Ruvos has been fortunate to colab with many amazing teams to create innovative and groundbreaking technology and systems.
One of these being this being the “Modernizing Newborn Screening (NBS) Through Partnerships and Collaborations” project.
We created this poster for the 2022 APHL conference.
Another of our exciting collaborations was with one of our longstanding partners, MITRE.
The purpose of the Alliance Participant Engagement Portal initiative is to enable clinical trial teams to better engage with patients who participate in oncology clinical trials, with the aim to improve outreach and longitudinal connection to trial participants independent of participant or trial site resources.
The process for anomaly detection of labs submitting ELR begins with aggregating daily message volumes per lab and creating a time series model that forecasts an expected volume for the subsequent day. Several model archetypes were evaluated including Regression, Rolling Average, Deep Neural Network (DNN), Fourier Transformation, and a Prophet Model. The model with the greatest combination of consistent forecasting, high fidelity to variance, reduced computational cost, ease of implementation, and ease of automated hyperparameter fitting was an Auto-Regressive Moving Average Model (ARIMA).
Ruvos works with federal partners and state public health departments to build the infrastructure needed to modernize electronic test orders and results processes and implement HL7 data sharing capabilities. Local jurisdictions, including county and city health departments, can benefit from implementing these capabilities.