Bias in AI, Digital Mental Health Tools, and Educating Young People about AI: Interview with Computer Scientist and Engineer, Dr. Theodora Chaspari

In this episode of Healthy Minds Science, Dr. Alicia Sepulveda speaks with Dr. Theodora Ciasparri about the intersection of artificial intelligence, machine learning, and mental health. They explore the implications of demographic bias in machine learning algorithms, particularly in the context of speech-based models used for digital health. The conversation highlights the importance of interdisciplinary collaboration, the challenges of integrating AI into mental health treatment, and the need for education around AI for young people. Dr. Ciasparri shares insights from her research on socio-demographic disparities in mental health outcomes and emphasizes the necessity of user-centric design in developing effective digital health technologies. Articles Discussed: Timmons, A. C., Duong, J. B., Simo Fiallo, N., Lee, T., Vo, H. P. Q., Ahle, M. W., Comer, J. S., Brewer, L. C., Frazier, S. L., & Chaspari, T. (2023). A Call to Action on Assessing and Mitigating Bias in Artificial Intelligence Applications for Mental Health. Perspectives on psychological science : a journal of the Association for Psychological Science, 18(5), 1062–1096. https://doi.org/10.1177/17456916221134490 Yang, M., El-Attar, A. A., & Chaspari, T. (2024). Deconstructing demographic bias in speech-based machine learning models for digital health. Frontiers in digital health, 6, 1351637. https://doi.org/10.3389/fdgth.2024.1351637 Takeaways Interdisciplinary collaboration enhances understanding of human behavior. Demographic bias in AI can lead to disparities in healthcare outcomes. Speech characteristics can indicate mental health conditions like depression. Digital health technologies can improve real-world patient monitoring. AI algorithms are influenced by human decision-making processes. Education about AI is crucial for young people. Ethical considerations are essential in deploying digital health technologies. Machine learning models may not accurately reflect demographic differences. User input is vital in the development of AI technologies. The digital footprint of youth is expanding rapidly. Chapters 00:00 Introduction to Healthy Minds Science and Guest Background 02:51 Interdisciplinary Collaboration in Human Behavior Research 05:50 Understanding Demographic Bias in Machine Learning 07:00 Exploring Speech-Based Machine Learning Models 09:51 The Role of Digital Health in Mental Health Monitoring 12:46 Implications of Socio-Demographic Disparities in AI 16:00 The Importance of Education in AI for Young People 18:37 Future Directions in AI and Digital Health Research Keywords mental health, AI, machine learning, demographic bias, digital health, speech analysis, youth education, interdisciplinary research, emotional resilience, healthcare disparities Connect on LinkedIn: Dr. Theodora Chaspari: https://www.linkedin.com/in/chaspari/ Dr. Alicia Sepulveda: https://www.linkedin.com/in/alicia-sepulveda/ Center for Healthy Mind and Mood at CU Boulder: https://www.linkedin.com/company/mind-and-mood/