Assoc. Prof. Jiaxin Cai, Xiamen University of Technology, China
Biography: Jiaxin Cai received his Ph.D. degree in Information and Computation Science from Sun Yat-Sen University in 2014. He also received his M.S. degree and B.Sc. degree in Bio-medical Engineering from Southern Medical University in 2011 and 2008 respectively. Currently, he is an associate professor in the School of Mathematics and Statistics at Xiamen University of Technology. He has authored over 50 peer-reviewed papers at academic journals and conferences such as IEEE Trans as the first author or corresponding author, including 3 ESI Top1% highly cited paper. His current research interests include machine learning, computer vision and bio-medical engineering.
Speech Title: Later Temporal Attention in Computer Aided Medical Diagnosis
Abstract: The clinical course of COVID-19, as well as the immunological reaction, is notable for its extreme variability. Identifying the main associated factors might help understand the disease progression and physiological status of COVID-19 patients. The dynamic changes of the antibody against Spike protein are crucial for understanding the immune response. This work explores a temporal attention (TA) mechanism of deep learning to predict COVID-19 disease severity, clinical outcomes, and Spike antibody levels by screening serological indicators over time. We use feature selection techniques to filter feature subsets that are highly correlated with the target. The specific deep Long Short-Term Memory (LSTM) models are employed to capture the dynamic changes of disease severity, clinical outcome, and Spike antibody level. We also propose deep LSTMs with a TA mechanism to emphasize the later blood test records because later records often attract more attention from doctors. Risk factors highly correlated with COVID-19 are revealed. LSTM achieves the highest classification accuracy for disease severity prediction. Temporal Attention Long Short-Term Memory (TA-LSTM) achieves the best performance for clinical outcome prediction. For Spike antibody level prediction, LSTM achieves the best performance. The experimental results demonstrate the effectiveness of the proposed models. Simple factors like LDH, Mono%, ALB, LYMPH%, DM, and Sex are critical factors in disease severity. LDH, Neu#, hs-CRP, PLT, and Urea are critical factors in clinical outcomes. We further find that Age, RDW_CV, PLT, LDH, eGFR (CKD-EPI), LYMPH#,RDW_SD, PCT, and TCHO are the Top-9 significant predictors of the Spike antibody level. The proposed models can provide a computer-aided medical diagnostics system by simply using a time series of serological indicators.