Integrative computational modelling of endocrine dysregulation and post-hysterectomy healing mechanisms in gynaecological disorders

BACKGROUND: The interplay between endocrine imbalance and post-hysterectomy healing in gynaecological disorders remains insufficiently understood due to their conventional evaluation as independent processes. OBJECTIVE: This study presents ICMED-HG, an integrative computational framework that combines multi-modal data, including molecular profiles, clinical parameters, and ultrasonographic measurements, using machine learning and systems biology approaches. METHODS: The model captures the dynamic interactions between hormonal dysregulation and tissue regeneration, enabling improved prediction of disease progression and recovery outcomes. RESULTS: Compared with conventional models, ICMED-HG achieves a 15% increase in diagnostic accuracy, along with improvements of 18% in sensitivity and 12% in specificity. Additionally, it identifies key biomarkers and delineates personalised healing pathways, thereby enhancing prognostic precision and supporting clinical decision-making. CONCLUSION: Overall, the proposed framework bridges the gap between molecular mechanisms and clinical outcomes, contributing to the advancement of precision medicine in gynaecology and enabling more effective, patient-specific therapeutic strategies.