Quality of Life After Intravenous Thrombolysis for Acute Ischemic Stroke: Results From the AcT Randomized Controlled Trial.

BACKGROUND: Recent evidence from thrombolysis trials indicates the noninferiority of intravenous tenecteplase to intravenous alteplase with respect to good functional outcomes in patients with acute stroke. We examined whether the health-related quality of life (HRQOL) of patients with acute stroke differs by the type of thrombolysis treatment received. In addition, we examined the association between the modified Rankin Scale score 0 to 1 and HRQOL and patient-reported return to prebaseline stroke functioning at 90 days. METHODS: Data were from all patients included in the AcT trial (Alteplase Compared to Tenecteplase), a pragmatic, registry-linked randomized trial comparing tenecteplase with alteplase. HRQOL at 90-day post-randomization was assessed using the 5-item EuroQOL questionnaire (EQ5D), which consists of 5 items and a visual analog scale (VAS). EQ5D index values were estimated from the EQ5D items using the time tradeoff approach based on Canadian norms. Tobit regression and quantile regression models were used to evaluate the adjusted effect of tenecteplase versus alteplase treatment on the EQ5D index values and VAS score, respectively. The association between return to prebaseline stroke functioning and the modified Rankin Scale score 0 to 1 and HRQOL was quantified using correlation coefficient (r) with 95% CI. RESULTS: Of 1577 included in the intention-to-treat analysis patients, 1503 (95.3%) had complete data on the EQ5D. Of this, 769 (51.2%) were administered tenecteplase and 717 (47.7%) were female. The mean EQ5D VAS score and EQ5D index values were not significantly higher for those who received intravenous tenecteplase compared with those who received intravenous alteplase (P=0.10). Older age (P<0.01), more severe stroke assessed using the National Institutes of Health Stroke Scale (P<0.01), and longer stroke onset-to-needle time (P=0.004) were associated with lower EQ5D index and VAS scores. There was a strong association (r, 0.85 [95% CI, 0.81-0.89]) between patient-reported return to prebaseline functioning and modified Rankin Scale score 0 to 1 Similarly, there was a moderate association between return to prebaseline functioning and EQ5D index (r, 0.45 [95% CI, 0.40-0.49]) and EQ5D VAS scores (r, 0.42 [95% CI, 0.37-0.46]). CONCLUSIONS: Although there is no differential effect of thrombolysis type on patient-reported global HRQOL and EQ 5D-5L index values in patients with acute stroke, sex- and age-related differences in HRQOL were noted in this study. REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT03889249.

The Role of Artificial Intelligence in Predicting Optic Neuritis Subtypes From Ocular Fundus Photographs.

BACKGROUND: Optic neuritis (ON) is a complex clinical syndrome that has diverse etiologies and treatments based on its subtypes. Notably, ON associated with multiple sclerosis (MS ON) has a good prognosis for recovery irrespective of treatment, whereas ON associated with other conditions including neuromyelitis optica spectrum disorders or myelin oligodendrocyte glycoprotein antibody-associated disease is often associated with less favorable outcomes. Delay in treatment of these non-MS ON subtypes can lead to irreversible vision loss. It is important to distinguish MS ON from other ON subtypes early, to guide appropriate management. Yet, identifying ON and differentiating subtypes can be challenging as MRI and serological antibody test results are not always readily available in the acute setting. The purpose of this study is to develop a deep learning artificial intelligence (AI) algorithm to predict subtype based on fundus photographs, to aid the diagnostic evaluation of patients with suspected ON. METHODS: This was a retrospective study of patients with ON seen at our institution between 2007 and 2022. Fundus photographs (1,599) were retrospectively collected from a total of 321 patients classified into 2 groups: MS ON (262 patients; 1,114 photographs) and non-MS ON (59 patients; 485 photographs). The dataset was divided into training and holdout test sets with an 80%/20% ratio, using stratified sampling to ensure equal representation of MS ON and non-MS ON patients in both sets. Model hyperparameters were tuned using 5-fold cross-validation on the training dataset. The overall performance and generalizability of the model was subsequently evaluated on the holdout test set. RESULTS: The receiver operating characteristic (ROC) curve for the developed model, evaluated on the holdout test dataset, yielded an area under the ROC curve of 0.83 (95% confidence interval [CI], 0.72-0.92). The model attained an accuracy of 76.2% (95% CI, 68.4-83.1), a sensitivity of 74.2% (95% CI, 55.9-87.4) and a specificity of 76.9% (95% CI, 67.6-85.0) in classifying images as non-MS-related ON. CONCLUSION: This study provides preliminary evidence supporting a role for AI in differentiating non-MS ON subtypes from MS ON. Future work will aim to increase the size of the dataset and explore the role of combining clinical and paraclinical measures to refine deep learning models over time.