An Interactive Platform to Visualize Data-Driven Clinical Pathways for the Management of Multiple Chronic Conditions

Area of Science:

• Health Informatics
• Clinical Data Visualization
• Chronic Disease Management

Background:

• Managing patients with multiple chronic conditions (MCC) presents significant healthcare challenges due to a lack of coordinated care strategies.
• Existing approaches often fail to capture the complex interplay and progression of multiple diseases within individual patients.

Purpose of the Study:

• To describe a prototype interactive platform for visualizing data-driven clinical pathways of MCC.
• To support shared decision-making between clinicians and patients by illustrating disease co-progression patterns.

Main Methods:

• Developed an interactive visualization platform using a Python web framework, JavaScript library, and a clinical pathway learning algorithm.
• Utilized actual practice data to learn and represent dominant patterns of clinical event co-progression.
• Demonstrated platform functionality with a cohort of 36 patients having chronic kidney disease, hypertension, and diabetes.

Main Results:

• The platform enables interactive exploration and interpretation of MCC pathways derived from patient data.
• Visualizations highlight dominant patterns in the co-progression of multiple chronic conditions.
• Successfully demonstrated the platform's capability to represent complex patient journeys.

Conclusions:

• The developed platform offers a novel approach to understanding and managing MCC by visualizing patient-specific clinical pathways.
• Interactive data-driven visualizations can enhance shared decision-making and improve coordinated care for complex patient populations.
• Further evaluation is planned to explore the platform's impact on MCC management.