Search

Abstract Dystonia is a neurological movement disorder characterised by abnormal involuntary movements and postures, particularly affecting the head and neck. However, current clinical assessment methods for dystonia rely on simplified rating scales which lack the ability to capture the intricate spatiotemporal features of dystonic phenomena, hindering clinical management and limiting understanding of the underlying neurobiology. To address this, we developed a visual perceptive deep learning framework that utilizes standard clinical videos to comprehensively evaluate and quantify disease states and the impact of therapeutic interventions, specifically deep brain stimulation. This framework overcomes the limitations of traditional rating scales and offers an efficient and accurate method that is rater-independent for evaluating and monitoring dystonia patients. To evaluate the framework, we leveraged semi-standardized clinical video data collected in three retrospective, longitudinal cohort studies across seven academic centres. We extracted static head angle excursions for clinical validation and derived kinematic variables reflecting naturalistic head dynamics to predict dystonia severity, subtype, and neuromodulation effects. The framework was also applied to a fully independent cohort of generalised dystonia patients for comparison between dystonia sub-types. Computer vision-derived measurements of head angle excursions showed a strong correlation with clinically assigned scores. Across comparisons, we identified consistent kinematic features from full video assessments encoding information critical to disease severity, subtype, and effects of neural circuit interventions, independent of static head angle deviations used in scoring. Our visual perceptive machine learning framework reveals kinematic pathosignatures of dystonia, potentially augmenting clinical management, facilitating scientific translation, and informing personalized precision neurology approaches.

Abstract Background The HLA-DRB1 shared epitope (SE) is a risk factor for the development of rheumatoid arthritis (RA) and the production of anti-citrullinated protein antibodies (ACPAs) in RA patients. Our objective was to examine the real-world effectiveness of abatacept versus tumor necrosis factor inhibitors (TNFi) in patients with RA who were SE and anti-cyclic citrullinated peptide antibody (anti-CCP3) positive. Methods Abatacept or TNFi initiators who were SE + and anti-CCP3+ (> 20 U/mL) at or prior to treatment and had moderate or high CDAI score (> 10) at initiation were identified. The primary outcome was mean change in CDAI score over six months. Analyses were conducted in propensity score (PS)-trimmed and -matched populations overall and a biologic-experienced subgroup. Mixed-effects models were used. Results In the overall PS-trimmed (abatacept, n = 170; TNFi, n = 157) and PS-matched cohorts (abatacept, n = 111; TNFi, n = 111), there were numerically greater improvements in mean change in CDAI between abatacept and TNFi but were not statistically significant. Similar trends were seen for biologic-experienced patients, except that statistical significance was reached for mean change in CDAI in the PS-trimmed cohort (abatacept, 12.22 [95% confidence interval (95%CI) 10.13 to 14.31]; TNFi, 9.28 [95%CI 7.08 to 11.48]; p = 0.045). Conclusion In this real world cohort, there were numerical improvements in efficacy outcomes with abatacept over TNFi in patients with RA who were SE + and ACPA+, similar to results from a clinical trial population The only statistically significant finding after adjusting for covariates was greater improvement in CDAI with abatacept versus TNFi in the bio-experienced PS-trimmed cohort..