Optimising Personalised Medical Insights by Introducing a Scalable Health Informatics Application for Sensor Data...

Area of Science:

• Biomedical Engineering
• Digital Health
• Data Science

Background:

• Wearable sensors offer noninvasive remote healthcare monitoring but present data heterogeneity challenges.
• Balance problems are prevalent in neurodegenerative diseases, increasing fall risk and reducing quality of life.

Purpose of the Study:

• To introduce an online platform technology for uniform analysis of balance data from diverse wearable sensors.
• To facilitate comparative analyses and integration of advanced analytics for personalized medical insights.

Main Methods:

• Development of a versatile online platform for data preprocessing, feature extraction, analysis, and visualization.
• Enabling researchers to integrate chosen sensors or upload existing data.
• Facilitating the integration of machine learning and advanced data analytics.

Main Results:

• The platform reduces data heterogeneity, enabling easier sensor and dataset comparisons.
• It streamlines the analysis of quantitative balance data.
• Supports the application of machine learning for personalized health insights.

Conclusions:

• The presented platform addresses the challenge of data comparability in wearable sensor-based healthcare.
• It enhances the utility of balance data for understanding neurodegenerative conditions and personalizing treatment.
• Promotes scalable and quantitative assessment of balance for improved patient outcomes.