AMIA 2024
Implicit bias in patient-provider communication can lead to healthcare inequities, yet it is challenging to detect. Using ASR and NLP, we developed a pipeline to analyze social signals in audio recordings of 782 primary care visits, achieving 90.1% accuracy and fairness across patient groups. The analysis revealed significant disparities in provider behaviors, with more patient-centered communication observed toward white patients, highlighting the potential of automated tools to uncover biases and promote equitable healthcare.
JAMIA Open 2024
Implicit bias perpetuates health care inequities and manifests in patient–provider interactions, particularly nonverbal social cues like dominance. We investigated the use of artificial intelligence (AI) for automated communication assessment and feedback during primary care visits to raise clinician awareness of bias in patient interactions.
TOCHI 2024
Providing asynchronous feedback is a critical step in the 3D design workflow. A common approach to providing feedback is to pair textual comments with companion reference images, which helps illustrate the gist of text. Ideally, feedback providers should possess 3D and image editing skills to create reference images that can effectively describe what they have in mind. However, they often lack such skills, so they have to resort to sketches or online images which might not match well with the current 3D design. To address this, we introduce MemoVis, a text editor interface that assists feedback providers in creating reference images with generative AI driven by the feedback comments. First, a novel real-time viewpoint suggestion feature, based on a vision-language foundation model, helps feedback providers anchor a comment with a camera viewpoint. Second, given a camera viewpoint, we introduce three types of image modifiers, based on pre-trained 2D generative models, to turn a text comment into an updated version of the 3D scene from that viewpoint.
CHI 2024
Analyzing patient-provider communication through social signals like dominance, interactivity, engagement, and warmth can help improve care by identifying opportunities for better interactions. We introduce a machine-learning pipeline embedded in ConverSense, a web application that visualizes communication patterns across visits. A user study with clinicians and patients highlights its potential to provide actionable, context-specific feedback for enhancing communication quality and patient outcomes.
CHI 2024
Implicit bias among healthcare providers can negatively impact care quality and patient outcomes, necessitating tools to identify and address these biases. Through design sessions with 24 primary care providers, we found they prefer feedback with transparent metrics, trends across visits, and actionable tips presented in a dashboard. These insights can guide the development of interactive systems to support equitable healthcare, especially for marginalized communities.