Search

In many medical applications, interpretable models with high prediction performance are sought. Often, those models are required to handle semistructured data like tabular and image data. We show how to apply deep transformation models (DTMs) for distributional regression that fulfill these requirements. DTMs allow the data analyst to specify (deep) neural networks for different input modalities making them applicable to various research questions. Like statistical models, DTMs can provide interpretable effect estimates while achieving the state-of-the-art prediction performance of deep neural networks. In addition, the construction of ensembles of DTMs that retain model structure and interpretability allows quantifying epistemic and aleatoric uncertainty. In this study, we compare several DTMs, including baseline-adjusted models, trained on a semistructured data set of 407 stroke patients with the aim to predict ordinal functional outcome three months after stroke. We follow statistical principles of model-building to achieve an adequate trade-off between interpretability and flexibility while assessing the relative importance of the involved data modalities. We evaluate the models for an ordinal and dichotomized version of the outcome as used in clinical practice. We show that both tabular clinical and brain imaging data are useful for functional outcome prediction, whereas models based on tabular data only outperform those based on imaging data only. There is no substantial evidence for improved prediction when combining both data modalities. Overall, we highlight that DTMs provide a powerful, interpretable approach to analyzing semistructured data and that they have the potential to support clinical decision-making.

OBJECTIVE To characterise the population fulfilling the Assessment of SpondyloArthritis international Society (ASAS) consensus definition of early axial spondyloarthritis (axSpA) and to determine the effectiveness of a first tumour necrosis factor inhibitor (TNFi) in early versus established axSpA in a large observational registry. METHODS A total of 3064 patients with axSpA in the Swiss Clinical Quality Management registry with data on duration of axial symptoms were included (≤2 years=early axSpA, N=658; >2 years=established axSpA, N=2406). Drug retention was analysed in patients starting a first TNFi in early axSpA (N=250) versus established axSpA (N=874) with multiple-adjusted Cox proportional hazards models. Adjusted logistic regression analyses were used to determine the achievement of the ASAS criteria for 40% improvement (ASAS40) at 1 year. RESULTS Sex distribution, disease activity, impairments of function and health-related quality of life were comparable between patients with early and established axSpA. Patients with established disease were older, had more prevalent axial radiographical damage and had a higher impairment of mobility. A comparable TNFi retention was found in early versus established disease after adjustment for age, sex, human leucocyte antigen-B27 status, education, body mass index, smoking, elevated C reactive protein and sacroiliac inflammation on MRI (HR 1.05, 95% CI 0.78 to 1.42). The adjusted ASAS40 response was similar in the two groups (OR 1.09, 95% CI 0.67 to 1.78). Results were confirmed in the population fulfilling the ASAS classification criteria. CONCLUSION Considering the recent ASAS definition of early axSpA, TNFi effectiveness seems comparable in early versus established disease.

Methods: We performed an individual patient-level analysis of the OVID and ETHIC randomized controlled trials, which compared enoxaparin thromboprophylaxis for either 14 (OVID) or 21 days (ETHIC) vs. no thromboprophylaxis for outpatients with symptomatic COVID-19 and at least one additional risk factor. The primary efficacy outcome included all-cause hospitalization and all-cause death within 30 days from randomization. Both studies were prematurely stopped for futility. Secondary efficacy outcomes were major symptomatic venous thromboembolic events, arterial cardiovascular events, or their composite occurring within 30 days from randomization. The same outcomes were assessed over a 90-day follow-up. The primary safety outcome was major bleeding (ISTH criteria). Results: A total of 691 patients were randomized: 339 to receive enoxaparin and 352 to the control group. Over 30-day follow-up, the primary efficacy outcome occurred in 6.0 % of patients in the enoxaparin group vs. 5.8 % of controls for a risk ratio (RR) of 1.05 (95%CI 0.57-1.92). The incidence of major symptomatic venous thromboembolic events and arterial cardiovascular events was 0.9 % vs. 1.8 %, respectively (RR 0.52; 95%CI 0.13-2.06). Most cardiovascular thromboembolic events were represented by symptomatic venous thromboembolic events, occurring in 0.6 % vs. 1.5 % of patients, respectively. A similar distribution of outcomes between the treatment groups was observed over 90 days. No major bleeding occurred in the enoxaparin group vs. one (0.3 %) in the control group. Conclusions: We found no evidence for the clinical benefit of early administration of enoxaparin thromboprophylaxis in outpatients with symptomatic COVID-19. These results should be interpreted taking into consideration the relatively low occurrence of events.

