ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of ∼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.

Background: Rapid changes in medical education have led to the inclusion of different teaching strategies in the curriculum. Journal clubs and flipped classrooms are innovative techniques that are used worldwide. We have combined these techniques to assess their impact on critical thinking and active learning among dental students using SSACT questionnaire. This is a rigorous step for inculcating evidence-based medicine skills in early years of medical education. Methods: A quasi-experimental study was conducted at Dental College HITEC-IMS using convenience sampling. The SSACT questionnaire was validated through a pilot study. Students prepared and delivered PowerPoint presentations on the assigned topic. Instructors evaluated the presentations using judgment criteria from Texas Undergraduate Studies. Results: This study included 46 students (86% female, 14% male) with a mean age of 19 years. The reliability and internal consistency of the tool, as measured by Cronbach's alpha, was found to be 0.8. Paired sample t-test showed a mean value of 0.68 ± 0.4. The p value was highly significant (0.00). A significant majority (n = 41, 89%) showed a positive attitude towards setting their own learning objectives. An increase in the utilization of multiple learning strategies for independent learning, and reflecting on the learning process was seen at 93% (n = 43) and 98% (n = 45) respectively. Students reported enhancement in team-based performance (n = 44, 78%), demonstrated improvements in communication of ideas, application of previous knowledge from independent study, and linking of previous and new knowledge 93% (n = 43). The implementation of scenario-based questions has been found to significantly increase critical thinking skills among a majority of students (n = 40, 87%). Conclusion: Our results show that implementation of journal clubs and flip classrooms in a combined fashion has led to overall enhancement of critical thinking and active learning and SSACT questionnaire is a valid tool for self-assessment of students in our population.