Materials and Methods: A total of 324 undergraduate preclinical (year 2) and clinical (year 3-5) medical students participated in this study. The research design used thematic analysis of an open-ended questionnaire to analyze the qualitative data.
Results: The thematic analysis detected five major emergent themes: lack of remembering (18.2%), lack of understanding (28.4%), difficulty in applying (3.6%), difficulty in analysis (15.1%), and difficulty in interpretation (17.8%), of which addressing these challenges could be taken as a foundation step upon which medical educators put an emphasis on in order to improve ECG teaching and learning.
Conclusion: Negative attitude toward ECG learning poses a serious threat to acquire competency in ECG interpretation skill. The concept of student's memorizing ECG is not a correct approach; instead, understanding the concept and vector analysis is an elementary key for mastering ECG interpretation skill. The finding of this study sheds light into a better understanding of medical students' deficient points of ECG learning in parallel with taxonomy of cognitive domain and enables the medical teachers to come up with effective and innovative strategies for innovative ECG learning in an undergraduate medical curriculum.
METHODS: A dataset containing medical records of 809 patients suspected to suffer from ACS was used. For each subject, 266 clinical factors were collected. At first, a feature selection was performed based on interviews with 20 cardiologists; thereby 40 seminal features for classifying ACS were selected. Next, a feature selection algorithm was also applied to detect a subset of the features with the best classification accuracy. As a result, the feature numbers considerably reduced to only seven. Lastly, based on the seven selected features, eight various common pattern recognition tools for classification of ACS were used.
RESULTS: The performance of the aforementioned classifiers was compared based on their accuracy computed from their confusion matrices. Among these methods, the multi-layer perceptron showed the best performance with the 83.2% accuracy.
CONCLUSION: The results reveal that an integrated AI-based feature selection and classification approach is an effective method for the early and accurate classification of ACS and ultimately a timely diagnosis and treatment of this disease.