A neuro-symbolic method for understanding free-text medical evidence.
Ontology highlight
ABSTRACT: Objective
We introduce Medical evidence Dependency (MD)-informed attention, a novel neuro-symbolic model for understanding free-text clinical trial publications with generalizability and interpretability.Materials and methods
We trained one head in the multi-head self-attention model to attend to the Medical evidence Ddependency (MD) and to pass linguistic and domain knowledge on to later layers (MD informed). This MD-informed attention model was integrated into BioBERT and tested on 2 public machine reading comprehension benchmarks for clinical trial publications: Evidence Inference 2.0 and PubMedQA. We also curated a small set of recently published articles reporting randomized controlled trials on COVID-19 (coronavirus disease 2019) following the Evidence Inference 2.0 guidelines to evaluate the model's robustness to unseen data.Results
The integration of MD-informed attention head improves BioBERT substantially in both benchmark tasks-as large as an increase of +30% in the F1 score-and achieves the new state-of-the-art performance on the Evidence Inference 2.0. It achieves 84% and 82% in overall accuracy and F1 score, respectively, on the unseen COVID-19 data.Conclusions
MD-informed attention empowers neural reading comprehension models with interpretability and generalizability via reusable domain knowledge. Its compositionality can benefit any transformer-based architecture for machine reading comprehension of free-text medical evidence.
SUBMITTER: Kang T
PROVIDER: S-EPMC8135980 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectiveTo classify automatically lung tumor-node-metastases (TNM) cancer stages from free-text pathology reports using symbolic rule-based classification.DesignBy exploiting report substructure and the symbolic manipulation of systematized nomenclature of medicine-clinical terms (SNOMED CT) concepts in reports, statements in free text can be evaluated for relevance against factors relating to the staging guidelines. Post-coordinated SNOMED CT expressions based on templates were defined and populated by concepts in reports, and tested for subsumption by staging factors. The subsumption results were used to build logic according to the staging guidelines to calculate the TNM stage.MeasurementsThe accuracy measure and confusion matrices were used to evaluate the TNM stages classified by the symbolic rule-based system. The system was evaluated against a database of multidisciplinary team staging decisions and a machine learning-based text classification system using support vector machines.ResultsOverall accuracy on a corpus of pathology reports for 718 lung cancer patients against a database of pathological TNM staging decisions were 72%, 78%, and 94% for T, N, and M staging, respectively. The system's performance was also comparable to support vector machine classification approaches.ConclusionA system to classify lung TNM stages from free-text pathology reports was developed, and it was verified that the symbolic rule-based approach using SNOMED CT can be used for the extraction of key lung cancer characteristics from free-text reports. Future work will investigate the applicability of using the proposed methodology for extracting other cancer characteristics and types.
| S-EPMC2995652 | biostudies-literature
Project description:MotivationBiological data and knowledge bases increasingly rely on Semantic Web technologies and the use of knowledge graphs for data integration, retrieval and federated queries. In the past years, feature learning methods that are applicable to graph-structured data are becoming available, but have not yet widely been applied and evaluated on structured biological knowledge. Results: We develop a novel method for feature learning on biological knowledge graphs. Our method combines symbolic methods, in particular knowledge representation using symbolic logic and automated reasoning, with neural networks to generate embeddings of nodes that encode for related information within knowledge graphs. Through the use of symbolic logic, these embeddings contain both explicit and implicit information. We apply these embeddings to the prediction of edges in the knowledge graph representing problems of function prediction, finding candidate genes of diseases, protein-protein interactions, or drug target relations, and demonstrate performance that matches and sometimes outperforms traditional approaches based on manually crafted features. Our method can be applied to any biological knowledge graph, and will thereby open up the increasing amount of Semantic Web based knowledge bases in biology to use in machine learning and data analytics.Availability and implementationhttps://github.com/bio-ontology-research-group/walking-rdf-and-owl.Contactrobert.hoehndorf@kaust.edu.sa.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC5860058 | biostudies-literature
