Building a Natural Language Processing Tool to Identify Patients With High Clinical Suspicion for Kawasaki Disease from Emergency Department Notes.
Ontology highlight
ABSTRACT:
SUBMITTER: Doan S
PROVIDER: S-EPMC5031359 | biostudies-literature | 2016 May
REPOSITORIES: biostudies-literature
Publications
Building a Natural Language Processing Tool to Identify Patients With High Clinical Suspicion for Kawasaki Disease from Emergency Department Notes.
Doan Son S Maehara Cleo K CK Chaparro Juan D JD Lu Sisi S Liu Ruiling R Graham Amanda A Berry Erika E Hsu Chun-Nan CN Kanegaye John T JT Lloyd David D DD Ohno-Machado Lucila L Burns Jane C JC Tremoulet Adriana H AH
Academic emergency medicine : official journal of the Society for Academic Emergency Medicine 20160413 5
<h4>Objective</h4>Delayed diagnosis of Kawasaki disease (KD) may lead to serious cardiac complications. We sought to create and test the performance of a natural language processing (NLP) tool, the KD-NLP, in the identification of emergency department (ED) patients for whom the diagnosis of KD should be considered.<h4>Methods</h4>We developed an NLP tool that recognizes the KD diagnostic criteria based on standard clinical terms and medical word usage using 22 pediatric ED notes augmented by Uni ...[more]
Similar Datasets
Project description:BackgroundIdentifying pneumonia using diagnosis codes alone may be insufficient for research on clinical decision making. Natural language processing (NLP) may enable the inclusion of cases missed by diagnosis codes.ObjectivesThis article (1) develops a NLP tool that identifies the clinical assertion of pneumonia from physician emergency department (ED) notes, and (2) compares classification methods using diagnosis codes versus NLP against a gold standard of manual chart review to identify patients initially treated for pneumonia.MethodsAmong a national population of ED visits occurring between 2006 and 2012 across the Veterans Affairs health system, we extracted 811 physician documents containing search terms for pneumonia for training, and 100 random documents for validation. Two reviewers annotated span- and document-level classifications of the clinical assertion of pneumonia. An NLP tool using a support vector machine was trained on the enriched documents. We extracted diagnosis codes assigned in the ED and upon hospital discharge and calculated performance characteristics for diagnosis codes, NLP, and NLP plus diagnosis codes against manual review in training and validation sets.ResultsAmong the training documents, 51% contained clinical assertions of pneumonia; in the validation set, 9% were classified with pneumonia, of which 100% contained pneumonia search terms. After enriching with search terms, the NLP system alone demonstrated a recall/sensitivity of 0.72 (training) and 0.55 (validation), and a precision/positive predictive value (PPV) of 0.89 (training) and 0.71 (validation). ED-assigned diagnostic codes demonstrated lower recall/sensitivity (0.48 and 0.44) but higher precision/PPV (0.95 in training, 1.0 in validation); the NLP system identified more "possible-treated" cases than diagnostic coding. An approach combining NLP and ED-assigned diagnostic coding classification achieved the best performance (sensitivity 0.89 and PPV 0.80).ConclusionSystem-wide application of NLP to clinical text can increase capture of initial diagnostic hypotheses, an important inclusion when studying diagnosis and clinical decision-making under uncertainty.
