Search for: All records

Automatic assessment of impairment and disease severity is a key challenge in data-driven medicine. We propose a framework to address this challenge, which leverages AI models trained exclusively on healthy individuals. The COnfidence-Based chaRacterization of Anomalies (COBRA) score exploits the decrease in confidence of these models when presented with impaired or diseased patients to quantify their deviation from the healthy population. We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients. The gold-standard Fugl-Meyer Assessment (FMA) requires in-person administration by a trained assessor for 30-45 minutes, which restricts monitoring frequency and precludes physicians from adapting rehabilitation protocols to the progress of each patient. The COBRA score, computed automatically in under one minute, is shown to be strongly correlated with the FMA on an independent test cohort for two different data modalities: wearable sensors (ρ = 0.814, 95% CI [0.700,0.888]) and video (ρ = 0.736, 95% C.I [0.584, 0.838]). To demonstrate the generalizability of the approach to other conditions, the COBRA score was also applied to quantify severity of knee osteoarthritis from magnetic-resonance imaging scans, again achieving significant correlation with an independent clinical assessment (ρ = 0.644, 95% C.I [0.585,0.696]). 

ABSTRACT The International Pulsar Timing Array (IPTA)’s second data release (IPTA DR2) combines decades of observations of 65 millisecond pulsars from 7 radio telescopes. IPTA data sets should be the most sensitive data sets to nanohertz gravitational waves (GWs), but take years to assemble, often excluding valuable recent data. To address this, we introduce the IPTA ‘Lite’ analysis, where a Figure of Merit is used to select an optimal PTA data set to analyse for each pulsar, enabling immediate access to new data and preliminary results prior to full combination. We test the capabilities of the Lite analysis using IPTA DR2, finding that ‘DR2 Lite’ can be used to detect the common red noise process with an amplitude of $$A = 4.8^{+1.8}_{-1.8} \times 10^{-15}$$ at $$\gamma = 13/3$$. This amplitude is slightly large in comparison to the combined analysis, and likely biased high as DR2 Lite is more sensitive to systematic errors from individual pulsars than the full data set. Furthermore, although there is no strong evidence for Hellings-Downs correlations in IPTA DR2, we still find the full data set is better at resolving Hellings-Downs correlations than DR2 Lite. Alongside the Lite analysis, we also find that analysing a subset of pulsars from IPTA DR2, available at a hypothetical ‘early’ stage of combination (EDR2), yields equally competitive results as the full data set. Looking ahead, the Lite method will enable rapid synthesis of the latest PTA data, offering preliminary GW constraints before the superior full data set combinations are available.