Diseasomics: Actionable machine interpretable disease knowledge at the point-of-care.
Diseasomics: Actionable machine interpretable disease knowledge at the point-of-care.
复制标题
DOI：
10.1371/journal.pdig.0000128
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
中科院分区：
文献类型：
--
作者：
医生通过评估患者的体征、症状、年龄、性别、实验室检查结果和病史来确定诊断。所有这一切都必须在有限的时间内并在总体工作量不断增加的背景下完成。在循证医学的时代，临床医生必须掌握最新的指南和治疗方案，这些指南和治疗方案正在迅速变化。在资源有限的环境中，更新的知识通常不能到达护理点。本文提出了一种基于人工智能（AI）的方法，用于整合全面的疾病知识，以支持医生和医护人员在护理点获得准确的诊断。我们整合了不同的疾病相关知识体，构建了一个全面的、机器可解释的疾病组学知识图谱，其中包括疾病本体、疾病症状、SNOMED CT、DisGeNET和PharmGKB数据。所得到的疾病-症状网络包括来自症状本体、电子健康记录（EHR）、人类症状疾病网络、疾病本体、维基百科、PubMed、教科书和神经病学知识源的知识，准确率为84.56%。我们还整合了从EHR获得的两个人口数据集，分别从西班牙和瑞典的空间和时间的共时性知识。知识图谱作为疾病知识的数字孪生存储在图谱数据库中。我们使用node 2 vec（节点嵌入）作为疾病-症状网络中链接预测的数字三元组，以识别缺失的关联。这种疾病组学知识图谱有望使医学知识民主化，并使非专业卫生工作者能够做出基于证据的明智决策，并帮助实现全民健康覆盖（UHC）的目标。本文提出的机器可解释的知识图是各种实体之间的关联，并不意味着因果关系。我们的鉴别诊断工具侧重于体征和症状，不包括对患者生活方式和健康史的完整评估，这通常是排除疾病并得出最终诊断所必需的。预测的疾病根据南亚的具体疾病负担进行排序。这里介绍的知识图和工具可以作为指导。在护理点的医生预计将有完整的医学知识与最新的循证医学（EBM）。医生也被期望在与患者的医疗交互期间准确地使用这种完整的知识。事实并非如此，在知识获取和临床决策方面存在差距。为了解决这些差距，过去开发了基于AI的专家驱动的基于规则的临床决策支持系统。基于规则的系统是僵化的，并且在遇到复杂疾病时经常失败。因此，我们建立了一个基于人工智能的证据驱动的临床决策支持系统。我们挖掘PubMed、维基百科、教科书、医疗记录等来提取临床知识。我们使用这些临床知识作为粘合剂来连接本体，以构建机器可解释的反还原主义疾病组学知识图。疾病组学知识图谱存储在云中的Neo4j属性图谱数据库中，可使用JSON-RPC API进行在线和实时访问，其工作方式类似于医生的大脑数字孪生模型。我们使用了node 2 vec技术来挖掘未知的知识，并创建了一个学习型医疗保健系统。综合疾病组学知识系统可在https://triage.cyberneticcare.com/diseasePrediction上使用。
Physicians establish diagnosis by assessing a patient’s signs, symptoms, age, sex, laboratory test findings and the disease history. All this must be done in limited time and against the backdrop of an increasing overall workload. In the era of evidence-based medicine it is utmost important for a clinician to be abreast of the latest guidelines and treatment protocols which are changing rapidly. In resource limited settings, the updated knowledge often does not reach the point-of-care. This paper presents an artificial intelligence (AI)-based approach for integrating comprehensive disease knowledge, to support physicians and healthcare workers in arriving at accurate diagnoses at the point-of-care. We integrated different disease-related knowledge bodies to construct a comprehensive, machine interpretable diseasomics knowledge-graph that includes the Disease Ontology, disease symptoms, SNOMED CT, DisGeNET, and PharmGKB data. The resulting disease-symptom network comprises knowledge from the Symptom Ontology, electronic health records (EHR), human symptom disease network, Disease Ontology, Wikipedia, PubMed, textbooks, and symptomology knowledge sources with 84.56% accuracy. We also integrated spatial and temporal comorbidity knowledge obtained from EHR for two population data sets from Spain and Sweden respectively. The knowledge graph is stored in a graph database as a digital twin of the disease knowledge. We use node2vec (node embedding) as digital triplet for link prediction in disease-symptom networks to identify missing associations. This diseasomics knowledge graph is expected to democratize the medical knowledge and empower non-specialist health workers to make evidence based informed decisions and help achieve the goal of universal health coverage (UHC). The machine interpretable knowledge graphs presented in this paper are associations between various entities and do not imply causation. Our differential diagnostic tool focusses on signs and symptoms and does not include a complete assessment of patient’s lifestyle and health history which would typically be necessary to rule out conditions and to arrive at a final diagnosis. The predicted diseases are ordered according to the specific disease burden in South Asia. The knowledge graphs and the tools presented here can be used as a guide. A doctor at the point-of-care is expected to have the complete medical knowledge with latest updates in evidence-based medicine (EBM). The doctor is also expected to use this complete knowledge accurately during a medical interaction with a patient. In reality this is not the case—there are gaps in knowledge acquisition and gaps in clinical decision making. To address these gaps, in the past AI based expert driven rule-based clinical decision support systems were developed. Rule-based systems are rigid and often fail in case of complex diseases. We therefore built an AI based evidence driven clinical decision support system. We mined PubMed, Wikipedia, textbooks, medical records, etc. to extract clinical knowledge. We used this clinical knowledge as glue to connect ontologies to construct a machine interpretable antireductionistic diseasomics knowledge graph. The diseasomics knowledge graph is stored in a Neo4j property graph database in a cloud for online and realtime access using JSON-RPC API and works like the physicians’ brain digital twin. We used the digital triplet node2vec techniques to mine unknown knowledge and to create a learning healthcare system. The integrated diseasomics knowledge system is available for use at https://triage.cyberneticcare.com/diseasePrediction.