Impact of guidelines for the management of minor head injury on the utilization and diagnostic yield of CT over two decades, using natural language processing in a large dataset.

OBJECTIVES: We investigated the impact of clinical guidelines for the management of minor head injury on utilization and diagnostic yield of head CT over two decades. METHODS: Retrospective before-after study using multiple electronic health record data sources. Natural language processing algorithms were developed to rapidly extract indication, Glasgow Coma Scale, and CT outcome from clinical records, creating two datasets: one based on all head injury CTs from 1997 to 2009 (n = 9109), for which diagnostic yield of intracranial traumatic findings was calculated. The second dataset (2009-2014) used both CT reports and clinical notes from the emergency department, enabling selection of minor head injury patients (n = 4554) and calculation of both CT utilization and diagnostic yield. Additionally, we tested for significant changes in utilization and yield after guideline implementation in 2011, using chi-square statistics and logistic regression. RESULTS: The yield was initially nearly 60%, but in a decreasing trend dropped below 20% when CT became routinely used for head trauma. Between 2009 and 2014, of 4554 minor head injury patients overall, 85.4% underwent head CT. After guideline implementation in 2011, CT utilization significantly increased from 81.6 to 87.6% (p = 7 × 10-7), while yield significantly decreased from 12.2 to 9.6% (p = 0.029). CONCLUSIONS: The number of CTs performed for head trauma gradually increased over two decades, while the yield decreased. In 2011, despite implementation of a guideline aiming to improve selective use of CT in minor head injury, utilization significantly increased. KEY POINTS: • Over two decades, the number of head CTs performed for minor, moderate, and severe head injury gradually increased, while the diagnostic yield for intracranial findings showed a decreasing trend. • Despite the implementation of a guideline in 2011, aiming to improve selective use of CT in minor head injury, utilization significantly increased, while diagnostic yield significantly decreased. • Natural language processing is a valuable tool to monitor the utilization and diagnostic yield of imaging as a potential quality-of-care indicator.

Natural Language Processing in Radiology: A Systematic Review.

Radiological reporting has generated large quantities of digital content within the electronic health record, which is potentially a valuable source of information for improving clinical care and supporting research. Although radiology reports are stored for communication and documentation of diagnostic imaging, harnessing their potential requires efficient and automated information extraction: they exist mainly as free-text clinical narrative, from which it is a major challenge to obtain structured data. Natural language processing (NLP) provides techniques that aid the conversion of text into a structured representation, and thus enables computers to derive meaning from human (ie, natural language) input. Used on radiology reports, NLP techniques enable automatic identification and extraction of information. By exploring the various purposes for their use, this review examines how radiology benefits from NLP. A systematic literature search identified 67 relevant publications describing NLP methods that support practical applications in radiology. This review takes a close look at the individual studies in terms of tasks (ie, the extracted information), the NLP methodology and tools used, and their application purpose and performance results. Additionally, limitations, future challenges, and requirements for advancing NLP in radiology will be discussed.

ContextD: an algorithm to identify contextual properties of medical terms in a Dutch clinical corpus.

BACKGROUND: In order to extract meaningful information from electronic medical records, such as signs and symptoms, diagnoses, and treatments, it is important to take into account the contextual properties of the identified information: negation, temporality, and experiencer. Most work on automatic identification of these contextual properties has been done on English clinical text. This study presents ContextD, an adaptation of the English ConText algorithm to the Dutch language, and a Dutch clinical corpus. We created a Dutch clinical corpus containing four types of anonymized clinical documents: entries from general practitioners, specialists' letters, radiology reports, and discharge letters. Using a Dutch list of medical terms extracted from the Unified Medical Language System, we identified medical terms in the corpus with exact matching. The identified terms were annotated for negation, temporality, and experiencer properties. To adapt the ConText algorithm, we translated English trigger terms to Dutch and added several general and document specific enhancements, such as negation rules for general practitioners' entries and a regular expression based temporality module. RESULTS: The ContextD algorithm utilized 41 unique triggers to identify the contextual properties in the clinical corpus. For the negation property, the algorithm obtained an F-score from 87% to 93% for the different document types. For the experiencer property, the F-score was 99% to 100%. For the historical and hypothetical values of the temporality property, F-scores ranged from 26% to 54% and from 13% to 44%, respectively. CONCLUSIONS: The ContextD showed good performance in identifying negation and experiencer property values across all Dutch clinical document types. Accurate identification of the temporality property proved to be difficult and requires further work. The anonymized and annotated Dutch clinical corpus can serve as a useful resource for further algorithm development.

Adrenal Incidentaloma and Adherence to International Guidelines for Workup Based on a Retrospective Review of the Type of Language Used in the Radiology Report.

