JMIR Publications

ABSTRACT

Background:

Cancer and its treatment can affect the short and long-term psychological well-being of patients and families in significant ways. Emotional distress, particularly symptoms of depression, are often associated with poor treatment adherence, reduced quality of life and higher mortality. Cancer support groups, especially those led by health care professionals, provide a safe place for participants to discuss fear, normalize stress reactions, share solidarity, and learn about effective coping strategies to build resilience and enhance coping. However, “in-person” support groups may not always be accessible to individuals; geographic distance is one of the barriers for access, and compromised physical condition is another (e.g. fatigue, pain). Emerging evidence supports the effectiveness of online support groups (OSGs) to reduce access barriers. Text-based and professional-led OSGs have been offered by Cancer Chat Canada (CCC). Participants joined the group discussion using text in real time. Despite the reported benefits, therapist leaders report some challenges leading text-based OSGs in the absence of visual cues, particularly in tracking participant distress. With multiple participants typing at the same time, the nuances of the text messages or “red flags” for distress can sometimes be missed. Recent advances in artificial intelligence (AI) and natural language processing (NLP) offer potential solutions. NLP can be used to analyze OSG text data to track participants’ expressed emotions and distress, including anger, fear and sadness. NLP can monitor session activities in real-time and alert the therapist of participant’s disengagement.

Objective:

This protocol outlines the development and evaluation of an Artificial Intelligence-based Co-facilitator (AICF) prototype to track and monitor OSG participants’ distress through real-time analysis of text-based messages posted during synchronous sessions.

Methods:

AICF is developed to 1. Identify participant(s) who are at-risk for increased emotional distress, and track participant(s) engagement and in-session group cohesion levels, providing real-time alerts for therapist(s) to follow-up; 2. generate post-session participant profiles that contain discussion content keywords, and emotion profiles for each session; and 3. automatically suggests tailored resources to participants according to their needs.

Results:

The current paper provides preliminary results for phase I design of AICF.

Conclusions:

AICF offers a promising new mode of delivery of person-centred OSGs tailored to individual needs.