Capturing Semantic Relationships in Electronic Health Records Using Knowledge Graphs: An Implementation Using MIMIC III Dataset and GraphDB.

BackgroundArtificial intelligence methods applied to electronic medical records (EMRs) hold the potential to help physicians save time by sharpening their analysis and decisions, thereby improving the health of patients. On the one hand, machine learning algorithms have proven their effectiveness in extracting information and exploiting knowledge extracted from data. On the other hand, knowledge graphs capture human knowledge by relying on conceptual schemas and formalization and supporting reasoning. Leveraging knowledge graphs that are legion in the medical field, it is possible to pre-process and enrich data representation used by machine learning algorithms. Medical data standardization is an opportunity to jointly exploit the richness of knowledge graphs and the capabilities of machine learning algorithms.MethodsWe propose to address the problem of hospitalization prediction for patients with an approach that enriches vector representation of EMRs with information extracted from different knowledge graphs before learning and predicting. In addition, we performed an automatic selection of features resulting from knowledge graphs to distinguish noisy ones from those that can benefit the decision making. We report the results of our experiments on the PRIMEGE PACA database that contains more than 600,000 consultations carried out by 17 general practitioners (GPs).ResultsA statistical evaluation shows that our proposed approach improves hospitalization prediction. More precisely, injecting features extracted from cross-domain knowledge graphs in the vector representation of EMRs given as input to the prediction algorithm significantly increases the F1 score of the prediction.ConclusionsBy injecting knowledge from recognized reference sources into the representation of EMRs, it is possible to significantly improve the prediction of medical events. Future work would be to evaluate the impact of a feature selection step coupled with a combination of features extracted from several knowledge graphs. A possible avenue is to study more hierarchical levels and properties related to concepts, as well as to integrate more semantic annotators to exploit unstructured data.

Electronic medical records (EMRs) of patients with lung cancer (LC) capture a variety of health factors. Understanding the distribution of these factors will help identify key factors for risk prediction in preventive screening for LC. We aimed to generate an integrated biomedical graph from EMR data and Unified Medical Language System (UMLS) ontology for LC, and to generate an LC health factor distribution from a hospital EMR of approximately 1 million patients. The data were collected from 2 sets of 1397 patients with and those without LC. A patient-centered health factor graph was plotted with 108,000 standardized data, and a graph database was generated to integrate the graphs of patient health factors and the UMLS ontology. With the patient graph, we calculated the connection delta ratio (CDR) for each of the health factors to measure the relative strength of the factor's relationship to LC. The patient graph had 93,000 relations between the 2794 patient nodes and 650 factor nodes. An LC graph with 187 related biomedical concepts and 188 horizontal biomedical relations was plotted and linked to the patient graph. Searching the integrated biomedical graph with any number or category of health factors resulted in graphical representations of relationships between patients and factors, while searches using any patient presented the patient's health factors from the EMR and the LC knowledge graph (KG) from the UMLS in the same graph. Sorting the health factors by CDR in descending order generated a distribution of health factors for LC. The top 70 CDR-ranked factors of disease, symptom, medical history, observation, and laboratory test categories were verified to be concordant with those found in the literature. By collecting standardized data of thousands of patients with and those without LC from the EMR, it was possible to generate a hospital-wide patient-centered health factor graph for graph search and presentation. The patient graph could be integrated with the UMLS KG for LC and thus enable hospitals to bring continuously updated international standard biomedical KGs from the UMLS for clinical use in hospitals. CDR analysis of the graph of patients with LC generated a CDR-sorted distribution of health factors, in which the top CDR-ranked health factors were concordant with the literature. The resulting distribution of LC health factors can be used to help personalize risk evaluation and preventive screening recommendations.

