Join the Machine Learning in Medical Imaging Consortium (MaLMIC) for an opportunity to network on machine learning

Elham Dolatabadi, PhD
Assistant Professor, York University

Talk Title: Healthcare Horizons: AI to Navigate the Evolving Landscape

Talk Abstract: As healthcare evolves, data expands, and learning algorithms become increasingly sophisticated, the integration of artificial intelligence (AI) emerges as a transformative force, reshaping the healthcare landscape. In this talk, Elham will explore how AI goes beyond being a mere tool, driving revolutionary changes across the field. From continuous monitoring for specific single tasks to complex multimodal decision-making and conversational AI, the potential applications are vast. However, this journey is not without its challenges. Key hurdles include robust evaluation processes, mitigating biases, and cultivating the right mindset and knowledge to ensure that AI innovations are both effective and equitable. These challenges, and the strategies to overcome them, will be the focus of this talk.

Catherine Stinson, PhD
Assistant Professor, Queen’s University

Talk Title: Chatbots as Mental Healthcare Proxies: Possibilities and Limitations

Talk Abstract: There is a great need for more affordable, accessible mental health treatment options, especially labour-intensive talk therapy. Given the impressive abilities of a new generation of chatbots like ChatGPT to mimic human conversational skills, there is hope that they might prove useful as proxies for human psychotherapists. In particular, there is hope that for communities facing barriers to mental health care, chatbots might fill the gap. We look in detail at the current generation of chatbots to understand what they do well, and what their limitations are, with support from empirical work in natural language processing. Where these tools perform best is on formulaic language tasks, in domains well covered in training corpora, using standard English. Unfortunately among the under-served communities are migrant and minority groups who may not communicate in standard English, and are not well represented in training corpora. For some psychotherapeutic interactions, particularly formulaic ones, the capacities of chatbots may be a good match. However, for for interactions where an empathetic relationship is essential, the current generation of therapy chatbots are potentially dangerous. While there is some room for chatbots to act as proxies for human psychotherapists, we should not overestimate their abilities.