Improving Prehospital Stroke Diagnosis Using Natural Language Processing of Paramedic Reports

Stroke ◽  
2021 ◽  
Author(s):  
Anoop Mayampurath ◽  
Zahra Parnianpour ◽  
Christopher T. Richards ◽  
William J. Meurer ◽  
Jungwha Lee ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Final Diagnosis ◽  
Large Vessel ◽  
Support Vector ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Clinical Text ◽  
Comprehensive Stroke Center

Background and Purpose: Accurate prehospital diagnosis of stroke by emergency medical services (EMS) can increase treatments rates, mitigate disability, and reduce stroke deaths. We aimed to develop a model that utilizes natural language processing of EMS reports and machine learning to improve prehospital stroke identification. Methods: We conducted a retrospective study of patients transported by the Chicago EMS to 17 regional primary and comprehensive stroke centers. Patients who were suspected of stroke by the EMS or had hospital-diagnosed stroke were included in our cohort. Text within EMS reports were converted to unigram features, which were given as input to a support-vector machine classifier that was trained on 70% of the cohort and tested on the remaining 30%. Outcomes included final diagnosis of stroke versus nonstroke, large vessel occlusion, severe stroke (National Institutes of Health Stroke Scale score >5), and comprehensive stroke center-eligible stroke (large vessel occlusion or hemorrhagic stroke). Results: Of 965 patients, 580 (60%) had confirmed acute stroke. In a test set of 289 patients, the text-based model predicted stroke nominally better than models based on the Cincinnati Prehospital Stroke Scale ( c -statistic: 0.73 versus 0.67, P =0.165) and was superior to the 3-Item Stroke Scale ( c -statistic: 0.73 versus 0.53, P <0.001) scores. Improvements in discrimination were also observed for the other outcomes. Conclusions: We derived a model that utilizes clinical text from paramedic reports to identify stroke. Our results require validation but have the potential of improving prehospital routing protocols.

scholarly journals Automating Stroke Data Extraction From Free-Text Radiology Reports Using Natural Language Processing: Instrument Validation Study (Preprint)

2020 ◽  
Author(s):  
Amy Y X Yu ◽  
Zhongyu A Liu ◽  
Chloe Pou-Prom ◽  
Kaitlyn Lopes ◽  
Moira K Kapral ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Predictive Value ◽  
Large Vessel ◽  
Free Text ◽  
Imaging Data ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Radiology Reports

BACKGROUND Diagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews. OBJECTIVE We aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports. METHODS From the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data. RESULTS The overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status. CONCLUSIONS NLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.

scholarly journals Automating Stroke Data Extraction From Free-Text Radiology Reports Using Natural Language Processing: Instrument Validation Study

10.2196/24381 ◽  
2021 ◽  
Vol 9 (5) ◽  
pp. e24381
Author(s):  
Amy Y X Yu ◽  
Zhongyu A Liu ◽  
Chloe Pou-Prom ◽  
Kaitlyn Lopes ◽  
Moira K Kapral ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Predictive Value ◽  
Large Vessel ◽  
Free Text ◽  
Imaging Data ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Radiology Reports

Background Diagnostic neurovascular imaging data are important in stroke research, but obtaining these data typically requires laborious manual chart reviews. Objective We aimed to determine the accuracy of a natural language processing (NLP) approach to extract information on the presence and location of vascular occlusions as well as other stroke-related attributes based on free-text reports. Methods From the full reports of 1320 consecutive computed tomography (CT), CT angiography, and CT perfusion scans of the head and neck performed at a tertiary stroke center between October 2017 and January 2019, we manually extracted data on the presence of proximal large vessel occlusion (primary outcome), as well as distal vessel occlusion, ischemia, hemorrhage, Alberta stroke program early CT score (ASPECTS), and collateral status (secondary outcomes). Reports were randomly split into training (n=921) and validation (n=399) sets, and attributes were extracted using rule-based NLP. We reported the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the overall accuracy of the NLP approach relative to the manually extracted data. Results The overall prevalence of large vessel occlusion was 12.2%. In the training sample, the NLP approach identified this attribute with an overall accuracy of 97.3% (95.5% sensitivity, 98.1% specificity, 84.1% PPV, and 99.4% NPV). In the validation set, the overall accuracy was 95.2% (90.0% sensitivity, 97.4% specificity, 76.3% PPV, and 98.5% NPV). The accuracy of identifying distal or basilar occlusion as well as hemorrhage was also high, but there were limitations in identifying cerebral ischemia, ASPECTS, and collateral status. Conclusions NLP may improve the efficiency of large-scale imaging data collection for stroke surveillance and research.

scholarly journals A deep database of medical abbreviations and acronyms for natural language processing

