Predictive Algorithm for evaluating the efficacy of mushroom blends for optimizing Type 2 diabetes intervention (Preprint)

UNSTRUCTURED Natural sources such as herbs, nutraceuticals, and medicinal mushrooms are increasingly used to manage diseases and promote wellness by balancing metabolic, immune, and oxidative stress. Type 2 diabetes (T2D), characterized by metabolic dysregulation, is a key area where these natural interventions show significant promise. In this study, a predictive algorithm was developed and applied to assess the therapeutic potential of three specific mushrooms—Pleurotus citrinopileatus, Pleurotus sajor-caju, and Pleurotus ostreatus—in managing T2D biomarkers. The algorithm was first validated against existing literature, accurately predicting the effects of these mushroom combinations on key biomarkers, including fasting glucose, HbA1c, insulin, HOMA-IR, triglycerides, LDL/HDL ratio, and total cholesterol, with a maximum fold change difference of 0.5 between expected and predicted values.The algorithm also identified an optimal dosage that maximized biomarker improvement while considering cost efficiency. Simulated outcomes for the optimal combination (C19), comprising 50% P. ostreatus, 25% P. sajor-caju, and 25% P. citrinopileatus by net weight , indicated a 40% reduction in glucose levels, a 17% decrease in insulin levels, a 45% drop in triglyceride levels, and a 13% reduction in cholesterol levels within one month in a diabetic population. The formulation consistently normalized biomarker levels within three months. A case study using the C19 combination as an intervention further validated the algorithm, highlighting its accuracy and reliability through a close correlation with actual outcomes. By integrating literature data, case study validation, and cost analysis, this approach offers a robust framework for designing effective and economical interventions for T2D.