OBJECTIVE: To support ambulatory care innovation, we created Observer, a multimodal dataset comprising videotaped outpatient visits, electronic health record (EHR) data, and structured surveys. This paper describes the data collection procedures and summarizes the clinical and contextual features of the dataset. MATERIALS AND METHODS: A multistakeholder steering group shaped recruitment strategies, survey design, and privacy-preserving design. Consented patients and primary care providers (PCPs) were recorded using room-view and egocentric cameras. EHR data, metadata, and audit logs were also captured. A custom de-identification pipeline, combining transcript redaction, voice masking, and facial blurring, ensured video and EHR HIPAA compliance. RESULTS: We report on the first 100 visits in this continually growing dataset. Thirteen PCPs from 4 clinics participated. Recording the first 100 visits required approaching 210 patients, from which 129 consented (61%), with 29 patients missing their scheduled encounter after consenting. Visit lengths ranged from 5 to 100 minutes, covering preventive care to chronic disease management. Survey responses revealed high satisfaction: 4.24/5 (patients) and 3.94/5 (PCPs). Visit experience was unaffected by the presence of video recording technology. DISCUSSION: We demonstrate the feasibility of capturing rich, real-world primary care interactions using scalable, privacy-sensitive methods. Room layout and camera placement were key influences on recorded communication and are now added to the dataset. The Observer dataset enables future clinical AI research/development, communication studies, and informatics education among public and private user groups. CONCLUSION: Observer is a new, shareable, real-world clinic encounter research and teaching resource with a representative sample of adult primary care data.

Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an innovative method using state-of-the-art MLLMs to estimate the modality importance, which can serve as a proxy for human judgments of modality perception. With this MIS, we demonstrate the presence of unimodal bias and the scarcity of genuinely multimodal questions in existing datasets. We further validate the modality importance score with multiple ablation studies to evaluate the performance of MLLMs on permuted feature sets. Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets. Our proposed MLLM-derived MIS can guide the curation of modality-balanced datasets that advance multimodal learning and enhance MLLMs' capabilities to understand and utilize synergistic relations across modalities.

OBJECTIVE: The increasing use of audio-video (AV) data in healthcare has improved patient care, clinical training, and medical and ethnographic research. However, it has also introduced major challenges in preserving patient-provider privacy due to Protected Health Information (PHI) in such data. Traditional de-identification methods are inadequate for AV data, which can reveal identifiable information such as faces, voices, and environmental details. Our goal was to create a pipeline for de-identifying AV healthcare data that minimized the human effort required to guarantee successful de-identification. METHODS: We combined open-source tools with novel methods and infrastructure into a six-stage pipeline: (1) transcript extraction using WhisperX, (2) transcript de-identification with an adapted PHIlter, (3) audio de-identification through scrubbing, (4) video de-identification using YOLOv11 for pose detection and blurring, (5) recombining de-identified audio and video, and (6) validation and correction via manual quality control (QC). We developed two de-identification strategies to support different tolerances for lossy video images. We evaluated this pipeline using 10 h of simulated clinical AV recordings, comprising nearly 1.1 million video frames and approximately 72,000 words. RESULTS: In Precision Privacy Preservation (PPP) mode, MedVidDeId achieved a success rate of 50%, while in Greedy Privacy Preservation (GPP) mode, it achieved a 97.5% success rate. Compared to manual methods for a 15 min video segment, the pipeline reduced de-identification time by 26.7% in PPP and 64.2% in GPP modes. CONCLUSION: The MedVidDeID pipeline offers a viable, efficient hybrid solution for handling AV healthcare data and privacy preservation. Future work will focus on reducing upstream errors at each stage and minimizing the role of the human in the loop.