BackgroundIntensive Care Unit (ICU) readmissions represent both a health risk for patients,with increased mortality rates and overall health deterioration, and a financial burden for healthcare facilities. As healthcare became more data-driven with the introduction of Electronic Health Records (EHR), machine learning methods have been applied to predict ICU readmission risk. However, these methods disregard the meaning and relationships of data objects and work blindly over clinical data without taking into account scientific knowledge and context. Ontologies and Knowledge Graphs can help bridge this gap between data and scientific context, as they are computational artefacts that represent the entities of a domain and their relationships to each other in a formalized way.Methods and resultsWe have developed an approach that enriches EHR data with semantic annotations to ontologies to build a Knowledge Graph. A patient’s ICU stay is represented by Knowledge Graph embeddings in a contextualized manner, which are used by machine learning models to predict 30-days ICU readmissions. This approach is based on several contributions: (1) an enrichment of the MIMIC-III dataset with patient-oriented annotations to various biomedical ontologies; (2) a Knowledge Graph that defines patient data with biomedical ontologies; (3) a predictive model of ICU readmission risk that uses Knowledge Graph embeddings; (4) a variant of the predictive model that targets different time points during an ICU stay. Our predictive approaches outperformed both a baseline and state-of-the-art works achieving a mean Area Under the Receiver Operating Characteristic Curve of 0.827 and an Area Under the Precision-Recall Curve of 0.691. The application of this novel approach to help clinicians decide whether a patient can be discharged has the potential to prevent the readmission of 40% of Intensive Care Unit patients, without unnecessarily prolonging the stay of those who would not require it.ConclusionThe coupling of semantic annotation and Knowledge Graph embeddings affords two clear advantages: they consider scientific context and they are able to build representations of EHR information of different types in a common format. This work demonstrates the potential for impact that integrating ontologies and Knowledge Graphs into clinical machine learning applications can have.

In recent years, with the better availability of medical data such as Electronic Health Records (EHR), more and more data mining models have been developed to explore the data-driven insights for better human health. However, there are many challenges for analyzing EHR such as high-dimensionality, temporality, sparsity, etc., which make the data-driven models less reliable. Medical knowledge graph (MKG), which encodes comprehensive knowledge about the medical concepts and relationships extracted from medical literature, holds great promise to regularize the data-driven models as prior knowledge. Nonetheless, the MKGs are typically not complete, which limits its utility in helping with the data mining process. In this paper, we propose a mutual enhancement framework MendMKG for predictive modeling of clinical events with both EHR and MKG. In particular, MendMKG first conducts a self-supervised learning strategy to simultaneously pre-train a graph attention network for embedding nodes and complete the MKG. It iteratively performs (1) an embedding-based knowledge graph completion module to derive missing edges, (2) and a reconstruction module of unlabeled EHR data to select high-quality ones from these edges, which would be further appended to the MKG to update the embedding model. Through the iterations, the two modules mutually benefit each other. Then, MendMKG uses the pre-trained graph attention network and the updated MKG to generate the visit embeddings to represent patient’s historical visits, and predict the diagnosis in future visit, through a fine-tuning approach. Experimental results on real world EHR corpus are provided to demonstrate the superiority of the proposed framework, compared to a series of state-of-the-art baselines. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> The source code and knowledge graph data have been anonymously uploaded to https://github.com/1317375434/MendMKG.

The effective analysis of high-dimensional Electronic Health Record (EHR) data, with substantial potential for healthcare research, presents notable methodological challenges. Employing predictive modeling guided by a knowledge graph (KG), which enables efficient feature selection, can enhance both statistical efficiency and interpretability. While various methods have emerged for constructing KGs, existing techniques often lack statistical certainty concerning the presence of links between entities, especially in scenarios where the utilization of patient-level EHR data is limited due to privacy concerns. In this paper, we propose the first inferential framework for deriving a sparse KG with statistical guarantee based on a dynamic log-linear topic model. Within this model, the KG embeddings are estimated by performing singular value decomposition on the empirical pointwise mutual information matrix, offering a scalable solution. We then establish entrywise asymptotic normality for the KG low-rank estimator, enabling the recovery of sparse graph edges with controlled type I error. Our work uniquely addresses the under-explored domain of statistical inference about non-linear statistics under the low-rank temporal dependent models, a critical gap in existing research. We validate our approach through extensive simulation studies and then apply the method to real-world EHR data in constructing clinical KGs and generating clinical feature embeddings.

