MAV-clic: management, analysis, and visualization of clinical data

Area of Science:

• Healthcare Informatics
• Clinical Data Management
• Precision Medicine

Background:

• Effective management and analysis of large-scale healthcare datasets are crucial for advancing medical research and patient care.
• Existing platforms often lack the integrated functionality required for comprehensive data analysis.
• The need for secure, HIPAA-compliant systems is paramount in handling sensitive patient information.

Purpose of the Study:

• To develop a multifunctional analytics platform for efficient management and analysis of healthcare data.
• To create a HIPAA-compliant framework that supports data extraction, cleansing, encryption, and deidentification.
• To enable query, analysis, and visualization of clinical data through a user-friendly interface.

Main Methods:

• The Management, Analysis, and Visualization of Clinical Data (MAV-clic) framework utilizes the Butterfly Model.
• Data undergoes extraction, cleansing, encryption, and restructuring into a deidentified format.
• A graphical user interface facilitates data querying, analysis, and visualization.

Main Results:

• MAV-clic successfully manages healthcare data for over 800,000 subjects at UConn Health.
• The platform enables cohort creation based on specific criteria.
• Capabilities include measurement analysis for specific diagnoses/medications and longitudinal outcome calculation.

Conclusions:

• MAV-clic enhances clinical decision-making by enabling efficient subject stratification and scenario analysis.
• The platform supports clinicians and healthcare analysts in optimizing healthcare quality and transition.
• MAV-clic facilitates the integration of diverse data types for precision medicine initiatives.