Background Since image-based fracture prediction models using deep learning are lacking, we aimed to develop an X-ray-based fracture prediction model using deep learning with longitudinal data.
Methods This study included 1,595 participants aged 50 to 75 years with at least two lumbosacral radiographs without baseline fractures from 2010 to 2015 at Seoul National University Hospital. Positive and negative cases were defined according to whether vertebral fractures developed during follow-up. The cases were divided into training (n=1,416) and test (n=179) sets. A convolutional neural network (CNN)-based prediction algorithm, DeepSurv, was trained with images and baseline clinical information (age, sex, body mass index, glucocorticoid use, and secondary osteoporosis). The concordance index (C-index) was used to compare performance between DeepSurv and the Fracture Risk Assessment Tool (FRAX) and Cox proportional hazard (CoxPH) models.
Results Of the total participants, 1,188 (74.4%) were women, and the mean age was 60.5 years. During a mean follow-up period of 40.7 months, vertebral fractures occurred in 7.5% (120/1,595) of participants. In the test set, when DeepSurv learned with images and clinical features, it showed higher performance than FRAX and CoxPH in terms of C-index values (DeepSurv, 0.612; 95% confidence interval [CI], 0.571 to 0.653; FRAX, 0.547; CoxPH, 0.594; 95% CI, 0.552 to 0.555). Notably, the DeepSurv method without clinical features had a higher C-index (0.614; 95% CI, 0.572 to 0.656) than that of FRAX in women.
Conclusion DeepSurv, a CNN-based prediction algorithm using baseline image and clinical information, outperformed the FRAX and CoxPH models in predicting osteoporotic fracture from spine radiographs in a longitudinal cohort.
Citations
Citations to this article as recorded by
Automated detection of vertebral fractures from X-ray images: A novel machine learning model and survey of the field Li-Wei Cheng, Hsin-Hung Chou, Yu-Xuan Cai, Kuo-Yuan Huang, Chin-Chiang Hsieh, Po-Lun Chu, I-Szu Cheng, Sun-Yuan Hsieh Neurocomputing.2024; 566: 126946. CrossRef
Application of radiomics model based on lumbar computed tomography in diagnosis of elderly osteoporosis Baisen Chen, Jiaming Cui, Chaochen Li, Pengjun Xu, Guanhua Xu, Jiawei Jiang, Pengfei Xue, Yuyu Sun, Zhiming Cui Journal of Orthopaedic Research.2024;[Epub] CrossRef
Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis Satoshi Maki, Takeo Furuya, Masahiro Inoue, Yasuhiro Shiga, Kazuhide Inage, Yawara Eguchi, Sumihisa Orita, Seiji Ohtori Journal of Clinical Medicine.2024; 13(3): 705. CrossRef
A CT-based Deep Learning Model for Predicting Subsequent Fracture Risk in Patients with Hip Fracture Yisak Kim, Young-Gon Kim, Jung-Wee Park, Byung Woo Kim, Youmin Shin, Sung Hye Kong, Jung Hee Kim, Young-Kyun Lee, Sang Wan Kim, Chan Soo Shin Radiology.2024;[Epub] CrossRef
A Novel QCT-Based Deep Transfer Learning Approach for Predicting Stiffness Tensor of Trabecular Bone Cubes Pengwei Xiao, Tinghe Zhang, Yufei Huang, Xiaodu Wang IRBM.2024; 45(2): 100831. CrossRef
Deep learning in the radiologic diagnosis of osteoporosis: a literature review Yu He, Jiaxi Lin, Shiqi Zhu, Jinzhou Zhu, Zhonghua Xu Journal of International Medical Research.2024;[Epub] CrossRef
Development and Validation of a Convolutional Neural Network Model to Predict a Pathologic Fracture in the Proximal Femur Using Abdomen and Pelvis CT Images of Patients With Advanced Cancer Min Wook Joo, Taehoon Ko, Min Seob Kim, Yong-Suk Lee, Seung Han Shin, Yang-Guk Chung, Hong Kwon Lee Clinical Orthopaedics & Related Research.2023; 481(11): 2247. CrossRef
Automated Opportunistic Trabecular Volumetric Bone Mineral Density Extraction Outperforms Manual Measurements for the Prediction of Vertebral Fractures in Routine CT Sophia S. Goller, Jon F. Rischewski, Thomas Liebig, Jens Ricke, Sebastian Siller, Vanessa F. Schmidt, Robert Stahl, Julian Kulozik, Thomas Baum, Jan S. Kirschke, Sarah C. Foreman, Alexandra S. Gersing Diagnostics.2023; 13(12): 2119. CrossRef
Machine learning‐based prediction of osteoporosis in postmenopausal women with clinical examined features: A quantitative clinical study Kainat A. Ullah, Faisal Rehman, Muhammad Anwar, Muhammad Faheem, Naveed Riaz Health Science Reports.2023;[Epub] CrossRef
Skeletal Fracture Detection with Deep Learning: A Comprehensive Review Zhihao Su, Afzan Adam, Mohammad Faidzul Nasrudin, Masri Ayob, Gauthamen Punganan Diagnostics.2023; 13(20): 3245. CrossRef
Deep learning system for automated detection of posterior ligamentous complex injury in patients with thoracolumbar fracture on MRI Sang Won Jo, Eun Kyung Khil, Kyoung Yeon Lee, Il Choi, Yu Sung Yoon, Jang Gyu Cha, Jae Hyeok Lee, Hyunggi Kim, Sun Yeop Lee Scientific Reports.2023;[Epub] CrossRef
Vertebra Segmentation Based Vertebral Compression Fracture Determination from Reconstructed Spine X-Ray Images Srinivasa Rao Gadu, Chandra Sekhar Potala International Journal of Electrical and Electronics Research.2023; 11(4): 1225. CrossRef
Computer Vision in Osteoporotic Vertebral Fracture Risk Prediction: A Systematic Review Anthony K. Allam, Adrish Anand, Alex R. Flores, Alexander E. Ropper Neurospine.2023; 20(4): 1112. CrossRef
A Meaningful Journey to Predict Fractures with Deep Learning Jeonghoon Ha Endocrinology and Metabolism.2022; 37(4): 617. CrossRef
New Horizons: Artificial Intelligence Tools for Managing Osteoporosis Hans Peter Dimai The Journal of Clinical Endocrinology & Metabolism.2022;[Epub] CrossRef