Objectives To assess fairness and bias of a previously validated machine learning opioid misuse classifier. Materials & Methods Two experiments were conducted with the classifier’s original (n = 1000) and external validation (n = 53 974) datasets from 2 health systems. Bias was assessed via testing for differences in type II error rates across racial/ethnic subgroups (Black, Hispanic/Latinx, White, Other) using bootstrapped 95% confidence intervals. A local surrogate model was estimated to interpret the classifier’s predictions by race and averaged globally from the datasets. Subgroup analyses and post-hoc recalibrations were conducted to attempt to mitigate biased metrics. Results We identified bias in the false negative rate (FNR = 0.32) of the Black subgroup compared to the FNR (0.17) of the White subgroup. Top features included “heroin” and “substance abuse” across subgroups. Post-hoc recalibrations eliminated bias in FNR with minimal changes in other subgroup error metrics. The Black FNR subgroup had higher risk scores for readmission and mortality than the White FNR subgroup, and a higher mortality risk score than the Black true positive subgroup (P < .05). Discussion The Black FNR subgroup had the greatest severity of disease and risk for poor outcomes. Similar features were present between subgroups for predicting opioid misuse, but inequities were present. Post-hoc mitigation techniques mitigated bias in type II error rate without creating substantial type I error rates. From model design through deployment, bias and data disadvantages should be systematically addressed. Conclusion Standardized, transparent bias assessments are needed to improve trustworthiness in clinical machine learning models.
Background Unhealthy alcohol use (UAU) is known to disrupt pulmonary immune mechanisms and increase the risk of acute respiratory distress syndrome in patients with pneumonia; however, little is known about the effects of UAU on outcomes in patients with COVID-19 pneumonia. To our knowledge, this is the first observational cross-sectional study that aims to understand the effect of UAU on the severity of COVID-19. Objective We aim to determine if UAU is associated with more severe clinical presentation and worse health outcomes related to COVID-19 and if socioeconomic status, smoking, age, BMI, race/ethnicity, and pattern of alcohol use modify the risk. Methods In this observational cross-sectional study that took place between January 1, 2020, and December 31, 2020, we ran a digital machine learning classifier on the electronic health record of patients who tested positive for SARS-CoV-2 via nasopharyngeal swab or had two COVID-19 International Classification of Disease, 10th Revision (ICD-10) codes to identify patients with UAU. After controlling for age, sex, ethnicity, BMI, smoking status, insurance status, and presence of ICD-10 codes for cancer, cardiovascular disease, and diabetes, we then performed a multivariable regression to examine the relationship between UAU and COVID-19 severity as measured by hospital care level (ie, emergency department admission, emergency department admission with ventilator, or death). We used a predefined cutoff with optimal sensitivity and specificity on the digital classifier to compare disease severity in patients with and without UAU. Models were adjusted for age, sex, race/ethnicity, BMI, smoking status, and insurance status. Results Each incremental increase in the predicted probability from the digital alcohol classifier was associated with a greater odds risk for more severe COVID-19 disease (odds ratio 1.15, 95% CI 1.10-1.20). We found that patients in the unhealthy alcohol group had a greater odds risk to develop more severe disease (odds ratio 1.89, 95% CI 1.17-3.06), suggesting that UAU was associated with an 89% increase in the odds of being in a higher severity category. Conclusions In patients infected with SARS-CoV-2, UAU is an independent risk factor associated with greater disease severity and/or death.
We report on an indirect and non-invasive method to simultaneously characterise the energydependent emittance and source size of ultra-relativistic positron beams generated during the propagation of a laser-wakefield accelerated electron beam through a high-Z converter target. The strong correlation of the geometrical emittance of the positrons with that of the scattered electrons allows the former to be inferred, with high accuracy, from monitoring the latter. The technique has been tested in a proof-of-principle experiment where, for 100 MeV positrons, we infer geometrical emittances and source sizes of the order of e + ≈ 3 µm and D e + ≈ 150 µm, respectively. This is consistent with the numerically predicted possibility of achieving sub-µm geometrical emittances and micron-scale source sizes at the GeV level.
Background and Aim There is no gold‐standard and considerable heterogeneity in outcome measures used to evaluate treatments for opioid use disorder (OUD) along the opioid treatment cascade. The aim of this study was to develop the US National Institute on Drug Abuse (NIDA) National Drug Abuse Treatment Clinical Trials Network (CTN) opioid use disorder core outcomes set (OUD–COS). Design Four‐round, e‐Delphi expert panel consensus study and plenary research group discussion and targeted consultation. Setting United States. Participants A panel of 25 members including clinical practitioners, clinical researchers and administrative staff from the CTN, the network's affiliated clinical and community sites and the NIDA Centre for the CTN. Measurements From a pool of 24 candidate items in four domains (biomedical/disease status; behaviors, symptoms and functioning; opioid treatment cascade; and morbidity and mortality), the panel completed an on‐line questionnaire to rank items with defined specification on a 9‐point scale for importance, with a standard 70% consensus criterion. Findings After the fourth round of the questionnaire and subsequent discussion, consensus was reached for five outcomes: two patient‐reported (global impression of improvement and incident non‐fatal overdose); one clinician‐reported (illicit/non‐medical drug toxicology); and two from administrative records (duration of treatment and fatal opioid poisoning). Conclusions An e‐Delphi consensus study has produced the US National Institute on Drug Abuse (NIDA) National Drug Abuse Treatment Clinical Trials Network opioid use disorder core outcomes set (version 1) for opioid use disorder treatment efficacy and effectiveness research.
BACKGROUND Unhealthy alcohol use (UAU) is known to disrupt pulmonary immune mechanisms and increase the risk of acute respiratory distress syndrome in patients with pneumonia; however, little is known about the effects of UAU on outcomes in patients with COVID-19 pneumonia. To our knowledge, this is the first observational cross-sectional study that aims to understand the effect of UAU on the severity of COVID-19 disease. OBJECTIVE We aim to determine if UAU is associated with more severe clinical presentation and worse health outcomes related to COVID-19 and if socioeconomic status, smoking, age, body mass index (BMI), race/ethnicity, and pattern of alcohol use modify the risk. METHODS In this observational cross-sectional study, we ran a digital machine learning classifier on the electronic health record of patients who tested positive via nasopharyngeal swab for SARS-CoV-2 or had two COVID-19 international classification of disease codes to identify patients with UAU. We then performed a multivariable regression to examine the relationship between UAU and COVID-19 severity as measured by hospital care level, i.e. emergency department admission, emergency department admission with ventilator, or death. We used a predefined cutoff of 0.15 (optimal sensitivity and specificity) on the digital classifier to compare disease severity in patients with versus without UAU. Models were adjusted for age, sex, race/ethnicity, BMI, smoking status, and insurance status. RESULTS Each incremental increase in the predicted probability from the digital alcohol classifier was associated with a greater odds risk for more severe COVID-19 disease(OR 1.15, 95% CI: 1.10 - 1.20). Using the predefined cut-off of 0.15 to group patients into binary unhealthy alcohol group or not, we found that the unhealthy alcohol group had a greater odds risk to develop more severe disease (OR = 1.89, 95% CI: 1.17 - 3.06), suggesting that alcohol positive classification was associated with a 89% increase in the odds of being in a higher severity category. CONCLUSIONS In patients infected with SARS-CoV-2, UAU is an independent risk factor associated with greater disease severity and/or death.
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.
customersupport@researchsolutions.com
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.