Enhancing the Prediction of Ablation Outcomes Using Transfer Learning on Residual Network via Spectrogram in Persistent Atrial Fibrillation

Noor Qaqos1, Abdulhamed Mohammed Jasim1, Ekenedirichukwu Nelson Obianom1, Shamsu Idris Abdullahi1, Fan Feng2, Fernando Soares Schlindwein1, G. Andre Ng1, Xin Li1
1University of Leicester, 2Uni of Leicester


Abstract

Introduction: Ablation of persistent atrial fibrillation (persAF) targets using dominant frequency (DF), rotors, and complex fractionated atrial electrograms has been disappointing. A transfer learning technique applied to spectrograms may be a promising tool for predicting ablation outcomes. Methods: 3206 non-contact electrograms (EGMs) were collected for a time duration of 4 seconds before and after ablating 51 high DF locations of 10 patients with persAF. Two categories of data were labelled: 1490 EGMs (nodes) had positive ablation responses (AF termination or AF cycle length (AFCL) increased (≥10msec)), whereas 1716 EGMs had negative responses (AFCL increase (<10msec)) to catheter ablation. After the QRST subtraction process, EGMs were converted to spectrograms to visualize the variability of signals in the time-frequency domain. The residual network, equipped with a 50-layer pre-trained model, was utilized to extract features and train and test the transferred fully connected layers. The proposed model performance was evaluated by leaving EGMs of one patient out in a 10-fold cross-validation. Results: The 10-fold cross-validation accuracy, balanced accuracy, F1_score, AUC-ROC, sensitivity, specificity, and precision were 60.2%, 60.0%, 55.0%, 0.64, 51.5%, 67.8% and 58.2% respectively, based on the testing dataset. Conclusions: A transfer learning technique applied to features extracted from spectrograms might be useful to predict the responses of ablating electrograms and their effect on terminating AF and changes in CL.