| S-EPMC5821510 | biostudies-literature
Project description:To evaluate factors affecting performance of influenza detection, including accuracy of natural language processing (NLP), discriminative ability of Bayesian network (BN) classifiers, and feature selection.We derived a testing dataset of 124 influenza patients and 87 non-influenza (shigellosis) patients. To assess NLP finding-extraction performance, we measured the overall accuracy, recall, and precision of Topaz and MedLEE parsers for 31 influenza-related findings against a reference standard established by three physician reviewers. To elucidate the relative contribution of NLP and BN classifier to classification performance, we compared the discriminative ability of nine combinations of finding-extraction methods (expert, Topaz, and MedLEE) and classifiers (one human-parameterized BN and two machine-parameterized BNs). To assess the effects of feature selection, we conducted secondary analyses of discriminative ability using the most influential findings defined by their likelihood ratios.The overall accuracy of Topaz was significantly better than MedLEE (with post-processing) (0.78 vs 0.71, p<0.0001). Classifiers using human-annotated findings were superior to classifiers using Topaz/MedLEE-extracted findings (average area under the receiver operating characteristic (AUROC): 0.75 vs 0.68, p=0.0113), and machine-parameterized classifiers were superior to the human-parameterized classifier (average AUROC: 0.73 vs 0.66, p=0.0059). The classifiers using the 17 'most influential' findings were more accurate than classifiers using all 31 subject-matter expert-identified findings (average AUROC: 0.76>0.70, p<0.05).Using a three-component evaluation method we demonstrated how one could elucidate the relative contributions of components under an integrated framework. To improve classification performance, this study encourages researchers to improve NLP accuracy, use a machine-parameterized classifier, and apply feature selection methods.
| S-EPMC4147621 | biostudies-literature
Project description:BackgroundSymptoms are a core concept of nursing interest. Large-scale secondary data reuse of notes in electronic health records (EHRs) has the potential to increase the quantity and quality of symptom research. However, the symptom language used in clinical notes is complex. A need exists for methods designed specifically to identify and study symptom information from EHR notes.ObjectivesWe aim to describe a method that combines standardized vocabularies, clinical expertise, and natural language processing to generate comprehensive symptom vocabularies and identify symptom information in EHR notes. We piloted this method with five diverse symptom concepts: constipation, depressed mood, disturbed sleep, fatigue, and palpitations.MethodsFirst, we obtained synonym lists for each pilot symptom concept from the Unified Medical Language System. Then, we used two large bodies of text (clinical notes from Columbia University Irving Medical Center and PubMed abstracts containing Medical Subject Headings or key words related to the pilot symptoms) to further expand our initial vocabulary of synonyms for each pilot symptom concept. We used NimbleMiner, an open-source natural language processing tool, to accomplish these tasks and evaluated NimbleMiner symptom identification performance by comparison to a manually annotated set of nurse- and physician-authored common EHR note types.ResultsCompared to the baseline Unified Medical Language System synonym lists, we identified up to 11 times more additional synonym words or expressions, including abbreviations, misspellings, and unique multiword combinations, for each symptom concept. Natural language processing system symptom identification performance was excellent.DiscussionUsing our comprehensive symptom vocabularies and NimbleMiner to label symptoms in clinical notes produced excellent performance metrics. The ability to extract symptom information from EHR notes in an accurate and scalable manner has the potential to greatly facilitate symptom science research.
| S-EPMC9109773 | biostudies-literature
Project description:BackgroundSelf-harm occurring within pregnancy and the postnatal year ("perinatal self-harm") is a clinically important yet under-researched topic. Current research likely under-estimates prevalence due to methodological limitations. Electronic healthcare records (EHRs) provide a source of clinically rich data on perinatal self-harm.Aims(1) To create a Natural Language Processing (NLP) tool that can, with acceptable precision and recall, identify mentions of acts of perinatal self-harm within EHRs. (2) To use this tool to identify service-users who have self-harmed perinatally, based on their EHRs.MethodsWe used the Clinical Record Interactive Search system to extract de-identified EHRs of secondary mental healthcare service-users at South London and Maudsley NHS Foundation Trust. We developed a tool that applied several layers of linguistic processing based on the spaCy NLP library for Python. We evaluated mention-level performance in the following domains: span, status, temporality and polarity. Evaluation was done against a manually coded reference standard. Mention-level performance was reported as precision, recall, F-score and Cohen's kappa for each domain. Performance was also assessed at 'service-user' level and explored whether a heuristic rule improved this. We report per-class statistics for service-user performance, as well as likelihood ratios and post-test probabilities.ResultsMention-level performance: micro-averaged F-score, precision and recall for span, polarity and temporality >0.8. Kappa for status 0.68, temporality 0.62, polarity 0.91. Service-user level performance with heuristic: F-score, precision, recall of minority class 0.69, macro-averaged F-score 0.81, positive LR 9.4 (4.8-19), post-test probability 69.0% (53-82%). Considering the task difficulty, the tool performs well, although temporality was the attribute with the lowest level of annotator agreement.ConclusionsIt is feasible to develop an NLP tool that identifies, with acceptable validity, mentions of perinatal self-harm within EHRs, although with limitations regarding temporality. Using a heuristic rule, it can also function at a service-user-level.
