Interpretation of health-related expressions and dialogues: enabling personalized care with contextual measuring and machine learning

Abstract

We propose a new research framework that develops a method for interpretation of health-related expressions and dialogues to enable personalized care with contextual measuring and machine learning. The new research framework is implemented with a research project that gathers from various patient groups and other population groups a broad collection of essential perspectives towards health and well-being. In experimental setups persons (for example patients, their family members and representatives of care personnel) are asked to classify a given set of expressions (linguistic statements, image materials or other stimuli) into different categories, and these categorizations are then used as input vectors for computational models. To develop the method a central task is to classify with machine learning models health-related expressions and dialogues in respect to various events, processes and persons in healthcare. Our experimental results based on a sample of context-based linguistic health data indicated fruitful possibilities for gaining classifications of essential traits of language usage, appearance and activity for persons of diverse population groups based on various scales, perspectives, background assumptions and contexts.