Project description:BackgroundText-based patient medical records are a vital resource in medical research. In order to preserve patient confidentiality, however, the U.S. Health Insurance Portability and Accountability Act (HIPAA) requires that protected health information (PHI) be removed from medical records before they can be disseminated. Manual de-identification of large medical record databases is prohibitively expensive, time-consuming and prone to error, necessitating automatic methods for large-scale, automated de-identification.MethodsWe describe an automated Perl-based de-identification software package that is generally usable on most free-text medical records, e.g., nursing notes, discharge summaries, X-ray reports, etc. The software uses lexical look-up tables, regular expressions, and simple heuristics to locate both HIPAA PHI, and an extended PHI set that includes doctors' names and years of dates. To develop the de-identification approach, we assembled a gold standard corpus of re-identified nursing notes with real PHI replaced by realistic surrogate information. This corpus consists of 2,434 nursing notes containing 334,000 words and a total of 1,779 instances of PHI taken from 163 randomly selected patient records. This gold standard corpus was used to refine the algorithm and measure its sensitivity. To test the algorithm on data not used in its development, we constructed a second test corpus of 1,836 nursing notes containing 296,400 words. The algorithm's false negative rate was evaluated using this test corpus.ResultsPerformance evaluation of the de-identification software on the development corpus yielded an overall recall of 0.967, precision value of 0.749, and fallout value of approximately 0.002. On the test corpus, a total of 90 instances of false negatives were found, or 27 per 100,000 word count, with an estimated recall of 0.943. Only one full date and one age over 89 were missed. No patient names were missed in either corpus.ConclusionWe have developed a pattern-matching de-identification system based on dictionary look-ups, regular expressions, and heuristics. Evaluation based on two different sets of nursing notes collected from a U.S. hospital suggests that, in terms of recall, the software out-performs a single human de-identifier (0.81) and performs at least as well as a consensus of two human de-identifiers (0.94). The system is currently tuned to de-identify PHI in nursing notes and discharge summaries but is sufficiently generalized and can be customized to handle text files of any format. Although the accuracy of the algorithm is high, it is probably insufficient to be used to publicly disseminate medical data. The open-source de-identification software and the gold standard re-identified corpus of medical records have therefore been made available to researchers via the PhysioNet website to encourage improvements in the algorithm.
| S-EPMC2526997 | biostudies-literature
Project description:BackgroundThe ubiquitous use of mobile phones in sending and receiving text messages has become a norm for young people. Undeniably, text messaging has become a new and important communication medium not only in the social realm but in education as well. The aim of this study is to evaluate the effectiveness of using text messaging as a means to collect data for a medical research project.A cross sectional study was carried out during a double blind, randomized controlled trial to assess the efficacy and safety of a probiotic in the management of Irritable Bowel Syndrome (IBS). The study aim was to assess the response rate of weekly symptom reports via Short Message Service (SMS). The subjects were undergraduates in a private medical university in Malaysia. They were identified through a previous university wide study as suffering from IBS based on Rome III criteria. The subjects were randomly assigned to either the treatment arm receiving a daily probiotic, or the placebo arm. They were required to score their symptoms using eight-item-questionnaires at baseline, and thereafter weekly, for a total of 8 weeks. All subjects were given the choice to communicate their symptom scores by text messaging via mobile phones or by email. SMS text messages were sent to remind trial subjects to attend face-to-face visits and to complete a paper based 34-item-questionnaires on IBS quality of life assessment at baseline and at end of 8 weeks.FindingsThe response rate of weekly symptom scores via Short Message Service (SMS) from a total of 38 subjects was 100%. Through the study, 342 reports were submitted: 33.3% of these were received on the due date without reminder, 60.0% one day after the deadline, after a single reminder, 6.1% 2-3 days after the deadline, after 2-3 reminders and 0.6% 5 days after the deadline, after SMS, phone reminder and face-to-face encounter. All SMS symptom reports, whether on time or late, were complete. With the help of SMS reminder, all trial subjects completed the paper based IBS quality of life assessment at baseline and at end of study.ConclusionsThis study found using text messaging via mobile phone an excellent instrument for collecting weekly symptom reports in response to trial medication, reminding trial subjects to attend face to face visits and completing more complex paper based evaluation. The 100% response rate of weekly symptom reports was facilitated by using simple number codes for SMS submission.Trial registrationNot appropriate.
