Leveraging AI-Driven Business Intelligence for Personalised Nutrition in FemTech: An Integrated Framework for Data-Driven Women's Health Innovation

Purpose: This study explores the integration of artificial intelligence-driven business intelligence (AI-BI) within FemTech platforms to enhance personalised nutritional interventions for women. It aims to identify the key predictors of improvement in wellness outcomes based on behavioural, physiological, and algorithmic variables. Design/methodology/approach: A quantitative research design was employed, involving a sample of 217 women using a FemTech platform over an eight-week intervention period. The dependent variable was the change in self-reported wellness score. Independent variables included hormonal phase alignment, engagement level (EL), nutritional consistency (NC), sleep quality index (SQI), and AI personalisation depth (AIPD). A multiple linear regression model was utilised to examine the relationship between these predictors and wellness improvement. Findings: The results indicate that the combined predictors explain 68% of the variance in wellness outcomes. Statistically significant variables included hormonal phase alignment (β = 1.45, p = 0.014), EL (β =0.32, p = 0.005), NC (β = 0.07, p = 0.001), sleep quality (β = 0.05, p < 0.001), and AIPD (β = 0.89, p = 0.001). The findings underscore the critical role of biologically synchronised, behaviourally consistent, and algorithmically adaptive interventions in improving women's health outcomes through FemTech. Originality/value: This research presents a novel framework that bridges AI-BI and personalised nutrition within gender-specific digital health, offering practical and theoretical contributions to intelligent, feminist-informed health innovation.