unbiased

Depression Detection at the Point of Care: Automated Analysis of Linguistic Signals from Routine Primary Care Encounters

arXiv preprint 2026Depression is underdiagnosed in primary care, yet timely identification remains critical. Recorded clinical encounters, increasingly common with digital scribing technologies, present an opportunity to detect depression from naturalistic dialogue.

SocialLM: Social Signal Processing of Patient-Provider Communication using LLMs and Contextual Aggregation

CHIL 2026 Effective patient-provider communication is difficult to assess at scale. This work examines whether large language models can track 20 social behaviors from clinical transcripts without fine-tuning, and introduces an agreement-weighted ensemble to stabilise performance that otherwise varies by patient race and visit segment.

Envisioning the future of primary care: intervention strategies to support patient-centered communication feedback technology

JAMIA 2025Clinician implicit bias can impede patient-centered communication, leading to health care inequities. While the field of implicit bias education is evolving with advances in technology, clinicians’ perspectives remain underexplored.

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

AMIA 2024Using 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.

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.

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

JAMIA Open 2024 This study evaluates an AI system that provides automated feedback on social communication during primary care visits. By analyzing real clinical conversations, the system detects social signals and offers targeted feedback to clinicians. Results show that the feedback is technically reliable, usable, and has the potential to improve communication skills and patient care.

Leveraging Provocative Design Methods to Address Implicit Bias in Clinical Interactions through Technology

AMIA 2024Implicit bias impacts the quality of patient-clinician interactions, influencing patient outcomes and trust in healthcare. Most interventions to mitigate bias rely solely on expensive human assessments, rather than leveraging AI technology with clinician input.

Imagining Improved Interactions: Patients’ Designs To Address Implicit Bias

AMIA 2023 Implicit biases in healthcare harm communication, decision-making, and care quality for marginalized patients. Through co-design workshops with 32 BIPOC, LGBTQ+, and QTBIPOC individuals, we identified four patient-centered solutions: accountability measures, real-time correction, enablement tools, and provider resources. These insights advance patient-focused approaches to addressing bias in care.