Background Cardiovascular disease (CVD) annually claims more lives and costs more dollars than any other disease globally amid widening health disparities, despite the known significant reductions in this burden by low cost dietary changes. The world's first medical school-based teaching kitchen therefore launched CHOP-Medical Students as the largest known multisite cohort study of hands-on cooking and nutrition education versus traditional curriculum for medical students. Methods This analysis provides a novel integration of artificial intelligence-based machine learning (ML) with causal inference statistics. 43 ML automated algorithms were tested, with the top performer compared to triply robust propensity score-adjusted multilevel mixed effects regression panel analysis of longitudinal data. Inverse-variance weighted fixed effects meta-analysis pooled the individual estimates for competencies. Results 3,248 unique medical trainees met study criteria from 20 medical schools nationally from August 1, 2012, to June 26, 2017, generating 4,026 completed validated surveys. ML analysis produced similar results to the causal inference statistics based on root mean squared error and accuracy. Hands-on cooking and nutrition education compared to traditional medical school curriculum significantly improved student competencies (OR 2.14, 95% CI 2.00–2.28, p < 0.001) and MedDiet adherence (OR 1.40, 95% CI 1.07–1.84, p = 0.015), while reducing trainees' soft drink consumption (OR 0.56, 95% CI 0.37–0.85, p = 0.007). Overall improved competencies were demonstrated from the initial study site through the scale-up of the intervention to 10 sites nationally (p < 0.001). Discussion This study provides the first machine learning-augmented causal inference analysis of a multisite cohort showing hands-on cooking and nutrition education for medical trainees improves their competencies counseling patients on nutrition, while improving students' own diets. This study suggests that the public health and medical sectors can unite population health management and precision medicine for a sustainable model of next-generation health systems providing effective, equitable, accessible care beginning with reversing the CVD epidemic.
Background. Transesophageal echocardiogram (TEE) is superior to transthoracic echocardiogram (TTE) in detecting left atrial thrombus (LAT), a risk factor for stroke, but is costly and invasive, carrying a higher risk for complications. Aims. To determine the utility of using left atrial enlargement (LAE) on TTE to predict LAT on TEE. Methods. AIS patients who presented in 06/2008–7/2013 and underwent both TTE and TEE were identified from our prospective stroke registry. Analysis consisted of multivariate logistic regression with propensity score adjustment and receiver operating characteristic (ROC) area under the curve (AUC) analyses. Results. 219 AIS patients underwent both TTE and TEE. LAE on TTE was detected in 113 (51.6%) of AIS patients. Patients with LAE on TTE had higher proportion of LAT on TEE (8.4% versus 1.0%, p = 0.018). LAE on TTE predicted increased odds of LAT on TEE (OR = 8.83, 95% CI 1.04–74.83, p = 0.046). The sensitivity and specificity for LAT on TEE by LAE on TEE were 88.89% and 52.20%, respectively (AUC = 0.7054, 95% CI 0.5906–0.8202). Conclusions. LAE on TTE can predict LAT detected on TEE in nearly 90% of patients. This demonstrates the utility of LAE on TTE as a potential screening tool for LAT, potentially limiting unneeded costs and complications associated with TEE.
AimsComorbid anxiety and mood disorders occur in 30% and 60% of individuals post-ABI (acquired brain injury), respectively (Juengst et al, 2014). The presence of psychiatric symptoms correlate to poorer outcomes in post-stroke rehabilitation, worsened quality of life (QoL), and deficits in memory, attention, and processing speed that persists years following the index event. Despite this, it is unclear whether to what degree anxiety impacts cognition. Furthermore, the literature on this topic is inconsistent when comparing subjective and clinician measurements. This study seeks to ameliorate this gap in literature by analyzing how clinicians’ measures of anxiety and cognitive performance correlate with subjective assessments of patient's own anxiety symptoms.MethodIndividuals with an ABI who were seen in a clinical neuropsychiatry outpatient clinic between 2019 and 2020 completed a GAD-7 (Generalized Anxiety Disorder-7) questionnaire (patient's self-report of the severity of anxiety symptoms) and an observer completed a Neuropsychiatric Inventory Questionnaire (NPIQ) including a subscale for anxiety (NPIQ-A). Participants also underwent a formal cognitive examination with the Montreal Cognitive Assessment (MoCA). A total of 24 ABI patients (depressed ABI and non-depressed ABI) were analyzed for variation, statistical agreement and correlation. Here, total anxiety scores (using GAD-7 scores), anxiety severity (correlating category based on total GAD-7 score) were compared against the objective measures for anxiety (NPI-QA) and cognition (MoCA). In order to standardize MoCA scores, z scores were used in the statistical analysis.ResultThe patient's subjective raw scores of anxiety were statistically significantly different from the corresponding scores from objective observers on Wilcoxon-Rank Sum tests (p < 0.01), however, there was a statistical correlation between GAD (categorized by severity level) and NPI-QA (p = 0.75). Spearman Rank Correlation did show positive, but, statistically insignificant correlation between dyads of these independent variables (including GAD7/NPIQ-A, GAD 7 categorised/NPIQ-A, GAD7/MoCA, GAD 7 categorised/MoCA).ConclusionThese findings indicate (1) self-reported measures of anxiety (GAD7) in ABI were inconsistent with objective measures of anxiety in this cohort, (2) anxiety measures did not demonstrate significant correlation when compared to objective measures for cognitive function, and (3) ABI patients did not display good insight into the severity of their anxiety symptoms as measured by the GAD7. Further research should focus on utilizing other subjective measurement tools for anxiety and/or clinician evaluation tools with NPIQ-A.
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.