ABSTRACT
BACKGROUND: Tenecteplase is used as an alternative to alteplase and is considered noninferior for thrombolysis in acute ischemic stroke. OBJECTIVES: To compare the effectiveness and adverse effects of tenecteplase and alteplase in the real-world management of acute ischemic stroke. MATERIALS AND METHODS: In this retrospective observational study, we collected data from acute ischemic stroke patients admitted in six hospitals in West Bengal, India, and were thrombolysed with tenecteplase or alteplase between July 2021 and June 2022. Demographic data, baseline parameters, hospital course, and 3-month follow-up data were collected. The percentage of patients achieving a score of 0-2 in the modified Ranking scale at 3 months, rate of symptomatic intracranial hemorrhage, and all-cause mortality within 3 months were the main parameters of comparison between the two thrombolytic agents. RESULTS: A total of 162 patients were initially included in this study. Eight patients were excluded due to unavailability of follow-up data. Among the remaining patients, 71 patients received tenecteplase and 83 patients received alteplase. There was no statistically significant difference between tenecteplase and alteplase with respect to the percentage of patients achieving functional independence (modified Rankin scale score 0-2) at 3 months (53.5% vs. 60.2%, P = 0.706), rate of symptomatic intracranial hemorrhage (5.6% vs. 10.8%, P = 0.246), and all-cause mortality at 3 months (11.3% vs. 15.7%, P = 0.628). CONCLUSION: The effectiveness of tenecteplase is comparable to alteplase in the real-world management of acute ischemic stroke. Symptomatic intracranial hemorrhage and all-cause mortality rates are also similar in real-world practice.
ABSTRACT
Emotion recognition using Artificial Intelligence (AI) is a fundamental prerequisite to improve Human-Computer Interaction (HCI). Recognizing emotion from Electroencephalogram (EEG) has been globally accepted in many applications such as intelligent thinking, decision-making, social communication, feeling detection, affective computing, etc. Nevertheless, due to having too low amplitude variation related to time on EEG signal, the proper recognition of emotion from this signal has become too challenging. Usually, considerable effort is required to identify the proper feature or feature set for an effective feature-based emotion recognition system. To extenuate the manual human effort of feature extraction, we proposed a deep machine-learning-based model with Convolutional Neural Network (CNN). At first, the one-dimensional EEG data were converted to Pearson's Correlation Coefficient (PCC) featured images of channel correlation of EEG sub-bands. Then the images were fed into the CNN model to recognize emotion. Two protocols were conducted, namely, protocol-1 to identify two levels and protocol-2 to recognize three levels of valence and arousal that demonstrate emotion. We investigated that only the upper triangular portion of the PCC featured images reduced the computational complexity and size of memory without hampering the model accuracy. The maximum accuracy of 78.22% on valence and 74.92% on arousal were obtained using the internationally authorized DEAP dataset.