OBJECTIVE To investigate sex differences in spinal radiographic progression in axial spondyloarthritis (axSpA). METHODS AxSpA patients in the Swiss Clinical Quality Management cohort with available spinal radiographs every 2 years were included. Paired radiographs were scored by two readers according to the modified Stoke Ankylosing Spondylitis Spinal Score (mSASSS). Progression was defined as an increase of ≥2 mSASSS units in 2 years. The relationship between sex and progression was investigated with binomial generalised estimating equation models, considering baseline spinal damage as an intermediate covariate. Additional analyses included adjustments for explanatory variables and multiple imputations for missingness. RESULTS In a total of 505 axSpA patients (317 men and 188 women), mean±SD radiographic progression over 2 years was 1.0±2.8 years in men and 0.3±1.1 years in women (p<0.001). Male sex was associated with enhanced progression in a small model not including baseline damage (OR 3.41, 95% CI 1.87 to 6.21). Both a direct effect of male sex on spinal progression, and an indirect effect, via enhancement of baseline spinal damage were significant (OR 2.06, 95% CI 1.15 to 3.67 and OR 1.04, 95% CI 1.01 to 1.07, respectively). A significant impact of male sex on spinal radiographic progression was still demonstrated after multiple adjustments for covariates known to potentially affect spinal radiographic progression (OR 1.97, 95% CI 1.04 to 3.71). CONCLUSIONS Spinal radiographic progression in axSpA is more severe in men than in women, with three times higher odds of progression in male patients and an effect that is mediated in part through an increase in baseline radiographic damage.

BACKGROUND Within the spectrum of spondyloarthritides, axial spondyloarthritis (axSpA) and psoriatic arthritis (PsA) present with overlapping features. Axial involvement in PsA (axial PsA) is treated according to recommendations for axSpA, as specific studies in axial PsA are scarce. We compared characteristics of patients with axSpA (particularly of patients with axSpA and concomitant psoriasis (pso)) with those of patients with axial PsA. METHODS Patients with axSpA and PsA in the Swiss Clinical Quality Management (SCQM) registry were included if information on pso and axial involvement was available. Patients with AxSpA were stratified by axSpA with and without pso (axSpA±pso) and patients with PsA were stratified to axial PsA or strictly peripheral PsA. RESULTS Previous or current psoriasis was observed in 479/4489 patients with axSpA (10.7%). Of 2631 patients with PsA, 1153 (43.8%) presented with axial involvement (opinion of the treating rheumatologist). Compared with patients with axSpA+pso, patients with axial PsA were older at symptom onset and at inclusion in SCQM, were less frequently HLA-B27 positive, had back pain less frequently and a higher prevalence of dactylitis and peripheral arthritis. A positive family history of pso or PsA was more frequent in axial PsA, while a positive family history of axSpA was more frequent in patients with axSpA+pso. Disease activity, function and mobility were comparable in axSpA+pso versus axial PsA. CONCLUSION Patients with axial PsA differ from patients with axSpA+pso in important demographic and clinical characteristics, and genetically, but present with a comparable disease burden. Treatment studies specifically dedicated to axial PsA seem warranted.

INTRODUCTION The benefits of early thromboprophylaxis in symptomatic COVID-19 outpatients remain unclear. We present the 90-day results from the randomised, open-label, parallel-group, investigator-initiated, multinational OVID phase III trial. METHODS Outpatients aged 50 years or older with acute symptomatic COVID-19 were randomised to receive enoxaparin 40 mg for 14 days once daily vs. standard of care (no thromboprophylaxis). The primary outcome was the composite of untoward hospitalisation and all-cause death within 30 days from randomisation. Secondary outcomes included arterial and venous major cardiovascular events, as well as the primary outcome within 90 days from randomisation. The study was prematurely terminated based on statistical criteria after the predefined interim analysis of 30-day data, which has been previously published. In the present analysis, we present the final, 90-day data from OVID and we additionally investigate the impact of thromboprophylaxis on the resolution of symptoms. RESULTS Of the 472 patients included in the intention-to-treat population, 234 were randomised to receive enoxaparin and 238 no thromboprophylaxis. The median age was 57 (Q1-Q3: 53-62) years and 217 (46 %) were women. The 90-day primary outcome occurred in 11 (4.7 %) patients of the enoxaparin arm and in 11 (4.6 %) controls (adjusted relative risk 1.00; 95 % CI: 0.44-2.25): 3 events per group occurred after day 30. The 90-day incidence of cardiovascular events was 0.9 % in the enoxaparin arm vs. 1.7 % in controls (relative risk 0.51; 95 % CI: 0.09-2.75). Individual symptoms improved progressively within 90 days with no difference between groups. At 90 days, 42 (17.9 %) patients in the enoxaparin arm and 40 (16.8 %) controls had persistent respiratory symptoms. CONCLUSIONS In adult community patients with COVID-19, early thromboprophylaxis with enoxaparin did not improve the course of COVID-19 neither in terms of hospitalisation and death nor considering COVID-19-rel