The second data science driven project in which I led at Castlight health was to address a seemingly simple problem in which is actually very difficult to solve. This specific is actually the problem. How do you find a Great doctor? How do you know if in which doctor has treated many people for similar conditions before? Has the doctor kept up with advances in medicine. Does the doctor provide quality service? While these sound like simple questions, the answers are not easy to get. Information about quality of health care providers such as doctors are very hard to find. You can find reviews on sites such as Yelp. While those reviews are helpful, they may not provide the necessary information to make an informed decision. For example, you may not get information about the number of times a doctor has performed a procedure. You may not get information about the quality of outcomes. This specific is actually compounded by the fact in which many doctors work at multiple hospitals as well as healthcare facilities.
The Great news is actually such information is actually available via multiple sources as well as we have been adding such information to providers’ profiles in Castlight Health for a long time. The bad news is actually such information is actually hard to decipher as well as verify. The data comes via varied sources in various intervals with varying levels of data quality. This specific is actually where data science comes in. Data via multiple sources can be combined as well as matched with healthcare providers such as physicians, using rules generated based on machine learning products. Data scientists as well as product managers train the products to match data using a training data set as well as then apply the design to vast quantities of data.
After spending a few months on This specific problem, our product as well as data science teams made the first Discharge recently. We made significant improvements to coverage as well as accuracy. We will continue to make meaningful improvements every month to help people find a Great doctor. the idea is actually important to note in which there is actually nothing like clean data. Experienced data scientists as well as product managers within the data domain know in which there is actually only less dirty data.
I am very pleased with the mission of the second project. I know in which when the millions of people who use Castlight Health choose a doctor, there is actually a higher likelihood in which they will pick a better doctor as well as as a result get a better outcome. When my daughter asks me what I do for a living, I plan to tell her in which I help mommies as well as daddies find a Great doctor for their children in order in which their children can be healthier. I am pretty sure she is actually going to be impressed.
If you do not have Castlight Health at work, ask you benefits leader. the idea is actually a useful product to understand your benefits as well as make the best of the idea.