Dataset Information

Leveraging medical context to recommend semantically similar terms for chart reviews.

ABSTRACT:

Background

Information retrieval (IR) help clinicians answer questions posed to large collections of electronic medical records (EMRs), such as how best to identify a patient's cancer stage. One of the more promising approaches to IR for EMRs is to expand a keyword query with similar terms (e.g., augmenting cancer with mets). However, there is a large range of clinical chart review tasks, such that fixed sets of similar terms is insufficient. Current language models, such as Bidirectional Encoder Representations from Transformers (BERT) embeddings, do not capture the full non-textual context of a task. In this study, we present new methods that provide similar terms dynamically by adjusting with the context of the chart review task.

Methods

We introduce a vector space for medical-context in which each word is represented by a vector that captures the word's usage in different medical contexts (e.g., how frequently cancer is used when ordering a prescription versus describing family history) beyond the context learned from the surrounding text. These vectors are transformed into a vector space for customizing the set of similar terms selected for different chart review tasks. We evaluate the vector space model with multiple chart review tasks, in which supervised machine learning models learn to predict the preferred terms of clinically knowledgeable reviewers. To quantify the usefulness of the predicted similar terms to a baseline of standard word2vec embeddings, we measure (1) the prediction performance of the medical-context vector space model using the area under the receiver operating characteristic curve (AUROC) and (2) the labeling effort required to train the models.

Results

The vector space outperformed the baseline word2vec embeddings in all three chart review tasks with an average AUROC of 0.80 versus 0.66, respectively. Additionally, the medical-context vector space significantly reduced the number of labels required to learn and predict the preferred similar terms of reviewers. Specifically, the labeling effort was reduced to 10% of the entire dataset in all three tasks.

Conclusions

The set of preferred similar terms that are relevant to a chart review task can be learned by leveraging the medical context of the task.

SUBMITTER: Ye C

PROVIDER: S-EPMC8684266 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAlthough electronic health records (EHRs) have been widely adopted in health care, effective use of EHR data is often limited because of redundant information in clinical notes introduced by the use of templates and copy-paste during note generation. Thus, it is imperative to develop solutions that can condense information while retaining its value. A step in this direction is measuring the semantic similarity between clinical text snippets. To address this problem, we participated in the 2019 National NLP Clinical Challenges (n2c2)/Open Health Natural Language Processing Consortium (OHNLP) clinical semantic textual similarity (ClinicalSTS) shared task.ObjectiveThis study aims to improve the performance and robustness of semantic textual similarity in the clinical domain by leveraging manually labeled data from related tasks and contextualized embeddings from pretrained transformer-based language models.MethodsThe ClinicalSTS data set consists of 1642 pairs of deidentified clinical text snippets annotated in a continuous scale of 0-5, indicating degrees of semantic similarity. We developed an iterative intermediate training approach using multi-task learning (IIT-MTL), a multi-task training approach that employs iterative data set selection. We applied this process to bidirectional encoder representations from transformers on clinical text mining (ClinicalBERT), a pretrained domain-specific transformer-based language model, and fine-tuned the resulting model on the target ClinicalSTS task. We incrementally ensembled the output from applying IIT-MTL on ClinicalBERT with the output of other language models (bidirectional encoder representations from transformers for biomedical text mining [BioBERT], multi-task deep neural networks [MT-DNN], and robustly optimized BERT approach [RoBERTa]) and handcrafted features using regression-based learning algorithms. On the basis of these experiments, we adopted the top-performing configurations as our official submissions.ResultsOur system ranked first out of 87 submitted systems in the 2019 n2c2/OHNLP ClinicalSTS challenge, achieving state-of-the-art results with a Pearson correlation coefficient of 0.9010. This winning system was an ensembled model leveraging the output of IIT-MTL on ClinicalBERT with BioBERT, MT-DNN, and handcrafted medication features.ConclusionsThis study demonstrates that IIT-MTL is an effective way to leverage annotated data from related tasks to improve performance on a target task with a limited data set. This contribution opens new avenues of exploration for optimized data set selection to generate more robust and universal contextual representations of text in the clinical domain.

Project description:BACKGROUND:Many health care systems now allow patients to access their electronic health record (EHR) notes online through patient portals. Medical jargon in EHR notes can confuse patients, which may interfere with potential benefits of patient access to EHR notes. OBJECTIVE:The aim of this study was to develop and evaluate the usability and content quality of NoteAid, a Web-based natural language processing system that links medical terms in EHR notes to lay definitions, that is, definitions easily understood by lay people. METHODS:NoteAid incorporates two core components: CoDeMed, a lexical resource of lay definitions for medical terms, and MedLink, a computational unit that links medical terms to lay definitions. We developed innovative computational methods, including an adapted distant supervision algorithm to prioritize medical terms important for EHR comprehension to facilitate the effort of building CoDeMed. Ten physician domain experts evaluated the user interface and content quality of NoteAid. The evaluation protocol included a cognitive walkthrough session and a postsession questionnaire. Physician feedback sessions were audio-recorded. We used standard content analysis methods to analyze qualitative data from these sessions. RESULTS:Physician feedback was mixed. Positive feedback on NoteAid included (1) Easy to use, (2) Good visual display, (3) Satisfactory system speed, and (4) Adequate lay definitions. Opportunities for improvement arising from evaluation sessions and feedback included (1) improving the display of definitions for partially matched terms, (2) including more medical terms in CoDeMed, (3) improving the handling of terms whose definitions vary depending on different contexts, and (4) standardizing the scope of definitions for medicines. On the basis of these results, we have improved NoteAid's user interface and a number of definitions, and added 4502 more definitions in CoDeMed. CONCLUSIONS:Physician evaluation yielded useful feedback for content validation and refinement of this innovative tool that has the potential to improve patient EHR comprehension and experience using patient portals. Future ongoing work will develop algorithms to handle ambiguous medical terms and test and evaluate NoteAid with patients.

