Development and Validation of a Natural Language Processing Model to Identify Low-Risk Pulmonary Embolism in Real Time to Facilitate Safe Outpatient Management.

STUDY OBJECTIVE: This study aimed to (1) develop and validate a natural language processing model to identify the presence of pulmonary embolism (PE) based on real-time radiology reports and (2) identify low-risk PE patients based on previously validated risk stratification scores using variables extracted from the electronic health record at the time of diagnosis. The combination of these approaches yielded an natural language processing-based clinical decision support tool that can identify patients presenting to the emergency department (ED) with low-risk PE as candidates for outpatient management. METHODS: Data were curated from all patients who received a PE-protocol computed tomography pulmonary angiogram (PE-CTPA) imaging study in the ED of a 3-hospital academic health system between June 1, 2018 and December 31, 2020 (n=12,183). The "preliminary" radiology reports from these imaging studies made available to ED clinicians at the time of diagnosis were adjudicated as positive or negative for PE by the clinical team. The reports were then divided into development, internal validation, and temporal validation cohorts in order to train, test, and validate an natural language processing model that could identify the presence of PE based on unstructured text. For risk stratification, patient- and encounter-level data elements were curated from the electronic health record and used to compute a real-time simplified pulmonary embolism severity (sPESI) score at the time of diagnosis. Chart abstraction was performed on all low-risk PE patients admitted for inpatient management. RESULTS: When applied to the internal validation and temporal validation cohorts, the natural language processing model identified the presence of PE from radiology reports with an area under the receiver operating characteristic curve of 0.99, sensitivity of 0.86 to 0.87, and specificity of 0.99. Across cohorts, 10.5% of PE-CTPA studies were positive for PE, of which 22.2% were classified as low-risk by the sPESI score. Of all low-risk PE patients, 74.3% were admitted for inpatient management. CONCLUSION: This study demonstrates that a natural language processing-based model utilizing real-time radiology reports can accurately identify patients with PE. Further, this model, used in combination with a validated risk stratification score (sPESI), provides a clinical decision support tool that accurately identifies patients in the ED with low-risk PE as candidates for outpatient management.

Paclitaxel-coated devices in the treatment of femoropopliteal stenosis among patients ≥65 years old: An ACC PVI Registry Analysis.

BACKGROUND: The connection between paclitaxel-coated devices (PCD) use during peripheral vascular interventions (PVI) and mortality is debated. We aimed to analyze patterns of PCD use and the safety and effectiveness of PCD use in the superficial femoral and/or popliteal arteries. METHODS: Patients undergoing PVI of femoropopliteal lesions with and without PCD between January 1, 2015 and June 30, 2017 were compared using the American College of Cardiology's National Cardiovascular Data Registry PVI Registry. Outcomes were derived from Centers for Medicare & Medicaid claims data. The primary outcome was all-cause mortality at 6-, 12-, and 24-months following PVI. Inverse probability weighting and frailty models were used to assess the differences between groups. The analysis was IRB-approved. RESULTS: In the overall cohort consisting of 6,302 femoropopliteal PVIs, PCD-PVI patients were more likely to be treated for claudication (63.5% vs 51.3%, P< .001), less likely to have a chronic total occlusion (24.6% vs 34.7%, P < .001), and more likely to be treated in certain geographic and practice settings. In the analytic cohort consisting of 1,666 femoropopliteal PVIs with linked claims outcomes (888 PCD-PVI, 53.3%), unadjusted rates of all outcomes were lower in PCD-PVI patients. After adjustment, there were no significant differences in mortality following PCD-PVI versus non-PCD PVI at 1 year (adjusted RR 0.78, 95% CI 0.60-1.01, P= .055) or 2 years (aRR 0.98, 95% CI 0.77-1.24, P= .844). CONCLUSION: There were significant differences between the patients in whom and settings in which PCD-PVI was versus was not used. PCD-PVI was not associated with an increased risk of 2-year mortality in real-world use.

The impact of chronic kidney disease on outcomes following peripheral vascular intervention.

