2024

Toward Automated Detection of Biased Social Signals from the Content of Clinical Conversations

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.

Artificial intelligence-generated feedback on social signals in patient--provider communication: technical performance, feedback usability, and impact

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.

MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback

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.

Enhancing Accuracy, Time Spent, and Ubiquity in Critical Healthcare Delineation via Cross-Device Contouring

DIS 2024

ConverSense: An Automated Approach to Assess Patient-Provider Interactions using Social Signals

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.

Designing Communication Feedback Systems To Reduce Healthcare Providers’ Implicit Biases In Patient Encounters

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.

“I’d be watching him contour till 10 o’clock at night”: Understanding Tensions between Teaching Methods and Learning Needs in Healthcare Apprenticeship

CHI 2024