| S-EPMC3022815 | biostudies-literature
Project description:Formalizing eligibility criteria in a computer-interpretable language would facilitate eligibility determination for study subjects and the identification of studies on similar patient populations. Because such formalization is extremely labor intensive, we transform the problem from one of fully capturing the semantics of criteria directly in a formal expression language to one of annotating free-text criteria in a format called ERGO annotation. The annotation can be done manually, or it can be partially automated using natural-language processing techniques. We evaluated our approach in three ways. First, we assessed the extent to which ERGO annotations capture the semantics of 1000 eligibility criteria randomly drawn from ClinicalTrials.gov. Second, we demonstrated the practicality of the annotation process in a feasibility study. Finally, we demonstrate the computability of ERGO annotation by using it to (1) structure a library of eligibility criteria, (2) search for studies enrolling specified study populations, and (3) screen patients for potential eligibility for a study. We therefore demonstrate a new and practical method for incrementally capturing the semantics of free-text eligibility criteria into computable form.
| S-EPMC3129371 | biostudies-literature
Project description:As the volume of published medical research continues to grow rapidly, staying up-to-date with the best-available research evidence regarding specific topics is becoming an increasingly challenging problem for medical experts and researchers. The current COVID19 pandemic is a good example of a topic on which research evidence is rapidly evolving. Automatic query-focused text summarization approaches may help researchers to swiftly review research evidence by presenting salient and query-relevant information from newly-published articles in a condensed manner. Typical medical text summarization approaches require domain knowledge, and the performances of such systems rely on resource-heavy medical domain-specific knowledge sources and pre-processing methods (e.g., text classification) for deriving semantic information. Consequently, these systems are often difficult to speedily customize, extend, or deploy in low-resource settings, and they are often operationally slow. In this paper, we propose a fast and simple extractive summarization approach that can be easily deployed and run, and may thus aid medical experts and researchers obtain fast access to the latest research evidence. At runtime, our system utilizes similarity measurements derived from pre-trained medical domain-specific word embeddings in addition to simple features, rather than computationally-expensive pre-processing and resource-heavy knowledge bases. Automatic evaluation using ROUGE-a summary evaluation tool-on a public dataset for evidence-based medicine shows that our system's performance, despite the simple implementation, is statistically comparable with the state-of-the-art. Extrinsic manual evaluation based on recently-released COVID19 articles demonstrates that the summarizer performance is close to human agreement, which is generally low, for extractive summarization.
| S-EPMC8521877 | biostudies-literature
Project description:ObjectiveCoordination ellipsis is a linguistic phenomenon abound in medical text and is challenging for concept normalization because of difficulty in recognizing elliptical expressions referencing 2 or more entities accurately. To resolve this bottleneck, we aim to contribute a generalizable method to reconstruct concepts from medical coordinated elliptical expressions in a variety of biomedical corpora.Materials and methodsWe proposed a graph-based representation model and built a pipeline to reconstruct concepts from coordinated elliptical expressions in medical text (RECEEM). There are 4 modules: (1) identify all possible candidate conjunct pairs from original coordinated elliptical expressions, (2) calculate coefficients for candidate conjuncts using the embedding model, (3) select the most appropriate decompositions by global optimization, and (4) rebuild concepts based on a pathfinding algorithm. We evaluated the pipeline's performance on 2658 coordinated elliptical expressions from 3 different medical corpora (ie, biomedical literature, clinical narratives, and eligibility criteria from clinical trials). Precision, recall, and F1 score were calculated.ResultsThe F1 scores for biomedical publications, clinical narratives, and research eligibility criteria were 0.862, 0.721, and 0.870, respectively. RECEEM outperformed 2 previously released methods. By incorporating RECEEM into 2 existing NLP tools, the F1 scores increased from 0.248 to 0.460 and from 0.287 to 0.630 on concept mapping of 1125 coordination ellipses.ConclusionsRECEEM improves concept normalization for medical coordinated elliptical expressions in a variety of biomedical corpora. It outperformed existing methods and significantly enhanced the performance of 2 notable NLP systems for mapping coordination ellipses in the evaluation. The algorithm is open sourced online (https://github.com/chiyuan1126/RECEEM).
