Unified Medical Language System Research Articles

Searching COVID-19 Clinical Research Using Graph Queries: Algorithm Development and Validation.

Since the beginning of the COVID-19 pandemic, >1 million studies have been collected within the COVID-19 Open Research Dataset, a corpus of manuscripts created to accelerate research against the disease. Their related abstracts hold a wealth of information that remains largely unexplored and difficult to search due to its unstructured nature. Keyword-based search is the standard approach, which allows users to retrieve the documents of a corpus that contain (all or some of) the words in a target list. This type of search, however, does not provide visual support to the task and is not suited to expressing complex queries or compensating for missing specifications. This study aims to consider small graphs of concepts and exploit them for expressing graph searches over existing COVID-19-related literature, leveraging the increasing use of graphs to represent and query scientific knowledge and providing a user-friendly search and exploration experience. We considered the COVID-19 Open Research Dataset corpus and summarized its content by annotating the publications' abstracts using terms selected from the Unified Medical Language System and the Ontology of Coronavirus Infectious Disease. Then, we built a co-occurrence network that includes all relevant concepts mentioned in the corpus, establishing connections when their mutual information is relevant. A sophisticated graph query engine was built to allow the identification of the best matches of graph queries on the network. It also supports partial matches and suggests potential query completions using shortest paths. We built a large co-occurrence network, consisting of 128,249 entities and 47,198,965 relationships; the GRAPH-SEARCH interface allows users to explore the network by formulating or adapting graph queries; it produces a bibliography of publications, which are globally ranked; and each publication is further associated with the specific parts of the query that it explains, thereby allowing the user to understand each aspect of the matching. Our approach supports the process of query formulation and evidence search upon a large text corpus; it can be reapplied to any scientific domain where documents corpora and curated ontologies are made available.

The power of graphs in medicine: Introducing BioGraphSum for effective text summarization

In biomedicine, the expansive scientific literature combined with the frequent use of abbreviations, acronyms, and symbols presents considerable challenges for text processing and summarization. The Unified Medical Language System (UMLS) has been a go-to for extracting concepts and determining correlations in these studies; hence, the BioGraphSum model introduced in this study aims to reduce this UMLS dependence. Through adoption of an innovative perspective, sentences within a piece of text are graphically conceptualized as nodes, enabling the concept of “Malatya centrality” to be leveraged. This approach focuses on pinpointing influential nodes on a graph and, by analogy, the most pertinent sentences within the text for summarization. In order to evaluate the performance of the BioGraphSum approach, a corpus was curated that consisted of 450 contemporary scientific research articles available on the PubMed database, aligned with proven research methodology. The BioGraphSum model was subjected to rigorous testing against this corpus in order to demonstrate its capabilities. Preliminary results, especially in the precision-based and f-score-based ROUGE-(1–2), ROUGE-L, and ROUGE-SU metrics reported significant improvements when compared to other existing models considered state-of-the-art in text summarization.

CoRTEx: contrastive learning for representing terms via explanations with applications on constructing biomedical knowledge graphs.

Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a lack of knowledge, previous contrastive learning models trained with Unified Medical Language System (UMLS) synonyms struggle at clustering difficult terms and do not generalize well beyond UMLS terms. In this work, we leverage the world knowledge from large language models (LLMs) and propose Contrastive Learning for Representing Terms via Explanations (CoRTEx) to enhance term representation and significantly improves term clustering. The model training involves generating explanations for a cleaned subset of UMLS terms using ChatGPT. We employ contrastive learning, considering term and explanation embeddings simultaneously, and progressively introduce hard negative samples. Additionally, a ChatGPT-assisted BIRCH algorithm is designed for efficient clustering of a new ontology. We established a clustering test set and a hard negative test set, where our model consistently achieves the highest F1 score. With CoRTEx embeddings and the modified BIRCH algorithm, we grouped 35 580 932 terms from the Biomedical Informatics Ontology System (BIOS) into 22 104 559 clusters with O(N) queries to ChatGPT. Case studies highlight the model's efficacy in handling challenging samples, aided by information from explanations. By aligning terms to their explanations, CoRTEx demonstrates superior accuracy over benchmark models and robustness beyond its training set, and it is suitable for clustering terms for large-scale biomedical ontologies.

