{"title":"Incorporating Lexical-Semantic Knowledge into Convolutional Neural Network Framework for Pediatric Disease Diagnosis","authors":"Xiaocong Liu, Huazhen Wang, Ting He, Xiaozheng Li, Weihan Zhang, Jian Chen","volume":177,"journal":"International Journal of Bioengineering and Life Sciences","pagesStart":93,"pagesEnd":100,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/10012268","abstract":"
The utilization of electronic medical record (EMR) data to establish the disease diagnosis model has become an important research content of biomedical informatics. Deep learning can automatically extract features from the massive data, which brings about breakthroughs in the study of EMR data. The challenge is that deep learning lacks semantic knowledge, which leads to impracticability in medical science. This research proposes a method of incorporating lexical-semantic knowledge from abundant entities into a convolutional neural network (CNN) framework for pediatric disease diagnosis. Firstly, medical terms are vectorized into Lexical Semantic Vectors (LSV), which are concatenated with the embedded word vectors of word2vec to enrich the feature representation. Secondly, the semantic distribution of medical terms serves as Semantic Decision Guide (SDG) for the optimization of deep learning models. The study evaluates the performance of LSV-SDG-CNN model on four kinds of Chinese EMR datasets. Additionally, CNN, LSV-CNN, and SDG-CNN are designed as baseline models for comparison. The experimental results show that LSV-SDG-CNN model outperforms baseline models on four kinds of Chinese EMR datasets. The best configuration of the model yielded an F1 score of 86.20%. The results clearly demonstrate that CNN has been effectively guided and optimized by lexical-semantic knowledge, and LSV-SDG-CNN model improves the disease classification accuracy with a clear margin.<\/p>","references":"[1]\tA. Boonstra and M. Broekhuis, \u201cBarriers to the acceptance of electronic medical records by physicians from systematic review to taxonomy and interventions,\u201d BMC Health Services Research, vol. 10, no. 1, pp. 231\u2013241, 2010.\r\n[2]\tW. Mackinnon and M. Wasserman, \u201cIntegrated electronic medical record systems: Critical success factors for implementation,\u201d in Proc. of the Hawaii International Conference on System Sciences, 2009, pp. 1\u201310.\r\n[3]\tY. Li, B. Qian, X. Zhang, et al., \u201cGraph neural network-based diagnosis prediction,\u201d Big Data, vol. 8, no. 5, pp. 379-390, 2020\r\n[4]\tY. Li, R Shishir, Solares, et al., \u201cBEHRT: Transformer for electronic health records,\u201d Entific Reports, vol. 10, no. 1, pp. 7155-7167, 2020.\r\n[5]\tJ. Gao, X. Wang, Y. Wang, et al., \u201cCAMP: Co-attention memory networks for diagnosis prediction in healthcare,\u201d in Proc. of the 19th IEEE International Conference on Data Mining, New York, 2019, pp. 1036\u20131041.\r\n[6]\tX. S. Hang, F. Tang, H. H. Dodge, et al., \u201cMetaPred: Meta-learning for clinical risk prediction with limited patient electronic health records,\u201d in Proc. of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2019, pp. 2487\u20132495.\r\n[7]\tW. Wang, H. Xu, Z. Gan, et al., \u201cGraph-driven generative models for heterogeneous multi-task learning\u201d in Proc. of the 35th AAAI Conference on Artificial Intelligence. Menlo Park, 2020, pp. 979\u2013988.\r\n[8]\tJ. Jiang, H. Wang, J. Xie, et al., \u201cMedical knowledge embedding based on recursive neural network for multi-disease diagnosis,\u201d Artificial Intelligence in Medicine, vol. 103, no. 1, pp. 101772\u2013101787, 2020.\r\n[9]\tL. Wang, H. Wang, Y. Song, et al., \u201cMCPL-Based FT-LSTM: medical representation learning-based clinical prediction model for time series events,\u201d IEEE Access, vol. 7, no. 1, pp. 70253\u201370264, 2019.\r\n[10]\tH. Liang, B. Y. Tsui, H. Ni, et al., \u201cEvaluation and accurate diagnoses of pediatric diseases using artificial intelligence,\u201d Nature medicine, vol. 25, no. 3, pp. 433\u2013443, 2019.\r\n[11]\tA. Bordes, J. Weston, R. Collobert, et al., \u201cLearning structured embeddings of knowledge bases,\u201d in Proc. of the 25th AAAI Conference on Artificial Intelligence, Menlo Park, vol. 25, no. 1, 2011.\r\n[12]\tA. Bordes, N. Usunier, A. Garcia-Duran, et al., \u201cTranslating embeddings for modeling multi-relational data,\u201d in Proc. of the neural information processing systems, Cambridge, 2013, pp. 2787\u20132795.\r\n[13]\tA. Rajkomar, E. Oren, C. Kai, et al., \u201cScalable and accurate deep learning with electronic health records,\u201d NPJ Digital Medicine, vol. 1, no. 1, pp. 18, 2018.\r\n[14]\tT. Ching, D. S. Himmelstein, B. K. Beaulieu-Jones, et al., \u201cOpportunities and obstacles for deep learning in biology and medicine,\u201d Journal of the Royal Society Interface, vol. 15, no. 141, pp. 20170387, 2018.\r\n[15]\tL. Fang, Y. Luo, K. Feng, et al., \u201cKnowledge-enhanced ensemble learning for word embeddings,\u201d in Proc. of the World Wide Web Conference, New York, 2019, pp. 427\u2013437.\r\n[16]\tJ. Xu, Z. Zhang, T. Friedman, et al., \u201cA semantic loss function for deep learning with symbolic knowledge,\u201d in Proc. of the 35th International Conference on Machine Learning, Cambridge, 2018, pp. 5502\u20135511.\r\n[17]\tE. Choi, M. T. Bahadori, S. Le, et al., \u201cGRAM: Graph-based attention model for healthcare representation learning,\u201d in Proc of the 23th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, 2017, pp. 787\u2013795.\r\n[18]\tN. Rojas, L. B. Crane, E. Yeager, et al., \u201cIntroduction to Linguistics,\u201d Modern Language Journal, vol. 66, no. 4, pp. 445,1998.\r\n[19]\tX. Shen, \u201cPediatrics,\u201d 7th ed. Beijing: People\u2019s Health Publishing House, 2013.\r\n[20]\tV. Jayawardana, D. Lakmal, N. D. Silva, et al., \u201cDeriving a representative vector for ontology classes with instance word vector embeddings,\u201d in Proc. of the Seventh International Conference on Innovative Computing Technology, 2017, pp. 79-84.\r\n[21]\tT. Mikolov, K. Chen, G. Corrado, et al., \u201cEfficient estimation of word representations in vector space,\u201d in Proc of 7th International Conference on Learning Representations, Stroudsburg, 2013, pp. 1\u201312.\r\n[22]\tN. Liu, P. Lu, W. Zhang, et al., \u201cKnowledge-aware deep dual networks for text-based mortality prediction,\u201d in Proc. of 35th International Conference on Data Engineering, 2019, pp. 1406\u20131417.\r\n[23]\tH. Wang, Y. Li, S. A. Khan, et al., \u201cPrediction of breast cancer distant recurrence using natural language processing and knowledge-guided convolutional neural network,\u201d Artificial Intelligence in Medicine, vol. 110, p. 101977, 2020.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 177, 2021"}