The world right now is awash in Predictive Analytics, the mystery of Big Data, and the rise of the glorious and magical Data Scientist. Most of the time we hear these buzz words in relation to some marketing campaign, election, or credit score application process, but what about applying these tools and people to a project that can benefit the welfare of humanity?
Well, one group of data scientists and a healthcare provider in Washington State are doing just that.
A partnership between data scientists at the University of Washington Tacoma (UWT) and MultiCare Health System, the South Puget Sound’s largest hospital and healthcare system, is fine-tuning algorithms to better predict which chronic heart failure (CHF) patients would be most susceptible to readmission within 30 days, with the goal of understanding which adjustments to treatment plans have the most impact on preventing readmissions.
Their goal is to create a “readmission score as-a-service” that would enable providers to use the bank of predictive models for many chronic conditions, not just heart failure.
Of course this project has a multi-pronged benefit, not only does it help CHF suffering people to get better healthcare, but it also reduces costs in the long run. Win-win in my book.
There was one other interesting nugget that that caught my eye.
The current project status is prototype, he said. “We are working on physician validation in a clinical setting. Once we are able to show that it works well and gets the kinks out, then the next step would be a full-on EHR implementation.” (emphasis mine)
Operationalizing Predictive Analytics falls into the realm of Prescriptive Analytics, where you automatically extract your insight and act on it. Unfortunately, this is typically where organizations stumble, and stumble hard. It's one thing to build a new algorithm, model it, and predict the different classes with a high degree of confidence, but it's another problem altogether to operationalize it.
Tl;dr: A Data Scientist a day keeps the Doctor away