Europe's Largest Research Infrastructure for Curated Medical Data Models with Semantic Annotations.

Structural metadata from the majority of clinical studies and routine health care systems is currently not yet available to the scientific community. To provide an overview of available contents in the Portal of Medical Data Models (MDM Portal). The MDM Portal is a registered European information infrastructure for research and health care, and its contents are curated and semantically annotated by medical experts. It enables users to search, view, discuss, and download existing medical data models. The most frequent keyword is "clinical trial" (n = 18,777), and the most frequent disease-specific keyword is "breast neoplasms" (n = 1,943). Most data items are available in English (n = 545,749) and German (n = 109,267). Manually curated semantic annotations are available for 805,308 elements (554,352 items, 58,101 item groups, and 192,855 code list items), which were derived from 25,257 data models. In total, 1,609,225 Unified Medical Language System (UMLS) codes have been assigned, with 66,373 unique UMLS codes. To our knowledge, the MDM Portal constitutes Europe's largest collection of medical data models with semantically annotated elements. As such, it can be used to increase compatibility of medical datasets and can be utilized as a large expert-annotated medical text corpus for natural language processing.

Streamlining social media information retrieval for public health research with deep learning.

Social media-based public health research is crucial for epidemic surveillance, but most studies identify relevant corpora with keyword-matching. This study develops a system to streamline the process of curating colloquial medical dictionaries. We demonstrate the pipeline by curating a Unified Medical Language System (UMLS)-colloquial symptom dictionary from COVID-19-related tweets as proof of concept. COVID-19-related tweets from February 1, 2020, to April 30, 2022 were used. The pipeline includes three modules: a named entity recognition module to detect symptoms in tweets; an entity normalization module to aggregate detected entities; and a mapping module that iteratively maps entities to Unified Medical Language System concepts. A random 500 entity samples were drawn from the final dictionary for accuracy validation. Additionally, we conducted a symptom frequency distribution analysis to compare our dictionary to a pre-defined lexicon from previous research. We identified 498480 unique symptom entity expressions from the tweets. Pre-processing reduces the number to 18226. The final dictionary contains 38175 unique expressions of symptoms that can be mapped to 966 UMLS concepts (accuracy = 95%). Symptom distribution analysis found that our dictionary detects more symptoms and is effective at identifying psychiatric disorders like anxiety and depression, often missed by pre-defined lexicons. This study advances public health research by implementing a novel, systematic pipeline for curating symptom lexicons from social media data. The final lexicon's high accuracy, validated by medical professionals, underscores the potential of this methodology to reliably interpret, and categorize vast amounts of unstructured social media data into actionable medical insights across diverse linguistic and regional landscapes.

Using word evolution to predict drug repurposing

BackgroundTraditional literature based discovery is based on connecting knowledge pairs extracted from separate publications via a common mid point to derive previously unseen knowledge pairs. To avoid the over generation often associated with this approach, we explore an alternative method based on word evolution. Word evolution examines the changing contexts of a word to identify changes in its meaning or associations. We investigate the possibility of using changing word contexts to detect drugs suitable for repurposing.ResultsWord embeddings, which represent a word’s context, are constructed from chronologically ordered publications in MEDLINE at bi-monthly intervals, yielding a time series of word embeddings for each word. Focusing on clinical drugs only, any drugs repurposed in the final time segment of the time series are annotated as positive examples. The decision regarding the drug’s repurposing is based either on the Unified Medical Language System (UMLS), or semantic triples extracted using SemRep from MEDLINE.ConclusionsThe annotated data allows deep learning classification, with a 5-fold cross validation, to be performed and multiple architectures to be explored. Performance of 65% using UMLS labels, and 81% using SemRep labels is attained, indicating the technique’s suitability for the detection of candidate drugs for repurposing. The investigation also shows that different architectures are linked to the quantities of training data available and therefore that different models should be trained for every annotation approach.

