Annotating temporal information in clinical narratives

Temporal reasoning with medical data—A review with emphasis on medical natural language processing

The goal of this study is to develop a robust Time Event Ontology (TEO), which can formally represent and reason both structured and unstructured temporal information. Using our previous Clinical Narrative Temporal Relation Ontology 1.0 and 2.0 as a starting point, we redesigned concept primitives (clinical events and temporal expressions) and enriched temporal relations. Specifically, 2 sets of temporal relations (Allen's interval algebra and a novel suite of basic time relations) were used to specify qualitative temporal order relations, and a Temporal Relation Statement was designed to formalize quantitative temporal relations. Moreover, a variety of data properties were defined to represent diversified temporal expressions in clinical narratives. TEO has a rich set of classes and properties (object, data, and annotation). When evaluated with real electronic health record data from the Mayo Clinic, it could faithfully represent more than 95% of the temporal expressions. Its reasoning ability was further demonstrated on a sample drug adverse event report annotated with respect to TEO. The results showed that our Java-based TEO reasoner could answer a set of frequently asked time-related queries, demonstrating that TEO has a strong capability of reasoning complex temporal relations. TEO can support flexible temporal relation representation and reasoning. Our next step will be to apply TEO to the natural language processing field to facilitate automated temporal information annotation, extraction, and timeline reasoning to better support time-based clinical decision-making.

Medical natural language processing (NLP) systems are a key enabling technology for transforming Big Data from clinical report repositories to information used to support disease models and validate intervention methods. However, current medical NLP systems fall considerably short when faced with the task of logically interpreting clinical text. In this paper, we describe a framework inspired by mechanisms of human cognition in an attempt to jump the NLP performance curve. The design centers on a hierarchical semantic compositional model (HSCM), which provides an internal substrate for guiding the interpretation process. The paper describes insights from four key cognitive aspects: semantic memory, semantic composition, semantic activation, and hierarchical predictive coding. We discuss the design of a generative semantic model and an associated semantic parser used to transform a free-text sentence into a logical representation of its meaning. The paper discusses supportive and antagonistic arguments for the key features of the architecture as a long-term foundational framework.

Detecting adverse drug events (ADEs) and medications related information in clinical notes is important for both hospital medical care and medical research. We describe our clinical natural language processing (NLP) system to automatically extract medical concepts and relations related to ADEs and medications from clinical narratives. This work was part of the 2018 National NLP Clinical Challenges Shared Task and Workshop on Adverse Drug Events and Medication Extraction. The authors developed a hybrid clinical NLP system that employs a knowledge-based general clinical NLP system for medical concepts extraction, and a task-specific deep learning system for relations identification using attention-based bidirectional long short-term memory networks. The systems were evaluated as part of the 2018 National NLP Clinical Challenges challenge, and our attention-based bidirectional long short-term memory networks based system obtained an F-measure of 0.9442 for relations identification task, ranking fifth at the challenge, and had <2% difference from the best system. Error analysis was also conducted targeting at figuring out the root causes and possible approaches for improvement. We demonstrate the generic approaches and the practice of connecting general purposed clinical NLP system to task-specific requirements with deep learning methods. Our results indicate that a well-designed hybrid NLP system is capable of ADE and medication-related information extraction, which can be used in real-world applications to support ADE-related researches and medical decisions.

Natural language processing systems for capturing and standardizing unstructured clinical information: A systematic review

Extraction of temporal relations from clinical free text: A systematic review of current approaches.

: The Neal-Montgomery NLP Evaluation Methodology was developed under the 'Benchmark Investigation/Identification' project as a means of determining the linguistic competence of Natural Language Processing (NLP) systems. Embodied in an evaluation tool based on a detailed classification of linguistic phenomena with, currently, over 350 test items, the methodology produces descriptive profiles of NLP system linguistic capabilities, and can be applied without regard to the current system application, domain, or specific language processing function. To date, it has been applied to three NL data base query systems and three text processing systems. Researchers are invited to apply the evaluation methodology (included within this report) to their systems and report their critique and recommendations towards the evolution of standard evaluation procedures for NLP systems.

