Development of an artificial intelligence diagnostic model based on dynamic uncertain causality graph for the differential diagnosis of dyspnea

doi:10.1007/s11684-020-0762-0

Front. Med.

2020, Vol. 14

Issue (4) : 488-497 https://doi.org/10.1007/s11684-020-0762-0

RESEARCH ARTICLE

Development of an artificial intelligence diagnostic model based on dynamic uncertain causality graph for the differential diagnosis of dyspnea

Yang Jiao¹(

), Zhan Zhang², Ting Zhang³, Wen Shi⁴, Yan Zhu⁵, Jie Hu⁶, Qin Zhang⁷(

)

¹. Department of General Internal Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China
². Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing 100084, China
³. Department of Pulmonary and Critical Care Medicine, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China
⁴. Department of Gastroenterology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing 100730, China
⁵. Institute of Internet Industry, Tsinghua University, Beijing 100084, China
⁶. Department of Medical Administration, Suining Central Hospital, Suining 629000, China
⁷. Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China

Download: PDF(1800 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Dyspnea is one of the most common manifestations of patients with pulmonary disease, myocardial dysfunction, and neuromuscular disorder, among other conditions. Identifying the causes of dyspnea in clinical practice, especially for the general practitioner, remains a challenge. This pilot study aimed to develop a computer-aided tool for improving the efficiency of differential diagnosis. The disease set with dyspnea as the chief complaint was established on the basis of clinical experience and epidemiological data. Differential diagnosis approaches were established and optimized by clinical experts. The artificial intelligence (AI) diagnosis model was constructed according to the dynamic uncertain causality graph knowledge-based editor. Twenty-eight diseases and syndromes were included in the disease set. The model contained 132 variables of symptoms, signs, and serological and imaging parameters. Medical records from the electronic hospital records of Suining Central Hospital were randomly selected. A total of 202 discharged patients with dyspnea as the chief complaint were included for verification, in which the diagnoses of 195 cases were coincident with the record certified as correct. The overall diagnostic accuracy rate of the model was 96.5%. In conclusion, the diagnostic accuracy of the AI model is promising and may compensate for the limitation of medical experience.

Keywords knowledge representation uncertain causality graphical model artificial intelligence diagnosis dyspnea

Corresponding Author(s): Yang Jiao,Qin Zhang

Just Accepted Date: 13 May 2020 Online First Date: 16 July 2020 Issue Date: 26 August 2020

Cite this article:

Yang Jiao,Zhan Zhang,Ting Zhang, et al. Development of an artificial intelligence diagnostic model based on dynamic uncertain causality graph for the differential diagnosis of dyspnea[J]. Front. Med., 2020, 14(4): 488-497.

URL:

https://academic.hep.com.cn/fmd/EN/10.1007/s11684-020-0762-0
https://academic.hep.com.cn/fmd/EN/Y2020/V14/I4/488

Tab.1 Functions of variables in DUCG

Fig.1 Example of a dynamic uncertain causality graph.

Tab.2 Diseases causing dyspnea in the DUCG knowledge base

Fig.2 DUCG subgraph example of chronic obstructive pulmonary disease.

Fig.3 Knowledge graph of the AI diagnostic model of dyspnea database.

Tab.3 Example of a COPD patient’s test result

Fig.4 Sorted diagnoses by DUCG for a test case, according to

h k j s

. Abbreviation: PE, pulmonary embolism; PAH, pulmonary artery hypertension; COPD, chronic obstructive pulmonary disease; HCM, hypertrophic cardiomyopathy.

Fig.5 Graph of the causal relationship between the diagnosis heart failure (ranking the first in Fig. 4) and its evidence.

Fig.6 Graph of the causal relationship between the disease pericardial effusion (ranking second in Fig. 4) and its evidence, in which two isolated abnormal symptoms cannot be explained by the disease.

