Experiences of pregnancy and perinatal healthcare access of women who are deaf: a qualitative study.

OBJECTIVE: Women who are deaf experience higher rates of reproductive healthcare barriers and adverse birth outcomes compared with their peers who can hear. This study explores the pregnancy experiences of women who are deaf to better understand their barriers to and facilitators of optimal pregnancy-related health care. DESIGN: Qualitative study using thematic analysis. SETTING: Semi-structured, individual, remote or in-person interviews conducted in the USA. SAMPLE: Forty-five women who are deaf and communicate using American Sign Language (ASL) and gave birth in the USA within the past 5 years participated in the interviews. METHODS: Semi-structured interviews explored how mothers who are deaf experienced pregnancy and birth, including access to perinatal information and resources, relationships with healthcare providers, communication access and their involvement with the healthcare system throughout pregnancy. A thematic analysis was conducted. MAIN OUTCOME MEASURES: Barriers and facilitators related to a positive experience of perinatal care access among women who are deaf. RESULTS: Three major themes emerged: (1) communication accessibility; (2) communication satisfaction; and (3) healthcare provider and team support. Common barriers included choosing healthcare providers, inconsistent communication access and difficulty accessing health information. However, when women who are deaf were able to use ASL interpreters, they had more positive pregnancy and birth experiences. Self-advocacy served as a common facilitator for more positive pregnancy and healthcare experiences. CONCLUSIONS: Healthcare providers need to be more aware of the communication and support needs of their patients who are deaf, especially how to communicate effectively. Increased cultural awareness and consistent provision of on-site interpreters can improve pregnancy and birth experiences for women who are deaf.

Maternal Health Experiences of Black Deaf and Hard of Hearing Women in the United States.

INTRODUCTION: Deaf and hard of hearing (DHH) women are faced with numerous health inequities, including adverse pregnancy and birth outcomes. These outcomes are likely exacerbated for Black DHH women because of the intersection of disability and race. This study aimed to explore the pregnancy and birth experiences of Black DHH women to identify factors that influence their pregnancy outcomes. METHODS: Semistructured interviews were conducted between 2018 and 2019 with 67 DHH women who gave birth in the past five years. The present study represents a subgroup analysis of eight of the 67 women who self-identified as Black. Interviews were recorded, transcribed, and analyzed for emerging themes. RESULTS: Primary themes centered on unmet needs, barriers, and facilitators. Barriers included limited access to health information owing to communication difficulties and challenges obtaining accommodations. Key facilitators included the availability of sign language interpreters, familial support, and cultural understanding from providers. Participants emphasized these facilitators in their recommendations to providers and DHH women. Findings also underscored the critical role of recognizing cultural identity in perinatal health care delivery. CONCLUSIONS: This study outlines themes that affect pregnancy and birthing experiences among Black DHH women in the United States. Study implications include a call to action for providers to prioritize communication accommodations, accessible information, and compassionate care for all Black DHH women. Furthermore, future work should explore the impact of cultural and racial concordance between patients and their health care providers and staff. Understanding how intersectional identities affect perinatal health care access is crucial for reducing disparities among Black DHH women.

Metrics and Algorithms for Locally Fair and Accurate Classifications using Ensembles.

To obtain accurate predictions of classifiers, model ensembles comprising multiple trained machine learning models are nowadays used. In particular, dynamic model ensembles pick the most accurate model for each query object, by applying the model that performed best on similar data. Dynamic model ensembles may however suffer, similarly to single machine learning models, from bias, which can eventually lead to unfair treatment of certain groups of a general population. To mitigate unfair classification, recent work has thus proposed fair model ensembles, that instead of focusing (solely) on accuracy also optimize global fairness. While such global fairness globally minimizes bias, imbalances may persist in different regions of the data, e.g., caused by some local bias maxima leading to local unfairness. Therefore, we extend our previous work by including a framework that bridges the gap between dynamic model ensembles and fair model ensembles. More precisely, we investigate the problem of devising locally fair and accurate dynamic model ensembles, which ultimately optimize for equal opportunity of similar subjects. We propose a general framework to perform this task and present several algorithms implementing the framework components. In this paper we also present a runtime-efficient framework adaptation that keeps the quality of the results on a similar level. Furthermore, new fairness metrics are presented as well as detailed informations about necessary data preparations. Our evaluation of the framework implementations and metrics shows that our approach outperforms the state-of-the art for different types and degrees of bias present in training data in terms of both local and global fairness, while reaching comparable accuracy.