Background: Systemic thrombolysis (ST) may not be ideal for many patients with acute pulmonary embolism (PE) due to bleeding risk. In this analysis, we evaluated the safety and effectiveness of mechanical thrombectomy (MT) as an alternative to ST for acute PE. Methods: Patients aged ≥18 years who underwent MT and/or ST for PE were identified from the National Inpatient Sample database from 2016 to 2017. Patients who underwent catheter-directed thrombolysis were excluded. We compared in-hospital outcomes of both groups in this retrospective study. Results: Of 16 890 patients who received an intervention for acute PE, 1380 (8.2%) received MT and 15 510 (91.8%) received ST. There was no difference in age between both groups. In-hospital mortality was significantly lower in patients who received MT than that in those who received ST (11.9% vs 20.6%, odds ratio [OR]: 0.52, 95% confidence interval [CI]: 0.29–0.93, p=0.028). There was no statistically significant difference in terms of periprocedural bleeding, intracranial hemorrhage, and acute kidney injury between the 2 groups (p≥0.608 for all). Patients who received MT had a higher rate of respiratory complications (19.0% vs 11.6%, OR: 1.79, 95% CI: 1.06–3.03, p=0.030) and discharge to an outside facility (34.1% vs 19.2%, OR: 2.18, 95% CI: 1.41–3.37, p<0.001) than those who received ST. Conclusion: Mortality was significantly lower with MT than that with ST, but larger randomized studies are needed to validate this. The use of MT should be individualized on the basis of the patients’ clinical presentation, risk profile, and local resources. Clinical Impact In this study, we utilized the National Inpatient Sample database to study the in-hospital outcomes of pulmonary embolism patients who underwent mechanical thrombectomy compared to those who underwent systemic thrombolysis. We found that the patients who were diagnosed with pulmonary embolism and underwent mechanical thrombectomy had significantly lower mortality compared to those who were treated using systemic thrombolysis. This study was the first of its kind, utilizing the national inpatient sample database for evaluation of mechanical thrombectomy in comparison with the standard of care. These result would direct further randomized controlled trials for better evaluation of the utilization of mechanical thrombectomy in the correct clinical context. Furthermore, our study demonstrated comparable peri-operative complications between the mechanical thrombectomy group and the systemic thrombolysis group. These results would direct clinicians to consider mechanical thrombectomy if clinically indicated given the promising results.
Chronic obstructive pulmonary disease (COPD) is the third leading cause of death in the United States. It is prevalent in 15 million in the USA alone, and one out of 10 people are affected worldwide. It has negative effects on patient's quality of life and impacts many healthcare systems around the United States.[1-4] COPD accounts for an annual direct cost of $50 billion, with $13.2 billion relating to hospitalizations. Unfortunately, one out of 5 patients admitted for COPD, have a 30-day readmission. 30day hospital readmission rates have been used as a metric to evaluate the quality of care provided by hospitals across the country and have subsequently been used to determine reimbursement.[5] Risk prediction models have been developed to help identify patients at high risk of readmission with goals to reduce hospital readmissions and healthcare costs. Results with these various models have varied. Machine learning models using artificial intelligence (AI) have also been developed to predict hospital readmissions. A commercially available AI/ machine learning product was deployed through the electronic health record to predict risk of readmission. The aim of this study was to assess the accuracy of artificial intelligence in predicting which patients are at high risk for readmission at 30 days and comparing it with a validated prediction tool, the LACE index for patients admitted with COPD.METHODS: Data was collected retrospectively on patients 18 years or older with a primary diagnosis of COPD who were discharged from a tertiary care center from 11/26/2018 to 02/01/2020. We evaluated the effectiveness and accuracy of the proprietary AI product to identify patients at high risk for hospital readmission. This was compared with the risk predictions made by the LACE Index. The primary evaluated outcome was all-cause readmissions for COPD within 30-days from the index hospitalization. The statistical method for comparison was logistic regression with LACE score as a single predictor. Sensitivities were compared after choosing a threshold that most closely matched the proprietary AI product specificity.
RESULTS:After matching for specificity, the proprietary AI product had a greater sensitivity (27.0%) as compared to LACE Index score (9.5%) in detecting all-cause readmissions for COPD.CONCLUSIONS: This study concludes that proprietary AI product is a more useful predictor of readmission rates for COPD as compared to prior conventional prediction tools, specifically the LACE index score. Models using AI should be implicated in clinical settings to predict readmission rates for medical conditions like COPD. We recommend that future studies should be performed to include AI models in everyday practice.CLINICAL IMPLICATIONS: Models using AI should be implicated in clinical settings to predict readmission rates for medical conditions like COPD as they are superior to prior conventional prediction tools.
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.