A Data-Centric Approach to Detecting and Mitigating Demographic Bias in Pediatric Mental Health Text: A Case Study in Anxiety Detection
University College London（伦敦大学学院）；Queen Mary University of London（伦敦玛丽女王大学）；University of Cincinnati（辛辛那提大学）；Oak Ridge National Laboratory（橡树岭国家实验室）
Julia Ive, Paulina Bondaronek, Vishal Yadav, Daniel Santel, Tracy Glauser, Tina Cheng, Jeffrey R. Strawn, Greeshma Agasthya, Jordan Tschida, Sanghyun Choo, Maya… 展开作者
Julia Ive, Paulina Bondaronek, Vishal Yadav, Daniel Santel, Tracy Glauser, Tina Cheng, Jeffrey R. Strawn, Greeshma Agasthya, Jordan Tschida, Sanghyun Choo, Mayanka Chandrashekar, Anuj J. Kapadia, John Pestian
Introduction: Healthcare AI models often inherit biases from their training data. While efforts have primarily targeted bias in structured data, mental health heavily depends on unstructured data. This study aims to detect and mitigate linguistic differences related to non-biological differences in the training data of AI models designed to assist in pediatric mental health screening. Our objectives are: (1) to assess the presence of bias by evaluating outcome parity across sex subgroups, (2) to identify bias sources through textual distribution analysis, and (3) to develop a de-biasing method for mental health text data. Methods: We examined classification parity across demographic groups and assessed how gendered language influences model predictions. A data-centric de-biasing method was applied, focusing on neutralizing biased terms while retaining salient clinical information. This methodology was tested on a model for automatic anxiety detection in pediatric patients. Results: Our findings revealed a systematic under-diagnosis of female adolescent patients, with a 4% lower accuracy and a 9% higher False Negative Rate (FNR) compared to male patients, likely due to disparities in information density and linguistic differences in patient notes. Notes for male patients were on average 500 words longer, and linguistic similarity metrics indicated distinct word distributions between genders. Implementing our de-biasing approach reduced diagnostic bias by up to 27%, demonstrating its effectiveness in enhancing equity across demographic groups. Discussion: We developed a data-centric de-biasing framework to address gender-based content disparities within clinical text. By neutralizing biased language and enhancing focus on clinically essential information, our approach demonstrates an effective strategy for mitigating bias in AI healthcare models trained on text.
Large Language Models for Mental Health Diagnostic Assessments: Exploring The Potential of Large Language Models for Assisting with Mental Health Diagnostic Assessments -- The Depression and Anxiety Case
Indian Institute of Research and Science, Bhopal（博帕尔印度研究与科学学院）；Indian Institute of Technology, Kharagpur（克勒格布尔印度理工学院）
StressRoBERTa: Cross-Condition Transfer Learning from Depression, Anxiety, and PTSD to Stress Detection
The George Washington University（乔治华盛顿大学）；King Saud University（沙特国王大学）；Johns Hopkins University Applied Physics Laboratory（约翰霍普金斯大学应用物理实验室）；Carnegie Mellon University（卡内基梅隆大学）
AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models' Responses to Depression, Anxiety, and Stress Queries
University of Tehran（塔里斯坦大学）；University of South Carolina（南卡罗来纳大学）；University of West London（西伦敦大学）；Azad University（阿扎德大学）；Amirkabir University of Technology（阿米卡比尔技术大学）
Still Not Quite There! Evaluating Large Language Models for Comorbid Mental Health Diagnosis
University of Southern California（美国南加州大学）；Georgia Institute of Technology（佐治亚理工学院）；Sion Hospital（Sion医院）；Clinical Psychotherapist（临床心理治疗师）；Sophia College for Women（Sophia女子学院）；Indian Institute of Technology Bombay（印度班加罗尔理工学院）
What Are You Anxious About? Examining Subjects of Anxiety during the COVID-19 Pandemic
Institute for Clarity in Documentation（文档清晰化研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗克库尔中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕尔默研究实验室）
Early Linguistic Pattern of Anxiety from Social Media Using Interpretable Linguistic Features: A Multi-Faceted Validation Study with Author-Disjoint Evaluation
Optimizing Large Language Models for Detecting Symptoms of Comorbid Depression or Anxiety in Chronic Diseases: Insights from Patient Messages
Stanford University（斯坦福大学）；Stanford School of Medicine（斯坦福医学院）；Stanford Health Care（斯坦福医疗保健系统）；Google LLC（谷歌公司）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Veterans Affairs Palo Alto Health Care System（帕洛阿尔托退伍军人事务医疗保健系统）
Exploring Large Language Models for Detecting Mental Disorders
AIRI；ISP RAS Research Center for Trusted Artificial Intelligence（俄罗斯科学院信息与系统研究信任人工智能研究中心）；FRC CSC RAS（俄罗斯科学院应用数学与计算机科学研究所）；MIPT（米哈伊尔·伊万诺维奇·普京高等经济学院）；RUDN University（俄罗斯人民友谊大学）；MBZUAI（马斯喀特大学人工智能研究所）
MAQuA: Adaptive Question-Asking for Multidimensional Mental Health Screening using Item Response Theory
Language Technologies Institute, Carnegie Mellon University（卡内基梅隆大学语言技术研究所）；Stony Brook University（石溪大学）；Aarhus University（奥胡斯大学）；Department of Psychology, Lund University（吕勒欧大学心理学系）；College of Connected Computing, Vanderbilt University（范德比尔特大学连接计算学院）
Extracting Social Determinants of Health from Pediatric Patient Notes Using Large Language Models: Novel Corpus and Methods
University of Washington（华盛顿大学）；George Mason University（乔治梅森大学）；Dana-Farber Cancer Institute（达纳-法伯癌症研究所）；Boston Children's Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）
The Expressions of Depression and Anxiety in Chinese Psycho-counseling: Usage of First-person Singular Pronoun and Negative Emotional Words
Hangzhou Normal University（杭州师范大学）；Zhejiang University（浙江大学）；Westlake University（西湖大学）；Queen Mary University of London（伦敦玛丽女王大学）；Hangzhou Polytechnic（杭州职业技术学院）
Efficient or Powerful? Trade-offs Between Machine Learning and Deep Learning for Mental Illness Detection on Social Media
University of Pennsylvania（宾夕法尼亚大学）；School of Engineering and Applied Science（工程与应用科学学院）；New York University（纽约大学）；Center for Data Science（数据科学中心）；Georgia Institute of Technology（佐治亚理工学院）；College of Computing（计算学院）；University of California, Berkeley（加州大学伯克利分校）；Department of EECS（电子工程与科学系）；Northeastern University（东北大学）；Khoury College of Computer Science（计算机科学学院）
Multi-Level Narrative Evaluation Outperforms Lexical Features for Mental Health
Institute for Artificial Intelligence（人工智能研究院）；School of Psychological and Cognitive Sciences（心理学与认知科学学院）；School of Intelligence Science and Technology（智能科学与技术学院）；State Key Laboratory of General AI（通用人工智能国家重点实验室）；Beijing Key Laboratory of Behavior and Mental Health（北京行为与心理健康重点实验室）；PKU-Changsha Institute for Computing and Digital Economy（北京大学长沙计算与数字经济研究院）
