional and 101 telemedicine). Telemedicine visits decreased indirect and direct costs (P = 0.032). Travel costs and travel times were lower (P , 0.001) in the telemedicine group. Patient satisfaction was similar. Only 8 of 101 patients in the telemedicine cohort preferred their next visit to be a conventional follow-up.

Utilization of video consultation and trained physician assistants to provide pediatric orthopaedic care across suburban/rural areas can increase pediatric orthopaedic surgeon access and decrease travel costs while maintaining patient satisfaction.

The full article can be downloaded below.  

An awakening in medicine: the partnership of humanity and intelligent machines

In concurrence with the introduction of the internet, widely networked computers, and the collection of large amounts of digital data, the medical profession as a whole has become more self-aware and self-critical. It is increasingly apparent that suboptimal decisions are made at times and, on other occasions, are fatally flawed. Most clinical decisions rest largely on what is referred to as the art of medicine: that is, decision-making that is based on inconsistent and incomplete provider knowledge; variable skills, training, and experience; and last but not the least, an array of biases. Unsurprisingly, the result is an unacceptable degree of care variation that is not explained by patient factors or the clinical context. Every minute, a medical decision is being made somewhere that could be more informed, more objective, more precise, and more safe. How does medicine move on to adapt to an era of big data and a need to make consistent, data driven, evidence and value-based clinical decisions?

The full article can be downloaded below.  

Spinning the lens on physician power: narratives of humanism and healing

Divisive, disabling and dangerous power has featured heavily in health professions literature, social media and medical education. Negative accounts of the wielding of power have discoloured the lens through which the public sees medicine and distorted the view of a profession long associated with healing, humanism and heart. What has been buried in the midst of this discourse are positive accounts of power where the yielding of power is encouraging, empathetic and empowering. This article offers three personal vignettes illustrating the ability of power to positively affect lives in the practice of medicine, for patients and doctors alike. More of these stories are needed to uplift and rebalance the conversation on physician power and how it can be used for good. It is necessary to provide a narrative framework of what it looks like to be a healer and a humanistic doctor to satisfy the general public through a commitment to cultivate multidimensional future healthcare providers.

The full article can be downloaded below.  

Physician Burnout: Are Too Many Patients Making Doctors Sick?

It’s common knowledge that doctors work long hours. From late nights studying in medical school to the 28-hour shifts many young doctors experience during residency, physicians are conditioned to push their bodies and minds to the extreme in pursuit of a noble goal – making patients better. What if, however, those very patients are adversely affecting their doctor’s well-being?

The U.S. is facing what has been called a severe and growing epidemic of physician burnout, with nearly half of all clinicians reporting feelings of exhaustion, depression, depersonalization and failure. The epidemic threatens to affect not only the health of physicians but that of patients as well, since tired and overworked doctors are inherently less engaged and more prone to mistakes. In fact, a recent Stanford study found that burnout influences quality of care, patient safety and patient satisfaction – and that medical errors double among physicians suffering from the syndrome. With over 1.1 million physicians in the U.S. and a rapidly growing pool of patients, physician burnout is everyone’s issue. 

How did we get here and what can be done to reduce the burden placed on physicians?  

The full Forbes article can be viewed at this link.  

AI needs patients’ voices in order to revolutionize health care

Patients’ stories — what doctors call patient histories — are the bedrock of medicine. “Listen to your patient; they are telling you the diagnosis,” an aphorism attributed to Dr. William Osler, the founder of modern medicine, still holds true today. The disappearance of patients’ stories from electronic health records could be one reason that artificial intelligence and machine learning have so far failed to deliver their promised revolution of health care.

The medical industry’s fascination with artificial intelligence is understandable. Advancements in medicine have dramatically improved patient outcomes, and there is every reason to believe that machine learning, deep learning, artificial intelligence, and the like will do the same. But before we jump on the AI bandwagon, I offer this caution: consider the source of the data it is dependent on.

The full STAT article can be viewed at this link.