Patterns of antidepressant therapy and clinical outcomes among ischaemic stroke survivors.

BACKGROUND AND PURPOSE: Depression is common after stroke and is often treated with antidepressant medications (AD). ADs have also been hypothesised to improve stroke recovery, although recent randomised trials were neutral. We investigated the patterns of in-hospital AD initiation after ischaemic stroke and association with clinical and readmission outcomes. METHODS: All Medicare fee-for-service beneficiaries aged 65 or older hospitalised for ischaemic stroke in participating Get With The Guidelines-Stroke hospitals between April and December 2014 were eligible for this analysis. Outcome measures included days alive and not in a healthcare institution (home time), all-cause mortality and readmission within 1-year postdischarge. Propensity score (PS)-adjusted logistic regression models were used to evaluate the associations between AD use and each outcome measure. We also compared outcomes in patients prescribed selective serotonin reuptake inhibitors (SSRIs) AD versus those prescribed non-SSRI ADs. RESULTS: Of 21 805 AD naïve patients included in this analysis, 1835 (8.4%) were started on an AD at discharge. Patients started on an AD had higher rates of depression and prior ischaemic stroke, presented with higher admission National Institutes of Health Stroke Scale score and were less likely to be discharged home. Similarly, patients started on an SSRI had lower rates of discharge to home. Adjusting for stroke severity, patients started on an AD had worse all-cause mortality, all-cause readmission, major adverse cardiac events, readmission for depression and decreased home-time. However, AD use was also associated with an increased risk for the sepsis, a falsification endpoint, suggesting the presence of residual confounding. CONCLUSIONS: Patients with ischaemic stroke initiated on AD therapy are at increased risk of poor clinical outcomes and readmission even after PS adjustment, suggesting that poststroke depression requiring medication is a poor prognostic sign. Further research is needed to explore the reasons why depression is associated with worse outcome, and whether AD treatment modifies this risk or not.

Multi-atlas image registration of clinical data with automated quality assessment using ventricle segmentation.

Registration is a core component of many imaging pipelines. In case of clinical scans, with lower resolution and sometimes substantial motion artifacts, registration can produce poor results. Visual assessment of registration quality in large clinical datasets is inefficient. In this work, we propose to automatically assess the quality of registration to an atlas in clinical FLAIR MRI scans of the brain. The method consists of automatically segmenting the ventricles of a given scan using a neural network, and comparing the segmentation to the atlas ventricles propagated to image space. We used the proposed method to improve clinical image registration to a general atlas by computing multiple registrations - one directly to the general atlas and others via different age-specific atlases - and then selecting the registration that yielded the highest ventricle overlap. Finally, as an example application of the complete pipeline, a voxelwise map of white matter hyperintensity burden was computed using only the scans with registration quality above a predefined threshold. Methods were evaluated in a single-site dataset of more than 1000 scans, as well as a multi-center dataset comprising 142 clinical scans from 12 sites. The automated ventricle segmentation reached a Dice coefficient with manual annotations of 0.89 in the single-site dataset, and 0.83 in the multi-center dataset. Registration via age-specific atlases could improve ventricle overlap compared to a direct registration to the general atlas (Dice similarity coefficient increase up to 0.15). Experiments also showed that selecting scans with the registration quality assessment method could improve the quality of average maps of white matter hyperintensity burden, instead of using all scans for the computation of the white matter hyperintensity map. In this work, we demonstrated the utility of an automated tool for assessing image registration quality in clinical scans. This image quality assessment step could ultimately assist in the translation of automated neuroimaging pipelines to the clinic.