In an effort to know more about the etiopathogenesis of non-treatment responding to depression and to improve its management, Takeda and ConvergeHEALTH, data science institute by Deloitte collaborate to analyze patient datastores.

Disease datasets of conditions like non- treatment responding migraine from insurance claims data including diagnoses, management protocols and prescribed medicines were used to conduct linear and non-linear models on.

The researchers aimed at spotting the key aspects of the data that brought out the maximum impact on treatment results. A right mix of the correct data and apt questions lead to the enhancement in result estimation of deep learning models. Hence, larger labyrinthine datasets were available for evaluation and a clearer perception of patient response was obtained.

"In severe depression, patients often go through multiple medications before finding one that works," said Dan Housman, chief technology officer at ConvergeHEALTH by Deloitte. "This testing process can be challenging for patients and their psychiatrists."

The method is "prescribed after other medications did not work in what is deemed a treatment-resistant patient,” he added. “We’re interested in looking at depression patients and their journey between treatments to better understand which patients may fall into the treatment-resistant category and when a certain switch will be sustained without further switches."

Machine learning is applied to claims data sets to design prognostic models that identify the resistant patients and the different drugs for depression which the patients can shift to. The successful prognostic models, so designed, enable organizations to alter protocols and offer digital diagnostic devices that evaluate past events of patients to pick which individual would be positively affected by a change in medication or which drug could be started as the primary treatment for that patient.

"The benefit to the patient is a shorter journey to a drug that will keep them well and less time struggling with their depression," Housman described. "The benefit to Takeda is to be able to build tools both with guidelines or decision support systems to help physicians find the patients who can benefit from our products.”