Sublingual Edaravone Dexborneol for the Treatment of Acute Ischemic Stroke: The TASTE-SL Randomized Clinical Trial.

Importance: Sublingual edaravone dexborneol, which can rapidly diffuse and be absorbed through the oral mucosa after sublingual exposure, is a multitarget brain cytoprotection composed of antioxidant and anti-inflammatory ingredients edaravone and dexborneol. Objective: To investigate the efficacy and safety of sublingual edaravone dexborneol on 90-day functional outcome in patients with acute ischemic stroke (AIS). Design, Setting, and Participants: This was a double-blind, placebo-controlled, multicenter, parallel-group, phase 3 randomized clinical trial conducted from June 28, 2021, to August 10, 2022, with 90-day follow-up. Participants were recruited from 33 centers in China. Patients randomly assigned to treatment groups were aged 18 to 80 years and had a National Institutes of Health Stroke Scale score between 6 and 20, a total motor deficit score of the upper and lower limbs of 2 or greater, a clinically diagnosed AIS symptom within 48 hours, and a modified Rankin Scale (mRS) score of 1 or less before stroke. Patients who did not meet the eligibility criteria or declined to participate were excluded. Intervention: Patients were assigned, in a 1:1 ratio, to receive sublingual edaravone dexborneol (edaravone, 30 mg; dexborneol, 6 mg) or placebo (edaravone, 0 mg; dexborneol, 60 µg) twice daily for 14 days and were followed up until 90 days. Main Outcomes and Measures: The primary efficacy outcome was the proportion of patients with mRS score of 1 or less on day 90 after randomization. Results: Of 956 patients, 42 were excluded. A total of 914 patients (median [IQR] age, 64.0 [56.0-70.0] years; 608 male [66.5%]) were randomly allocated to the edaravone dexborneol group (450 [49.2%]) or placebo group (464 [50.8%]). The edaravone dexborneol group showed a significantly higher proportion of patients experiencing good functional outcomes on day 90 after randomization compared with the placebo group (290 [64.4%] vs 254 [54.7%]; risk difference, 9.70%; 95% CI, 3.37%-16.03%; odds ratio, 1.50; 95% CI, 1.15-1.95, P = .003). The rate of adverse events was similar between the 2 groups (89.8% [405 of 450] vs 90.1% [418 of 464]). Conclusion and Relevance: Among patients with AIS within 48 hours, sublingual edaravone dexborneol could improve the proportion of those achieving a favorable functional outcome at 90 days compared with placebo. Trial Registration: ClinicalTrials.gov Identifier: NCT04950920.

Efficacy and safety of Y-2 sublingual tablet for patients with acute ischaemic stroke: protocol of a phase III randomised double-blind placebo-controlled multicentre trial.

BACKGROUND AND PURPOSE: Clinical studies have demonstrated that edaravone dexborneol can improve the functional outcomes in patients with acute ischaemic stroke (AIS). The present clinical trial aimed at testing the efficacy and safety of Y-2 sublingual tablet on 90-day functional outcome in patients with AIS. METHODS AND DESIGN: This is a randomised, double-blind, placebo-controlled, multicentre, parallel-group trial of Y-2 sublingual tablet on patients with AIS.An estimated 914 patients at age of 18-80 years with AIS within 48 hours after symptom onset from 40 hospitals will be randomly assigned to receive Y-2 sublingual tablet or placebo for 14 days. Patients are at score 6-20 points on National Institutes of Health Stroke Scale (NIHSS) and had a modified Rankin Scale (mRS) ≤1 before this stroke, except mechanical thrombectomy and neuroprotective agents treatment. STUDY OUTCOMES: The primary outcome is the proportion of patients with mRS ≤1 on day 90 after randomisation. Secondary efficacy outcomes include mRS score on day 90, the proportion of patients with mRS ≤2 on day 90; the change of NIHSS score from baseline to day 14 and the proportion of patients with NIHSS score ≤1 at the days 14, 30 and 90. DISCUSSION: This trial will provide valuable evidence for the efficacy and safety of Y-2 sublingual table for improving 90 days the functional outcomes in patients with AIS. TRIAL REGISTRATION NUMBER: NCT04950920.

Partial Consistency for Stabilizing Undiscounted Reinforcement Learning.

Undiscounted return is an important setup in reinforcement learning (RL) and characterizes many real-world problems. However, optimizing an undiscounted return often causes training instability. The causes of this instability problem have not been analyzed in-depth by existing studies. In this article, this problem is analyzed from the perspective of value estimation. The analysis result indicates that the instability originates from transient traps that are caused by inconsistently selected actions. However, selecting one consistent action in the same state limits exploration. For balancing exploration effectiveness and training stability, a novel sampling method called last-visit sampling (LVS) is proposed to ensure that a part of actions is selected consistently in the same state. The LVS method decomposes the state-action value into two parts, i.e., the last-visit (LV) value and the revisit value. The decomposition ensures that the LV value is determined by consistently selected actions. We prove that the LVS method can eliminate transient traps while preserving optimality. Also, we empirically show that the method can stabilize the training processes of five typical tasks, including vision-based navigation and manipulation tasks.

Orientation-Preserving Rewards' Balancing in Reinforcement Learning.

Auxiliary rewards are widely used in complex reinforcement learning tasks. However, previous work can hardly avoid the interference of auxiliary rewards on pursuing the main rewards, which leads to the destruction of the optimal policy. Thus, it is challenging but essential to balance the main and auxiliary rewards. In this article, we explicitly formulate the problem of rewards' balancing as searching for a Pareto optimal solution, with the overall objective of preserving the policy's optimization orientation for the main rewards (i.e., the policy driven by the balanced rewards is consistent with the policy driven by the main rewards). To this end, we propose a variant Pareto and show that it can effectively guide the policy search toward more main rewards. Furthermore, we establish an iterative learning framework for rewards' balancing and theoretically analyze its convergence and time complexity. Experiments in both discrete (grid word) and continuous (Doom) environments demonstrated that our algorithm can effectively balance rewards, and achieve remarkable performance compared with those RLs with heuristically designed rewards. In the ViZDoom platform, our algorithm can learn expert-level policies.

Research on Tire Marking Point Completeness Evaluation Based on K-Means Clustering Image Segmentation.

The tire marking points of dynamic balance and uniformity play a crucial guiding role in tire installation. Incomplete marking points block the recognition of tire marking points, and then affect the installation of tires. It is usually necessary to evaluate the marking point completeness during the quality inspection of finished tires. In order to meet the high-precision requirements of the evaluation of tire marking point completeness in the smart factories, the K-means clustering algorithm is introduced to segment the image of marking points in this paper. The pixels within the contour of the marking point are weighted to calculate the marking point completeness on the basis of the image segmentation. The completeness is rated and evaluated by completeness calculation. The experimental results show that the accuracy of the marking point completeness ratings is 95%, and the accuracy of the marking point evaluations is 99%. The proposed method has an important guiding significance of practice to evaluate the tire marking point completeness during the tire quality inspection based on machine vision.