Clinical fracture risk evaluated by hierarchical agglomerative clustering

• Published in: Osteoporosis international Vol. 28; no. 3; pp. 819 - 832
• Main Authors: Kruse, C., Eiken, P., Vestergaard, P.
• Format: Journal Article
• Language: English
• Published: London Springer London 01.03.2017; Springer Nature B.V
• Subjects: Absorptiometry, Photon; Adult; Aged; Aged, 80 and over; Algorithms; Bone density; Bone Density - physiology; Bone mineral density; Cluster Analysis; Clustering; Comorbidity; Denmark - epidemiology; Dual energy X-ray absorptiometry; Endocrinology; Female; Fractures; Hip; Hip Joint - physiopathology; Humans; Learning algorithms; Lumbar Vertebrae - physiopathology; Machine Learning; Medicine; Medicine & Public Health; Middle Aged; Original Article; Orthopedics; Osteoporosis; Osteoporosis - complications; Osteoporosis - epidemiology; Osteoporosis - physiopathology; Osteoporosis, Postmenopausal - complications; Osteoporosis, Postmenopausal - epidemiology; Osteoporosis, Postmenopausal - physiopathology; Osteoporotic Fractures - epidemiology; Osteoporotic Fractures - etiology; Osteoporotic Fractures - physiopathology; Reproducibility of Results; Rheumatology; Risk assessment; Risk Factors; Spine (lumbar); Statistical analysis; Osteoporosis; Densitometry; Clustering; Risk factors; Machine learning

Summary Clustering analysis can identify subgroups of patients based on similarities of traits. From data on 10,775 subjects, we document nine patient clusters of different fracture risks. Differences emerged after age 60 and treatment compliance differed by hip and lumbar spine bone mineral density...