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Lisa Grossman Liu ◽  
Raymond H. Grossman ◽  
Elliot G. Mitchell ◽  
Chunhua Weng ◽  
Karthik Natarajan ◽  
...  
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
American English ◽  
Substantial Improvement ◽  
Future Application ◽  
Multiple Sources ◽  
High Coverage ◽  
Clinical Text ◽  
Automated Quality Control

AbstractThe recognition, disambiguation, and expansion of medical abbreviations and acronyms is of upmost importance to prevent medically-dangerous misinterpretation in natural language processing. To support recognition, disambiguation, and expansion, we present the Medical Abbreviation and Acronym Meta-Inventory, a deep database of medical abbreviations. A systematic harmonization of eight source inventories across multiple healthcare specialties and settings identified 104,057 abbreviations with 170,426 corresponding senses. Automated cross-mapping of synonymous records using state-of-the-art machine learning reduced redundancy, which simplifies future application. Additional features include semi-automated quality control to remove errors. The Meta-Inventory demonstrated high completeness or coverage of abbreviations and senses in new clinical text, a substantial improvement over the next largest repository (6–14% increase in abbreviation coverage; 28–52% increase in sense coverage). To our knowledge, the Meta-Inventory is the most complete compilation of medical abbreviations and acronyms in American English to-date. The multiple sources and high coverage support application in varied specialties and settings. This allows for cross-institutional natural language processing, which previous inventories did not support. The Meta-Inventory is available at https://bit.ly/github-clinical-abbreviations.

Effect of “drip-and-ship” and “drip-and-drive” on endovascular treatment of acute ischemic stroke with large vessel occlusion: a single-center retrospective study

2021 ◽  
pp. 028418512110068
Author(s):  
Yu Hang ◽  
Zhen Yu Jia ◽  
Lin Bo Zhao ◽  
Yue Zhou Cao ◽  
Huang Huang ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Endovascular Treatment ◽  
Acute Ischemic Stroke ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
Vessel Occlusion ◽  
Primary Stroke Center ◽  
Secondary Endpoints ◽  
Comprehensive Stroke Center ◽  
Stroke Center

Background Patients with acute ischemic stroke (AIS) caused by large vessel occlusion (LVO) were usually transferred from a primary stroke center (PSC) to a comprehensive stroke center (CSC) for endovascular treatment (drip-and-ship [DS]), while driving the doctor from a CSC to a PSC to perform a procedure is an alternative strategy (drip-and-drive [DD]). Purpose To compare the efficacy and prognosis of the two strategies. Material and Methods From February 2017 to June 2019, 62 patients with LVO received endovascular treatment via the DS and DD models and were retrospectively analyzed from the stroke alliance based on our CSC. Primary endpoint was door-to-reperfusion (DTR) time. Secondary endpoints included puncture-to-recanalization (PTR) time, modified Thrombolysis in Cerebral Infarction (mTICI) rates at the end of the procedure, and modified Rankin Scale (mRS) at 90 days. Results Forty-one patients received the DS strategy and 21 patients received the DD strategy. The DTR time was significantly longer in the DS group compared to the DD group (315.5 ± 83.8 min vs. 248.6 ± 80.0 min; P < 0.05), and PTR time was shorter (77.2 ± 35.9 min vs. 113.7 ± 69.7 min; P = 0.033) compared with the DD group. Successful recanalization (mTICI 2b/3) was achieved in 89% (36/41) of patients in the DS group and 86% (18/21) in the DD group ( P = 1.000). Favorable functional outcomes (mRS 0–2) were observed in 49% (20/41) of patients in the DS group and 71% (15/21) in the DD group at 90 days ( P = 0.089). Conclusion Compared with the DS strategy, the DD strategy showed more effective and a trend of better clinical outcomes for AIS patients with LVO.

Systematic review of current natural language processing methods and applications in cardiology

Heart ◽  
2021 ◽  
pp. heartjnl-2021-319769
Author(s):  
Meghan Reading Turchioe ◽  
Alexander Volodarskiy ◽  
Jyotishman Pathak ◽  
Drew N Wright ◽  
James Enlou Tcheng ◽  
...  
Keyword(s):  
Systematic Review ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Clinical Care ◽  
Real World Data ◽  
Clinical Text ◽  
Clinical Notes ◽  
Artery Disease ◽  
Automated Methods