| S-EPMC8336818 | biostudies-literature
Project description:BackgroundAbout 30% of home healthcare patients are hospitalized or visit an emergency department (ED) during a home healthcare (HHC) episode. Novel data science methods are increasingly used to improve identification of patients at risk for negative outcomes.ObjectivesThe aim of the study was to identify patients at heightened risk hospitalization or ED visits using HHC narrative data (clinical notes).MethodsThis study used a large database of HHC visit notes (n = 727,676) documented for 112,237 HHC episodes (89,459 unique patients) by clinicians of the largest nonprofit HHC agency in the United States. Text mining and machine learning algorithms (Naïve Bayes, decision tree, random forest) were implemented to predict patient hospitalization or ED visits using the content of clinical notes. Risk factors associated with hospitalization or ED visits were identified using a feature selection technique (gain ratio attribute evaluation).ResultsBest performing text mining method (random forest) achieved good predictive performance. Seven risk factors categories were identified, with clinical factors, coordination/communication, and service use being the most frequent categories.DiscussionThis study was the first to explore the potential contribution of HHC clinical notes to identifying patients at risk for hospitalization or an ED visit. Our results suggest that HHC visit notes are highly informative and can contribute significantly to identification of patients at risk. Further studies are needed to explore ways to improve risk prediction by adding more data elements from additional data sources.
| S-EPMC7606545 | biostudies-literature
Project description:BackgroundNovel approaches that complement and go beyond evidence-based medicine are required in the domain of chronic diseases, given the growing incidence of such conditions on the worldwide population. A promising avenue is the secondary use of electronic health records (EHRs), where patient data are analyzed to conduct clinical and translational research. Methods based on machine learning to process EHRs are resulting in improved understanding of patient clinical trajectories and chronic disease risk prediction, creating a unique opportunity to derive previously unknown clinical insights. However, a wealth of clinical histories remains locked behind clinical narratives in free-form text. Consequently, unlocking the full potential of EHR data is contingent on the development of natural language processing (NLP) methods to automatically transform clinical text into structured clinical data that can guide clinical decisions and potentially delay or prevent disease onset.ObjectiveThe goal of the research was to provide a comprehensive overview of the development and uptake of NLP methods applied to free-text clinical notes related to chronic diseases, including the investigation of challenges faced by NLP methodologies in understanding clinical narratives.MethodsPreferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed and searches were conducted in 5 databases using "clinical notes," "natural language processing," and "chronic disease" and their variations as keywords to maximize coverage of the articles.ResultsOf the 2652 articles considered, 106 met the inclusion criteria. Review of the included papers resulted in identification of 43 chronic diseases, which were then further classified into 10 disease categories using the International Classification of Diseases, 10th Revision. The majority of studies focused on diseases of the circulatory system (n=38) while endocrine and metabolic diseases were fewest (n=14). This was due to the structure of clinical records related to metabolic diseases, which typically contain much more structured data, compared with medical records for diseases of the circulatory system, which focus more on unstructured data and consequently have seen a stronger focus of NLP. The review has shown that there is a significant increase in the use of machine learning methods compared to rule-based approaches; however, deep learning methods remain emergent (n=3). Consequently, the majority of works focus on classification of disease phenotype with only a handful of papers addressing extraction of comorbidities from the free text or integration of clinical notes with structured data. There is a notable use of relatively simple methods, such as shallow classifiers (or combination with rule-based methods), due to the interpretability of predictions, which still represents a significant issue for more complex methods. Finally, scarcity of publicly available data may also have contributed to insufficient development of more advanced methods, such as extraction of word embeddings from clinical notes.ConclusionsEfforts are still required to improve (1) progression of clinical NLP methods from extraction toward understanding; (2) recognition of relations among entities rather than entities in isolation; (3) temporal extraction to understand past, current, and future clinical events; (4) exploitation of alternative sources of clinical knowledge; and (5) availability of large-scale, de-identified clinical corpora.