The development of a process approach to cost management in a digital environment has great prospects. Firstly, the use of digital technologies allows for greater accuracy in cost accounting, which is particularly important for enterprises with large production volumes and numerous processes. Secondly, digitization enables the automation of many processes and reduces the human factor in cost management. Thirdly, digital technologies enable faster and more efficient data analysis and decisionmaking based on this data. One promising direction for the development of a process approach to cost management in enterprises is the use of blockchain technologies. Blockchain can provide transparency and security in storing and transmitting information about cost accounting between enterprises and their partners. This can be particularly important in areas where it is important to accurately track the origin and distribution of costs, such as in agriculture or food production. It is also worth noting that the development and use of artificial intelligence and machine learning can improve cost management processes and allow for faster and more accurate data analysis and decision-making. Overall, the development of a process approach to cost management in enterprises in a digital environment will continue, and its successful implementation will enable enterprises to optimize their costs, increase efficiency, and competitiveness in the market.

The explosive growth of biomedical Big Data presents both significant opportunities and challenges in the realm of knowledge discovery and translational applications within precision medicine. Efficient management, analysis, and interpretation of big data can pave the way for groundbreaking advancements in precision medicine. However, the unprecedented strides in the automated collection of large‐scale molecular and clinical data have also introduced formidable challenges in terms of data analysis and interpretation, necessitating the development of novel computational approaches. Some potential challenges include the curse of dimensionality, data heterogeneity, missing data, class imbalance, and scalability issues. This overview article focuses on the recent progress and breakthroughs in the application of big data within precision medicine. Key aspects are summarized, including content, data sources, technologies, tools, challenges, and existing gaps. Nine fields—Datawarehouse and data management, electronic medical record, biomedical imaging informatics, Artificial intelligence‐aided surgical design and surgery optimization, omics data, health monitoring data, knowledge graph, public health informatics, and security and privacy—are discussed.

Digging rich knowledge from clinical texts becomes a popular topic today. Knowledge graph has been widely used to integrate and manage abundant knowledge. Entity recognition and relation extraction play important roles in constructing knowledge graphs. In this paper, we develop a system to recognize entities and extract their relations from clinical texts in Electronic Medical Records. Our system implements four major functions: manual entity annotation, automatic entity recognition, manual relation annotation and automatic relation extraction. Tools of entity annotation and relation annotation are designed for professionals to help them manually annotate objects given original clinical texts. Moreover, entity recognition and relation recognition, which CRF and CNN are applied in, are accessible for professionals before manual annotation in order to increase the efficiency. Our system has been used in several applications, such as medical knowledge graph construction and health QA system.

Dynamische zellulare Prozesse wie Zellzyklus, Signaltransduktion oder Transkription zu analysieren wird Live-cell-imaging mittels Zeitraffermikroskopie verwendet. Um nun aber Zellabstammungsbaume aus einem Zeitraffervideo zu extrahieren, mussen die Zellen segmentiert und verfolgt werden konnen. Besonders hier, wo lebende Zellen uber einen langen Zeitraum betrachtet werden, sind Fehler in der Analyse fatal: Selbst eine extrem niedrige Fehlerrate kann sich amplifizieren, wenn viele Zeitpunkte aufgenommen werden, und damit den gesamten Datensatz unbrauchbar machen. In dieser Arbeit verwenden wir einen einfachen aber praktischen Ansatz, der die Vorzuge der manuellen und automatischen Ansatze kombiniert. Das von uns entwickelte Live-cell-Imaging Datenanalysetool ‘eDetect’ erganzt die automatische Zellsegmentierung und -verfolgung durch Nachbearbeitung. Das Besondere an dieser Arbeit ist, dass sie mehrere interaktive Datenvisualisierungsmodule verwendet, um den Benutzer zu fuhren und zu unterstutzen. Dies erlaubt den gesamten manuellen Eingriffsprozess zu rational und effizient zu gestalten. Insbesondere werden zwei Streudiagramme und eine Heatmap verwendet, um die Merkmale einzelner Zellen interaktiv zu visualisieren. Die Streudiagramme positionieren ahnliche Objekte in unmittelbarer Nahe. So kann eine grose Gruppe ahnlicher Fehler mit wenigen Mausklicks erkannt und korrigiert werden, und damit die manuellen Eingriffe auf ein Minimum reduziert werden. Die Heatmap ist darauf ausgerichtet, alle ubersehenen Fehler aufzudecken und den Benutzern dabei zu helfen, bei der Zellabstammungsrekonstruktion schrittweise die perfekte Genauigkeit zu erreichen. Die quantitative Auswertung zeigt, dass eDetect die Genauigkeit der Nachverfolgung innerhalb eines akzeptablen Zeitfensters erheblich verbessern kann. Beurteilt nach biologisch relevanten Metriken, ubertrifft die Leistung von eDetect die derer Tools, die den Wettbewerb ‘Cell Tracking Challenge’ gewonnen haben.%%%%Live cell imaging based on time-lapse microscopy has been used to study dynamic cellular behaviors, such as cell cycle, cell signaling and transcription. Extracting cell lineage trees out of a time-lapse video requires cell segmentation and cell tracking. For long term live cell imaging, data analysis errors are particularly fatal. Even an extremely low error rate could potentially be amplified by the large number of sampled time points and render the entire video useless. In this work, we adopt a straightforward but practical design that combines the merits of manual and automatic approaches. We present a live cell imaging data analysis tool `eDetect', which uses post-editing to complement automatic segmentation and tracking. What makes this work special is that eDetect employs multiple interactive data visualization modules to guide and assist users, making the error detection and correction procedure rational and efficient. Specifically, two scatter plots and a heat map are used to interactively visualize single cells' visual features. The scatter plots…

