A Cloud-based Risk Stratification Platform Cardiovascular Disease, Depression and Comorbidities

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Computational Psychiatry

Background:

• Co-occurrence of depression and cardiovascular disease (CVD) is clinically significant.
• Accurate identification of patients with comorbid depression and CVD is crucial for optimal management.
• Existing research lacks integrated tools for diagnosing both conditions simultaneously.

Purpose of the Study:

• To develop a cloud-based platform integrating AI models for diagnosing depression and CVD.
• To provide an easier, accurate, and cost-effective diagnostic solution.
• To facilitate clinical practice by enabling seamless AI model integration.

Main Methods:

• Development of a cloud-enabled computing unit utilizing REST architecture.
• Integration of AI algorithms and data exchange services.
• Implementation using Python 3, Java SDK 11, MySQL, and Payara Application Server on a Linux VM.

Main Results:

• A cost-effective, accurate, and efficient platform for risk stratification of depression and CVD.
• Seamless and transparent interfacing of AI models and applications for end-users.
• Successful hosting on a Linux Virtual Machine.

Conclusions:

• The developed platform represents a state-of-the-art solution for CVD and depression risk stratification.
• Cardiologists and psychiatrists can utilize this platform for improved patient identification and further examination.
• The integrated approach enhances the management of comorbid cardiovascular and depressive conditions.