Abstract

Electronic Health Record adoption has reached its saturation point, near 100%; however, it has not been fully utilized for clinical intervention research outcomes. Traditional clinical trial studies for medical intervention guidelines have proven to be time-demanding, expensive, with limited coverage and effectiveness. This study aims to discover conclusive evidence with high significance to the established clinical correlation between obstructive sleep apnea and related comorbidities, along with an application of analytics to establish the impact of obstructive sleep apnea on stroke risk rate using a large, feature-rich electronic health record database. Long term goal of this research is to use a variety of data sources, including electronic health record data, along with big data analytics tools to develop a new stroke-risk stratification score. The scoring system is expected to be able to generate the granular measures for a patient-centric dose-drug combination, consequently reducing the side effects while improving the treatment plan.

Share

COinS
 

Clinical Intervention Research with EHR: A Big Data Analytics Approach

Electronic Health Record adoption has reached its saturation point, near 100%; however, it has not been fully utilized for clinical intervention research outcomes. Traditional clinical trial studies for medical intervention guidelines have proven to be time-demanding, expensive, with limited coverage and effectiveness. This study aims to discover conclusive evidence with high significance to the established clinical correlation between obstructive sleep apnea and related comorbidities, along with an application of analytics to establish the impact of obstructive sleep apnea on stroke risk rate using a large, feature-rich electronic health record database. Long term goal of this research is to use a variety of data sources, including electronic health record data, along with big data analytics tools to develop a new stroke-risk stratification score. The scoring system is expected to be able to generate the granular measures for a patient-centric dose-drug combination, consequently reducing the side effects while improving the treatment plan.