Meta-analysis and machine learning-augmented mixed effects cohort analysis of improved diets among 5847 medical trainees, providers and patients

Abstract

Abstract Objective: We sought to produce the first meta-analysis (of medical trainee competency improvement in nutrition counseling) informing the first cohort study of patient diet improvement through medical trainees and providers counseling patients on nutrition. Design: (Part A) A systematic review and meta-analysis informing (Part B) the intervention analysed in the world’s largest prospective multi-centre cohort study on hands-on cooking and nutrition education for medical trainees, providers and patients. Settings: (A) Medical educational institutions. (B) Teaching kitchens. Participants: (A) Medical trainees. (B) Trainees, providers and patients. Results: (A) Of the 212 citations identified (n 1698 trainees), eleven studies met inclusion criteria. The overall effect size was 9·80 (95 % CI (7·15, 12·45) and 95 % CI (6·87, 13·85); P < 0·001), comparable with the machine learning (ML)-augmented results. The number needed to treat for the top performing high-quality study was 12. (B) The hands-on cooking and nutrition education curriculum from the top performing study were applied for medical trainees and providers who subsequently taught patients in the same curriculum (n 5847). The intervention compared with standard medical care and education alone significantly increased the odds of superior diets (high/medium v. low Mediterranean diet adherence) for residents/fellows most (OR 10·79, 95 % CI (4·94, 23·58); P < 0·001) followed by students (OR 9·62, 95 % CI (5·92, 15·63); P < 0·001), providers (OR 5·19, 95 % CI (3·23, 8·32), P < 0·001) and patients (OR 2·48, 95 % CI (1·38, 4·45); P = 0·002), results consistent with those from ML. Conclusions: The current study suggests that medical trainees and providers can improve patients’ diets with nutrition counseling in a manner that is clinically and cost effective and may simultaneously advance societal equity.