Scholarlink

<p>Artificial intelligence (AI) holds immense potential to provide scalable, personalized and accessible solutions to mental healthcare. However, biases in AI systems might exacerbate current mental healthcare disparities, particularly for minoritized populations. In this Perspective, we introduce a model for bias reduction and inclusion through dynamic generative equity (adaptive AI), which has been designed to prioritize equity throughout the development and implementation of AI systems in mental health interventions. This model integrates fair-aware machine learning with co-creation techniques, combining quantitative methodologies to detect bias in AI algorithms with qualitative input from community collaborators to ensure cultural relevance and practical application. We describe the model’s procedures and iterative feedback loops, which ensure that AI-based interventions are culturally responsive and evolve dynamically with real-time feedback. We also&#xa0;discuss the model’s potential applications, current limitations and areas for future research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bridging fair-aware artificial intelligence and co-creation for equitable mental healthcare

  • 期刊论文

  • 发表日期：

    2025年9月19日

查看全文
  • Adela C. Timmons,
  • Jacqueline B. Duong,
  • Sierra N. Walters,
  • Kayla E. Carta,
  • Grace A. Jumonville,
  • Alyssa S. Carrasco,
  • Daniela N. Romero,
  • Matthew W. Ahle,
  • Jonathan S. Comer,
  • Ishita P. Khurd,
  • Theodora Chaspari

摘要

Artificial intelligence (AI) holds immense potential to provide scalable, personalized and accessible solutions to mental healthcare. However, biases in AI systems might exacerbate current mental healthcare disparities, particularly for minoritized populations. In this Perspective, we introduce a model for bias reduction and inclusion through dynamic generative equity (adaptive AI), which has been designed to prioritize equity throughout the development and implementation of AI systems in mental health interventions. This model integrates fair-aware machine learning with co-creation techniques, combining quantitative methodologies to detect bias in AI algorithms with qualitative input from community collaborators to ensure cultural relevance and practical application. We describe the model’s procedures and iterative feedback loops, which ensure that AI-based interventions are culturally responsive and evolve dynamically with real-time feedback. We also discuss the model’s potential applications, current limitations and areas for future research.