Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1942–1955 June 6–11, 2021. ©2021 Association for Computational Linguistics 1942 Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network Haoran Wu1,2, Wei Chen1, Shuang Xu1 and Bo Xu1,2 1Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China 2School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China {wuhaoran2018, w.chen, shuang.xu, xubo}@ia.ac.cn Abstract Providing a reliable explanation for clinical diagnosis based on the Electronic Medical Record (EMR) is fundamental to the applica- tion of Artificial Intelligence in the medical field. Current methods mostly treat the EMR as a text sequence and provide explanations based on a precise medical knowledge base, which is disease-specific and difficult to ob- tain for experts in reality. Therefore, we pro- pose a counterfactual multi-granularity graph supporting facts extraction (CMGE) method to extract supporting facts from the irregular EMR itself without external knowledge bases in this paper. Specifically, we first structure the sequence of the EMR into a hierarchical graph network and then obtain the causal re- lationship between multi-granularity features and diagnosis results through counterfactual intervention on the graph. Features having the strongest causal connection with the results provide interpretive support for the diagnosis. Experimental results on real Chinese EMRs of the lymphedema demonstrate that our method can diagnose four types of EMRs correctly, and can provide accurate supporting facts for the results. More importantly, the results on different diseases demonstrate the robustness of our approach, which represents the poten- tial application in the medical field1. 1 Introduction Electronic Medical Record (EMR) based diagnosis has attracted extensive attention due to its compre- hensive historical information and clinical descrip- tions with the development of natural language processing and medical informatics (Yang et al., 2018; Choi et al., 2018; Liu et al., 2019; Dong et al., 2020; Ma et al., 2020b). The application of deep learning in medicine requires adequate med- ical explanations for the result. Specific to the diagnosis of EMR, the model needs to provide the text description supporting the diagnosis results. 1The code is available at https://github.com/CKRE/CMGE Figure 1: An example of EMR. We consolidated the various parts of the EMR into a single document as in- put and our goal is to extract supporting facts at the granularity of the clause. As shown in Figure 1, an irregular EMR is a document of disease-related information, including symptoms, history of the disease, preliminary ex- amination results, and so on, which is disordered and sparse with meaningless noisy text. Existing methods provide explanation through medical en- tities (Yuan et al., 2020), text spans (Mullenbach et al., 2018) and the weights of external knowledge (Ma et al., 2018). The entity is critical to the diag- nosis (Sha and Wang, 2017; Girardi et al., 2018), but for the medical explanation, it cannot provide specific information of symptoms (such as posi- tive or negative). And the form of the span is …

Content truncated to 500 words