Chronic pain is a prevalent issue in Australia, driving many individuals to seek medical care. However, most chronic pain conditions are incurable and require education, exercise, and other interventions for management. This makes chronic pain a complex, common, and costly health challenge.

The challenge becomes even more pronounced when treating children and individuals with diverse needs, such as those with language deficits and varying learning abilities. To address this, a team of researchers from CSIRO, RECOVER Injury Research Centre, the Tess Cramond Pain and Research Centre, and the Queensland Interdisciplinary Paediatric Pain Service are exploring the use of therapeutic chatbots to improve communication between people with chronic pain and healthcare professionals.

The researchers have developed a chatbot named Dolores, which has a unique feature: a canvas that allows users to visually depict their pain through drawings, sketches, and doodles. This visual representation proves to be highly effective in conveying information about pain experiences.

Dolores primarily functions as a tool for users to report data on their pain and receive personalized education. It aims to enhance communication between users and healthcare professionals and improve pain management. The chatbot engages in conversation with users, prompting them for more information and tailoring its responses based on the user’s age and level of understanding.

Privacy and ethical considerations were taken into account during the design of Dolores, as it often captures sensitive data. Unlike other chatbots that rely on large language models, Dolores operates based on a knowledge base and conversation flow developed by occupational, speech, and physiotherapists with diverse experience in working with clients of different ages.

Dolores is also utilized to conduct “pain history interviews,” where it asks users questions about the onset, location, duration, sensations, emotions, and impact of their pain on daily life. Users can respond to Dolores through speech, typing, or drawing. The chatbot then generates a transcript that can be shared with medical professionals.

The future version of Dolores aims to incorporate sketch recognition, allowing the chatbot to interpret drawings and gain further insight into the user’s pain experiences. This development is expected to enhance engagement and provide more comprehensive support to clients.

Dolores has been well-received by patients of various age groups and will soon be integrated into the broader chronic pain intervention platform, Pain ROADMAP. The chatbot is a significant step forward in addressing the communication barriers faced by clients and communities with different languages or language disorders. By identifying and conveying symbols of pain to clinicians, Dolores can facilitate more effective communication and ultimately improve pain management.