1
|
Zhao C, Keyak JH, Cao X, Sha Q, Wu L, Luo Z, Zhao LJ, Tian Q, Serou M, Qiu C, Su KJ, Shen H, Deng HW, Zhou W. Multi-view information fusion using multi-view variational autoencoder to predict proximal femoral fracture load. Front Endocrinol (Lausanne) 2023; 14:1261088. [PMID: 38075049 PMCID: PMC10710145 DOI: 10.3389/fendo.2023.1261088] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/24/2023] [Accepted: 10/30/2023] [Indexed: 12/18/2023] Open
Abstract
Background Hip fracture occurs when an applied force exceeds the force that the proximal femur can support (the fracture load or "strength") and can have devastating consequences with poor functional outcomes. Proximal femoral strengths for specific loading conditions can be computed by subject-specific finite element analysis (FEA) using quantitative computerized tomography (QCT) images. However, the radiation and availability of QCT limit its clinical usability. Alternative low-dose and widely available measurements, such as dual energy X-ray absorptiometry (DXA) and genetic factors, would be preferable for bone strength assessment. The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion. Results We developed new models using multi-view variational autoencoder (MVAE) for feature representation learning and a product of expert (PoE) model for multi-view information fusion. We applied the proposed models to an in-house Louisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345 African Americans and 586 Caucasians. We performed genome-wide association studies (GWAS) to select 256 genetic variants with the lowest p-values for each proximal femoral strength and integrated whole genome sequence (WGS) features and DXA-derived imaging features to predict proximal femoral strength. The best prediction model for fall fracture load was acquired by integrating WGS features and DXA-derived imaging features. The designed models achieved the mean absolute percentage error of 18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads using linear models of fall loading, nonlinear models of fall loading, and nonlinear models of stance loading, respectively. Conclusion The proposed models are capable of predicting proximal femoral strength using WGS features and DXA-derived imaging features. Though this tool is not a substitute for predicting FEA using QCT images, it would make improved assessment of hip fracture risk more widely available while avoiding the increased radiation exposure from QCT.
Collapse
Affiliation(s)
- Chen Zhao
- Department of Applied Computing, Michigan Technological University, Houghton, MI, United States
| | - Joyce H. Keyak
- Department of Radiological Sciences, Department of Biomedical Engineering, Department of Mechanical and Aerospace Engineering, and Chao Family Comprehensive Cancer Center, University of California, Irvine, Irvine, CA, United States
| | - Xuewei Cao
- Department of Mathematical Sciences, Michigan Technological University, Houghton, MI, United States
| | - Qiuying Sha
- Department of Mathematical Sciences, Michigan Technological University, Houghton, MI, United States
| | - Li Wu
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Zhe Luo
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Lan-Juan Zhao
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Qing Tian
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Michael Serou
- Department of Radiology, Deming Department of Medicine, School of Medicine, Tulane University, New Orleans, LA, United States
| | - Chuan Qiu
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Kuan-Jui Su
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Hui Shen
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Hong-Wen Deng
- Division of Biomedical Informatics and Genomics, Tulane Center of Biomedical Informatics and Genomics, Deming Department of Medicine, Tulane University, New Orleans, LA, United States
| | - Weihua Zhou
- Department of Applied Computing, Michigan Technological University, Houghton, MI, United States
- Center for Biocomputing and Digital Health, Institute of Computing and Cybersystems, and Health Research Institute, Michigan Technological University, Houghton, MI, United States
| |
Collapse
|
3
|
Wang S, Yang X, Han Z, Wu X, Fan YB, Sun LW. Changes of cortical bone pores structure and their effects on mechanical properties in tail-suspended rats. MEDICINE IN NOVEL TECHNOLOGY AND DEVICES 2022. [DOI: 10.1016/j.medntd.2022.100175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022] Open
|
4
|
Gomindes A, Remtulla M, Cooper J, Nikolaides AP. Fracture of pubic rami during hip fracture fixation: a rare case of traction table-related injury. BMJ Case Rep 2022; 15:e246581. [PMID: 34980641 PMCID: PMC8724731 DOI: 10.1136/bcr-2021-246581] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/30/2021] [Indexed: 11/04/2022] Open
Abstract
We present a case of an elderly and comorbid patient who was scheduled to undergo a hip fracture fixation using an intramedullary nail. Unfortunately, this was delayed by 3 weeks as the patient was unfit to undergo this procedure. She was placed onto the traction table and intraoperatively sustained a superior and inferior pubic rami fracture while attempting reduction on the traction table. Closed-reduction techniques using traction tables and perineal posts are not without morbidity. Risk factors such as osteoporosis and delayed-fixation should be accounted for when managing this complex and often frail group of patients.
Collapse
Affiliation(s)
- Austin Gomindes
- Department of Trauma and Orthopaedics, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
- University of Edinburgh Division of Clinical and Surgical Sciences, Edinburgh, UK
| | - Mohammedabbas Remtulla
- Department of Trauma and Orthopaedics, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - Julian Cooper
- Department of Trauma and Orthopaedics, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - Anastasios P Nikolaides
- Department of Trauma and Orthopaedics, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| |
Collapse
|