Safety and Efficacy of Reduced-Dose Versus Full-Dose Alteplase for Acute Pulmonary Embolism: A Multicenter Observational Comparative Effectiveness Study

OBJECTIVES

Systemic thrombolysis improves outcomes in patients with pulmonary embolism (PE) but is associated with the risk of hemorrhage. The data on efficacy and safety of reduced-dose alteplase are limited. The study objective was to compare the characteristics, outcomes, and complications of patients with PE treated with full- or reduced-dose alteplase regimens.

DESIGN

Multicenter retrospective observational study.

SETTING

Tertiary care hospital and 15 community and academic centers of a large healthcare system.

PATIENTS

Hospitalized patients with PE treated with systemic alteplase.

INTERVENTIONS

None.

MEASUREMENTS AND MAIN RESULTS

Pre- and post-alteplase hemodynamic and respiratory variables, patient outcomes, and complications were compared. Propensity score (PS) weighting was used to adjust for imbalances of baseline characteristics between reduced- and full-dose patients. Separate analyses were performed using the unweighted and weighted cohorts. Ninety-eight patients were treated with full-dose (100 mg) and 186 with reduced-dose (50 mg) regimens. Following alteplase, significant improvements in shock index, blood pressure, heart rate, respiratory rate, and supplemental oxygen requirements were observed in both groups. Hemorrhagic complications were lower with the reduced-dose compared with the full-dose regimen (13% vs. 24.5%, p = 0.014), and most were minor. Major extracranial hemorrhage occurred in 1.1% versus 6.1%, respectively ( p = 0.022). Complications were associated with supratherapeutic levels of heparin anticoagulation in 37.5% of cases and invasive procedures in 31.3% of cases. The differences in complications persisted after PS weighting (15.4% vs. 24.7%, p = 0.12 and 1.3% vs. 7.1%, p = 0.067), but did not reach statistical significance. There were no significant differences in mortality, discharge destination, ICU or hospital length of stay, or readmission after PS weighting.

CONCLUSIONS

In a retrospective, PS-weighted observational study, when compared with the full-dose, reduced-dose alteplase results in similar outcomes but fewer hemorrhagic complications. Avoidance of excessive levels of anticoagulation or invasive procedures should be considered to further reduce complications.

Machine Learning for Automated Classification of Abnormal Lung Sounds Obtained from Public Databases: A Systematic Review

Pulmonary auscultation is essential for detecting abnormal lung sounds during physical assessments, but its reliability depends on the operator. Machine learning (ML) models offer an alternative by automatically classifying lung sounds. ML models require substantial data, and public databases aim to address this limitation. This systematic review compares characteristics, diagnostic accuracy, concerns, and data sources of existing models in the literature. Papers published from five major databases between 1990 and 2022 were assessed. Quality assessment was accomplished with a modified QUADAS-2 tool. The review encompassed 62 studies utilizing ML models and public-access databases for lung sound classification. Artificial neural networks (ANN) and support vector machines (SVM) were frequently employed in the ML classifiers. The accuracy ranged from 49.43% to 100% for discriminating abnormal sound types and 69.40% to 99.62% for disease class classification. Seventeen public databases were identified, with the ICBHI 2017 database being the most used (66%). The majority of studies exhibited a high risk of bias and concerns related to patient selection and reference standards. Summarizing, ML models can effectively classify abnormal lung sounds using publicly available data sources. Nevertheless, inconsistent reporting and methodologies pose limitations to advancing the field, and therefore, public databases should adhere to standardized recording and labeling procedures.