This paper presents a method to classify different subtypes of atrial fibrillation episodes by analyzing short segments of electrocardiograms. We will process surface ECGs segments by time-frequency transforms to extract relevant features that will be used as input to a neural network classifier. As atrial fibrillation presents a progressive nature, this method can be a very useful tool in order to differentiate the progress of the arrythmia in each patient.

A869143 CDMP patients with hypertension. A total number of 8 physicians and 7 private PHC managers were involved in this study. Level satisfaction of physicians and private PHC managers were observed by using a qualitative study through in-depth interviews. Results: Patient satisfaction was estimated to be 68.52±8.54, which could be interpreted that patient satisfy with CDMP. In-depth interviews showed that physicians did not satisfy with CDMP due to several factors (e.g.,unintegrated prescription systems, lack of medicines, uncompleted laboratory facilities, lack of physicians, and lack of collaboration between primary and secondary healthcare system). On the other hand, private PHC managers were quite satisfied with CDMP due to its linearity with other activities in private PHCs. ConClusions: Level satisfaction of patients with CDMP is quite good, while physicians might not satisfy with this program. In particular, private PHC managers confirmed that they are satisfied with this program.