Blending camera and 77 GHz radar sensing for equitable, robust plethysmography

With the resurgence of non-contact vital sign sensing due to the COVID-19 pandemic, remote heart-rate monitoring has gained significant prominence. Many existing methods use cameras;however previous work shows a performance loss for darker skin tones. In this paper, we show through light transport analysis that the camera modality is fundamentally biased against darker skin tones. We propose to reduce this bias through multi-modal fusion with a complementary and fairer modality - radar. Through a novel debiasing oriented fusion framework, we achieve performance gains over all tested baselines and achieve skin tone fairness improvements over the RGB modality. That is, the associated Pareto frontier between performance and fairness is improved when compared to the RGB modality. In addition, performance improvements are obtained over the radar-based method, with small trade-offs in fairness. We also open-source the largest multi-modal remote heart-rate estimation dataset of paired camera and radar measurements with a focus on skin tone representation. © 2022 Owner/Author.

Evaluation of patient financial savings from telemedicine implementation in a neurology department in a major urban academic medical center

Objective: We wanted to see how outpatient neurology clinics at UCLA changed following COVID-19. Background: The COVID-19 pandemic forced rapid adoption of telemedicine for care of neurology patients. This study describes the structure and implementation of telemedicine-based outpatient neurology clinics at UCLA Medical Center, before and after the California COVID-19 "Safer at Home" order, with a novel method to determine patient cost savings. We also present patient and provider satisfaction. Design/Methods: This was a retrospective, non-randomized, case series of telemedicine-based neurological management in an urban academic medical center from October 2018 to June 2020. Estimated roundtrip travel time, travel distance, and total travel cost are reported. Time-based opportunity savings were estimated using publicly available Internal Revenue Service statistics of income tax data to approximate hourly earnings by ZIP code. Patient satisfaction surveys were automatically sent to each patient following every video visit encounter. Results: We conducted 9,189 telemedicine video visits by 7,194 patients seeking neurological care. Telemedicine patients avoided a median roundtrip driving distance of 33 miles and saved a median roundtrip travel time of 75 minutes. With in the sample, median hourly earnings were $27/hr. Patients saved a median of $18 on fuel and parking, and $36 in time-based opportunity savings, for $54 median total savings per telemedicine visit. In 1,000 surveys, 86% of patients were satisfied with the video visit experience. Satisfaction of 37 providers was surveyed, with 29 responses (78.4%) supporting effectiveness of video visits as meeting expectations. Conclusions: Telemedicine offers travel and time savings for neurology patients. Successful implementation of telemedicine-based neurology clinics in an academic metropolitan medical center achieved high patient and provider satisfaction and cost savings. Future studies should explore transitions into hybrid approaches that combine in-person visits with telemedicine.