The purpose of this project was to determine if evidence-based practice change related to antibiotic administration criteria for outpatients receiving percutaneous nephrostomy tube exchanges implemented by a medical c...
详细信息
The purpose of this project was to determine if evidence-based practice change related to antibiotic administration criteria for outpatients receiving percutaneous nephrostomy tube exchanges implemented by a medical center's Vascular and Interventional Radiology department impacted hospital admission rates for infection in these patients. The 2017 practice change was based on 2010 guidelines from the Society of Interventional Radiology (SIR), stating that outpatients with a low risk of acquiring infection did not need to receive a perioperative antibiotic, as evidence has shown prophylactic therapy has no significant effect on infection rates for this population. Using a retrospective review design, 1 year of data before and after the practice change were collected and analyzed using the repeated measures generalized estimating equation (GEE) model with a binomial output by Liang & Zeger. Fisher's exact test was used to evaluate demographic variables by level of risk of infection. Data included 493 procedural events for 126 outpatients. The mean number of events per patient was 3.91 (SD: 4.15;median: 2;interquartile range: 3). Admission and infection criteria within thirty days of the event and infection risk factors were collected for each patient. Age, sex, and race were the variables that had a significant relationship with risk level of infection. Due to sample size, the GEE model could not be run using risk level (high/low) to predict admissions before or after the practice change. The relationship between the number of risk factors (0-5) and the odds of admission for infection was the same regardless of the practice change (before: odds ratio [OR] = 2.17, 95% confidence interval [CI] = 1.19-3.95;after: OR = 1.9, 95% CI = 1.12-3.22, pinteraction =. 67). For every increase in a patient's number of risk factors, the odds of developing an infection would be expected to increase by almost 90% (OR = 1.9, 95% CI = 1.27-2.84). Although it was not possible t
Objective: While machine learning (ML) includes a valuable array of tools for analyzing biomedical data with multivariate and complex underlying associations, significant time and expertise is required to assemble eff...
详细信息
Objective: While machine learning (ML) includes a valuable array of tools for analyzing biomedical data with multivariate and complex underlying associations, significant time and expertise is required to assemble effective, rigorous, comparable, reproducible, and unbiased pipelines. Automated ML (AutoML) tools seek to facilitate ML application by automating a subset of analysis pipeline elements. In this study we develop and validate a Simple, Transparent, End-to-end Automated Machine Learning Pipeline (STREAMLINE) and apply it to investigate the added utility of photography-based phenotypes for predicting obstructive sleep apnea (OSA);a common and underdiagnosed condition associated with a variety of health, economic, and safety consequences. Methods: STREAMLINE is designed to tackle biomedical binary classification tasks while (1) avoiding common mistakes, (2) accommodating complex associations and common data challenges, and (3) allowing scalability, reproducibility, and model interpretation. It automates the majority of established, generalizable, and reliably automatable aspects of an ML analysis pipeline while incorporating cutting edge algorithms and providing opportunities for human-in-the-loop customization. We present a broadly refactored and extended release of STREAMLINE, validating and benchmarking performance across simulated and real-world datasets. Then we applied STREAMLINE to evaluate the utility of demographics (DEM), self-reported comorbidities (DX), symptoms (SYM), and photography-based craniofacial (CF) and intraoral (IO) anatomy measures in predicting ‘any OSA’ or ‘moderate/severe OSA’ using 3,111 participants from Sleep Apnea Global Interdisciplinary Consortium (SAGIC). Results: Benchmarking analyses validated the efficacy of STREAMLINE across data simulations with increasingly complex patterns of association including epistatic interactions and genetic heterogeneity. OSA analyses identified a significant increase in ROC-AUC when adding CF t
暂无评论