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.

Biological variation in A1c is a robust quantitative trait that can be assessed using HGI calculated from routine clinic data. This suggests that HGI could be used clinically for more personalized assessment of complications risk.

Respiratory syncytial virus (RSV) infects small foci of respiratory epithelial cells via infected droplets. Infection induces expression of type I and III interferons (IFNs) and proinflammatory cytokines, the balance of which may restrict viral replication and affect disease severity. We explored this balance by infecting two respiratory epithelial cell lines with low doses of recombinant RSV expressing green fluorescent protein (rgRSV). A549 cells were highly permissive, whereas BEAS-2B cells restricted infection to individual cells or small foci. After infection, A549 cells expressed higher levels of IFN-β-, IFN-λ-, and NF-κB-inducible proinflammatory cytokines. In contrast, BEAS-2B cells expressed higher levels of antiviral interferon-stimulated genes, pattern recognition receptors, and other signaling intermediaries constitutively and after infection. Transcriptome analysis revealed that constitutive expression of antiviral and proinflammatory genes predicted responses by each cell line. These two cell lines provide a model for elucidating critical mediators of local control of viral infection in respiratory epithelial cells. Airway epithelium is both the primary target of and the first defense against respiratory syncytial virus (RSV). Whether RSV replicates and spreads to adjacent epithelial cells depends on the quality of their innate immune responses. A549 and BEAS-2B are alveolar and bronchial epithelial cell lines, respectively, that are often used to study RSV infection. We show that A549 cells are permissive to RSV infection and express genes characteristic of a proinflammatory response. In contrast, BEAS-2B cells restrict infection and express genes characteristic of an antiviral response associated with expression of type I and III interferons. Transcriptome analysis of constitutive gene expression revealed patterns that may predict the response of each cell line to infection. This study suggests that restrictive and permissive cell lines may provide a model for identifying critical mediators of local control of infection and stresses the importance of the constitutive antiviral state for the response to viral challenge.

Whether respiratory syncytial virus (RSV) induces severe infantile pulmonary disease may depend on viral strain and expression of types I and III interferons (IFNs). These IFNs impact disease severity by inducing expression of many anti-viral IFN-stimulated genes (ISGs). To investigate the impact of RSV strain on IFN and ISG expression, we stimulated human monocyte-derived DCs (MDDCs) with either RSV A2 or Line 19 and measured expression of types I and III IFNs and ISGs. At 24h, A2 elicited higher ISG expression than Line 19. Both strains induced MDDCs to express genes for IFN-β, IFN-α1, IFN-α8, and IFN-λ1–3, but only A2 induced IFN-α2, -α14 and -α21. We then show that IFN-α8 and IFN-α14 most potently induced MDDCs and bronchial epithelial cells (BECs) to express ISGs. Our findings demonstrate that RSV strain may impact patterns of types I and III IFN expression and the magnitude of the ISG response by DCs and BECs.