Background Machine learning has been used extensively in clinical text classification tasks. Deep learning approaches using word embeddings have been recently gaining momentum in biomedical applications. In an effort to automate the identification of altered mental status (AMS) in emergency department provider notes for the purpose of decision support, we compare the performance of classic bag-of-words-based machine learning classifiers and novel deep learning approaches. Methods We used a case-control study design to extract an adequate number of clinical notes with AMS and non-AMS based on ICD codes. The notes were parsed to extract the history of present illness, which was used as the clinical text for the classifiers. The notes were manually labeled by clinicians. As a baseline for comparison, we tested several traditional bag-of-words based classifiers. We then tested several deep learning models using a convolutional neural network architecture with three different types of word embeddings, a pre-trained word2vec model and two models without pre-training but with different word embedding dimensions. Results We evaluated the models on 1130 labeled notes from the emergency department. The deep learning models had the best overall performance with an area under the ROC curve of 98.5% and an accuracy of 94.5%. Pre-training word embeddings on the unlabeled corpus reduced training iterations and had performance that was statistically no different than the other deep learning models. Conclusion This supervised deep learning approach performs exceedingly well for the detection of AMS symptoms in clinical text in our environment. Further work is needed for the generalizability of these findings, including evaluation of these models in other types of clinical notes and other environments. The results seem promising for the ultimate use of these types of classifiers in combination with other information derived from the electronic health records as input for clinical decision support. Electronic supplementary material The online version of this article (10.1186/s12911-019-0894-9) contains supplementary material, which is available to authorized users.
Objective The HEART Pathway is an evidence-based decision tool for identifying emergency department (ED) patients with acute chest pain who are candidates for early discharge, to reduce unhelpful and potentially harmful hospitalizations. Guided by the Consolidated Framework for Implementation Research (CFIR), we sought to identify important barriers and facilitators to implementation of the HEART Pathway. Study Setting Data were collected at 4 academic medical centers. Study Design We conducted semi-structured interviews with 25 key stakeholders (e.g., health system leaders, ED physicians). We conducted interviews before implementation of the HEART Pathway tool to identify potential barriers and facilitators to successful adoption at other regional academic medical centers. We also conducted post-implementation interviews at one medical center, to understand factors that contributed to successful adoption. Data Collection Interviews were recorded and transcribed verbatim. We used a CFIR framework-driven deductive approach for coding and analysis. Principal Findings Potential barriers to implementation include time and resource burden, challenges specific to the electronic health record (EHR), sustained communication with and engagement of stakeholders, and patient concerns. Facilitators to implementation include strength of evidence for reduced length of stay and unnecessary testing and iatrogenic complications, ease of use, and supportive provider climate for evidence-based decision tools. Conclusions Successful dissemination of the HEART Pathway will require addressing institution-specific barriers, which includes engaging clinical and financial stakeholders. New SMART-FHIR technologies, compatible with many EHR systems, can overcome barriers to health systems with limited information technology resources.
A cute chest pain (ACP) is one of the most common reasons for presentation to the emergency department (ED). However, the differential diagnosis of ACP and the need to exclude significant coronary artery disease (CAD) as the cause of symptoms creates a complex scenario for the ED physician (1). Triple-rule-out CT angiography allows for simultaneous assessment of the coronary arteries, aorta, and pulmonary arteries in a single diagnostic test. This approach is most appropriate for patients with a low to intermediate risk of acute coronary syndrome and symptoms that may also be attributed to pulmonary embolism or aortic dissection (2,3). Since its early description (4), several studies have demonstrated good diagnostic accuracy of triple-rule-out CT angiography for evaluation of CAD (5-7). In general, the use of cardiac CT in the setting of ACP has been shown to enhance the effectiveness of evaluation in the ED (8-10), although some researchers have argued that the rate of downstream testing and overall radiation exposure may increase (11).Advances in computational fluid dynamics and patientspecific three-dimensional image modeling allow for the noninvasive calculation of fractional flow reserve (FFR) derived from coronary CT angiography (CT FFR) data sets (12)(13)(14). CT FFR based on these physical principles has shown high diagnostic accuracy in the assessment of hemodynamic significance of individual coronary lesions and improved patient outcomes when basing further treatment on functional as opposed to anatomic data (13,(15)(16)(17)(18). Other approaches for CT FFR derivation use investigational artificial intelligence (AI) deep machine learning algorithm software ( 19), which has previously demonstrated good accuracy as well as potential time efficiency for patient management in an elective setting (19)(20)(21)(22). This AIbased algorithm uses learned relationships to compute the This copy is for personal use only. To order printed copies, contact
