JZUS - Journal of Zhejiang University SCIENCE

Journal of Zhejiang University SCIENCE B 2017 Vol.18 No.5 P.393-401

Intelligent diagnosis of jaundice with dynamic uncertain causality graph model

Author(s): Shao-rui Hao, Shi-chao Geng, Lin-xiao Fan, Jia-jia Chen, Qin Zhang, Lan-juan Li
Affiliation(s): State Key Laboratory for Diagnosis and Treatment of Infectious Diseases, Collaborative Innovation Center for Diagnosis and Treatment of Infectious Diseases, the First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou 310003, China; more
Corresponding email(s): zhangqin@buaa.edu.cn, ljli@zju.edu.cn
Key Words: Jaundice, Intelligent diagnosis, Dynamic uncertain causality graph, Expert system

Share this article to： More <<< Previous Article \|Next Article >>>

Abstract: jaundice is a common and complex clinical symptom potentially occurring in hepatology, general surgery, pediatrics, infectious diseases, gynecology, and obstetrics, and it is fairly difficult to distinguish the cause of jaundice in clinical practice, especially for general practitioners in less developed regions. With collaboration between physicians and artificial intelligence engineers, a comprehensive knowledge base relevant to jaundice was created based on demographic information, symptoms, physical signs, laboratory tests, imaging diagnosis, medical histories, and risk factors. Then a diagnostic modeling and reasoning system using the dynamic uncertain causality graph was proposed. A modularized modeling scheme was presented to reduce the complexity of model construction, providing multiple perspectives and arbitrary granularity for disease causality representations. A “chaining” inference algorithm and weighted logic operation mechanism were employed to guarantee the exactness and efficiency of diagnostic reasoning under situations of incomplete and uncertain information. Moreover, the causal interactions among diseases and symptoms intuitively demonstrated the reasoning process in a graphical manner. Verification was performed using 203 randomly pooled clinical cases, and the accuracy was 99.01% and 84.73%, respectively, with or without laboratory tests in the model. The solutions were more explicable and convincing than common methods such as Bayesian Networks, further increasing the objectivity of clinical decision-making. The promising results indicated that our model could be potentially used in intelligent diagnosis and help decrease public health expenditure.

基于动态不确定性因果图（DUCG）模型的黄疸待查智能诊断研究

目的：黄疸待查是一个常见而复杂的临床问题，涉及到内、外、妇、儿等多个学科。目前我国医学专家存在数量相对不足，分布不均匀等情况，导致了区域性和部门性医疗服务水平不足。本研究旨在建立一个客观的黄疸待查智能诊断系统，以提高医学诊断的正确性，提升基层医院及急诊的诊断水平，同时减少病人的花费。
创新点：本研究采用了国际先进的动态不确定性因果图（DUCG）模型，建立了黄疸待查相关疾病的知识库，通过203例临床病例的测试，其准确率达99.01%。文章以图形化的方式给出了疾病的诊断过程，方便医师理解和学习。
方法：本研究采用了DUCG模型进行疾病诊断，首先根据DUCG模型的定义和黄疸诊断思路建立了包含27种黄疸相关疾病（表4）的知识库（图2），其中包括了疾病的危险因素、临床症状和体征、客观检查检验结果等。然后与根据DUCG算法（公式1-4）编写的推理软件相结合形成诊断系统，对203例临床黄疸患者进行智能诊断，准确率达99.01%。最后对一例丙型病毒性肝炎患者的具体诊断过程进行了拆解阐述，体现了DUCG模型适用于复杂逻辑关系、计算效率高、不依赖推理概率和结果易于理解等优点。
结论：DUCG模型成功实现了对黄疸待查相关疾病的智能诊断，准确率高，实用性好。该方法具有在其他医学领域推广应用的价值。

关键词：动态不确定性因果图（DUCG）；人工智能；黄疸；智能诊断

Reference

[1]Avci, E., 2012. A new expert system for diagnosis of lung cancer: GDA-LS_SVM. J. Med. Syst., 36(3):2005-2009.

[2]Bhat, S., Acharya, U.R., Adeli, H., et al., 2014. Automated diagnosis of autism: in search of a mathematical marker. Rev. Neurosci., 25(6):851-861.

[3]Bhutani, V.K., Johnson-Hamerman, L., 2015. The clinical syndrome of bilirubin-induced neurologic dysfunction. Semin. Fetal Neonatal Med., 20(1):6-13.

[4]Dong, C., Wang, Y., Zhang, Q., et al., 2014a. The methodology of dynamic uncertain causality graph for intelligent diagnosis of vertigo. Comput. Methods Prog. Biomed., 113(1):162-174.

