RapidMiner and Tableau: Data Science Improves Quality of Care for Critically Ill Patients

“The fusion of these two technologies allows us to go from anecdotal approach to operational decisions to a data-supported approach that enables us to create more meaningful interventions and better patient care moving forward.”

Director, Health Informatics

Customer Profile

Privately held

Healthcare Company

Location

US

Industry

Healthcare

CASE STUDY

The Challenge An analytics division in a privately held healthcare company wanted to use their vast amount of patient treatment data to help drive better care and outcomes. They monitored each patient’s progression over their entire course of treatment, storing vast amounts of data in many different formats and across many facilities. This led to a complex dataset, which the company needed to quickly cleanse, simplify and draw fast, actionable treatment conclusions to share with doctors. Most data science solutions the company was looking at required multiple tools and were very time consuming to prep data, create models and operationalize results. Other solutions enabled them to export data to spreadsheets, which was deemed too cumbersome and difficult to make targeted treatment determinations. The company needed a data science solution to streamline the whole analytics process: from prepping their complex data, to creating predictive models that would determine the most-effective treatment options for each patient, and then share insights with doctors through Tableau dashboards.

The Solution RapidMiner’s unified platform was chosen for its easy-to-use drag and drop visual programming and ability to integrate with 3rd party software like Tableau. This gave them the robust data prep and predictive modeling functionality of RapidMiner along with the ability to operationalize results directly into the user-friendly, interactive dashboards of Tableau. RapidMiner allowed the analytics team to quickly build reusable workflows that loaded spreadsheets and accessed patient care data from SQL databases and other data sources, mashing them up into one cohesive dataset. Once the data was extracted, they designed a clustering model in RapidMiner to identify the factors common to a subset of data. This model was used to predict patients that would require advanced levels of treatment and care, which was shared with doctors through Tableau. By speeding-up the data prep process, analysts had more time to prove out and adjust their predictive models. Using RapidMiner plus Tableau, they were able to generate new features on the fly, get immediate feedback from doctors and then update the models in real-time based on that feedback.

The Results RapidMiner’s lightning-fast data science platform gave the analytics team the ability to collect, cleanse and

segment new and existing patient data in a matter of hours. The clustering model quickly pinpointed patients

with a higher probability of needing advanced care. The RapidMiner-Tableau integration allowed the

analytics division to present predictive insights to doctors in a visual format that was easy to understand.

Having a better understanding of each patient’s progress helped doctors to adjust treatment plans, create

more meaningful interventions and ultimately improve the quality of life for their critically ill patients.

CASE STUDY

RapidMiner & Tableau: Data Science Improves Quality of Care for Critically Ill Patients

RapidMiner, the industry’s #1 open source predictive analytics platform, is disrupting the industry by empowering organizations to include predictive analytics in any business process—closing the loop between insight and action.

RapidMiner’s effortless solution makes predictive analytics lightning-fast for today’s modern analysts, radically reducing the time to unearth opportunities and risks. RapidMiner delivers game-changing expertise from the largest

worldwide predictive analytics community.

For more information, visit www.rapidminer.com

2