1	MB Parshall, RM Schwartzstein, L Adams, RB Banzett, HL Manning, J Bourbeau, PM Calverley, AG Gift, A Harver, SC Lareau, DA Mahler, PM Meek, DE O’Donnell; American Thoracic Society Committee on Dyspnea. An official American Thoracic Society statement: update on the mechanisms, assessment, and management of dyspnea. Am J Respir Crit Care Med 2012; 185(4): 435–452 https://doi.org/10.1164/rccm.201111-2042ST pmid: 22336677
2	GR Pesola, V Terla, N Malik, H Ahsan. Chronic dyspnoea: finding the cause to reduce mortality. J Thorac Dis 2018; 10(Suppl 33): S4057–S4060 https://doi.org/10.21037/jtd.2018.09.60 pmid: 30631554
3	B Ehteshami Bejnordi, M Veta, P Johannes van Diest, B van Ginneken, N Karssemeijer, G Litjens, JAWM van der Laak; the CAMELYON16 Consortium, M Hermsen, QF Manson, M Balkenhol, O Geessink, N Stathonikos, MC van Dijk, P Bult, F Beca, AH Beck, D Wang, A Khosla, R Gargeya, H Irshad, A Zhong, Q Dou, Q Li, H Chen, HJ Lin, PA Heng, C Haß, E Bruni, Q Wong, U Halici, MÜ Öner, R Cetin-Atalay, M Berseth, V Khvatkov, A Vylegzhanin, O Kraus, M Shaban, N Rajpoot, R Awan, K Sirinukunwattana, T Qaiser, YW Tsang, D Tellez, J Annuscheit, P Hufnagl, M Valkonen, K Kartasalo, L Latonen, P Ruusuvuori, K Liimatainen, S Albarqouni, B Mungal, A George, S Demirci, N Navab, S Watanabe, S Seno, Y Takenaka, H Matsuda, H Ahmady Phoulady, V Kovalev, A Kalinovsky, V Liauchuk, G Bueno, MM Fernandez-Carrobles, I Serrano, O Deniz, D Racoceanu, R Venâncio. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017; 318(22): 2199–2210 https://doi.org/10.1001/jama.2017.14585 pmid: 29234806
4	MR Daliri. A hybrid automatic system for the diagnosis of lung cancer based on genetic algorithm and fuzzy extreme learning machines. J Med Syst 2012; 36(2): 1001–1005 https://doi.org/10.1007/s10916-011-9806-y pmid: 22113438
5	D Salas-Gonzalez, JM Górriz, J Ramírez, M López, I Alvarez, F Segovia, R Chaves, CG Puntonet. Computer-aided diagnosis of Alzheimer’s disease using support vector machines and classification trees. Phys Med Biol 2010; 55(10): 2807–2817 https://doi.org/10.1088/0031-9155/55/10/002 pmid: 20413829
6	Q Zhang. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: directed cyclic graph and joint probability distribution. IEEE Trans Neural Netw Learn Syst 2015; 26(7): 1503–1517 https://doi.org/10.1109/TNNLS.2015.2402162 pmid: 25781960
7	Q Zhang, Q Yao. Dynamic uncertain causality graph for knowledge representation and reasoning: utilization of statistical data and domain knowledge in complex cases. IEEE Trans Neural Netw Learn Syst 2018; 29(5): 1637–1651 https://doi.org/10.1109/TNNLS.2017.2673243 pmid: 28328514
8	C Dong, Y Wang, Q Zhang, N Wang. The methodology of dynamic uncertain causality graph for intelligent diagnosis of vertigo. Comput Methods Programs Biomed 2014; 113(1): 162–174 https://doi.org/10.1016/j.cmpb.2013.10.002 pmid: 24176413
9	SR Hao, SC Geng, LX Fan, JJ Chen, Q Zhang, LJ Li. Intelligent diagnosis of jaundice with dynamic uncertain causality graph model. J Zhejiang Univ Sci B 2017; 18(5): 393–401 https://doi.org/10.1631/jzus.B1600273 pmid: 28471111
10	Q Zhang. Dynamic uncertain causality graph for knowledge representation and reasoning: discrete DAG cases. J Comput Sci Technol 2012; 27(1): 1–23
11	Q Zhang, CL Dong, Y Cui, ZH Yang. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: statistics base, matrix and fault diagnosis. IEEE Trans Neural Netw Learn Syst 2014; 25(4): 645–663
12	Q Zhang. Dynamic uncertain causality graph for knowledge representation and probabilistic reasoning: directed cyclic graph and joint probability distribution. IEEE Trans Neural Netw Learn Syst 2015; 26(7): 1503–1517
13	C Dong, Y Zhao, Q Zhang. Assessing the influence of an individual event in complex fault spreading network based on dynamic uncertain causality graph. IEEE Trans Neural Netw Learn Syst 2016; 27(8): 1615–1630 https://doi.org/10.1109/TNNLS.2016.2547339 pmid: 27101619
14	S Ceccon, DF Garway-Heath, DP Crabb, A Tucker. Exploring early glaucoma and the visual field test: classification and clustering using Bayesian networks. IEEE J Biomed Health Inform 2014; 18(3): 1008–1014 https://doi.org/10.1109/JBHI.2013.2289367 pmid: 24808230
15	RH Lin, CL Chuang. A hybrid diagnosis model for determining the types of the liver disease. Comput Biol Med 2010; 40(7): 665–670 https://doi.org/10.1016/j.compbiomed.2010.06.002 pmid: 20591425