Natural language processing (NLP) is a set of automated methods to organise and evaluate the information contained in unstructured clinical notes, which are a rich source of real-world data from clinical care that may be used to improve outcomes and understanding of disease in cardiology. The purpose of this systematic review is to provide an understanding of NLP, review how it has been used to date within cardiology and illustrate the opportunities that this approach provides for both research and clinical care. We systematically searched six scholarly databases (ACM Digital Library, Arxiv, Embase, IEEE Explore, PubMed and Scopus) for studies published in 2015–2020 describing the development or application of NLP methods for clinical text focused on cardiac disease. Studies not published in English, lacking a description of NLP methods, non-cardiac focused and duplicates were excluded. Two independent reviewers extracted general study information, clinical details and NLP details and appraised quality using a checklist of quality indicators for NLP studies. We identified 37 studies developing and applying NLP in heart failure, imaging, coronary artery disease, electrophysiology, general cardiology and valvular heart disease. Most studies used NLP to identify patients with a specific diagnosis and extract disease severity using rule-based NLP methods. Some used NLP algorithms to predict clinical outcomes. A major limitation is the inability to aggregate findings across studies due to vastly different NLP methods, evaluation and reporting. This review reveals numerous opportunities for future NLP work in cardiology with more diverse patient samples, cardiac diseases, datasets, methods and applications.

Detection of Large Vessel Occlusion Stroke in the Prehospital Setting

Stroke ◽  
2021 ◽  
Author(s):  
Laura C.C. van Meenen ◽  
Maritta N. van Stigt ◽  
Arjen Siegers ◽  
Martin D. Smeekes ◽  
Joffry A.F. van Grondelle ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Stroke Care ◽  
Prehospital Setting ◽  
Large Vessel ◽  
Large Vessel Occlusion ◽  
User Friendliness ◽  
Vessel Occlusion ◽  
Comprehensive Stroke Center ◽  
Stroke Center ◽  
Good Diagnostic Accuracy

A reliable and fast instrument for prehospital detection of large vessel occlusion (LVO) stroke would be a game-changer in stroke care, because it would enable direct transportation of LVO stroke patients to the nearest comprehensive stroke center for endovascular treatment. This strategy would substantially improve treatment times and thus clinical outcomes of patients. Here, we outline our view on the requirements of an effective prehospital LVO detection method, namely: high diagnostic accuracy; fast application and interpretation; user-friendliness; compactness; and low costs. We argue that existing methods for prehospital LVO detection, including clinical scales, mobile stroke units and transcranial Doppler, do not fulfill all criteria, hindering broad implementation of these methods. Instead, electroencephalography may be suitable for prehospital LVO detection since in-hospital studies have shown that quantification of hypoxia-induced changes in the electroencephalography signal have good diagnostic accuracy for LVO stroke. Although performing electroencephalography measurements in the prehospital setting comes with challenges, solutions for fast and simple application of this method are available. Currently, the feasibility and diagnostic accuracy of electroencephalography in the prehospital setting are being investigated in clinical trials.

scholarly journals EventEpi–A Natural Language Processing Framework for Event-Based Surveillance

2019 ◽  
Author(s):  
Auss Abbood ◽  
Alexander Ullrich ◽  
Rüdiger Busche ◽  
Stéphane Ghozzi
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Web Application ◽  
Fine Tuning ◽  
Entity Recognition ◽  
World Health ◽  
Support Vector ◽  
Event Based ◽  
Processing Framework

AbstractAccording to the World Health Organization (WHO), around 60% of all outbreaks are detected using informal sources. In many public health institutes, including the WHO and the Robert Koch Institute (RKI), dedicated groups of epidemiologists sift through numerous articles and newsletters to detect relevant events. This media screening is one important part of event-based surveillance (EBS). Reading the articles, discussing their relevance, and putting key information into a database is a time-consuming process. To support EBS, but also to gain insights into what makes an article and the event it describes relevant, we developed a natural-language-processing framework for automated information extraction and relevance scoring. First, we scraped relevant sources for EBS as done at RKI (WHO Disease Outbreak News and ProMED) and automatically extracted the articles’ key data: disease, country, date, and confirmed-case count. For this, we performed named entity recognition in two steps: EpiTator, an open-source epidemiological annotation tool, suggested many different possibilities for each. We trained a naive Bayes classifier to find the single most likely one using RKI’s EBS database as labels. Then, for relevance scoring, we defined two classes to which any article might belong: The article is relevant if it is in the EBS database and irrelevant otherwise. We compared the performance of different classifiers, using document and word embeddings. Two of the tested algorithms stood out: The multilayer perceptron performed best overall, with a precision of 0.19, recall of 0.50, specificity of 0.89, F1 of 0.28, and the highest tested index balanced accuracy of 0.46. The support-vector machine, on the other hand, had the highest recall (0.88) which can be of higher interest for epidemiologists. Finally, we integrated these functionalities into a web application called EventEpi where relevant sources are automatically analyzed and put into a database. The user can also provide any URL or text, that will be analyzed in the same way and added to the database. Each of these steps could be improved, in particular with larger labeled datasets and fine-tuning of the learning algorithms. The overall framework, however, works already well and can be used in production, promising improvements in EBS. The source code is publicly available at https://github.com/aauss/EventEpi.

Sign in / Sign up

Export Citation Format

Share Document