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
Reinforcement learning for personalization : A systematic literature review
Floris den Hengst,Eoin Martino Grua,Ali el Hassouni,Mark Hoogendoorn +3 more
- 11 Nov 2020
TL;DR: This compressed contribution presents a survey into reinforcement learning (RL) for personalization and its applications in the rapidly changing environment.
47
Values, Attitudes, and Ideologies: Explicit and Implicit Constructs Shaping Perception and Action
Steven Hitlin,Kevin Pinkston +1 more
- 01 Jan 2013
TL;DR: This paper explored how beliefs are reciprocally influenced by social structure, as well as how and when these constructs influence situated behavior, and paid particular attention to the recent surge of research on implicit beliefs, vital for social psychological understanding of the socialized actor.
46
Transforming clinical practice guidelines and clinical pathways into fast-and-frugal decision trees to improve clinical care strategies.
TL;DR: Fast-and-frugal provides a simple and transparent, yet solid and robust, methodological framework connecting decision science to clinical care, a sorely needed missing link between CPGs/CPs and patient outcomes.
43
Gender De-Biasing in Speech Emotion Recognition.
Cristina Gorrostieta,Reza Lotfian,Kye Taylor,Richard Brutti,John Kane +4 more
- 15 Sep 2019
TL;DR: The effect of gender bias in speech emotion recognition is assessed and it is found that emotional activation model accuracy is consistently lower for female compared to male audio samples and a fairer and more consistent model accuracy can be achieved by applying a simple de-biasing training technique.
41