Data science Institute Converge-Health by Deloitte and Pharmaceutical company Takeda and research and development have partnered together to study patient datasets to have a keen understanding of the etiology, progression and most effective therapies for difficult diseases using insurance claims information for diagnoses, medical procedures, and prescriptions, they ran linear and non-linear models on disease datasets. The main objective was to identify data factors that have the highest impact on patient outcomes. They identified the potential for the machine-learning techniques to use on other predominant diseases to determine what patients are more prone to these illnesses and the best courses for personalized treatment.
Dan Housman, chief technology officer at Converge-Health by Deloitte stated that “In severe depression, patients often go through multiple medications before finding one that fits their standard. We’re interested in looking at depression patients and their journey between treatments to better understand which patients may go through the treatment-resistant category.
In this technique, we are generally looking to use AI, machine learning and deep learning to demonstrate that we can predict a future event in a data set on a realistic platform and exact accuracy.”
Now the organizations are using claims data sets with machine learning to build predictive models to determine the patient behavior under depression who may be resistant on the medications or classes of depression medications so that they can adjust guidelines or provide digital diagnostic tools that look at patient histories to identify who would likely benefit patients.
“We employ traditional machine learning models that are able to identify among the thousands of potential variations in a patient and record them both separately. The data scientists perform this by turning the data that will be available into training and test datasets. The training data allows them to hone models”. These prediction systems such as random mechanism are extremely powerful tools but they fall short in certain key areas,” Housman said. ”
He concluded the statement saying that, “We leveraged the Amazon Web Services computing systems including GPU on servers in order to build and train the models, where the analytical tools, data availability, and scalable computational infrastructure has brought the cost of doing data science experiments gigantic but the results of the application of the various artificial intelligence methods were promising”.
The researchers are encouraged that the models using different techniques demonstrated increasing predictive power based on the betterment in technology and they are looking at the key features among hundreds of thousands of features and could see that most of the features related to the known etiology of the disease but also some unknown correlations that we can investigate further.