Biomedical text readability after hypernym substitution with fine-tuned large language models.

The advent of patient access to complex medical information online has highlighted the need for simplification of biomedical text to improve patient understanding and engagement in taking ownership of their health. However, comprehension of biomedical text remains a difficult task due to the need for domain-specific expertise. We aimed to study the simplification of biomedical text via large language models (LLMs) commonly used for general natural language processing tasks involve text comprehension, summarization, generation, and prediction of new text from prompts. Specifically, we finetuned three variants of large language models to perform substitutions of complex words and word phrases in biomedical text with a related hypernym. The output of the text substitution process using LLMs was evaluated by comparing the pre- and post-substitution texts using four readability metrics and two measures of sentence complexity. A sample of 1,000 biomedical definitions in the National Library of Medicine's Unified Medical Language System (UMLS) was processed with three LLM approaches, and each showed an improvement in readability and sentence complexity after hypernym substitution. Readability scores were translated from a pre-processed collegiate reading level to a post-processed US high-school level. Comparison between the three LLMs showed that the GPT-J-6b approach had the best improvement in measures of sentence complexity. This study demonstrates the merit of hypernym substitution to improve readability of complex biomedical text for the public and highlights the use case for fine-tuning open-access large language models for biomedical natural language processing.

Representation of child and youth participation within the Unified Medical Language System (UMLS)

Purpose To examine (1) how much participation is represented in the benchmark Unified Medical Language System (UMLS) resource, and (2) to what extent that representation reflects the definition of child and youth participation and/or its related constructs per the family of Participation-Related Constructs framework. Materials and methods We searched and analysed UMLS concepts related to the term “participation.” Identified UMLS concepts were rated according to their representation of participation (i.e., attendance, involvement, both) as well as participation-related constructs using deductive content analysis. Results 363 UMLS concepts were identified. Of those, 68 had at least one English definition, resulting in 81 definitions that were further analysed. Results revealed 2 definitions (2/81; 3%; 2/68 UMLS concepts) representing participation “attendance” and 18 definitions (18/81; 22%; 14/68 UMLS concepts) representing participation “involvement.” No UMLS concept definition represented both attendance and involvement (i.e., participation). Most of the definitions (11/20; 55%; 9/16 UMLS concepts) representing attendance or involvement also represent a participation-related construct. Conclusion(s) The representation of participation within the UMLS is limited and poorly aligned with the contemporary definition of child and youth participation. Expanding ontological resources to represent child and youth participation is needed to enable better data analytics that reflect contemporary paediatric rehabilitation practice.

Knowledge-enhanced Graph Topic Transformer for Explainable Biomedical Text Summarization.

Given the overwhelming and rapidly increasing volumes of the published biomedical literature, automatic biomedical text summarization has long been a highly important task. Recently, great advances in the performance of biomedical text summarization have been facilitated by pre-trained language models (PLMs) based on fine-tuning. However, existing summarization methods based on PLMs do not capture domain-specific knowledge. This can result in generated summaries with low coherence, including redundant sentences, or excluding important domain knowledge conveyed in the full-text document. Furthermore, the black-box nature of the transformers means that they lack explainability, i.e. it is not clear to users how and why the summary was generated. The domain-specific knowledge and explainability are crucial for the accuracy and transparency of biomedical text summarization methods. In this article, we aim to address these issues by proposing a novel domain knowledge-enhanced graph topic transformer (DORIS) for explainable biomedical text summarization. The model integrates the graph neural topic model and the domain-specific knowledge from the Unified Medical Language System (UMLS) into the transformer-based PLM, to improve the explainability and accuracy. Experimental results on four biomedical literature datasets show that our model outperforms existing state-of-the-art (SOTA) PLM-based summarization methods on biomedical extractive summarization. Furthermore, our use of graph neural topic modeling means that our model possesses the desirable property of being explainable, i.e. it is straightforward for users to understand how and why the model selects particular sentences for inclusion in the summary. The domain-specific knowledge helps our model to learn more coherent topics, to better explain the performance.

