Rethink IT

2015-12-21

Clinical visualizations - Antiobiotic grid

11:28 AM Posted by David, MD design, EMR, patient safety No comments

Physicians need to be able to understand the history of antibiotics given in order to make decisions about broadening antibiotics, narrowing antibiotics, and administering the correct duration of therapy. The standard EMR's medication administration record is not optimized for these needs (Figure 1).

Figure 1: EMR's medication administration record

Problems of the current visual display include

Difficult to tell at a glance what antibiotics a patient is currently on
Difficult to tell how long a patient has been on antibiotics for
The need to scroll
Visual sparseness

The first step in our redesign is to use a filter to select the antimicrobials. The second is to reduce the visual sparseness of the grid by grouping by day (Figure 2).

Figure 2

While this view is cleaner than the original, we lost some information about sequence due to grouping--for example, it's not clear what the dose progression of vancomycin has been. To fix this problem, we can create multiple time bins daily, experimenting with three daily time bins (Figure 3) and four daily time bins (Figure 4).

Figure 3: Grouping by up to three time bins daily

Figure 4: Grouping by up to four time bins daily

For the purpose of conveying antibiotic history, three time bins seems to have the best balance of chronology while limiting sparseness. Finally, for visual simplicity, we remove gridlines and lightly shade every other day (Figure 5).

Figure 5: Final design for an antibiotic grid to help make management decisions

Hospital census tracking

10:08 PM Posted by David, MD design, workflow 1 comment

Problem
Patient census in the hospital is dynamic--patients are seen by many different teams throughout their stay, and these interactions can be difficult to track. Time of admission and time of discharge do not tell the entire story. Accurate census data is important in order to staff services appropriately.

Solution
We used "service lists" from our EMR in order to infer when patients were being seen. These service lists are maintained by providers and includes lists of patients for consult teams and primary teams. They are accessible in real time through an API run by our IS Department and an archive of these lists is stored by our Data Science Department. We used these data to trend the number of consults and admissions over time, with no added work or manual entry.

Credit
Visualization and design: David Do
Back end: Eugene Gitelman
Data Science Department: Corey Chivers and others
IS Team

A Call for Innovators

10:16 PM Posted by David, MD hackathons, health IT writings No comments

This weekend, 1500 hackers will descend upon Philadelphia to try to change the world at the 12th gathering of PennApps, the nation's largest collegiate hackathon. These college students will identify real-world problems, form teams and pull all-nighters to design and build technological solutions that solve them in less than 48 hours. Since last year, PennApps features a health component, which promises prizes for notable healthcare innovations.

Innovation is a hot topic for hospitals these days, in large part due to a changing landscape of reimbursement that includes quality-based adjustments, disease-related groups, and withheld payments for hospital-acquired conditions and readmissions. Administrators and providers understand they must adapt, but they often lack the design skills and the technical skills to implement change in this era defined by the digitization of medicine. That is why their survival depends on startup companies and the wave of technological innovation fueled by talent seen at hackathons like these.

Innovators, if you are reading, here is what healthcare needs from you. Forget the wearables, the quantified self, and automated diagnosis. There are more pressing needs that often require adaptation of ideas already proven in consumer web. Here are some ideas:

Trello for patients - There is tremendous emphasis on decreasing length of stay because each day in the hospital is expensive. Streamlining the processes is difficult. Imagine an automobile factory in which every product is completely different and requires a different subset of skilled mechanics. This is the type of factory that a hospital resembles. Patients often stay extra days to see a specialist. Hospitals need tools that coordinate and streamline schedules for providers, patients, and social workers. Those familiar with project management will know that tools like Kanban or apps like Trello can help keep projects on time.
Google Analytics for Provider-specific Prescribing habits - Another component of increasing value is eliminating unnecessary testing. The amount of testing varies tremendously by provider; there is scant evidence about when and how often a patient should get blood draws, and consequently most patients in the hospital get them once daily. A platform that allows providers to see their prescribing habits and patient outcomes compared with peers would be essential in helping them change.
Patient-based Twitter or Slack - Communications between providers exist in many forms, including written notes in the chart, text messages, telephone calls, and emails. The nature of healthcare is team-based, with members of the team entering and exiting at various points in care. Providers need a way to be involved in this ongoing conversation, perhaps similar to an internal Twitter in which they can hash-tag the patient's name, allowing more providers to be part of the conversations.
Airline Price Predictor for illness severity - In a setting with many patients and providers, it's difficult to know who needs more resources at any given time. Despite the digitization of vital signs and other parts of the medical record, there are few good predictors for clinical events like sepsis and intubation. Most of the tools currently in place are built to respond to problems rather than predict them.
Kayak for Pharmaceuticals - When patients are discharged with medications like antibiotics, the insurance approval process can take days. Further, upon approval, providers and patients may discover they face copays in the $1000s. Providers need realtime lookups for pricing so they can choose an alternative medication that is covered by the patient's insurer. Some companies, like Eligible API have started to offer data services to help solve problems like these.