IntroductionIn the USA, many emergency departments (EDs) have established protocols to treat patients with newly diagnosed deep vein thrombosis (DVT) as outpatients. Similar treatment of patients with pulmonary embolism (PE) has been proposed, but no large-scale study has been published to evaluate a comprehensive, integrated protocol that employs monotherapy anticoagulation to treat patients diagnosed with DVT and PE in the ED.Methods and analysisThis protocol describes the implementation of the Monotherapy Anticoagulation To expedite Home treatment of Venous ThromboEmbolism (MATH-VTE) study at 33 hospitals in the USA. The study was designed and executed to meet the requirements for the Standards for Reporting Implementation Studies guideline. The study was funded by investigator-initiated awards from industry, with Indiana University as the sponsor. The study principal investigator and study associates travelled to each site to provide on-site training. The protocol identically screens patients with both DVT or PE to determine low risk of death using either the modified Hestia criteria or physician judgement plus a negative result from the simplified PE severity index. Patients must be discharged from the ED within 24 hours of triage and treated with either apixaban or rivaroxaban. Overall effectiveness is based upon the primary efficacy and safety outcomes of recurrent VTE and bleeding requiring hospitalisation respectively. Target enrolment of 1300 patients was estimated with efficacy success defined as the upper limit of the 95% CI for the 30-day frequency of VTE recurrence below 2.0%. Thirty-three hospitals in 17 states were initiated in 2016–2017.Ethics and disseminationAll sites had Institutional Review Board approval. We anticipate completion of enrolment in June 2020; study data will be available after peer-reviewed publication. MATH-VTE will provide information from a large multicentre sample of US patients about the efficacy and safety of home treatment of VTE with monotherapy anticoagulation.
BACKGROUND: The objective was to test if low-risk emergency department patients with vitamin K antagonist (venous thromboembolism [VTE]; including venous thrombosis and pulmonary embolism [PE]) can be safely and effectively treated at home with direct acting oral (monotherapy) anticoagulation in a large-scale, real-world pragmatic effectiveness trial. METHODS: This was a single-arm trial, conducted from 2016 to 2019 in accordance with the Standards for Reporting Implementation Studies guideline in 33 emergency departments in the United States. Participants had newly diagnosed VTE with low risk of death based upon either the modified Hestia criteria, or physician judgment plus the simplified PE severity index score of zero, together with nonhigh bleeding risk were eligible. Patients had to be discharged within 24 hours of triage and treated with either apixaban or rivaroxaban. Effectiveness was defined by the primary efficacy and safety outcomes, image-proven recurrent VTE and bleeding requiring hospitalization >24 hours, respectively, with an upper limit of the 95% CI for the 30-day frequency of VTE recurrence below 2.0% for both outcomes. RESULTS: We enrolled 1421 patients with complete outcomes data, including 903 with venous thrombosis and 518 with PE. The recurrent VTE requiring hospitalization occurred in 14/1421 (1.0% [95% CI, 0.5%–1.7%]), and bleeding requiring hospitalization occurred in 12/1421 (0.8% [0.4%–1.5%). The rate of severe bleeding using International Society for Thrombosis and Haemostasis criteria was 2/1421 (0.1% [0%–0.5%]). No patient died, and serious adverse events occurred in 2.5% of venous thrombosis patients and 2.3% of patients with PE. Medication nonadherence was reported by patients in 8.0% (6.6%–9.5%) and was associated with a risk ratio of 6.0 (2.3–15.2) for VTE recurrence. Among all patients diagnosed with VTE in the emergency department during the period of study, 18% of venous thrombosis patients and 10% of patients with PE were enrolled. CONCLUSIONS: Monotherapy treatment of low-risk patients with venous thrombosis or PE in the emergency department setting produced a low rate of bleeding and VTE recurrence, but may be underused. Patients with venous thrombosis and PE should undergo risk-stratification before home treatment. Improved patient adherence may reduce rate of recurrent VTE. REGISTRATION: URL: https://www.clinicaltrials.gov ; Unique identifier: NCT03404635
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.