Healthcare utilization and clinical characteristics of genetic epilepsy in electronic health records.

Understanding the clinical characteristics and medical treatment of individuals affected by genetic epilepsies is instrumental in guiding selection for genetic testing, defining the phenotype range of these rare disorders, optimizing patient care pathways and pinpointing unaddressed medical need by quantifying healthcare resource utilization. To date, a matched longitudinal cohort study encompassing the entire spectrum of clinical characteristics and medical treatment from childhood through adolescence has not been performed. We identified individuals with genetic and non-genetic epilepsies and onset at ages 0-5 years by linkage across the Cleveland Clinic Health System. We used natural language processing to extract medical terms and procedures from longitudinal electronic health records and tested for cross-sectional and temporal associations with genetic epilepsy. We implemented a two-stage design: in the discovery cohort, individuals were stratified as being 'likely genetic' or 'non-genetic' by a natural language processing algorithm, and controls did not receive genetic testing. The validation cohort consisted of cases with genetic epilepsy confirmed by manual chart review and an independent set of controls who received negative genetic testing. The discovery and validation cohorts consisted of 503 and 344 individuals with genetic epilepsy and matched controls, respectively. The median age at the first encounter was 0.1 years and 7.9 years at the last encounter, and the mean duration of follow-up was 8.2 years. We extracted 188,295 Unified Medical Language System annotations for statistical analysis across 9659 encounters. Individuals with genetic epilepsy received an earlier epilepsy diagnosis and had more frequent and complex encounters with the healthcare system. Notably, the highest enrichment of encounters compared with the non-genetic groups was found during the transition from paediatric to adult care. Our computational approach could validate established comorbidities of genetic epilepsies, such as behavioural abnormality and intellectual disability. We also revealed novel associations for genitourinary abnormalities (odds ratio 1.91, 95% confidence interval: 1.66-2.20, P = 6.16 × 10-19) linked to a spectrum of underrecognized epilepsy-associated genetic disorders. This case-control study leveraged real-world data to identify novel features associated with the likelihood of a genetic aetiology and quantified the healthcare utilization of genetic epilepsies compared with matched controls. Our results strongly recommend early genetic testing to stratify individuals into specialized care paths, thus improving the clinical management of people with genetic epilepsies.

BioLORD-2023: semantic textual representations fusing large language models and clinical knowledge graph insights.

In this study, we investigate the potential of large language models (LLMs) to complement biomedical knowledge graphs in the training of semantic models for the biomedical and clinical domains. Drawing on the wealth of the Unified Medical Language System knowledge graph and harnessing cutting-edge LLMs, we propose a new state-of-the-art approach for obtaining high-fidelity representations of biomedical concepts and sentences, consisting of 3 steps: an improved contrastive learning phase, a novel self-distillation phase, and a weight averaging phase. Through rigorous evaluations of diverse downstream tasks, we demonstrate consistent and substantial improvements over the previous state of the art for semantic textual similarity (STS), biomedical concept representation (BCR), and clinically named entity linking, across 15+ datasets. Besides our new state-of-the-art biomedical model for English, we also distill and release a multilingual model compatible with 50+ languages and finetuned on 7 European languages. Many clinical pipelines can benefit from our latest models. Our new multilingual model enables a range of languages to benefit from our advancements in biomedical semantic representation learning, opening a new avenue for bioinformatics researchers around the world. As a result, we hope to see BioLORD-2023 becoming a precious tool for future biomedical applications. In this article, we introduced BioLORD-2023, a state-of-the-art model for STS and BCR designed for the clinical domain.

