The objective of this study is to construct a multi-department symptom-based automatic diagnosis model. However, it is difficult to establish a model to classify plenty of diseases and collect thousands of diseasesymptom datasets simultaneously. Inspired by the thought of “knowledge graph is model”, this study proposes to build an experience-infused knowledge model by continuously learning the experiential knowledge from data, and incrementally injecting it into the knowledge graph. Therefore, incremental learning and injection are used to solve the data collection problem, and the knowledge graph is modeled and containerized to solve the large-scale
multi-classification problems. First, an entity linking method is designed and a heterogeneous knowledge graph is constructed by graph fusion. Then, an adaptive neural network model is constructed for each dataset, and the data is used for statistical initialization and model training. Finally, the weights and biases of the learned neural network model are updated to the knowledge graph. It is worth noting that for the incremental process, we consider both the data and class increments. We evaluate the diagnostic effectiveness of the model on the current dataset and the anti-forgetting ability on the historical dataset after class increment on three public datasets. Compared with the classical model, the proposed model improves the diagnostic accuracy of the three datasets by 5%, 2%, and 15% on average, respectively. Meanwhile, the model under incremental learning has a better ability to resist forgetting.
TIAN Yuanyuan (田圆圆), JIN Yanrui (金衍瑞), LI Zhiyuan (李志远), LIU Jinlei (刘金磊), LIU Chengliang∗ (刘成良)
. Weighted Heterogeneous Graph-Based Incremental Automatic Disease Diagnosis Method[J]. Journal of Shanghai Jiaotong University(Science), 2024
, 29(1)
: 120
-130
.
DOI: 10.1007/s12204-022-2537-z
[1] ZHANG W, ZHOU J, LIU G, et al. A study on the online medical consulting websites based on the personal computer side [J]. Chinese Journal of Epidemiology, 2021, 42(2): 303-308 (in Chinese).
[2] The epidemic has led to an explosion in online consultations and telemedicine [J]. Chinese Computed Medical Imaging, 2020, 26(6): 520 (in Chinese).
[3] LIU Q C, ZHANG P Z. Panoramic and personalised intelligent healthcare mode [J]. Journal of Shanghai Jiao Tong University (Science), 2022, 27(1): 121-136.
[4] CUI X R. Profession research on China’s mobile health industry [D]. Beijing: Beijing Foreign Studies University, 2021 (in Chinese).
[5] ESTEVA A, ROBICQUET A, RAMSUNDAR B, et al. A guide to deep learning in healthcare [J]. Nature Medicine, 2019, 25(1): 24-29.
[6] WEI Z Y, LIU Q L, PENG B L, et al. Task-oriented dialogue system for automatic diagnosis [C] // 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). Melbourne: ACL, 2018: 201-207.
[7] LIAO K, LIU Q L, WEI Z Y, et al. Task-oriented dialogue system for automatic disease diagnosis via hierarchical reinforcement learning [DB/OL]. (2020-04-29). https://arxiv.org/abs/2004.14254.
[8] KAO H C, TANG K F, CHANG E Y. Context-aware symptom checking for disease diagnosis using hierarchical reinforcement learning [J] .Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32: 2305-2313.
[9] XIA Y, ZHOU J B, SHI Z H, et al. Generative adversarial regularized mutual information policy gradient framework for automatic diagnosis [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34: 1062-1069.
[10] LIN X, ZHOU Q X, GONG K, et al. End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis [J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33: 7346-7353.
[11] ZHAO X, CHEN L, CHEN H. A weighted heterogeneous graph-based dialog system [J]. IEEE Transactions on Neural Networks and Learning Systems, 2021. https://doi.org/10.1109/TNNLS.2021.3124640.
[12] TIWARI A, SAHA S, BHATTACHARYYA P. A knowledge infused context driven dialogue agent for disease diagnosis using hierarchical reinforcement learning [J]. Knowledge-Based Systems, 2022, 242: 108292.
[13] NILASHI M, AHMADI H, MANAF A A, et al. Coronary heart disease diagnosis through self-organizing map and fuzzy support vector machine with incremental updates [J]. International Journal of Fuzzy Systems, 2020, 22(4): 1376-1388.
[14] RODR′IGUEZ ALDANA Y, MARAN ON REYES E J, MACIAS F S, et al. Nonconvulsive epileptic seizure monitoring with incremental learning [J]. Computers in Biology and Medicine, 2019, 114: 103434.
[15] SIRSHAR M, HASSAN T, AKRAM M U, et al. An incremental learning approach to automatically recognize pulmonary diseases from the multi-vendor chest radiographs [J]. Computers in Biology and Medicine, 2021, 134: 104435.
[16] CHAI X Q. Diagnosis method of thyroid disease combining knowledge graph and deep learning [J]. IEEE Access, 2020, 8: 149787-149795.
[17] XIE Y, HU L, CHEN X, et al. Auxiliary diagnosis based on the knowledge graph of TCM syndrome [J]. Computers, Materials & Continua, 2020, 65(1): 481-494.
[18] XIE J, JIANG J C, WANG Y H, et al. Learning an expandable EMR-based medical knowledge network to enhance clinical diagnosis [J]. Artificial Intelligence in Medicine, 2020, 107: 101927.
[19] HOU M W, WEI R, LU L, et al. Research review of knowledge graph and its application in medical domain [J]. Journal of Computer Research and Development, 2018, 55(12): 2587-2599 (in Chinese).
[20] SONG D Q, ZHOU B, SHEN X W, et al. Dynamic knowledge graph modeling method for ship block manufacturing process [J]. Journal of Shanghai Jiao Tong University, 2021, 55(5): 544-556 (in Chinese).
[21] FENG G F, DU Z K, WU X. A Chinese question answering system in medical domain [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(5): 678-683.
[22] ZAN H Y, HAN Y C, FAN Y X, et al. Construction and analysis of symptom knowledge base in Chinese [J]. Journal of Chinese Information Processing, 2020, 34(4): 30-37 (in Chinese).
[23] LIN X Z, HE X H, CHEN Q, et al. Enhancing dialogue symptom diagnosis with global attention and symptom graph [C]// 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing. Hong Kong: ACL, 2019: 5033-5042.
[24] CUI Y M, CHE W X, LIU T, et al. Revisiting pre-trained models for Chinese natural language processing [DB/OL]. (2020-11-02). https://arxiv.org/abs/2004.13922.
[25] MASANA M, LIU X, TWARDOWSKI B, et al. Classincremental learning: survey and performance evaluation on image classification [DB/OL]. (2021-05-06). https://arxiv.org/abs/2010.15277.
[26] JIN Y R, LIU J L, LIU Y Q, et al. A novel interpretable method based on dual-level attentional deep neural network for actual multilabel arrhythmia detection [J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-11.
[27] TEIXEIRA M S, MARAN V, DRAGONI M. The interplay of a conversational ontology and AI planning for health dialogue management [C]//36th ACM/SIGAPP Symposium on Applied Computing.Online. ACM, 2021: 611-619.