[5]Dong, C., Zhang, Q., Geng, S., 2014b. A modeling and probabilistic reasoning method of dynamic uncertain causality graph for industrial fault diagnosis. Int. J. Automat. Comput., 11(3):288-298.

[6]Gottesman, L.E., del Vecchio, M.T., Aronoff, S.C., 2015. Etiologies of conjugated hyperbilirubinemia in infancy: a systematic review of 1692 subjects. BMC Pediatrics, 15(1):8.

[7]Hatzilygeroudis, I., Prentzas, J., 2004. Integrating (rules, neural networks) and cases for knowledge representation and reasoning in expert systems. Expert Syst. Appl., 27(1): 63-75.

[8]Keith, R.D., Beckley, S., Garibaldi, J.M., et al., 1995. A multicentre comparative study of 17 experts and an intelligent computer system for managing labour using the cardiotocogram. Br. J. Obstet. Gynaecol., 102(9): 688-700.

[9]Kruk, M., Osowski, S., Markiewicz, T., et al., 2014. Computer approach to recognition of Fuhrman grade of cells in clear-cell renal cell carcinoma. Anal. Quant Cytopathol. Histpathol., 36(3):147-160.

[10]Lee, G.H., 2008. Rule-based and case-based reasoning approach for internal audit of bank. Knowl.-Based Syst., 21(2):140-147.

[11]Li, P., Bi, T., Huang, J., et al., 2014. Breast cancer early diagnosis based on hybrid strategy. Biomed. Mater. Eng., 24(6):3397-3404.

[12]Madabhushi, A., Doyle, S., Lee, G., et al., 2010. Integrated diagnostics: a conceptual framework with examples. Clin. Chem. Lab. Med., 48(7):989-998.

[13]Malek, S., Phillips, R., Mohsen, A., et al., 2005. Computer assisted orthopaedic surgical system for insertion of distal locking screws in intra-medullary nails: a valid and reliable navigation system. Int. J. Med. Robot. Comput. Assist. Surg., 1(4):34-44.

[14]Oladipupo, O.O., Uwadia, C.O., Ayo, C.K., 2012. Improving medical rule-based expert systems comprehensibility: fuzzy association rule mining approach. Int. J. Artif. Intell. Soft Comput., 3(1):29-38.

[15]Pearl, J., 2009. Causality: Models, Reasoning, and Inference. Cambridge University Press, New York.

[16]Poole, D., Zhang, N.L., 2003. Exploiting contextual independence in probabilistic inference. J. Artif. Intell. Res., 18:263-313.

[17]Sasikumar, M., Ramani, S., Raman, S.M., et al., 2007. A practical introduction to rule based expert systems. Narosa Publishing House, New Delhi.

[18]Shen, Y., Colloc, J., Jacquet-Andrieu, A., et al., 2015. Emerging medical informatics with case-based reasoning for aiding clinical decision in multi-agent system. J. Biomed. Inform., 56:307-317.

[19]Siniscalchi, S.M., Svendsen, T., Lee, C., 2014. An artificial neural network approach to automatic speech processing. Neurocomputing, 140:326-338.

[20]Suk, H.I., Lee, S.W., Shen, D., 2014. Subclass-based multi-task learning for Alzheimer’s disease diagnosis. Front. Aging Neurosci., 6:168.

[21]Xu, B.G., 2012. Intelligent fault inference for rotating flexible rotors using bayesian belief network. Expert Syst. Appl., 39(1):816-822.

[22]Zhang, Q., 2012. Dynamic uncertain causality graph for knowledge representation and reasoning: discrete DAG cases. J. Comput. Sci. Technol., 27(1):1-23.

[23]Zhang, Q., 2015a. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: directed cyclic graph and joint probability distribution. IEEE Trans. Neural Netw. Learn. Syst., 26(7):1503-1517.

[24]Zhang, Q., 2015b. Dynamic uncertain causality graph for knowledge representation and reasoning: continuous variable, uncertain evidence, and failure forecast. IEEE Trans. Syst. Man Cybern. Syst., 45(7):990-1003.

[25]Zhang, Q., Geng, S., 2015. Dynamic uncertain causality graph applied to dynamic fault diagnoses of large and complex systems. IEEE Trans. Reliab., 64(3):910-927.

[26]Zhang, Q., Dong, C., Cui, Y., et al., 2014. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: statistics base, matrix, and application. IEEE Trans. Neural Netw. Learn. Syst., 25(4): 645-663.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Similar articles

- Go to

基于动态不确定性因果图（DUCG）模型的黄疸待查智能诊断研究

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference