MEDSEEK Announces Newly Enhanced Marketing Propensity & Prediction Models

MEDSEEK announced today the availability of new and powerful predictive models for its precision marketing solution, MEDSEEK Predict. Developed leveraging the latest data science and analysis techniques over bigger data with broader dimensionality, these models have greater predictive power than traditional healthcare segmentation modeling approaches and pave the way for more effective campaigns that generate a higher return on marketing investment.

Building and deploying predictive models requires a specialized combination of skills covering data management, data exploration, signal identification, model construction and validation. MEDSEEK employs a full-time team of research scientists, led by Chief Analytics Officer, Venky Ravirala, PhD, to keep pace with the latest advances in analytic techniques and meet marketers’ growing demand for data insights that enable them to achieve greater results. Today, MEDSEEK announced this team has produced forty new and highly explanatory predictive models that not only measure and score a named individual’s propensity to need a specific service line or procedure, but also their likelihood to respond and engage with marketing outreach methods.

“At MEDSEEK, we evolve our teams, tools and technology to provide our clients with the solutions they need to meet their most strategic objectives. More than anything, healthcare marketers have made it clear that their highest priority (in a precision marketing solution) is the performance of their marketing campaigns and the associated return on marketing investment,” stated Peter Kuhn, CEO, MEDSEEK. “Over the past year, Dr. Ravirala and our world class analytics team have focused on this goal. We are proud today to unveil the healthcare industry’s most advanced predictive models. This is only the first of many exciting scientific advances coming from our team—we look forward to many more.”

Traditional predictive modeling applications for healthcare marketing rely primarily on claims, provider and single-dimension response data. While models developed from these data sources may be effective at predicting clinical risk, they typically ignore or make limited use of socio-economic, lifestyle, demographic, financial and behavioral characteristics that can accurately predict an individual’s likelihood to respond to outreach methods and convert to profitable revenue. MEDSEEK’s newly enhanced multivariate models are developed and continuously evolved leveraging machine learning techniques across bigger data to improve upon basic industry-standard models that rely on qualitative rating scales and segmentation schemes.

“Unlike the traditional response rate metric, MEDSEEK’s Propensity differentiates the severity, value and risk, and in turn supports an organization’s goals of achieving higher campaign response rates and maximizing return on investment. This precision targeting approach increases relevance and value-oriented responses while effectively managing population risk and wellness,” Dr. Venky Ravirala explains. Additionally, he continued, “We update the clusters and regression equations and run the neural network monthly so our models are always adapting to the latest patterns in healthcare consumer behavior and emerging population health patterns, avoiding model fatigue.”

To learn more about how MEDSEEK’s groundbreaking approach to predictive analytics can help your organization execute highly profitable campaigns visit

About Influence Health

Influence Health provides the healthcare industry’s only integrated digital consumer engagement and activation platform. The Influence Health platform enables providers, employers and payers to positively influence consumer decision making and health-behaviors well beyond the physical care setting through personalized and interactive multi-channel engagement. Since 1996, the Birmingham, AL-based company has helped more than 1,100 provider organizations influence consumers in a way that is transformative to financial and quality outcomes. For more information, please visit