| S-EPMC6528438 | biostudies-literature
Project description:ObjectivesThe outcome of emergency medicine (EM) training is to produce physicians who can competently run an emergency department (ED) shift. However, there are few tools with supporting validity evidence specifically designed to assess multiple key competencies across an entire shift. The investigators developed and gathered validity evidence for a novel entrustment-based tool to assess a resident's ability to safely run an ED shift.MethodsThrough a nominal group technique, local and national stakeholders identified dimensions of performance that are reflective of a competent ED physician and are required to safely manage an ED shift. These were included as items in the Ottawa Emergency Department Shift Observation Tool (O-EDShOT), and each item was scored using an entrustment-based rating scale. The tool was implemented in 2018 at the University of Ottawa Department of Emergency Medicine, and quantitative data and qualitative feedback were collected over 6 months.ResultsA total of 1,141 forms were completed by 78 physicians for 45 residents. An analysis of variance demonstrated an effect of training level with statistically significant increases in mean O-EDShOT scores with each subsequent postgraduate year (p < 0.001). Scores did not vary by ED treatment area. Residents rated as able to safely run the shift had significantly higher mean ± SD scores (4.8 ± 0.3) than those rated as not able (3.8 ± 0.6; p < 0.001). Faculty and residents reported that the tool was feasible to use and facilitated actionable feedback aimed at progression toward independent practice.ConclusionsThe O-EDShOT successfully discriminated between trainees of different levels regardless of ED treatment area. Multiple sources of validity evidence support the O-EDShOT as a tool to assess a resident's ability to safely run an ED shift. It can serve as a stimulus for daily observation and feedback making it practical to use within an EM residency program.
| S-EPMC7592826 | biostudies-literature
Project description:The risk stratification of patients in the emergency department begins at triage. It is vital to stratify patients early based on their severity, since undertriage can lead to increased morbidity, mortality and costs. Our aim was to present a new approach to assist healthcare professionals at triage in the stratification of patients and in identifying those with higher risk of ICU admission. Adult patients assigned Manchester Triage System (MTS) or Emergency Severity Index (ESI) 1 to 3 from a Portuguese and a United States Emergency Departments were analyzed. Variables routinely collected at triage were used and natural language processing was applied to the patient chief complaint. Stratified random sampling was applied to split the data in train (70%) and test (30%) sets and 10-fold cross validation was performed for model training. Logistic regression, random forests, and a random undersampling boosting algorithm were used. We compared the performance obtained with the reference model-using only triage priorities-with the models using additional variables. For both hospitals, a logistic regression model achieved higher overall performance, yielding areas under the receiver operating characteristic and precision-recall curves of 0.91 (95% CI 0.90-0.92) and 0.30 (95% CI 0.27-0.33) for the United States hospital and of 0.85 (95% CI 0.83-0.86) and 0.06 (95% CI 0.05-0.07) for the Portuguese hospital. Heart rate, pulse oximetry, respiratory rate and systolic blood pressure were the most important predictors of ICU admission. Compared to the reference models, the models using clinical variables and the chief complaint presented higher recall for patients assigned MTS/ESI 3 and can identify patients assigned MTS/ESI 3 who are at risk for ICU admission.
