Bonyani, M.Yeganli, FaezehYeganli, S.F.Shahidi, N.2024-02-242024-02-2420239798350328967https://doi.org/10.1109/TIPTEKNO59875.2023.10359225https://hdl.handle.net/20.500.14365/51722023 Medical Technologies Congress, TIPTEKNO 2023 -- 10 November 2023 through 12 November 2023 -- 195703Liver transplantation (LT) offers a vital solution for end-stage liver disease patients. Predicting post-LT survival, however, remains challenging. This paper introduces an artificial intelligence (AI)-based model to predict post-operative survival after LT. The proposed model employs a two-stream recurrent neural network (RNN) using deep long short-term memory (LSTM-RNN) and bidirectional long short-term memory (BiLSTM-RNN) to extract inherent features of donors and recipients, respectively. Additionally, a self-attention based module is developed to capture the influential features of donors' and patients' data. To eliminate errors in the prediction model caused by imbalanced distributions, implicit semantic data augmentation (ISDA) is employed. Tested with 5-fold cross-validation, the proposed model achieved 99.47% accuracy and 0.996 the area under the curve, outperforming existing models in prediction performance. © 2023 IEEE.eninfo:eu-repo/semantics/closedAccessBiLSTM-RNNLiver TransplantationLSTM-RNNPost-OperativePredictionSelf-AttentionSurvivalBrainLong short-term memorySemanticsBiLSTM-recurrent neural networkLiver diseaseLiver transplantationLSTM-recurrent neural networkPatient dataPost-operativePrediction modellingSelf-attentionSurvivalTwo-streamForecastingConference Object10.1109/TIPTEKNO59875.2023.103592252-s2.0-85182737660