AI/ML models for a DTx platform
![](https://cdn.prod.website-files.com/6583529b1de32f1a92d93901/65904a0bcc289cdec0079ad0_OmniScience-Photography-08-min.jpg)
Our client developed a proprietary wearable device and has a large collection of clinical trial data for neurological diseases. Our client wanted to find ways to extract valuable insights to distill clinician decision-making insights, and assess the predictive power in their dataset to develop a novel DTx. The client’s data came from diverse trials, each with unique protocols and procedures, resulting in a wide variety of data types, including time series wearable data, ePROs, physician notes, and medication dosing and adherence. To realize the potential of this data, we needed to leverage AI/ML techniques to uncover digital biomarkers to characterize patients, learn from prior outcomes, and recommend the next best action within a digital therapeutic.
Our team started by identifying the most critical strategic objectives needed to support DTx development. We then developed and validated AI/ML models capable of classifying disease subtypes, monitoring medication adherence, recommending treatment types and drug dosing, monitoring side effects, and providing early detection of worsening disease symptoms. These models successfully demonstrated a path towards DTx development, using digital biomarkers to improve disease treatment and management.