[1]	Joseph JY Sung, Nicholas CH Poon. Artificial intelligence in gastroenterology: where are we heading?[J]. Front. Med., 2020, 14(4): 511-517.
[2]	Dongping Ning, Zhan Zhang, Kun Qiu, Lin Lu, Qin Zhang, Yan Zhu, Renzhi Wang. Efficacy of intelligent diagnosis with a dynamic uncertain causality graph model for rare disorders of sex development[J]. Front. Med., 2020, 14(4): 498-505.
[3]	Ke Sheng. Artificial intelligence in radiotherapy: a technological review[J]. Front. Med., 2020, 14(4): 431-449.
[4]	Xiao-Yun Zhou, Yao Guo, Mali Shen, Guang-Zhong Yang. Application of artificial intelligence in surgery[J]. Front. Med., 2020, 14(4): 417-430.
[5]	Allison J. Navarrete-Welton, Daniel A. Hashimoto. Current applications of artificial intelligence for intraoperative decision support in surgery[J]. Front. Med., 2020, 14(4): 369-381.
[6]	Hanyu Zhu, Bo Fu, Yong Wang, Jing Gao, Qiuxia Han, Wenjia Geng, Xiaoli Yang, Guangyan Cai, Xiangmei Chen, Dong Zhang. Comparative analysis of membranous and other nephropathy subtypes and establishment of a diagnostic model[J]. Front. Med., 2019, 13(5): 618-625.
[7]	Xiaolin Fan, Yanzhen Xiong, Yuan Wang. A reignited debate over the cell(s) of origin for glioblastoma and its clinical implications[J]. Front. Med., 2019, 13(5): 531-539.
[8]	Min Zhang, Jingwen Yang, Wenjing Hua, Zhong Li, Zenghui Xu, Qijun Qian. Monitoring checkpoint inhibitors: predictive biomarkers in immunotherapy[J]. Front. Med., 2019, 13(1): 32-44.
[9]	Liru Qiu, Fengjie Yang, Yonghua He, Huiqing Yuan, Jianhua Zhou. Clinical characterization and diagnosis of cystic fibrosis through exome sequencing in Chinese infants with Bartter-syndrome-like hypokalemia alkalosis[J]. Front. Med., 2018, 12(5): 550-558.
[10]	Changlin Cao, Jingxian Gu, Jingyao Zhang. Soluble triggering receptor expressed on myeloid cell-1 (sTREM-1): a potential biomarker for the diagnosis of infectious diseases[J]. Front. Med., 2017, 11(2): 169-177.
[11]	Lei Huang,Aman Xu. Detection of digestive malignancies and post-gastrectomy complications via gastrointestinal fluid examination[J]. Front. Med., 2017, 11(1): 20-31.
[12]	Jing Zhang,Shan Gao,Zhongping Duan,Ke-Qin Hu. Overview on acute-on-chronic liver failure[J]. Front. Med., 2016, 10(1): 1-17.
[13]	Wanqiu Huang,Yang Luan,Lu Jin,Tao Wang,Ruibao Chen,Zheng Liu,Zhiqiang Chen,Ruzhu Lan. Small cell carcinoma of the urinary bladder without gross hematuria: a case report[J]. Front. Med., 2015, 9(3): 384-387.
[14]	Yi Cao. Environmental pollution and DNA methylation: carcinogenesis, clinical significance, and practical applications[J]. Front. Med., 2015, 9(3): 261-274.
[15]	Lingqiang Zhang,Runchen Miao,Xiude Zhang,Wei Chen,Yanyan Zhou,Ruitao Wang,Ruiyao Zhang,Qing Pang,Xinsen Xu,Chang Liu. Exploring the diagnosis markers for gallbladder cancer based on clinical data[J]. Front. Med., 2015, 9(3): 350-355.

Viewed

Full text

Abstract

Cited

Shared

Discussed