Quantifying 60 Years of Gender Bias in Biomedical Research with Word Embeddings

Gender bias in biomedical research can have an adverse impact on the health of real people. For example, there is evidence that heart disease-related funded research generally focuses on men. Health disparities can form between men and at-risk groups of women (i.e., elderly and low-income) if there is not an equal number of heart disease-related studies for both genders. In this paper, we study temporal bias in biomedical research articles by measuring gender differences in word embeddings. Specifically, we address multiple questions, including, How has gender bias changed over time in biomedical research, and what health-related concepts are the most biased? Overall, we find that traditional gender stereotypes have reduced over time. However, we also find that the embeddings of many medical conditions are as biased today as they were 60 years ago (e.g., concepts related to drug addiction and body dysmorphia).

[1]  Anthony Rios,et al.  FuzzE: Fuzzy Fairness Evaluation of Offensive Language Classifiers on African-American English , 2020, AAAI.

[2]  Sean A. Munson,et al.  Unequal Representation and Gender Stereotypes in Image Search Results for Occupations , 2015, CHI.

[3]  J. Astbury,et al.  Gender disparities in mental health , 2001 .

[4]  Chandler May,et al.  On Measuring Social Biases in Sentence Encoders , 2019, NAACL.

[5]  Rui Dai,et al.  Classifying medical relations in clinical text via convolutional neural networks , 2018, Artif. Intell. Medicine.

[6]  Roger Levy,et al.  Simple dynamic word embeddings for mapping perceptions in the public sphere , 2019, Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science.

[7]  Maryam Habibi,et al.  Deep learning with word embeddings improves biomedical named entity recognition , 2017, Bioinform..

[8]  Vahid Garousi,et al.  GENSIM 2.0: A Customizable Process Simulation Model for Software Process Evaluation , 2008, ICSP.

[9]  Hongfang Liu,et al.  A Comparison of Word Embeddings for the Biomedical Natural Language Processing , 2018, J. Biomed. Informatics.

[10]  P. Albert,et al.  Why is depression more prevalent in women? , 2015, Journal of psychiatry & neuroscience : JPN.

[11]  Alan W Black,et al.  Quantifying Social Biases in Contextual Word Representations , 2019, ACL 2019.

[12]  Michael Carl Tschantz,et al.  Automated Experiments on Ad Privacy Settings , 2014, Proc. Priv. Enhancing Technol..

[13]  D. Brody,et al.  Depression and obesity in the U.S. adult household population, 2005-2010. , 2014, NCHS data brief.

[14]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[15]  Zeyu Li,et al.  Learning Gender-Neutral Word Embeddings , 2018, EMNLP.

[16]  M. Micale.  On the "Disappearance" of Hysteria: A Study in the Clinical Deconstruction of a Diagnosis , 1993, Isis.

[17]  Daniel Jurafsky,et al.  Word embeddings quantify 100 years of gender and ethnic stereotypes , 2017, Proceedings of the National Academy of Sciences.

[18]  Josephine Mokonogho,et al.  Racial and ethnic differences in depression: current perspectives , 2019, Neuropsychiatric disease and treatment.

[19]  Joel Escudé Font.  Determining Bias in Machine Translation with Deep Learning Techniques , 2019 .

[20]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[21]  Richard A. Harshman,et al.  Indexing by Latent Semantic Analysis , 1990, J. Am. Soc. Inf. Sci..

[22]  Madeleine van Zuylen,et al.  Quantifying Sex Bias in Clinical Studies at Scale With Automated Data Extraction , 2019, JAMA network open.

[23]  Sampo Pyysalo,et al.  How to Train good Word Embeddings for Biomedical NLP , 2016, BioNLP@ACL.

[24]  Latanya Sweeney,et al.  Discrimination in online ad delivery , 2013, CACM.

[25]  Irene Koshik,et al.  Journal of the american society for information science and technology-2012 , 2012 .

[26]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[27]  Adam Tauman Kalai,et al.  Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings , 2016, NIPS.

[28]  C. Hartung,et al.  Gender differences in the diagnosis of mental disorders: conclusions and controversies of the DSM-IV. , 1998, Psychological bulletin.

[29]  Ryan Cotterell,et al.  Gender Bias in Contextualized Word Embeddings , 2019, NAACL.

[30]  Vasudeva Varma,et al.  Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations , 2019, WWW.

[31]  Jeff M. Phillips,et al.  Attenuating Bias in Word Vectors , 2019, AISTATS.

[32]  Graeme Hirst,et al.  Understanding Undesirable Word Embedding Associations , 2019, ACL.

[33]  A. Greenwald,et al.  Measuring individual differences in implicit cognition: the implicit association test. , 1998, Journal of personality and social psychology.

[34]  Olivier Bodenreider,et al.  The Unified Medical Language System (UMLS): integrating biomedical terminology , 2004, Nucleic Acids Res..

[35]  H. Christensen,et al.  Perceived barriers and facilitators to mental health help-seeking in young people: a systematic review , 2010, BMC psychiatry.

[36]  Ruben Amarasingham,et al.  The legal and ethical concerns that arise from using complex predictive analytics in health care. , 2014, Health affairs.

[37]  Gender bias in research: how does it affect evidence based medicine? , 2007, Journal of the Royal Society of Medicine.

[38]  Arvind Narayanan,et al.  Semantics derived automatically from language corpora contain human-like biases , 2016, Science.

[39]  Calvin K. Lai,et al.  Estimating Implicit and Explicit Gender Bias Among Health Care Professionals and Surgeons. , 2019, JAMA network open.

[40]  Lucy Vasserman,et al.  Measuring and Mitigating Unintended Bias in Text Classification , 2018, AIES.

[41]  C. Dine,et al.  Assessment of Gender-Based Linguistic Differences in Physician Trainee Evaluations of Medical Faculty Using Automated Text Mining , 2019, JAMA network open.

[42]  V. Rodwin,et al.  Gender and the treatment of heart disease in older persons in the United States, France, and England: a comparative, population-based view of a clinical phenomenon. , 2004, Gender medicine.

[43]  T. Young,et al.  The gender bias in sleep apnea diagnosis : Are women missed because they have different symptoms ? , 1996 .

[44]  Marta R. Costa-jussà,et al.  Equalizing Gender Bias in Neural Machine Translation with Word Embeddings Techniques , 2019, Proceedings of the First Workshop on Gender Bias in Natural Language Processing.

[45]  Alfredo Maldonado,et al.  Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word Categories , 2019, Proceedings of the First Workshop on Gender Bias in Natural Language Processing.

[46]  Ted Pedersen,et al.  UMLS-Interface and UMLS-Similarity : Open Source Software for Measuring Paths and Semantic Similarity , 2009, AMIA.

[47]  Pascale Fung,et al.  Reducing Gender Bias in Abusive Language Detection , 2018, EMNLP.

[48]  Ramakanth Kavuluru,et al.  Convolutional neural networks for biomedical text classification: application in indexing biomedical articles , 2015, BCB.

[49]  R. Poínhos.  [Gender bias in medicine]. , 2011, Acta medica portuguesa.

[50]  T. Young,et al.  The gender bias in sleep apnea diagnosis. Are women missed because they have different symptoms? , 1996, Archives of internal medicine.