Therapeutic Adherence to Osteoporosis Treatment

This dataset contains 1,958 anonymized patient-level records curated to support predictive modeling of therapeutic adherence among individuals undergoing osteoporosis treatment. The dataset integrates demographic, clinical, lifestyle, and treatment-related variables required for developing interpretable and explainable AI models. Key attributes include Age, Gender, Hormonal Changes, Family History, Race\/Ethnicity, Body Weight, Calcium Intake, Vitamin D Intake, Physical Activity, Smoking, Alcohol Consumption, Medical Conditions, Medications, Prior Fractures, Osteoporosis status, and a binary Adherence label indicating whether a patient adhered to treatment recommendations. The data originate from structured questionnaires and clinical summaries collected during supervised research activities. All records were cleaned, standardized, and anonymized to remove personal identifiers. The dataset serves as a reliable benchmark for researchers interested in machine learning, hybrid deep learning architectures, and XAI techniques applied in therapeutic adherence prediction, epidemiology, and digital health informatics.This dataset provides value for model benchmarking, feature-importance analysis, adherence risk stratification, and educational applications in data science and healthcare analytics. It aligns with ongoing efforts in interpretable AI, patient behavior modeling, and personalized medicine, especially for chronic disease management. Researchers, clinicians, and developers can use this dataset to build adherence-support tools or to explore patterns affecting treatment continuity among osteoporosis patients