There was never an era that had so many gatherings of problem solvers and innovators. Healthcare must tap into this talent pool. Stay tuned to see what comes out of PennApps.

Designing Better Clinical Views

5:50 PM Posted by David, MD design, EMR, patient safety, workflow No comments

Designers: David Do, Eugene Gitelman, Ian Oppenheim, Jason Maley, and Barry Fuchs

The dashboard concept has been around for a long time, but dashboards still see limited adoption in medicine. Why is that so? How can we be different? By thinking about dashboards firstly through the provider’s eyes, and secondly as a platform, we address several key barriers to adoption:

Simplicity – in these examples, we allowed ourselves to be inspired by paper notes and diagrams that doctors use. We plot data on trendlines and we can put data side-by-side to examine the interplay of assessments and interventions.
Designability – A straightforward interface lets providers design and share dashboards. The respiratory dashboard is not only informative but also instructive, training users to dichotomize “oxygenation” and “ventilation”. Other specialists in the hospital may have analogous lessons.
Tweakability – as we learned in the Carealign process, not all data are of equal importance. The most time consuming part of construction happens after the design, finding the right study names, filtering and “massaging” data (e.g. formatting to fit the fishbones). This dashboard platform lets users make instantaneous adjustments.

Figure 1: Respiratory view is informative and instructive, helping users think about ventilator settings in terms of “Oxygenation” v “Ventilation”.

Figure 2: Each view is designed to answer a particular question. The ID view should contain all the data that an infectious disease specialist uses in order to make an antibiotic decision.

Figure 3: A quick glance at the Quality Indicators view shows patients with foley catheters or indwelling lines

Figure 4: Users can become designers by defining their own views, choosing the types of data to be displayed in each panel

Figure 5: Diabetes views

Mednote: a note-taking app that builds a medical ontology while you use it

5:35 PM Posted by David, MD No comments

Introduction

Mednote is a lightweight medical note-taking app that builds a medical ontology while you use it. I built this and used it during medical school when trying to organize the vast differentials and arrays of supporting evidence for different diagnoses.

This web-based app has an interface similar to Evernote. Users can create a page to take notes on a particular concept, like 'chest pain'. Within the body of the text, users denote relationships with other medical terms, which gets extracted from the text and placed into the sidebar. As you build pages and connections, linkages develop, allowing you to navigate back and forth between concepts. On the 'chest pain' page, as an emergent property, you can see the different causes, and recommendations on which examinations or tests to run to differentiate them.

Source code

Open source

https://bitbucket.org/davehdo/mednote2

Technologies

Ruby on Rails

The index of terms

The chest pain page

The differential diagnosis for chest pain is inferred from the body of the text

Agent - EMR data straight to your phone

11:14 AM Posted by David, MD design, EMR, full-stack development, patient safety No comments

Introduction

Agent is a project I am leading at the Hospital of the University of Pennsylvania. Healthcare providers who directly interact with patients can use this app to receive up-to-the-minute results through Push Notifications.

Aside from streamlining workflow, the Agent platform offers the ability to improve care by delivering targeted notifications based on data. Interventions that would have previously required extensive IT resources to build can now be implemented and tested in a week's time.

Examples of how this can be applied:

Antibiotics medications often expire without provider awareness, leading to missed doses. Agent alerts providers when it's time to renew a medication.
Previously there was no automated notification for when patients arrive on the floor. Agent ensure providers are aware so patients can be seen immediately.

The possibilities are limitless. The goal of Agent is to create an environment where people can design, test, and iterate on process improvements. This is where Agile Development meets medicine.

Agent Landing Page

We needed a way to communicate to administrators the benefits of the new technology to gain support. We also needed a way to onboard beta testers with email confirmation and a survey.