Journal Article10.1177/17456916221134490
A Call to Action on Assessing and Mitigating Bias in Artificial Intelligence Applications for Mental Health.
Adela C. Timmons,Jacqueline B Duong,Natalia Simo Fiallo,Theodore Lee,Huong Phuc Quynh Vo,Matthew W. Ahle,Jonathan S. Comer,La Princess C. Brewer,Stacy L. Frazier,Theodora Chaspari +9 more
89
TL;DR: In this paper , the authors review the health-equity implications of applying AI to mental health problems, outline state-of-the-art methods for assessing and mitigating algorithmic bias, and present a call to action to guide the development of fair-aware AI in psychological science.
read more
Abstract: Advances in computer science and data-analytic methods are driving a new era in mental health research and application. Artificial intelligence (AI) technologies hold the potential to enhance the assessment, diagnosis, and treatment of people experiencing mental health problems and to increase the reach and impact of mental health care. However, AI applications will not mitigate mental health disparities if they are built from historical data that reflect underlying social biases and inequities. AI models biased against sensitive classes could reinforce and even perpetuate existing inequities if these models create legacies that differentially impact who is diagnosed and treated, and how effectively. The current article reviews the health-equity implications of applying AI to mental health problems, outlines state-of-the-art methods for assessing and mitigating algorithmic bias, and presents a call to action to guide the development of fair-aware AI in psychological science.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Leveraging Large Language Models for Mental Health Prediction via Online Text Data
Xuhai Xu,Bingsheng Yao,Yuanzhe Dong,Hong Yu,James A. Hendler,Anind K. Dey,Dakuo Wang +6 more
TL;DR: This work presents the first comprehensive evaluation of multiple LLMs, including AlPaca, Alpaca-LoRA, and GPT-3.5, on various mental health prediction tasks via online text data and shows that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously.
74
The risks of using ChatGPT to obtain common safety-related information and advice
Oscar Oviedo‐Trespalacios,Amy E. Peden,Thomas Cole-Hunter,Arianna Costantini,Milad Haghani,J.E. Rod,Sage Kelly,Helma Torkamaan,Amina Tariq,James David Albert Newton,Timothy Gallagher,Steffen Steinert,Ashleigh J. Filtness,Genserik Reniers +13 more
TL;DR: ChatGPT has the potential to provide inaccurate or harmful safety-related information, potentially leading to ecological fallacy. There is a need for caution when using ChatGPT for safety-related information and expert verification.
54
Mental-LLM: Leveraging Large Language Models for Mental Health Prediction via Online Text Data
Xuhai Xu,Bingsheng Yao,Yu Dong,Hong Yu,James A. Hendler,Anind K. Dey,Dakuo Wang +6 more
- 26 Jul 2023
TL;DR: A comprehensive evaluation of multiple LLMs on various mental health prediction tasks via online text data, including Alpaca, Alpaca-LoRA, FLAN-T5, GPT-3.5, and GPT-4.5, and a set of action guidelines for potential methods to enhance LLMs' capability for mental health tasks are presented.
AI Chatbots in Digital Mental Health
TL;DR: Artificial intelligence chatbots hold promise in transforming digital mental health but must navigate complex ethical and practical challenges, and the integration of HAI principles, responsible regulation and scoping reviews are crucial to maximizing their benefits while minimizing potential risks.
37
Ethical Considerations in the Use of Artificial Intelligence and Machine Learning in Health Care: A Comprehensive Review
Mitul Harishbhai Tilala,Pradeep Kumar Chenchala,Ashok Choppadandi,Jagbir Kaur,Savitha Naguri,Rahul Saoji,Bhanu Devaguptapu +6 more
TL;DR: Ethical considerations in AI and ML in healthcare involve privacy, data security, algorithmic bias, transparency, clinical validation, and professional responsibility.
References
•Posted Content
The Architecture of Inclusion: Advancing Workplace Equity in Higher Education
TL;DR: In this paper, the authors develop a paradigm for advancing workplace equality when the problems causing racial and gender under-participation are structural, and the legal environment surrounding diversity initiatives is uncertain.
A cross-cultural study on emotion expression and the learning of social norms.
TL;DR: Cross-cultural differences in how group emotional expressions can be used to deduce a norm violation in four cultures, which differ in terms of decoding rules for negative emotions, demonstrate both cultural universality and cultural differences in the use of group emotion expressions in norm learning.
Using artificial intelligence on dermatology conditions in Uganda: A case for diversity in training data sets for machine learning
Louis Henry Kamulegeya,Mark Okello,John Mark Bwanika,Davis Musinguzi,William Lubega,Davis Rusoke,Faith Nassiwa,Alexander Börve +7 more
TL;DR: There is a need for diversity in the image datasets used when training dermatology algorithms for AI applications in clinical decision support as a means to increase accuracy and thus offer correct treatment across skin types and geographies.
Environment of childhood poverty
Gary W. Evans
- 01 Jan 2006
TL;DR: The accumulation of multiple environmental risks rather than singular risk exposure may be an especially pathogenic aspect of childhood poverty.
•Posted Content
Diversity in Faces.
TL;DR: Diversity in Faces (DiF) provides a data set of one million annotated human face images for advancing the study of facial diversity, and believes that by making the extracted coding schemes available on a large set of faces, can accelerate research and development towards creating more fair and accurate facial recognition systems.