Project description:BackgroundMuch has been written in the educational literature on the value of communities of practise in enhancing student learning. Here, we take the experience of senior undergraduate medical students involved in short-term research as a member of a team as a paradigm for learning in a community of practise. Based on feedback from experienced supervisors, we offer recommendations for initiating students into the research culture of their team. In so doing, we endeavour to create a bridge between theory and practise through disseminating advice on good supervisory practise, where the supervisor is perceived as an educator responsible for designing the research process to optimize student learning.MethodsUsing the questionnaire design tool SurveyMonkey and comprehensive lists of contact details of staff who had supervised research projects at the University of Edinburgh during 1995-2008, current and previous supervisors were invited to recommend procedures which they had found successful in initiating students into the research culture of a team. Text responses were then coded in the form of derivative recommendations and categorized under general themes and sub-themes.ResultsUsing the chi-square tests of linear trend and association, evidence was found for a positive trend towards more experienced supervisors offering responses (?2 = 16.833, p < 0.0005, n = 215) while there was a lack of evidence of bias in the gender distribution of respondents (?2 = 0.482, p = 0.487, n = 203), respectively. A total of 126 codes were extracted from the text responses of 65 respondents. These codes were simplified to form a complete list of 52 recommendations, which were in turn categorized under seven derivative overarching themes, the most highly represented themes being Connecting the student with others and Cultivating self-efficacy in research competence.ConclusionsThrough the design of a coding frame for supervisor responses, a wealth of ideas has been captured to make communities of research practise effective mediums for undergraduate student learning. The majority of these recommendations are underpinned by educational theory and have the potential to take the learner beyond the stage of initiation to that of integration within their community of research practise.

Project description:MotivationAutomatically quantifying semantic similarity and relatedness between clinical terms is an important aspect of text mining from electronic health records, which are increasingly recognized as valuable sources of phenotypic information for clinical genomics and bioinformatics research. A key obstacle to development of semantic relatedness measures is the limited availability of large quantities of clinical text to researchers and developers outside of major medical centers. Text from general English and biomedical literature are freely available; however, their validity as a substitute for clinical domain to represent semantics of clinical terms remains to be demonstrated.ResultsWe constructed neural network representations of clinical terms found in a publicly available benchmark dataset manually labeled for semantic similarity and relatedness. Similarity and relatedness measures computed from text corpora in three domains (Clinical Notes, PubMed Central articles and Wikipedia) were compared using the benchmark as reference. We found that measures computed from full text of biomedical articles in PubMed Central repository (rho = 0.62 for similarity and 0.58 for relatedness) are on par with measures computed from clinical reports (rho = 0.60 for similarity and 0.57 for relatedness). We also evaluated the use of neural network based relatedness measures for query expansion in a clinical document retrieval task and a biomedical term word sense disambiguation task. We found that, with some limitations, biomedical articles may be used in lieu of clinical reports to represent the semantics of clinical terms and that distributional semantic methods are useful for clinical and biomedical natural language processing applications.Availability and implementationThe software and reference standards used in this study to evaluate semantic similarity and relatedness measures are publicly available as detailed in the article.Contactpakh0002@umn.eduSupplementary information: Supplementary data are available at Bioinformatics online.

Project description:ObjectivesOver the last two decades, the number of scoping reviews in core medical education journals has increased by 4200%. Despite this growth, research on scoping reviews provides limited information about their nature, including how they are conducted or why medical educators undertake this knowledge synthesis type. This gap makes it difficult to know where the field stands and may hamper attempts to improve the conduct, reporting and utility of scoping reviews. Thus, this review characterises the nature of medical education scoping reviews to identify areas for improvement and highlight future research opportunities.MethodThe authors searched PubMed for scoping reviews published between 1/1999 and 4/2020 in 14 medical education journals. The authors extracted and summarised key bibliometric data, the rationales given for conducting a scoping review, the research questions and key reporting elements as described in the PRISMA-ScR. Rationales and research questions were mapped to Arksey and O'Malley's reasons for conducting a scoping review.ResultsOne hundred and one scoping reviews were included. On average, 10.1 scoping reviews (SD = 13.1, median = 4) were published annually with the most reviews published in 2019 (n = 42). Authors described multiple reasons for undertaking scoping reviews; the most prevalent being to summarise and disseminate research findings (n = 77). In 11 reviews, the rationales for the scoping review and the research questions aligned. No review addressed all elements of the PRISMA-ScR, with few authors publishing a protocol (n = 2) or including stakeholders (n = 20). Authors identified shortcomings of scoping reviews, including lack of critical appraisal.ConclusionsScoping reviews are increasingly conducted in medical education and published by most core journals. Scoping reviews aim to map the depth and breadth of emerging topics; as such, they have the potential to play a critical role in the practice, policy and research of medical education. However, these results suggest improvements are needed for this role to be fully realised.