Evaluating MedDRA-to-ICD terminology mappings

BackgroundIn this era of big data, data harmonization is an important step to ensure reproducible, scalable, and collaborative research. Thus, terminology mapping is a necessary step to harmonize heterogeneous data. Take the Medical Dictionary for Regulatory Activities (MedDRA) and International Classification of Diseases (ICD) for example, the mapping between them is essential for drug safety and pharmacovigilance research. Our main objective is to provide a quantitative and qualitative analysis of the mapping status between MedDRA and ICD.We focus on evaluating the current mapping status between MedDRA and ICD through the Unified Medical Language System (UMLS) and Observational Medical Outcomes Partnership Common Data Model (OMOP CDM). We summarized the current mapping statistics and evaluated the quality of the current MedDRA-ICD mapping; for unmapped terms, we used our self-developed algorithm to rank the best possible mapping candidates for additional mapping coverage.ResultsThe identified MedDRA-ICD mapped pairs cover 27.23% of the overall MedDRA preferred terms (PT). The systematic quality analysis demonstrated that, among the mapped pairs provided by UMLS, only 51.44% are considered an exact match. For the 2400 sampled unmapped terms, 56 of the 2400 MedDRA Preferred Terms (PT) could have exact match terms from ICD.ConclusionSome of the mapped pairs between MedDRA and ICD are not exact matches due to differences in granularity and focus. For 72% of the unmapped PT terms, the identified exact match pairs illustrate the possibility of identifying additional mapped pairs. Referring to its own mapping standard, some of the unmapped terms should qualify for the expansion of MedDRA to ICD mapping in UMLS.

Standardizing Extracted Data Using Automated Application of Controlled Vocabularies.

Extraction of toxicological end points from primary sources is a central component of systematic reviews and human health risk assessments. To ensure optimal use of these data, consistent language should be used for end point descriptions. However, primary source language describing treatment-related end points can vary greatly, resulting in large labor efforts to manually standardize extractions before data are fit for use. To minimize these labor efforts, we applied an augmented intelligence approach and developed automated tools to support standardization of extracted information via application of preexisting controlled vocabularies. We created and applied a harmonized controlled vocabulary crosswalk, consisting of Unified Medical Language System (UMLS) codes, German Federal Institute for Risk Assessment (BfR) DevTox harmonized terms, and The Organization for Economic Co-operation and Development (OECD) end point vocabularies, to roughly 34,000 extractions from prenatal developmental toxicology studies conducted by the National Toxicology Program (NTP) and 6,400 extractions from European Chemicals Agency (ECHA) prenatal developmental toxicology studies, all recorded based on the original study report language. We automatically applied standardized controlled vocabulary terms to 75% of the NTP extracted end points and 57% of the ECHA extracted end points. Of all the standardized extracted end points, about half (51%) required manual review for potential extraneous matches or inaccuracies. Extracted end points that were not mapped to standardized terms tended to be too general or required human logic to find a good match. We estimate that this augmented intelligence approach saved hours of manual effort and yielded valuable resources including a controlled vocabulary crosswalk, organized related terms lists, code for implementing an automated mapping workflow, and a computationally accessible dataset. Augmenting manual efforts with automation tools increased the efficiency of producing a findable, accessible, interoperable, and reusable (FAIR) dataset of regulatory guideline studies. This open-source approach can be readily applied to other legacy developmental toxicology datasets, and the code design is customizable for other study types. https://doi.org/10.1289/EHP13215.

Using a Natural Language Processing Approach to Support Rapid Knowledge Acquisition.

Implementing artificial intelligence to extract insights from large, real-world clinical data sets can supplement and enhance knowledge management efforts for health sciences research and clinical care. At Vanderbilt University Medical Center (VUMC), the in-house developed Word Cloud natural language processing system extracts coded concepts from patient records in VUMC's electronic health record repository using the Unified Medical Language System terminology. Through this process, the Word Cloud extracts the most prominent concepts found in the clinical documentation of a specific patient or population. The Word Cloud provides added value for clinical care decision-making and research. This viewpoint paper describes a use case for how the VUMC Center for Knowledge Management leverages the condition-disease associations represented by the Word Cloud to aid in the knowledge generation needed to inform the interpretation of phenome-wide association studies.

