Case report on anorexia nervosa

Exploring Biases of Large Language Models in the Field of Mental Health: Comparative Questionnaire Study of the Effect of Gender and Sexual Orientation in Anorexia Nervosa and Bulimia Nervosa Case Vignettes

Background

Large language models (LLMs) are increasingly used in mental health, showing promise in assessing disorders. However, concerns exist regarding their accuracy, reliability, and fairness. Societal biases and underrepresentation of certain populations may impact LLMs. Because LLMs are already used for clinical practice, including decision support, it is important to investigate potential biases to ensure a responsible use of LLMs. Anorexia nervosa (AN) and bulimia nervosa (BN) show a lifetime prevalence of 1%-2%, affecting more women than men. Among men, homosexual men face a higher risk of eating disorders (EDs) than heterosexual men. However, men are underrepresented in ED research, and studies on gender, sexual orientation, and their impact on AN and BN prevalence, symptoms, and treatment outcomes remain limited.

objectives

We aimed to estimate the presence and size of bias related to gender and sexual orientation produced by a common LLM as well as a smaller LLM specifically trained for mental health analyses, exemplified in the context of ED symptomatology and health-related quality of life (HRQoL) of patients with AN or BN.

Methods

We extracted 30 case vignettes (22 AN and 8 BN) from scientific papers. We adapted each vignette to create 4 versions, describing a female versus male patient living with their female versus male partner (2 × 2 design), yielding 120 vignettes. We then fed each vignette into ChatGPT-4 and to "MentaLLaMA" based on the Large Language Model Meta AI (LLaMA) architecture thrice with the instruction to evaluate them by providing responses to 2 psychometric instruments, the RAND-36 questionnaire assessing HRQoL and the eating disorder examination questionnaire. With the resulting LLM-generated scores, we calculated multilevel models with a random intercept for gender and sexual orientation (accounting for within-vignette variance), nested in vignettes (accounting for between-vignette variance).

Results

In ChatGPT-4, the multilevel model with 360 observations indicated a significant association with gender for the RAND-36 mental composite summary (conditional means: 12.8 for male and 15.1 for female cases; 95% CI of the effect -6.15 to -0.35; P=.04) but neither with sexual orientation (P=.71) nor with an interaction effect (P=.37). We found no indications for main effects of gender (conditional means: 5.65 for male and 5.61 for female cases; 95% CI -0.10 to 0.14; P=.88), sexual orientation (conditional means: 5.63 for heterosexual and 5.62 for homosexual cases; 95% CI -0.14 to 0.09; P=.67), or for an interaction effect (P=.61, 95% CI -0.11 to 0.19) for the eating disorder examination questionnaire overall score (conditional means 5.59-5.65 95% CIs 5.45 to 5.7). MentaLLaMA did not yield reliable results.

Conclusions

LLM-generated mental HRQoL estimates for AN and BN case vignettes may be biased by gender, with male cases scoring lower despite no real-world evidence supporting this pattern. This highlights the risk of bias in generative artificial intelligence in the field of mental health. Understanding and mitigating biases related to gender and other factors, such as ethnicity, and socioeconomic status are crucial for responsible use in diagnostics and treatment recommendations.

A case report of anorexia nervosa in a 23-year-old Ethiopian woman

Key Clinical Messages

Limited studies on AN in Africa, including Ethiopia. Internet and media have changed body image portrayal in developing countries. A need for a multidisciplinary approach to treatment, training on positive coaching styles, and future research.

Abstract

The Global Burden of Disease had estimated anorexia nervosa (AN) or bulimia nervosa to be 13.6 million people. The lifetime prevalence of AN ranges from 2.4 to 4.3 percent. During their lifetime, up to 4% of females and up to 0.3% of males suffer from anorexia nervosa. Studies assessing AN in Africa, including Ethiopia, are limited. This case report describes a 23-year-old female patient who presented with anorectic symptoms and signs in Ethiopia. This case report describes a 23-year-old female patient who participated in sports activities. She had a low body weight based on a BMI of 13.15 kg/m2 and lost around 10 kg within the past 6 months. She feared gaining weight or becoming fat, thus restricting food intake. The findings on psychiatric evaluation encompassing detailed history and mental state examination suggested the diagnosis of Extreme anorexia nervosa, restricting type; adult malnutrition; major depressive disorder (MDD) (in remission); low risk of aggression; low risk of suicide; severe functional impairment. The general management principles implemented in this patient included assessment of medical complications, weight restoration, psychological intervention, medication for comorbid depression, and long-term psychological and biological treatment follow-up to avoid relapse. The presented case of a 23-year-old Ethiopian female patient who is athletic shows weight-controlled sports activities and the manifestation of anorexia nervosa. Easy access to the Internet and media has changed body image portrayal in developing countries including Ethiopia. There is a need for a multidisciplinary approach involving psychiatrists, psychologists, internists, and nutritionists for the management of AN. The early screening and management of medical complications are crucial. There is a need for close monitoring of vital signs, restriction of caffeine, excess fluid, and salt, and limiting excessive exercise. Furthermore, to assess micronutrient deficiencies, vitamin supplements should be prescribed in the form of multivitamin and thiamine preparations. The need for future training about positive coaching styles for coaches is mandatory to reduce the future impacts on young athletes. There is a need for future research on eating disorders in developing countries such as Ethiopia.

Eating Disorders: An Overview of Indian Research

There has been sporadic research on eating disorders in India, with no published attempt to collate and summarize the literature landscape. Hence, the present narrative review aims to summarize Indian work related to eating disorders, discern current trends, and highlight gaps in research that will provide directions for future work in the area. Electronic search using the MEDLINE, Google Scholar, and PsycINFO databases was done to identify relevant peer-reviewed English language articles, in October 2018, using combinations of the following medical subject headings or free text terms: "eating disorders," "anorexia nervosa," "bulimia," "treatment," "epidemiology," "co-morbidity," "management," "medications," "behavioral intervention," and "psychosocial intervention." The data extracted from studies included details such as author names, year, from which of the states in India the work originated, type of intervention (for interventional studies), comparator (if any), and major outcomes. There is increasing research focused on eating disorders from India over the last decade, but it continues to be an under-researched area as evidenced by the relative paucity of original research. The cultural differences between east and west have contributed to variations in the presentation as well as challenges in the diagnosis. Hence, there is a need for the development of culturally sensitive instruments for diagnosis, as well as generating locally relevant epidemiological data about eating disorders from community and hospital settings.