Graph data models are an emerging approach to structure clinical and biomedical information. These models offer intriguing opportunities for novel approaches in healthcare, such as disease phenotyping, risk prediction, and personalized precision care. The combination of data and information in a graph model to create knowledge graphs has rapidly expanded in biomedical research, but the integration of real-world data from the electronic health record has been limited. To broadly apply knowledge graphs to EHR and other real-world data, a deeper understanding of how to represent these data in a standardized graph model is needed. We provide an overview of the state-of-the-art research for clinical and biomedical data integration and summarize the potential to accelerate healthcare and precision medicine research through insight generation from integrated knowledge graphs.

The basic analysis steps of spatial transcriptomics require obtaining gene expression information from both space and cells. The existing tools for these analyses incur performance issues when dealing with large datasets. These issues involve computationally intensive spatial localization, RNA genome alignment, and excessive memory usage in large chip scenarios. These problems affect the applicability and efficiency of the analysis. Here, a high-performance and accurate spatial transcriptomics data analysis workflow, called Stereo-seq Analysis Workflow (SAW), was developed for the Stereo-seq technology developed at BGI. SAW includes mRNA spatial position reconstruction, genome alignment, gene expression matrix generation, and clustering. The workflow outputs files in a universal format for subsequent personalized analysis. The execution time for the entire analysis is ∼148 min with 1 GB reads 1 × 1 cm chip test data, 1.8 times faster than with an unoptimized workflow.

