There are several methods for building prediction models. The wealth of currently available modeling techniques usually forces the researcher to judge, a priori, what will likely be the best method. Super learning (SL) is a methodology that facilitates this decision by combining all identified prediction algorithms pertinent for a particular prediction problem. SL generates a final model that is at least as good as any of the other models considered for predicting the outcome. The overarching aim of this work is to introduce SL to analysts and practitioners. This work compares the performance of logistic regression, penalized regression, random forests, deep learning neural networks, and SL to predict successful substance use disorders (SUD) treatment. A nationwide database including 99,013 SUD treatment patients was used. All algorithms were evaluated using the area under the receiver operating characteristic curve (AUC) in a test sample that was not included in the training sample used to fit the prediction models. AUC for the models ranged between 0.793 and 0.820. SL was superior to all but one of the algorithms compared. An explanation of SL steps is provided. SL is the first step in targeted learning, an analytic framework that yields double robust effect estimation and inference with fewer assumptions than the usual parametric methods. Different aspects of SL depending on the context, its function within the targeted learning framework, and the benefits of this methodology in the addiction field are discussed.
Post-acute sequelae of SARS-CoV-2 (PASC) is a poorly understood condition with significant impact on quality of life. We aimed to better understand the lived experiences of patients with PASC, focusing on the impact of cognitive complaints (“brain fog”) and fatigue on (1) daily activities, (2) work/employment, and (3) interpersonal relationships. We conducted semi-structured qualitative interviews with 15 patients of a Midwestern academic hospital’s post-COVID-19 clinic. We audio-recorded, transcribed, and analyzed interviews thematically using a combined deductive-inductive approach and collected participants’ characteristics from chart review. Participants frequently used descriptive and metaphorical language to describe symptoms that were relapsing-remitting and unpredictable. Fatigue and brain fog affected all domains and identified subthemes included symptoms’ synergistic effects, difficulty with multitasking, lack of support, poor self-perception, and fear of loss of income and employment. Personal relationships were affected with change of responsibilities, difficulty parenting, social isolation, and guilt due to the burdens placed on family. Furthermore, underlying social stigma contributed to negative emotions, which significantly affected emotional and mental health. Our findings highlight PASC’s negative impact on patients’ daily lives. Providers can better support COVID-19 survivors during their recovery by identifying their needs in a sensitive and timely manner.
Purpose The recent opioid crisis is characterized by a relatively greater increase in opioid use disorder and related mortality in rural populations when compared with urban populations.1‐5 As almost a quarter of our nation's veterans reside in rural settings, the United States Veterans Health Administration (VHA) is interested in the impact of this epidemic on rural veterans. This study aims to develop a comprehensive understanding of the trends in substance use disorders (SUD) in veterans seeking treatment from community, non‐VHA providers. Methods Using Substance Abuse and Mental Health Services Administration (SAMHSA)’s Treatment Episode Data Set (TEDS), this study presents the prevalence of treatment for veterans seeking initial admission into publicly funded non‐VHA SUD treatment centers for years 2011‐2016. Comparisons were made for all SUD types. Multivariate trend analysis based on annual data from 2011 to 2016 compared urban and rural veterans for opioid use disorder treatment. Findings Both urban and rural veterans had comparable rates of treatment for SUD, though rural veterans had slightly higher rates of injectable (11.2% vs 8.7%; P < .001) and opiate drug use disorder admissions (20.7% vs 18.1%; P = .014). Both urban and rural showed an increase in admissions for opioid, heroin, and injectable drug use disorders between 2011 and 2016 (P < .001). Conclusions Comprehensive understanding of veteran SUD and treatment should include national‐level data on community non‐VHA treatment. SAMHSA's TEDS for years 2011‐2016 provides clinical information for more than 90,000 veterans and indicates continued increase in treatment seeking for opioid use disorders, particularly for rural veterans.
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.