Gender equality by 2045: reimagining a healthier future for women and girls

Amin, Avni; Remme, Michelle; Allotey, Pascale; Askew, Ian

doi:10.1136/bmj.n1621

Cited by 8 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Women's health is a field with a significant diagnostic and treatment gap. [5,6,8,35] Caution must be taken that, through these technologies, it does not widen. Safety in the context of women's health must be a priority.…”

Section: Discussionmentioning

confidence: 99%

“…O&G, a field with a history of significant diagnostic and treatment gaps, could leverage LLMs to bridge these disparities. [4][5][6][7][8] AI could aid in analysing patient histories, imaging, and test results to assist in early and accurate diagnoses. Additionally, AI-driven tools could provide personalized treatment options by processing large datasets to predict the most effective interventions for individual patients.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Capabilities of ChatGPT in Women’s Health

Bachmann,

Duta,

Mazey

et al. 2024

Preprint

View full text Add to dashboard Cite

Introduction: Artificial Intelligence (AI) is redefining healthcare, with Large Language Models (LLMs) like ChatGPT offering novel and powerful capabilities in processing and generating human-like information. These advancements offer potential improvements in Women's Health, particularly Obstetrics and Gynaecology (O&G), where diagnostic and treatment gaps have long existed. Despite its generalist nature, ChatGPT is increasingly being tested in healthcare, necessitating a critical analysis of its utility, limitations and safety. This study examines ChatGPT's performance in interpreting and responding to international gold standard benchmark assessments in O&G: the RCOG's MRCOG Part One and Two examinations. We evaluate ChatGPT's domain- and knowledge area-specific accuracy, the influence of linguistic complexity on performance and its self-assessment confidence and uncertainty, essential for safe clinical decision-making. Methods: A dataset of MRCOG examination questions from sources beyond the reach of LLMs was developed to mitigate the risk of ChatGPT's prior exposure. A dual-review process validated the technical and clinical accuracy of the questions, omitting those dependent on previous content, duplicates, or requiring image interpretation. Single Best Answer (SBA) and Extended Matching (EMQ) Questions were converted to JSON format to facilitate ChatGPT's interpretation, incorporating question types and background information. Interaction with ChatGPT was conducted via OpenAI's API, structured to ensure consistent, contextually informed responses from ChatGPT. The response from ChatGPT was recorded and compared against the known accurate response. Linguistic complexity was evaluated using unique token counts and Type-Token ratios (vocabulary breadth and diversity) to explore their influence on performance. ChatGPT was instructed to assign confidence scores to its answers (0-100%), reflecting its self-perceived accuracy. Responses were categorized by correctness and statistically analysed through entropy calculation, assessing ChatGPT's capacity for self-evaluating certainty and knowledge boundaries. Findings: Of 1,824 MRCOG Part One and Two questions, ChatGPT's accuracy on MRCOG Part One was 72.2% (95% CI 69.2-75.3). For Part Two, it achieved 50.4% accuracy (95% CI 47.2-53.5) with 534 correct out of 989 questions, performing better on SBAs (54.0%, 95% CI 50.0-58.0) than on EMQs (45.0%, 95% CI 40.1-49.9). In domain-specific performance, the highest accuracy was in Biochemistry (79.8%, 95% CI 71.4-88.1) and the lowest in Biophysics (51.4%, 95% CI 35.2-67.5). The best-performing subject in Part Two was Urogynaecology (63.0%, 95% CI 50.1-75.8) and the worst was Management of Labour (35.6%, 95% CI 21.6-49.5). Linguistic complexity analysis showed a marginal increase in unique token count for correct answers in Part One (median 122, IQR 114-134) compared to incorrect (median 120, IQR 112-131, p=0.05). TTR analysis revealed higher medians for correct answers with negligible effect sizes (Part One: 0.66, IQR 0.63-0.68; Part Two: 0.62, IQR 0.57-0.67) and p-values <0.001. Regarding self-assessed confidence, the median confidence for correct answers was 70.0% (IQR 60-90), the same as for incorrect choices identified as correct (p<0.001). For correct answers deemed incorrect, the median confidence was 10.0% (IQR 0-10), and for incorrect answers accurately identified, it was 5.0% (IQR 0-10, p<0.001). Entropy values were identical for correct and incorrect responses (median 1.46, IQR 0.44-1.77), indicating no discernible distinction in ChatGPT's prediction certainty. Conclusions: ChatGPT demonstrated commendable accuracy in basic medical queries on the MRCOG Part One, yet its performance was markedly reduced in the clinically demanding Part Two exam. The model's high self-confidence across correct and incorrect responses necessitates scrutiny for its application in clinical decision-making. These findings suggest that while ChatGPT has potential, its current form requires significant refinement before it can enhance diagnostic efficacy and clinical workflow in women's health.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploring the Capabilities of ChatGPT in Women’s Health