Over the past decade, Knowledge Graphs (KG) have emerged as a prominent repository for storing facts about the world in a linked data architecture. Providing machines with the capability of exploring such Knowledge Graphs and answering natural language questions over them, has been an active area of research. The purpose of this work, is to delve further into the research of retrieving information stored in KGs, based on the natural language questions posed by the user. Knowledge Graph Question Answering (KGQA) aims to produce a concise answer to a user question, such that the user is exempt from using KG vocabulary and overheads of learning a formal query language. Existing KGQA systems have achieved excellent results over Simple Questions, where the information required is limited to a single triple and a single formal query pattern. Our motivation is to improve the performance of KGQA over Complex Questions, where formal query patterns significantly vary, and a single triple is not confining for all the required information. Complex KGQA provides several challenges such as understanding semantics and syntactic structure of questions, Entity Linking, Relation Linking and Answer Representation. Lack of suitable datasets for complex question answering further adds to research gaps. Hence, in this thesis, we focus the research objective of laying the foundations for the advancement of the state-of-the-art for Complex Question Answering over Knowledge Graphs, by providing techniques to solve various challenges and provide resources to fill the research gaps. First, we propose Normalized Query Structure (NQS), which is a linguistic analyzer module that helps the QA system to detect inputs and intents and the relation between them in the users' question. NQS acts like an intermediate language between natural language questions and formal expressions to ease the process of query formulation for complex questions. We then developed a framework named LC-QuAD to generate large scale question answering dataset by reversing the process of question answering, thereby translating natural language questions from the formal query using intermediate templates. Our goal is to use this framework for high variations in the query patterns and create a large size dataset with minimum human effort. The first version of the dataset consists of 5,000 complex questions. By extending the LC-QuAD framework to support Reified KGs and crowd-sourcing, we published the second version of the dataset as LC-QuAD 2.0, consisting of 30,000 questions with their paraphrases and has higher complexity and new variations in the questions. To overcome the problem of Entity Linking and Relation Linking in KGQA, we develop EARL, a module performing these two tasks as a single joint task for complex question answering. We develop approaches for this module, first by formalizing the task as an instance of the Generalized Traveling Salesman Problem (GTSP) and the second approach uses machine learning to exploit the connection density between nodes in the Knowledge Graph. Lastly, we create another large scale dataset to answer verbalization and provide results for multiple baseline system s on it. The Verbalization dataset is introduced to make the system's response more human-like. The NQS based KGQA system was next to the best system in terms of accuracy on the QALD-5 dataset. We empirically prove that NQS is robust to tackle paraphrases of the questions. EARL achieves the state of the art results in Entity Linking and Relation Linking for question answering on several KGQA datasets. The dataset curated in this thesis has helped the research community to move forward in the direction of improving the accuracy of complex question answering as a task as other researchers too developed several KGQA systems and modules around these published datasets. With the large-scale datasets, we have encouraged the use of large scale machine learning, deep learning and emergence of new techniques to advance the state-of-the-art in complex question answering over knowledge graphs. We further developed core components for the KGQA pipeline to overcome the challenges of Question Understanding, Entity-Relation Linking and Answer Verbalization and thus achieve our research objective. All the proposed approaches mentioned in this thesis and the published resources are available at https://github.com/AskNowQA and are released under the umbrella project AskNow.

An electronic medical record (EMR) can enhance the quality of care and patient outcomes. Ethiopia started the implementation of EMR in 2013. However, its adoption among healthcare providers has been low. Thus, this study explored the barriers and facilitators of EMR adoption among healthcare providers in Addis Ababa, Ethiopia. A descriptive-phenomenological approach was used. Data were collected from one hospital and three health centers from 5-13 June, 2023, that implemented the EMR. A total of 25 EMR users (physicians, health officers, pharmacists, nurses, laboratory technologists, radiology technicians) were included in the key informant interviews. The interviews were audio-recorded, transcribed verbatim, translated to English, and exported to OpenCode 4.03 software for analysis. Thematic analysis was applied to analyze, summarize, and present the data. Healthcare providers reported barriers operating at three levels: individual, technological, and organizational. Individual barriers included lack of digital literacy, technical knowledge, skill; motivation; and favorable attitude. Technological barriers included lack of infrastructure including computers, networks, and reliable power supply; and software-related challenges such as system downtime, lack of interoperability, comprehensiveness, and decision support systems; and system security and privacy concerns. Organizational barriers included poor quality of training, lack of follow-up, supervision and technical support; poor leadership commitment; lack of incentives and motivation; and staff turnover and workload. Perceived benefits of the system, such as ease of access to quality data, improved quality of care and work efficiency; availability of onsite technical support; presence of information technology supplies; and feedback from supervisors, were identified as facilitators of EMR adoption. The study identified different barriers and facilitators to the adoption of the EMR. The health system should prioritize strategies to address technological, individual, and organizational factors influencing the successful adoption of the EMR to support the delivery of quality care and improve patient outcomes.

The Roundup

In recent years, medical Question Answering (QA) systems have gained a lot of attentions, since they can not only help professionals make quick decisions, but also give ordinary people advice when they seek for helpful information. However, the interpretability and accuracy problems have plagued QA systems for a long time. In this paper, we propose a QA system, DSQA, based on knowledge graph for answering domain-specific medical questions. The data we use are from Electronic Medical Records (EMRs) that are complex and heterogeneous with varied qualities. We introduce doctor-in-the-loop mechanism to design the knowledge graph, which improves the interpretability and the accuracy of our QA system. For every natural-language question, we generate the answer with a hybrid of the traditional deep learning model and the reasoning on the knowledge graph. Finally, the answer is returned to the user in the format of a subgraph with corresponding natural-language sentences. Our system shows high interpretability and gives excellent performance according to the experiment results.