Artificial Intelligence Applications to Personalized Dietary Recommendations: A Systematic Review

Background/Objectives: Personalized dietary recommendations are essential for managing chronic conditions such as diabetes and irritable bowel syndrome (IBS). However, traditional approaches often fall short in accounting for individual metabolic variability. This systematic review evaluates the effectiveness of artificial intelligence (AI)-generated dietary interventions in improving clinical outcomes among adults. Methods: Following PRISMA guidelines, we searched six electronic databases for peer-reviewed studies published between 19 November 2015 to 6 September 2024. Eligible studies included adults aged 18 to 91 who received AI-generated dietary recommendations based on biomarkers such as blood glucose, gut microbiome composition, and self-reported data. Study designs included randomized controlled trials (RCTs), pre-post studies, and cross-sectional analyses. The GRADE system was used to assess the quality of evidence. Results: Eleven studies met inclusion criteria (five RCTs, five pre-post designs, one cross-sectional). Most AI methods used in the included studies were based on machine learning (ML), including conventional ML algorithms, deep learning (DL), and hybrid approaches integrating ML with IoT-based systems. Interventions led to improved glycemic control, metabolic health, and psychological well-being. Notable outcomes included a 39% reduction in IBS symptom severity and a 72.7% diabetes remission rate. Among nine studies with comparison groups, six reported statistically significant improvements in AI groups, two found comparable or better outcomes, and one found no difference. Mild side effects such as fatigue and constipation were observed. Conclusions: AI-generated dietary interventions show promise in surpassing traditional approaches by providing personalized, data-driven recommendations. Further research is needed to validate long-term effects, refine intervention protocols, and enhance user adherence in both clinical and public health settings.