Berkeley Open Extended Reality Recordings 2023 (BOXRR-23): 4.7 Million Motion Capture Recordings from 105,000 XR Users.

Extended reality (XR) devices such as the Meta Quest and Apple Vision Pro have seen a recent surge in attention, with motion tracking "telemetry" data lying at the core of nearly all XR and metaverse experiences. Researchers are just beginning to understand the implications of this data for security, privacy, usability, and more, but currently lack large-scale human motion datasets to study. The BOXRR-23 dataset contains 4,717,215 motion capture recordings, voluntarily submitted by 105,852 XR device users from over 50 countries. BOXRR-23 is over 200 times larger than the largest existing motion capture research dataset and uses a new, highly efficient and purpose-built XR Open Recording (XROR) file format.

Erratum: Author Correction: Human-machine partnership with artificial intelligence for chest radiograph diagnosis.

[This corrects the article DOI: 10.1038/s41746-019-0189-7.].

Human-machine partnership with artificial intelligence for chest radiograph diagnosis.

Human-in-the-loop (HITL) AI may enable an ideal symbiosis of human experts and AI models, harnessing the advantages of both while at the same time overcoming their respective limitations. The purpose of this study was to investigate a novel collective intelligence technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms. Using small groups of radiologists, the swarm-based technology was applied to the diagnosis of pneumonia on chest radiographs and compared against human experts alone, as well as two state-of-the-art deep learning AI models. Our work demonstrates that both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy than the human experts alone. Our work further demonstrates that when used in combination, the swarm-based technology and deep-learning technology outperformed either method alone. The superior diagnostic accuracy of the combined HITL AI solution compared to radiologists and AI alone has broad implications for the surging clinical AI deployment and implementation strategies in future practice.

Longitudinal changes in visual acuity in keratoconus.

PURPOSE: The present investigation aimed to identify factors that predict reduced visual acuity in keratoconus from a prospective, longitudinal study. METHODS: This report from the Collaborative Longitudinal Evaluation of Keratoconus (CLEK) Study used 7 years of follow-up data from 953 CLEK subjects who did not have penetrating keratoplasty in either eye at baseline and who provided enough data to compute the slope of the change over time in high- or low-contrast best-corrected visual acuity (BCVA). Outcome measures included these slopes and whether the number of letters correctly read decreased by 10 letters or more in at least one eye in 7 years. RESULTS: Mean age of the subjects at the first follow-up visit was 40.2 +/- 11.0 years (mean +/- SD). Overall, 44.4% were female, and 71.9% were white. The slope of the change in high- and low-contrast BCVA (-0.29 +/- 1.5 and -0.58 +/- 1.7 letters correct/year, respectively) translated into expected 7-year decreases of 2.03 high- and 4.06 low-contrast letters correct. High- and low-contrast visual acuity decreases of 10 or more letters correct occurred in 19.0% and 30.8% of subjects, respectively. Independent predictors of reduced high- and low-contrast BCVA included better baseline acuity, steeper first definite apical clearance lens (FDACL), and fundus abnormalities. Each diopter of steeper baseline FDACL predicted an increased deterioration of 0.49 high- and 0.63 low-contrast letters correct. CONCLUSIONS: CLEK Study subjects with keratoconus exhibited a slow but clear decrease in BCVA during follow-up, with low-contrast acuity deteriorating more rapidly than high-contrast. Better baseline BCVA, steeper FDACL, and fundus abnormalities were predictive of greater acuity loss with time.