Emma Fauss: Leverage Your Device Data for Advanced Event Detection

Clinical staffers spend about 20% of their time on documentation alone. While it’s difficult to summarize the error rates, studies show that they range from 5% to 95%, depending upon the condition, patient, and measurement. Inaccurate documentation has many risks, from clinical risks such as cherry-picked vitals and handoff, to financial risks such as revenue loss and increased lengths of stay.

Biomedical engineers are front and center in looking at technologies and devices to help solve the clinical documentation problem. Device integration has helped by removing the manual process of charting. However, there is a growing need to find ways to make the data collected from biomedical devices actionable.

My first piece of advice is to start with the problem you’re trying to solve with the data. For example, one of the greatest needs in healthcare is automated event detection: the ability for a computer to automatically recognize and, in some cases, predict an event. This capability can help with improving clinical documentation as well patient care, clinical workflows, and even outcomes. However, this problem can be complex. The main reasons for the complexity relate to the three critical components required to “automatically” detect an event: the right data, the right analytics, and the ability to transform and visualize that data to make it actionable. Each of these components has its own factors to consider when making a decision.

At the upcoming AAMI Annual Conference & Expo, my colleague Rajeen Patel and I will speak about how we have developed a solution to meet these three critical components of advanced event detection. We will talk about how to leverage real-time and historical data including waveforms across devices and then apply machine learning and analytics to help solve a multitude of clinical and operational initiatives. Our session will include three case examples where we’ve applied our process for ventilator, apnea, and cardiac arrest detection. We will also hold an interactive breakout session where we discuss your documentation challenges and desires for event detection, and walk through the steps to implementing your own advanced event detection solution.

Please join us Sunday, June 11, at 8:00 a.m. (local time) in Room 18D for Bringing Forth the Next Generation of Quality Improvement and EHR Documentation by Leveraging Analytics for Automated Event Detection.  If you would like to send us questions or information about your advanced event detection needs, please don’t hesitate to email Raj at raj@mic.healthcare or me at emma@mic.healthcare.

If you would like to schedule a personal demo at AAMI or can’t make it to the session, feel free to contact us with your questions and needs. Thank you, and we hope to see you there.

 Emma Fauss, PhD, MBA, is chief executive officer of Medical Informatics Corp.

2 thoughts on “Emma Fauss: Leverage Your Device Data for Advanced Event Detection

  1. Automatic data entry gets the information into the record, but it potentially bypasses the step of anyone looking at it seriously at the time of collection. This might increase the need for accurate event detection as a result of clinicians paying less attention.

    • @WilliamAHyman Yes, better analytics that automatically synthesizes large amounts of data and is capable of making at least initial-level predictions of acute events occurring. Such things exist — or are well along on their way to development.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s