The goal of this study was to develop a practical framework for recognizing and disambiguating clinical abbreviations, thereby improving current clinical natural language processing (NLP) systems' capability to handle abbreviations in clinical narratives. We developed an open-source framework for clinical abbreviation recognition and disambiguation (CARD) that leverages our previously developed methods, including: (1) machine learning based approaches to recognize abbreviations from a clinical corpus, (2) clustering-based semiautomated methods to generate possible senses of abbreviations, and (3) profile-based word sense disambiguation methods for clinical abbreviations. We applied CARD to clinical corpora from Vanderbilt University Medical Center (VUMC) and generated 2 comprehensive sense inventories for abbreviations in discharge summaries and clinic visit notes. Furthermore, we developed a wrapper that integrates CARD with MetaMap, a widely used general clinical NLP system. CARD detected 27 317 and 107 303 distinct abbreviations from discharge summaries and clinic visit notes, respectively. Two sense inventories were constructed for the 1000 most frequent abbreviations in these 2 corpora. Using the sense inventories created from discharge summaries, CARD achieved an F1 score of 0.755 for identifying and disambiguating all abbreviations in a corpus from the VUMC discharge summaries, which is superior to MetaMap and Apache's clinical Text Analysis Knowledge Extraction System (cTAKES). Using additional external corpora, we also demonstrated that the MetaMap-CARD wrapper improved MetaMap's performance in recognizing disorder entities in clinical notes. The CARD framework, 2 sense inventories, and the wrapper for MetaMap are publicly available at https://sbmi.uth.edu/ccb/resources/abbreviation.htm . We believe the CARD framework can be a valuable resource for improving abbreviation identification in clinical NLP systems.

The prevalence of temporal references across all types of natural language utterances makes temporal analysis a key issue in Natural Language Processing. This work adresses three research questions: 1/is temporal expression recognition specific to a particular domain? 2/if so, can we characterize domain specificity? and 3/how can subdomain specificity be integrated in a single tool for unified temporal expression extraction? Herein, we assess temporal expression recognition from documents written in French covering three domains. We present a new corpus of clinical narratives annotated for temporal expressions , and also use existing corpora in the newswire and historical domains. We show that temporal expressions can be extracted with high performance across domains (best F-measure 0.96 obtained with a CRF model on clinical narratives). We argue that domain adaptation for the extraction of temporal expressions can be done with limited efforts and should cover pre-processing as well as temporal specific tasks.

Many ongoing clinical research projects, such as projects involving studies associated with cancer, involve manual capture of information in surgical pathology reports so that the information can be used to determine the eligibility of recruited patients for the study and to provide other information, such as cancer prognosis. Natural language processing (NLP) systems offer an alternative to automated coding, but pathology reports have certain features that are difficult for NLP systems. This paper describes how a preprocessor was integrated with an existing NLP system (MedLEE) in order to reduce modification to the NLP system and to improve performance. The work was done in conjunction with an ongoing clinical research project that assesses disparities and risks of developing breast cancer for minority women. An evaluation of the system was performed using manually coded data from the research project's database as a gold standard. The evaluation outcome showed that the extended NLP system had a sensitivity of 90.6% and a precision of 91.6%. Results indicated that this system performed satisfactorily for capturing information for the cancer research project.

Evaluation of Natural Language Processing (NLP) systems to annotate drug product labeling with MedDRA terminology

To evaluate the feasibility, accuracy, and interoperability of a natural language processing (NLP) system that extracts diagnostic assertions of pneumonia in different clinical notes and institutions. A rule-based NLP system was designed to identify assertions of pneumonia in 3 types of clinical notes from electronic health records (EHRs): emergency department notes, radiology reports, and discharge summaries. The lexicon and classification logic were tailored for each note type. The system was first developed and evaluated using annotated notes from the Department of Veterans Affairs (VA). Interoperability was assessed using data from the University of Utah (UU). The NLP system was comprised of 782 rules and achieved moderate-to-high performance in all 3 note types in VA (precision/recall/f1: emergency = 88.1/86.0/87.1; radiology = 71.4/96.2/82.0; discharge = 88.3/93.0/90.1). When applied to UU data, performance was maintained in emergency and radiology but decreased in discharge summaries (emergency = 84.7/94.3/89.3; radiology = 79.7/100.0/87.9; discharge = 65.5/92.7/76.8). Customization with 34 additional rules increased performance for all note types (emergency = 89.3/94.3/91.7; radiology = 87.0/100.0/93.1; discharge = 75.0/95.1/83.4). NLP can be used to accurately identify the diagnosis of pneumonia across different clinical settings and institutions. A limited amount of customization to account for differences in lexicon, clinical definition of pneumonia, and EHR structure can achieve high accuracy without substantial modification.