| S-EPMC7053743 | biostudies-literature
Project description:OBJECTIVE:To examine the association between the medical imaging utilization and information related to patients' socioeconomic, demographic and clinical factors during the patients' ED visits; and to develop predictive models using these associated factors including natural language elements to predict the medical imaging utilization at pediatric ED. METHODS:Pediatric patients' data from the 2012-2016 United States National Hospital Ambulatory Medical Care Survey was included to build the models to predict the use of imaging in children presenting to the ED. Multivariable logistic regression models were built with structured variables such as temperature, heart rate, age, and unstructured variables such as reason for visit, free text nursing notes and combined data available at triage. NLP techniques were used to extract information from the unstructured data. RESULTS:Of the 27,665 pediatric ED visits included in the study, 8394 (30.3%) received medical imaging in the ED, including 6922 (25.0%) who had an X-ray and 1367 (4.9%) who had a computed tomography (CT) scan. In the predictive model including only structured variables, the c-statistic was 0.71 (95% CI: 0.70-0.71) for any imaging use, 0.69 (95% CI: 0.68-0.70) for X-ray, and 0.77 (95% CI: 0.76-0.78) for CT. Models including only unstructured information had c-statistics of 0.81 (95% CI: 0.81-0.82) for any imaging use, 0.82 (95% CI: 0.82-0.83) for X-ray, and 0.85 (95% CI: 0.83-0.86) for CT scans. When both structured variables and free text variables were included, the c-statistics reached 0.82 (95% CI: 0.82-0.83) for any imaging use, 0.83 (95% CI: 0.83-0.84) for X-ray, and 0.87 (95% CI: 0.86-0.88) for CT. CONCLUSIONS:Both CT and X-rays are commonly used in the pediatric ED with one third of the visits receiving at least one. Patients' socioeconomic, demographic and clinical factors presented at ED triage period were associated with the medical imaging utilization. Predictive models combining structured and unstructured variables available at triage performed better than models using structured or unstructured variables alone, suggesting the potential for use of NLP in determining resource utilization.
| S-EPMC6937987 | biostudies-literature
Project description:ImportanceEmergency department (ED) triage substantially affects how long patients wait for care but triage scoring relies on few objective criteria. Prior studies suggest that Black and Hispanic patients receive unequal triage scores, paralleled by disparities in the depth of physician evaluations.ObjectivesTo examine whether racial disparities in triage scores and physician evaluations are present across a multicenter network of academic and community hospitals and evaluate whether patients who do not speak English face similar disparities.Design, setting, and participantsThis was a cross-sectional, multicenter study examining adults presenting between February 28, 2019, and January 1, 2023, across the Mass General Brigham Integrated Health Care System, encompassing 7 EDs: 2 urban academic hospitals and 5 community hospitals. Analysis included all patients presenting with 1 of 5 common chief symptoms.ExposuresEmergency department nurse-led triage and physician evaluation.Main outcomes and measuresAverage Triage Emergency Severity Index [ESI] score and average visit work relative value units [wRVUs] were compared across symptoms and between individual minority racial and ethnic groups and White patients.ResultsThere were 249 829 visits (149 861 female [60%], American Indian or Alaska Native 0.2%, Asian 3.3%, Black 11.8%, Hispanic 18.8%, Native Hawaiian or Other Pacific Islander <0.1%, White 60.8%, and patients identifying as Other race or ethnicity 5.1%). Median age was 48 (IQR, 29-66) years. White patients had more acute ESI scores than Hispanic or Other patients across all symptoms (eg, chest pain: Hispanic, 2.68 [95% CI, 2.67-2.69]; White, 2.55 [95% CI, 2.55-2.56]; Other, 2.66 [95% CI, 2.64-2.68]; P < .001) and Black patients across most symptoms (nausea/vomiting: Black, 2.97 [95% CI, 2.96-2.99]; White: 2.90 [95% CI, 2.89-2.91]; P < .001). These differences were reversed for wRVUs (chest pain: Black, 4.32 [95% CI, 4.25-4.39]; Hispanic, 4.13 [95% CI, 4.08-4.18]; White 3.55 [95% CI, 3.52-3.58]; Other 3.96 [95% CI, 3.84-4.08]; P < .001). Similar patterns were seen for patients whose primary language was not English.Conclusions and relevanceIn this cross-sectional study, patients who identified as Black, Hispanic, and Other race and ethnicity were assigned less acute ESI scores than their White peers despite having received more involved physician workups, suggesting some degree of mistriage. Clinical decision support systems might reduce these disparities but would require careful calibration to avoid replicating bias.
| S-EPMC10570890 | biostudies-literature