INTRODUCTION: The purpose of this study is to explore what terms are used to describe adrenal incidentalomas and to determine what reporting factors are associated with clinicians adhering to international guidelines. METHODS: This retrospective study was approved by the institutional review board, with a waiver of informed consent. Adrenal incidentaloma cases were identified from CT reports between 2010 and 2012 and filtered based on terminology used to describe the adrenal mass at initial presentation. Cases were divided into two groups: masses described with specific terms (ie, nodule, presumably ≥1 cm in diameter) and nonspecific terms (ie, plump, likely to be smaller). P values were calculated using Student's t test and χ2 test. Rate of adherence of clinicians to workup guidelines was determined for both groups and was analyzed. RESULTS: Of 1,112 cases, 604 had a specific description of the adrenal mass. Patients of the specific group had a significantly larger mass (P < .01) and referral frequency was higher (P < .01). Of the nonspecific masses, 99.2% (504 of 508) were ≥1 cm in diameter, compared with 98.3% of the specific masses (594 of 604). Furthermore, diagnostic workup was more likely to occur when a specific term was used; when Houndsfield unit, size of the mass, and diagnostic recommendation were reported; and when adrenal incidentaloma findings were repeated in the conclusion of the report (all P < .01). CONCLUSION: Our study shows that inconsistent use of terms in radiology reports has to be avoided to increase adequate adrenal incidentaloma workup. A structured and thorough report with use of standardized terminology may increase adherence to international guidelines.

Patient-specific workup of adrenal incidentalomas.

PURPOSE: : To develop a clinical prediction model to predict a clinically relevant adrenal disorder for patients with adrenal incidentaloma. MATERIALS AND METHODS: : This retrospective study is approved by the institutional review board, with waiver of informed consent. Natural language processing is used for filtering of adrenal incidentaloma cases in all thoracic and abdominal CT reports from 2010 till 2012. A total of 635 patients are identified. Stepwise logistic regression is used to construct the prediction model. The model predicts if a patient is at risk for malignancy or hormonal hyperfunction of the adrenal gland at the moment of initial presentation, thus generates a predicted probability for every individual patient. The prediction model is evaluated on its usefulness in clinical practice using decision curve analysis (DCA) based on different threshold probabilities. For patients whose predicted probability is lower than the predetermined threshold probability, further workup could be omitted. RESULTS: : A prediction model is successfully developed, with an area under the curve (AUC) of 0.78. Results of the DCA indicate that up to 11% of patients with an adrenal incidentaloma can be avoided from unnecessary workup, with a sensitivity of 100% and specificity of 11%. CONCLUSION: : A prediction model can accurately predict if an adrenal incidentaloma patient is at risk for malignancy or hormonal hyperfunction of the adrenal gland based on initial imaging features and patient demographics. However, with most adrenal incidentalomas labeled as nonfunctional adrenocortical adenomas requiring no further treatment, it is likely that more patients could be omitting from unnecessary diagnostics.

Chemical entity recognition in patents by combining dictionary-based and statistical approaches.

We describe the development of a chemical entity recognition system and its application in the CHEMDNER-patent track of BioCreative 2015. This community challenge includes a Chemical Entity Mention in Patents (CEMP) recognition task and a Chemical Passage Detection (CPD) classification task. We addressed both tasks by an ensemble system that combines a dictionary-based approach with a statistical one. For this purpose the performance of several lexical resources was assessed using Peregrine, our open-source indexing engine. We combined our dictionary-based results on the patent corpus with the results of tmChem, a chemical recognizer using a conditional random field classifier. To improve the performance of tmChem, we utilized three additional features, viz. part-of-speech tags, lemmas and word-vector clusters. When evaluated on the training data, our final system obtained an F-score of 85.21% for the CEMP task, and an accuracy of 91.53% for the CPD task. On the test set, the best system ranked sixth among 21 teams for CEMP with an F-score of 86.82%, and second among nine teams for CPD with an accuracy of 94.23%. The differences in performance between the best ensemble system and the statistical system separately were small.Database URL: http://biosemantics.org/chemdner-patents.

Extraction of chemical-induced diseases using prior knowledge and textual information.

We describe our approach to the chemical-disease relation (CDR) task in the BioCreative V challenge. The CDR task consists of two subtasks: automatic disease-named entity recognition and normalization (DNER), and extraction of chemical-induced diseases (CIDs) from Medline abstracts. For the DNER subtask, we used our concept recognition tool Peregrine, in combination with several optimization steps. For the CID subtask, our system, which we named RELigator, was trained on a rich feature set, comprising features derived from a graph database containing prior knowledge about chemicals and diseases, and linguistic and statistical features derived from the abstracts in the CDR training corpus. We describe the systems that were developed and present evaluation results for both subtasks on the CDR test set. For DNER, our Peregrine system reached anF-score of 0.757. For CID, the system achieved anF-score of 0.526, which ranked second among 18 participating teams. Several post-challenge modifications of the systems resulted in substantially improvedF-scores (0.828 for DNER and 0.602 for CID). RELigator is available as a web service athttp://biosemantics.org/index.php/software/religator.