Bachmann,

Duta,

Mazey

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, the actor narratives of gender as inclusion through consideration of essentialised identities, highlights that this can lead to a binary and competing agenda on women's/girls' and boys'/men's health, without consideration and analysis of underlying gender inequalities [5,54]. This emphasises that categorical and binary understandings of gender are now inadequate and these can lead to zero-sum arguments for competing agendas and resources, and so diluted efforts to advance gender equality [5]. Moreover, the findings highlights the tensions in addressing gender in policy and programmes and that 'gender work' is both technical, but also about power and hence deeply political work [12,14,[58][59][60][61].…”

Section: Implications For Gender In Adolescent and Youth Health Policymentioning

confidence: 99%

“…More than 25 years after the landmark Beijing Platform for Action, advancing gender equality remains an ongoing global priority, as signalled by the impetus and focus of the UN Women Generation Equality Forum [1][2][3][4][5]. Over the past decades there have been some gains and improvements towards achieving substantive gender equality, however transforming policy, structures and systems that contribute to reproducing gender and intersecting inequalities remain a priority for action, both globally and in South Africa [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

How gender is socially constructed in policy making processes: a case study of the Adolescent and Youth Health Policy in South Africa

Jacobs

George

2023

Int J Equity Health

View full text Add to dashboard Cite

Background Gender equality remains an outstanding global priority, more than 25 years after the landmark Beijing Platform for Action. The disconnect between global health policy intentions and implementation is shaped by several conceptual, pragmatic and political factors, both globally and in South Africa. Actor narratives and different framings of gender and gender equality are one part of the contested nature of gender policy processes and their implementation challenges. The main aim of this paper is to foreground the range of policy actors, describe their narratives and different framings of gender, as part exploring the social construction of gender in policy processes, using the Adolescent Youth Health Policy (AYHP) as a case study. Methods A case study design was undertaken, with conceptual underpinnings combined from gender studies, sociology and health policy analysis. Through purposive sampling, a range of actors were selected, including AYHP authors from government and academia, members of the AYHP Advisory Panel, youth representatives from the National Department of Health Adolescent and Youth Advisory Panel, as well as adolescent and youth health and gender policy actors, in government, academia and civil society. Qualitative data was collected via in-depth, semi-structured interviews with 30 policy actors between 2019 and 2021. Thematic data analysis was used, as well as triangulation across both respondents, and the document analysis of the AYHP. Results Despite gender power relations and more gender-transformative approaches being discussed during the policy making process, these were not reflected in the final policy. Interviews revealed an interrelated constellation of diverse and juxtaposed actor gender narratives, ranging from framing gender as equating girls and women, gender as inclusion, gender as instrumental, gender as women’s rights and empowerment and gender as power relations. Some of these narrative framings were dominant in the policy making process and were consequently included in the final policy document, unlike other narratives. The way gender is framed in policy processes is shaped by actor narratives, and these diverse and contested discursive constructions were shaped by the dynamic interactions with the South Africa context, and processes of the Adolescent Youth Health Policy. These varied actor narratives were further contextualised in terms of reflections of what is needed going forward to advance gender equality in adolescent and youth health policy and programming. This includes prioritising gender and intersectionality on the national agenda, implementing more gender-transformative programmes, as well as having the commitments and capabilities to take the work forward. Conclusions The constellation of actors’ gender narratives reveals overlapping and contested framings of gender and what is required to advance gender equality. Understanding actor narratives in policy processes contributes to bridging the disconnect between policy commitments and reality in advancing the gender equality agenda.

show abstract

“…In this essay, I reflect on the misappropriation of the "gender transformative" language from its original intended purpose to becoming an important contributor in the continued marginalisation of gender equality concerns in global health programmes. As we consider the underwhelming achievements with respect to the many aspirations outlined in the Beijing Declaration at the Fourth World Conference on Women 25 years ago, and the recurrent examples of backsliding in the wake of the COVID-19 crisis [1,2], it is important to candidly assess why fundamental shifts towards gender equality have been much slower than desired or anticipated. In particular, it can be helpful to reflect on strategies that have taken a very different turn from our optimistic expectations so that we do not repeat mistakes of the past.…”

mentioning

confidence: 99%

The Disconnect Between Gender-Transformative Language and Action in Global Health

Malhotra¹

2021

View full text Add to dashboard Cite

Gender equality by 2045: reimagining a healthier future for women and girls

Abstract: Gender equality is achievable and an imperative

Cited by 8 publications

References 4 publications

Exploring the Capabilities of ChatGPT in Women’s Health

Exploring the Capabilities of ChatGPT in Women’s Health

How gender is socially constructed in policy making processes: a case study of the Adolescent and Youth Health Policy in South Africa

The Disconnect Between Gender-Transformative Language and Action in Global Health

Contact Info

Product

Resources

About