Mining Latent Disease Factors from Medical Literature using Causality
Mining Latent Disease Factors from Medical Literature using Causality
复制标题
DOI：
10.1109/bigdata55660.2022.10020994
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
P. Gujarathi;Jack VanSchaik;Venkatanaidu Karri;A. Rajapuri;Biju Cheriyan;T. Thyvalikakath;Sunandan Chakraborty
中科院分区：
文献类型：
--
作者：
P. Gujarathi;Jack VanSchaik;Venkatanaidu Karri;A. Rajapuri;Biju Cheriyan;T. Thyvalikakath;Sunandan Chakraborty
理解因果关系是跨越许多不同领域的长期目标。不同的文章，比如那些发表在医学杂志上的文章，发表的是新发现的知识，通常是因果关系。在本文中，我们利用这种直觉建立了一个模型，利用因果关系来挖掘与Sjögren综合征相关的因素。Sjögren综合征是一种影响310万美国人的自身免疫性疾病。这种疾病的罕见性质，加上其他自身免疫性疾病如类风湿关节炎的常见症状，临床医生很难及时诊断这种疾病。牙医和医生（包括风湿病学家和眼科医生）之间不理想的沟通使情况进一步恶化，因为这种疾病的临床表现要求患者去看不同专业的医生。一个集中的信息系统，可以方便地获取与Sjögren综合征相关的常见和不常见因素，可能会缓解这个问题。我们使用从医学文献中收集的与Sjögren综合征相关的文本中自动提取的因果关系来识别与该疾病相关的一组因素，如“体征和症状”和“相关条件”。我们表明，我们的方法能够以较高的精度和召回值检索这些因素。对比实验表明，与几种最先进的生物医学模型（包括BioBERT和Gram-CNN）相比，该方法的检索f1分数提高了25%。
Understanding causality is a longstanding goal across many different domains. Different articles, such as those published in medical journals, publish newly discovered knowledge, often causal. In this paper, we use this intuition to build a model that leverages causal relations to unearth factors related to Sjögren’s syndrome. Sjögren’s syndrome is an autoimmune disease affecting up to 3.1 million Americans. The uncommon nature of the disease, coupled with common symptoms of other autoimmune conditions such as rheumatoid arthritis, it is difficult for clinicians to timely diagnose the disease. This is further worsened by suboptimal communication between dentists, and physicians, including rheumatologists and ophthalmologists, because clinical manifestations of this disease require the patients to visit physicians with different specialties. A centralized information system with easy access to common and uncommon factors related to Sjögren’s syndrome may alleviate the problem. We use automatically extracted causal relationships from text related to Sjögren’s syndrome collected from the medical literature to identify a set of factors, such as “signs and symptoms” and “associated conditions”, related to this disease. We show that our approach is capable of retrieving such factors with high precision and recall values. Comparative experiments show that this approach leads to 25% improvement in retrieval F1-score compared to several state-of-the-art biomedical models, including BioBERT and Gram-CNN.