Blog

Author Archive

Reflecting on Wellpepper

I am a third year internal medicine resident from the University of Georgia. For the last four weeks I had the good fortune to travel from Athens, Georgia to Seattle, Washington and work with Wellpepper as a resident physician consultant. As a young physician, I have a lot of hope for electronic health systems and their ability to decrease our workload, increase our efficiency, and improve patient care. In residency, we spend anywhere from 25% to 75% of our time looking at the electronic medical record, but we do not get the opportunity to see it from the other side. When I found out about the opportunity to work with a health tech company for an elective rotation, it seemed like a great way to see things from different perspective. There was the added benefit of escaping a humid Georgia summer month and instead spending it in the beautiful Pacific Northwest where I hope to work after residency.

While at Wellpepper I worked on a variety of projects in several different roles. My primary responsibility was to work on care plan development. A particular care plan they were interested in based on feedback from their customers was pain and opioid management. Considering the opioid epidemic we are currently facing in medicine, this seemed like a great idea. Many of the patients in our resident clinic are chronic pain patients or come to us already on opioids from other providers. Unfortunately, I have received very little training in opioid management (our residency clinic is not allowed to prescribe opioids or benzodiazepines) . While I understand the sentiment behind this, it is not helpful to residents who need to learn how to manage these types of medications for their future practices . Developing a care plan around opioid management presented a wonderful learning opportunity. I designed the opioid care plan and taper program with the opioid-naïve physician in mind, providing a platform to help guide patients and physicians through the intricacies of opioid management and withdrawal. Many of the other care plans I helped work on throughout the month were more on the surgical side of things, but closely related to internal medicine because of how often we work with pre and post-surgical management of patients and these also provided great learning opportunities.

The month culminated in a trip to meet with Mayo Clinic in Rochester, Minnesota. Wellpepper has a unique partnership with Mayo Clinic to build their care plan best practices into the Wellpepper platform to help improve patient care and outcomes. Participating in meetings with administrators, secretaries, clinical research nurses, and physicians at the forefront of their specialties was an extremely unique opportunity . I thought my medical school, the University of Kansas, was a big hospital. It paled in comparison to the small city of Mayo Clinic. It was quite the experience just to be there.

In short, my month with Wellpepper provided a glimpse into the medical tech industry and provided a unique opportunity to work as a consultant outside of patient care. In the electronic medical record world, the focus is on functionality for the healthcare providers. Apps for patient use present an interesting challenge in creating something that is clinically useful for providers but also user friendly and not bogged down in medical jargon for the patients to be able to navigate. It was nice to experience seeing what creating those types of tools for patients looked like from a perspective other than the provider. There were plenty of learning opportunities throughout the month (as well as plenty of extremely valuable study time with board exams on the horizon). While I do not see working exclusively as a physician consultant in my immediate future, I plan to continue to champion electronic health records and mobile services to pursue continued improvement in patient care and outcomes .

From left to right: Myself, Anne Weiler, and Luke Feaster visiting Mayo Clinic.

Posted in: Healthcare Technology, Healthcare transformation

Leave a Comment (0) →

Machine Learning in Medicine

As a new intern, I remember frequently making my way to the Emergency Department for a new admission; “Chest pain,” the attending would tell me before sending me to my next patient. Like any good intern I would head directly to the paper chart where I knew the EKG was supposed to be waiting for me, already signed off on by the ER physician. Printed in standard block print, “Normal Sinus Rhythm, No significant ST segment changes” I would read and place the EKG back on the chart. It would be later in the year before I learned to ignore that pre-emptive diagnosis or even give a thought to about how it got there. This is one of many examples how machine learning has started to be integrated into our everyday life in medicine. It can be helpful as a diagnostic tool, or it can be a red herring.

Example of machine-learning EKG interpretation.

Machine learning is the scientific discipline that focuses on how computers learn from data and if there is one thing we have an abundance of in medicine, data fits the bill. Data has been used to teach computers how to play poker, learn laws of physics, become video game experts, and provide substantial data analysis in a variety of fields. Currently in medicine, the analytical power of machine learning has been applied to EKG interpretation, radiograph interpretation, and pathology specimen identification, just to name a few. But this scope seems limited. What other instances could we be using this technology in successfully? What are some of the barriers that could prevent its utilization?

Diagnostic tools are utilized in the inpatient and outpatient setting on a regular basis. We routinely pull out our phones or Google to risk stratify patients with ASCVD scoring, or maybe MELD scoring in the cirrhotic that just got admitted. Through machine learning, these scoring systems could be applied when the EMR identifies the correct patient to apply it to, make those calculations for the physician, and present it in our results before we even have to think about making the calculation ourselves. Imagine a patient with cirrhosis who is a frequent visitor to the hospital. As a patient known to the system, a physician has at some point keyed in the diagnosis of “cirrhosis.” Now, on their next admission, this prompts this EMR to automatically calculated and provide a MELD Score, a Maddrey Discriminant Function (if a diagnosis of “alcoholic hepatitis” is included in the medical history). The physician can clinically determine relevance of the provided scores; maybe they are helpful in management, or maybe they are of little consequence depending on the reason for admission. You can imagine similar settings for many of our other risk calculators that could be provided through the EMR. While machine learning has potential far beyond this, it is a practical example where it could easily be helpful in every day workflow. However, there are some drawbacks to machine learning.