BackgroundCognitive test results from electronic health records (EHRs) are key information for assessing the severity and progression of patients with mild cognitive impairment (MCI) and Alzheimer’s’ disease (AD). However, such information is often recorded in unstructured clinical notes rather than in an administrative database. We developed and validated a natural language processing (NLP) system to extract cognitive test results from clinical notes in the Veterans Affair (VA) Healthcare System.MethodAn NLP system was developed using regular expression‐based rules and Python to extract results for six tests that have been used most frequently in VA: Mini‐Mental State Exam (MMSE), Montreal Cognitive Assessment (MoCA), Saint Louis University Mental Status Examination (SLUMS), Mini‐cog, Boston Naming Test (BNT), and Benton Visual Retention Test (BVRT). The system extracted test results from each note in two steps: (1) searched a test name, or variations and abbreviation of the test name and, if successful, (2) searched the quantitative results (e.g., 12/30 for MMSE, 74th percentile for BNT) and/or descriptive results (e.g., “borderline impairment” for BVRT) within 5 words or one sentence before or after the test name. To balance the system performance and speed, we developed 3‐8 extraction rules per test based on a manual review of 30‐50 notes for each test. We further validated NLP performance on 6 held‐out datasets (50‐200 notes/test). We automatically sampled the development and held‐out notes by searching the test name and its variations/abbreviation to increase positive cases, i.e., notes that contained the above test results.ResultThe NLP system achieved 0.72‐0.92 predictive positive values (PPV), 0.96‐1.00 recall, and 0.83‐0.95 F1 scores on the validation test sets (Table 1). In addition, it demonstrated a scalable performance (processed 200,000 notes in 7 min), allowing an extraction of millions of notes from ∼1 million patients within hours.ConclusionRule‐based NLP can extract cognitive test results with adequate performance and scalable capability for clinical notes from patients with MCI or AD within the VA Healthcare System.

The purpose of this study is to evaluate the performance of a natural language processing (NLP) system in classifying a database of free-text knee MRI reports at two separate academic radiology practices. An NLP system that uses terms and patterns in manually classified narrative knee MRI reports was constructed. The NLP system was trained and tested on expert-classified knee MRI reports from two major health care organizations. Radiology reports were modeled in the training set as vectors, and a support vector machine framework was used to train the classifier. A separate test set from each organization was used to evaluate the performance of the system. We evaluated the performance of the system both within and across organizations. Standard evaluation metrics, such as accuracy, precision, recall, and F1 score (i.e., the weighted average of the precision and recall), and their respective 95% CIs were used to measure the efficacy of our classification system. The accuracy for radiology reports that belonged to the model's clinically significant concept classes after training data from the same institution was good, yielding an F1 score greater than 90% (95% CI, 84.6-97.3%). Performance of the classifier on cross-institutional application without institution-specific training data yielded F1 scores of 77.6% (95% CI, 69.5-85.7%) and 90.2% (95% CI, 84.5-95.9%) at the two organizations studied. The results show excellent accuracy by the NLP machine learning classifier in classifying free-text knee MRI reports, supporting the institution-independent reproducibility of knee MRI report classification. Furthermore, the machine learning classifier performed well on free-text knee MRI reports from another institution. These data support the feasibility of multiinstitutional classification of radiologic imaging text reports with a single machine learning classifier without requiring institution-specific training data.

BackgroundThe vast amount of data published in the primary biomedical literature represents a challenge for the automated extraction and codification of individual data elements. Biological databases that rely solely on manual extraction by expert curators are unable to comprehensively annotate the information dispersed across the entire biomedical literature. The development of efficient tools based on natural language processing (NLP) systems is essential for the selection of relevant publications, identification of data attributes and partially automated annotation. One of the tasks of the Biocreative 2010 Challenge III was devoted to the evaluation of NLP systems developed to identify articles for curation and extraction of protein-protein interaction (PPI) data.ResultsThe Biocreative 2010 competition addressed three tasks: gene normalization, article classification and interaction method identification. The BioGRID and MINT protein interaction databases both participated in the generation of the test publication set for gene normalization, annotated the development and test sets for article classification, and curated the test set for interaction method classification. These test datasets served as a gold standard for the evaluation of data extraction algorithms.ConclusionThe development of efficient tools for extraction of PPI data is a necessary step to achieve full curation of the biomedical literature. NLP systems can in the first instance facilitate expert curation by refining the list of candidate publications that contain PPI data; more ambitiously, NLP approaches may be able to directly extract relevant information from full-text articles for rapid inspection by expert curators. Close collaboration between biological databases and NLP systems developers will continue to facilitate the long-term objectives of both disciplines.