Machine Learning-Augmented Propensity Score-Adjusted Multilevel Mixed Effects Panel Analysis of Hands-On Cooking and Nutrition Education versus Traditional Curriculum for Medical Students as Preventive Cardiology: Multisite Cohort Study of 3,248 Trainees over 5 Years.

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.

The effects of zinc supplementation on serum zinc and cholesterol concentrations in hemodialysis patients.

OBJECTIVE: To examine the effect of zinc sulfate supplementation on the concentrations of serum zinc and serum cholesterol in hemodialysis (HD) patients. SETTING: Outpatient dialysis center in a large metropolitan city. DESIGN: Randomized, double-blind, before-after trial. PATIENTS: Twenty-eight maintenance HD patients were selected. Twenty (15 women and 5 men) completed the study. Subjects were identified for inclusion in the study by the following criteria: HD treatment for a minimum of 6 months, no signs of gastrointestinal disorders, and no record of hospitalizations for reasons other than vascular access complications within the last 3 months. INTERVENTIONS: Patients were given a daily supplement of 7.7 micromol zinc sulfate (50 mg elemental zinc) or a cornstarch placebo capsule for 90 days. Patients completed 2-day food records, at day 0 and day 90 of the study, which included 1 dialysis day and 1 nondialysis day. MAIN OUTCOME MEASURE: Fasting, predialysis serum samples were collected on days 0, 40, and 90 to determine serum zinc and total cholesterol (TCHOL) concentrations. Dietary parameters, including zinc, protein, and energy intake, were also analyzed on days 0 and 90. RESULTS: Initial concentrations of serum zinc indicated subjects were below the normal range for serum zinc standards (12 micromol/L [80 microg/dL]). After supplementation, subjects in the zinc-supplemented group showed significant increases in serum zinc concentrations from 0.79 microg/mL at day 0 to 0.96 microg/mL at day 90. Serum TCHOL concentrations were initially low among subjects in the control (2.914 +/- 0.158 mmol/L [112.7 +/- 6.1 mg/dL]) and zinc-supplemented (3.155 +/- 0.354 mmol/L [122.0 +/- 13.7 mg/dL]) groups. Serum TCHOL concentrations in the control group increased slightly throughout the study period but did not reach statistical significance. A progressive increase in serum TCHOL concentration was observed in the zinc-supplemented group from the beginning (3.155 +/- 0.354 mmol/L [122.0 +/- 13.7 mg/dL]) to the end (4.445 +/- 0.478 mmol/L [171.9 +/- 18.5 mg/dL]) of the study (r =.63, P <.05). Mean serum high-density lipoprotein (HDL) cholesterol concentrations for the zinc-supplemented group were 0.959 mmol/L +/- 0.11 (37.1 mg/dL +/- 4.3), 0.825 mmol/L +/- 0.08 (31.9 mg/dL +/- 3.2), and 0.908 mmol/L +/- 0.10 (35.1 mg/dL +/- 3.9) from the beginning to the end of the experimental period. The mean serum HDL cholesterol concentrations for the control group were 0.760 mmol/L +/- 0.075 (29.4 mg/dL +/- 2.9), 0.760 +/- 0.08 (29.4 mg/dL +/- 3.0), and 0.799 mmol/L +/- 0.13 (30.9 mg/dL +/- 4.9) from the beginning to the end of the experimental period. A progressive increase in low-density lipoprotein (LDL) cholesterol concentration was observed for the zinc-supplemented group throughout the study. Mean LDL cholesterol concentrations for the zinc-supplemented group were 2.19 mmol/L +/- 0.39 (85 mg/dL +/- 15.0), 3.30 mmol/L +/- 0.36 (127.8 mg/dL +/- 14.1), and 3.53 mmol/L +/- 0.53 (136.7 mg/dL +/- 20.6) from the beginning to the end of the study period. When serum zinc concentration was correlated with serum LDL cholesterol concentration, a significant correlation was found (r =.62, P <.03) for the zinc-supplemented group and no significant difference was found for the control group. No significant differences in LDL cholesterol concentrations were found within the control group from the beginning to the end of the study. Dietary intake of zinc, cholesterol, total fat, and saturated fat remained constant and did not statistically influence serum values. Reported energy intake increased significantly in the zinc-supplemented group from 5,799 kJ/24 h (1,385 kcal/d) at day 0 to 7,042 kJ/24 h (1,682 kcal/d) at day 90. CONCLUSION: Zinc supplementation is an effective means of improving serum levels of zinc and cholesterol in the HD patient.