UMLS-Based Approach for Developing VoiS: Voice-Activated Conversational Agent for Self-Management of Multiple Chronic Conditions

This abstract proposes a system design for an ontology-based conversational agent (CA) for the self-management of chronic conditions. The proposed system plans to integrate the largest medical ontology, the Unified Medical Language System (UMLS) (Bodenreider, 2004), aiming to narrow the vocabulary gaps between health professionals and patients and to make the agent more responsive to the users.
 Recently, conversational agents (CAs) like ChatGPT, or computer dialog systems that simulate human-to-human communication in natural language, have risen and gained popularity in various health contexts (Bin Sawad et al., 2022; Montenegro et al., 2019) including self-management of chronic conditions (Griffin et al., 2020). Despite their potential, the currently available CAs are often criticized for lacking the capability to understand natural language inputs (Montenegro et al., 2019). This limitation can be highlighted in medical areas due to the known vocabulary gaps between health professionals and health consumers. The knowledge-grounded dialog flow for CAs presents the potential to lift this limitation, making CAs naturally converse with their users.
 In the proposed voice-activated self-monitoring support (VoiS) application, the research team plans to integrate the UMLS to make the agent better understand lay terms from patients and properly map those terms to medical concepts. This automated process is expected to improve the user experience in two folds: a) promote the quality of communication between the patients and health providers and b) make the VoiS app more responsive to user inputs, overcoming accepting only constrained user inputs (e.g., multiple choice of utterance).

A new word embedding model integrated with medical knowledge for deep learning-based sentiment classification

The development of intelligent systems that use social media data for decision-making processes in numerous domains such as politics, business, marketing, and finance, has been made possible by the popularity of social media platforms. However, the utilization of textual data from social media in the healthcare management industry is still somewhat limited when it is compared to other industries. Investigating how current machine learning and natural language processing technologies can be used in the healthcare industry to gauge public sentiment is an important study. Earlier works on healthcare sentiment analysis have utilized traditional word embedding models trained on the general and medical corpus. However, integration of medical knowledge to pre-trained word embedding models has not been considered yet. Word embedding models trained on the general corpus led to the problem of lacking medical knowledge and the models trained on the small size of the medical corpus have limitations in capturing semantic and syntactic properties. This research proposes a new word embedding model named Word Embedding Integrated with Medical Knowledge Vector (WE-iMKVec). The proposed model integrates sentiment lexicons and medical knowledgebases into the pre-trained word embedding to enrich the properties of word embedding. A new medical-aware sentiment polarity score is proposed for the utilization in learning neural-network sentiment and these vectors incorporate with the original pre-trained word vectors. The resulting vectors are enriched with lexicon vectors and the medical knowledge vectors: Adverse Drug Reaction (ADR) vector and Unified Medical Language System (UMLS) vector are used to build the proposed WE-iMKVec model. WE-iMKVec is validated on the five different social media healthcare review datasets and the empirical results showed its superiority over traditional word embedding models in medical sentiment analysis. The highest improvement can be found in the patients.info medical condition dataset where the proposed model outperforms three conventional word2vec models (Google-News, PubMed-PMC, and Drug Reviews) by 12.7 %, 31.4 %, and 25.4 % respectively in terms of F1 score.

A metric learning-based method for biomedical entity linking.

Biomedical entity linking task is the task of mapping mention(s) that occur in a particular textual context to a unique concept or entity in a knowledge base, e.g., the Unified Medical Language System (UMLS). One of the most challenging aspects of the entity linking task is the ambiguity of mentions, i.e., (1) mentions whose surface forms are very similar, but which map to different entities in different contexts, and (2) entities that can be expressed using diverse types of mentions. Recent studies have used BERT-based encoders to encode mentions and entities into distinguishable representations such that their similarity can be measured using distance metrics. However, most real-world biomedical datasets suffer from severe imbalance, i.e., some classes have many instances while others appear only once or are completely absent from the training data. A common way to address this issue is to down-sample the dataset, i.e., to reduce the number instances of the majority classes to make the dataset more balanced. In the context of entity linking, down-sampling reduces the ability of the model to comprehensively learn the representations of mentions in different contexts, which is very important. To tackle this issue, we propose a metric-based learning method that treats a given entity and its mentions as a whole, regardless of the number of mentions in the training set. Specifically, our method uses a triplet loss-based function in conjunction with a clustering technique to learn the representation of mentions and entities. Through evaluations on two challenging biomedical datasets, i.e., MedMentions and BC5CDR, we show that our proposed method is able to address the issue of imbalanced data and to perform competitively with other state-of-the-art models. Moreover, our method significantly reduces computational cost in both training and inference steps. Our source code is publicly available here.