| S-EPMC7647336 | biostudies-literature
Project description:A core proposition in numerical cognition is numbers are represented spatially. Evidence for this proposition comes from the "spatial numerical association of response codes" effect (SNARC) in which faster responses are made by the left/right hand judging whether one of a pair of Arabic digits is smaller/larger than the other. Less is known if a similar SNARC effect exists for non-symbolic magnitudes; and research that has been conducted used stimuli which could be translated into symbolic terms. To overcome this limitation, we employed a referent-to-target judgment paradigm in which a referent dot array (n = 30 dots) was follow by a second array of dots (e.g., n = 45 or 15 dots)-participants judged if the second array contained fewer or more dots than the referent array. Dot arrays with fewer dots were judged more quickly with the left hand compared to the right hand (i.e., a SNARC effect). Not all participants demonstrated a SNARC effect, however. Neither visuospatial working memory nor math ability was associated with the presence/absence of a non-symbolic SNARC effect. Implications of the non-symbolic SNARC effect for accounts of numerical cognition are discussed.
| S-EPMC6116986 | biostudies-literature
Project description:BackgroundThe electronic medical record (EMR) contains a rich source of information that could be harnessed for epidemic surveillance. We asked if structured EMR data could be coupled with computerized processing of free-text clinical entries to enhance detection of acute respiratory infections (ARI).MethodologyA manual review of EMR records related to 15,377 outpatient visits uncovered 280 reference cases of ARI. We used logistic regression with backward elimination to determine which among candidate structured EMR parameters (diagnostic codes, vital signs and orders for tests, imaging and medications) contributed to the detection of those reference cases. We also developed a computerized free-text search to identify clinical notes documenting at least two non-negated ARI symptoms. We then used heuristics to build case-detection algorithms that best combined the retained structured EMR parameters with the results of the text analysis.Principal findingsAn adjusted grouping of diagnostic codes identified reference ARI patients with a sensitivity of 79%, a specificity of 96% and a positive predictive value (PPV) of 32%. Of the 21 additional structured clinical parameters considered, two contributed significantly to ARI detection: new prescriptions for cough remedies and elevations in body temperature to at least 38°C. Together with the diagnostic codes, these parameters increased detection sensitivity to 87%, but specificity and PPV declined to 95% and 25%, respectively. Adding text analysis increased sensitivity to 99%, but PPV dropped further to 14%. Algorithms that required satisfying both a query of structured EMR parameters as well as text analysis disclosed PPVs of 52-68% and retained sensitivities of 69-73%.ConclusionStructured EMR parameters and free-text analyses can be combined into algorithms that can detect ARI cases with new levels of sensitivity or precision. These results highlight potential paths by which repurposed EMR information could facilitate the discovery of epidemics before they cause mass casualties.
| S-EPMC2954790 | biostudies-literature
Project description:BackgroundPostoperative complication rates are often assessed through administrative data, although this method has proven to be imprecise. Recently, new developments in natural language processing have shown promise in detecting specific phenotypes from free medical text. Using the clinical challenge of extracting four specific and frequently undercoded postoperative complications (pneumonia, urinary tract infection, sepsis, and septic shock), it was hypothesized that natural language processing would capture postoperative complications on a par with human-level curation from electronic health record free medical text.MethodsElectronic health record data were extracted for surgical cases (across 11 surgical sub-specialties) from 18 hospitals in the Capital and Zealand regions of Denmark that were performed between May 2016 and November 2021. The data set was split into training/validation/test sets (30.0%/48.0%/22.0%). Model performance was compared with administrative data and manual extraction of the test data set.ResultsData were obtained for 17 486 surgical cases. Natural language processing achieved a receiver operating characteristic area under the curve of 0.989 for urinary tract infection, 0.993 for pneumonia, 0.992 for sepsis, and 0.998 for septic shock, whereas administrative data achieved a receiver operating characteristic area under the curve of 0.595 for urinary tract infection, 0.624 for pneumonia, 0.571 for sepsis, and 0.625 for septic shock.ConclusionThe natural language processing approach was able to capture complications with acceptable performance, which was superior to administrative data. In addition, the model performance approached that of manual curation and thereby offers a potential pathway for complete real-time coverage of postoperative complications across surgical procedures based on natural language processing assessment of electronic health record free medical text.
| S-EPMC11003538 | biostudies-literature