Some consequences of machine learning in medicine include reducing the skills of physician, the lack of machine learning to take data within context, and intrinsic uncertainties in medicine. One study includes that when internal medicine residents were presented with EKGs that had computer-annotated diagnoses, similar to the scenario I mentioned at the beginning of this post, diagnostic accuracy was actually reduced from 57% to 48% went compared to a control group without that assistance (Cabitza, JAMA 2017). An example that Cabitza brings up regarding taking data in context is regarding pneumonia patients with and without asthma and in-hospital mortality. The machine-learning algorithms used in this scenario identified that patients with pneumonia and asthma had a lower mortality, and drew the conclusion that asthma was protective against pneumonia. The contextual data that was missing from the machine learning algorithm was that the patient with asthma who were admitted with pneumonia were more frequently admitted to intensive care units as a precaution. Intrinsic uncertainties in medicine are present in modern medicine as physician who have different opinions regarding diagnosis and management of the same patient based on their evaluation. In a way, this seems like machine-learning could be both an advantage and disadvantage. An advantage this offers is removing physician bias. On the same line of thought, it removes the physician’s intuition.

At Wellpepper, with the Amazon Alexa challenge, machine learning was used to train a scale and camera device (named “Sugarpod“) in recognizing early changes in skin breakdown to help detect diabetic foot ulcers. Given the complications that come with diabetic foot ulcers, including infections and amputations, tools like this can be utilized by the provider to catch foot wounds earlier and provide appropriate treatment, ideally leading to less severe infections, less hospitalizations, less amputations, and lower burden on healthcare system as a whole. I believe these goals can be projected across medicine and machine learning can help assist us with them. With healthcare cost rising (3.3 Trillion dollars in 2016), most people can agree that any tools which can be used to decrease that cost should be utilized to the best of its ability. Machine learning, even in some of its simplest forms, can certainly be made to do this.

Posted in: Healthcare costs, Healthcare Technology, Healthcare transformation

Leave a Comment (0) →

Electronic Health Records and Physician Burnout: Fraught with Frustrations

Electronic Health Records (EHRs) have become a scapegoat for physician burnout. A quick google search of “EHR” and “burnout” will yield nearly 350,000 results. Systematic reviews over the last 10 to 15 years look at much of this data and draw a similar conclusion; higher physician burnout rates are correlated to use of EHRs. They point at increased documentation times, decreased user satisfaction, and “clerical burden” as causes of burnout. Data from other sources suggest we may be laying the blame in the wrong place.

At Stanford Children’s Health, in an effort to improve physician satisfaction with EHR use, they have created extensive and personalized education programs. They obtained data from the EHR to develop an efficiency profile, surveyed physicians on their perspective of their efficiency, and performed observation sessions with physicians so support staff could see how physicians used the EHR. With this information, personalized learning plans were developed. Providers were incentivized to participate and they found physician satisfaction with EHR improved as well as their efficiency and less time spent on medical records outside of the hospital.

This suggest that the problem with the EHR is not of the EHR, but rather the onboarding and training process related to it. Most EHRs can be made to work for you, rather than against you, and improve your efficiency with documentation and patient care.

Physician Burnout in the Electronic Health Record Era: Are We Ignoring the Real Cause? Annals of Internal Medicine. July 2018.

Drs. Downing and Bates recently published in JAMA that there may be another underlying cause that is driving physician burnout and dissatisfaction which is being blamed on the EHR. In looking at health systems across the United States and abroad on a similar EHR (Epic Systems), they found that physicians abroad reported higher satisfaction with the EHR and that it improved their efficiency. In other countries, they noted, documentation is briefer, containing only essential clinical information rather than bogged down by compliance and reimbursement documentation. On average, within the same EHR, notes in the United States were found to be four times longer than those abroad. Notes in the United States had documentation requirements from a “clinically irrelevant” number of elements in each part of a note so that fee-for-service components are fulfilled.

Their argument suggest that a key cause of physician burnout which is being blamed on EHRs is actually our “outdated regulatory requirements.” With reform of these requirements, documentation would become only the essential clinical data, rather than notes with strict documentation requirements of a “clinically irrelevant number of elements” in the various components of a note.

A third argument that I would challenge us to consider as a more likely cause of physician burnout rather than the EHR is the cultural state of medicine in the United States. Due to increasing numbers of lawsuits over the last 20 years, physicians are spending a lot of time on “CYA” medicine (Cover Your A**), feeling forced to order unnecessary testing for an unlikely diagnosis “just in case” things do not go according to planned. We also get pulled into the trap of what I refer to as “Burger King” medicine, playing off the fast food giant’s slogan of “Have it your way.” Patients are coming to the physician already “knowing” their diagnosis and requesting specific treatments or testing. If the physician disagrees? No problem, the patient will just go find one down the road who will do what they want.

In an era of electronic health records on the rise and an increase in rates of physician burnout in the United States, it looks easy on paper to show a correlation between the two. What if instead the EHR is not to blame, but any number of other things like lack of physician EHR training and support, documentation regulations, or “Burger King” medicine? Is it more likely that the relationship between EHR prevalence and physician burnout is only a correlation and not a causal relationship? My hope is that in the coming years we will recognize the EHR as a tool to improve patient care and outcomes, increase our efficiency, and return to practicing medicine at the bedside.

Posted in: Uncategorized

Leave a Comment (0) →
Google+