TeaBERT: An Efficient Knowledge Infused Cross-Lingual Language Model for Mapping Chinese Medical Entities to the Unified Medical Language System.

Medical entity normalization is an important task for medical information processing. The Unified Medical Language System (UMLS), a well-developed medical terminology system, is crucial for medical entity normalization. However, the UMLS primarily consists of English medical terms. For languages other than English, such as Chinese, a significant challenge for normalizing medical entities is the lack of robust terminology systems. To address this issue, we propose a translation-enhancing training strategy that incorporates the translation and synonym knowledge of the UMLS into a language model using the contrastive learning approach. In this work, we proposed a cross-lingual pre-trained language model called TeaBERT, which can align synonymous Chinese and English medical entities across languages at the concept level. As the evaluation results showed, the TeaBERT language model outperformed previous cross-lingual language models with Acc@5 values of 92.54%, 87.14% and 84.77% on the ICD10-CN, CHPO and RealWorld-v2 datasets, respectively. It also achieved a new state-of-the-art cross-lingual entity mapping performance without fine-tuning. The translation-enhancing strategy is applicable to other languages that face the similar challenge due to the absence of well-developed medical terminology systems.

Quantitative patient graph analysis for transient ischemic attack risk factor distribution based on electronic medical records

A transient ischemic attack (TIA) affects millions of people worldwide. Although TIA risk factors have been identified individually, a systemic quantitative analysis of all health factors relevant to TIA using electronic medical records (EMR) remains lacking. This study employed a data-driven approach, leveraging hospital EMR data to create a TIA patient health factor graph. This graph consisted of 737 TIA and 737 control patient nodes, 740 health factor nodes, and over 33,000 relations between patients and factors. For all health factors in the graph, the connection delta ratios (CDRs) were determined and ranked, generating a quantitative distribution of TIA health factors. A literature review confirmed 56 risk factors in the distribution and unveiled a potential new risk factor “rhinosinusitis” for future validation. Moreover, the patient graph was visualized together with the TIA knowledge graph in the Unified Medical Language System. This integration enables clinicians to access and visualize patient data and international standard knowledge within a unified graph. In conclusion, graph CDR analysis can effectively quantify the distribution of TIA risk factors. The resulting TIA risk factor distribution might be instrumental in developing new risk prediction machine learning models for screening and early detection of TIA.

Complementary and Integrative Health Information in the literature: its lexicon and named entity recognition.

To construct an exhaustive Complementary and Integrative Health (CIH) Lexicon (CIHLex) to help better represent the often underrepresented physical and psychological CIH approaches in standard terminologies, and to also apply state-of-the-art natural language processing (NLP) techniques to help recognize them in the biomedical literature. We constructed the CIHLex by integrating various resources, compiling and integrating data from biomedical literature and relevant sources of knowledge. The Lexicon encompasses 724 unique concepts with 885 corresponding unique terms. We matched these concepts to the Unified Medical Language System (UMLS), and we developed and utilized BERT models comparing their efficiency in CIH named entity recognition to well-established models including MetaMap and CLAMP, as well as the large language model GPT3.5-turbo. Of the 724 unique concepts in CIHLex, 27.2% could be matched to at least one term in the UMLS. About 74.9% of the mapped UMLS Concept Unique Identifiers were categorized as "Therapeutic or Preventive Procedure." Among the models applied to CIH named entity recognition, BLUEBERT delivered the highest macro-average F1-score of 0.91, surpassing other models. Our CIHLex significantly augments representation of CIH approaches in biomedical literature. Demonstrating the utility of advanced NLP models, BERT notably excelled in CIH entity recognition. These results highlight promising strategies for enhancing standardization and recognition of CIH terminology in biomedical contexts.