BACKGROUND: Patients with chronic kidney disease (CKD) have worsened clinical outcomes following percutaneous coronary intervention; however, limited evidence exists in patients undergoing peripheral vascular intervention (PVI). PURPOSE: We aimed to assess the effect of CKD on outcomes following PVI for symptomatic peripheral artery disease. METHODS: Using patients from the LIBERTY 360 study, we compared the rates of 30 day and 1 year major adverse vascular events (MAVE), a composite of all-cause mortality, major amputation, and target vessel/lesion revascularization, between patients with and without CKD (estimated glomular filtration rate less than 60) following PVI. Multivariable adjustment was performed to assess for independent association between CKD and outcomes. RESULTS: Among 1189 patients enrolled, 378 patients (31.8%) had CKD. At 1 year, patients with CKD had higher rates of MAVE (34.6% vs 25.6%), all-cause mortality (11.9% vs 5.5%), and major amputation (5.9% vs 2.6%) when compared with patients without CKD (all P < .05). After adjustment, patients with CKD had higher risks of 1-year MAVE (HR 1.30, 95% CI 1.04-1.64; P = .023) and all-cause mortality (HR 1.88, 95% CI 1.22-2.91; P = .005) when compared with patients without CKD. There was no statistically significant difference in risk of major amputations (HR 1.70, 95% CI 0.91-3.17; P = .094). CONCLUSIONS: Despite high procedural success and low amputation rates, patients with CKD remain at greater risk for MAVE and all-cause mortality after PVI. Further research is needed to determine treatment strategies to mitigate substantial mortality risk in this vulnerable population.

Model-Based Algorithms for Detecting Peripheral Artery Disease Using Administrative Data From an Electronic Health Record Data System: Algorithm Development Study.

BACKGROUND: Peripheral artery disease (PAD) affects 8 to 10 million Americans, who face significantly elevated risks of both mortality and major limb events such as amputation. Unfortunately, PAD is relatively underdiagnosed, undertreated, and underresearched, leading to wide variations in treatment patterns and outcomes. Efforts to improve PAD care and outcomes have been hampered by persistent difficulties identifying patients with PAD for clinical and investigatory purposes. OBJECTIVE: The aim of this study is to develop and validate a model-based algorithm to detect patients with peripheral artery disease (PAD) using data from an electronic health record (EHR) system. METHODS: An initial query of the EHR in a large health system identified all patients with PAD-related diagnosis codes for any encounter during the study period. Clinical adjudication of PAD diagnosis was performed by chart review on a random subgroup. A binary logistic regression to predict PAD was built and validated using a least absolute shrinkage and selection operator (LASSO) approach in the adjudicated patients. The algorithm was then applied to the nonsampled records to further evaluate its performance. RESULTS: The initial EHR data query using 406 diagnostic codes yielded 15,406 patients. Overall, 2500 patients were randomly selected for ground truth PAD status adjudication. In the end, 108 code flags remained after removing rarely- and never-used codes. We entered these code flags plus administrative encounter, imaging, procedure, and specialist flags into a LASSO model. The area under the curve for this model was 0.862. CONCLUSIONS: The algorithm we constructed has two main advantages over other approaches to the identification of patients with PAD. First, it was derived from a broad population of patients with many different PAD manifestations and treatment pathways across a large health system. Second, our model does not rely on clinical notes and can be applied in situations in which only administrative billing data (eg, large administrative data sets) are available. A combination of diagnosis codes and administrative flags can accurately identify patients with PAD in large cohorts.

A Hybrid Approach to Radiation-Induced Axillary Artery Hemorrhage.

Axillary artery blowout is a rare life- and limb-threatening condition. The traditional surgical approach of ligation and extra-anatomic bypass is associated with a high morbidity and mortality. We present a case report of a 65-year-old male with axillary artery hemorrhage secondary to an irradiated squamous cell cancer. We propose a staged hybrid approach for the treatment of this unusual clinical entity consisting of emergent stent grafting followed by planned elective extra-anatomic bypass, debridement, and a course of specific antimicrobial therapy.