Author: Johnathan W Adams1, Ziming Zhang1, Gregory M Noetscher1,2, Ara Nazarian3,4, Sergey N Makarov1,2,5
1 Department of Electrical and Computer EngineeringWorcester Polytechnic Institute Worcester MA 01609 USA.
2 Neva Electromagnetics LLC Yarmouth Port MA 02675 USA.
3 Musculoskeletal Translational Innovation InitiativeCarl J. Shapiro Department of Orthopaedic SurgeryBeth Israel Deaconess Medical Center, Harvard Medical School Boston MA 02215 USA.
4 Department of Orthopedic SurgeryYerevan State Medical University 0025 Yerevan Armenia.
5 Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General HospitalHarvard Medical School Boston MA 02114 USA.
Conference/Journal: IEEE J Transl Eng Health Med
Date published: 2021 Aug 30
Other: Volume ID: 9 , Pages: 4900907 , Special Notes: doi: 10.1109/JTEHM.2021.3108575. , Word Count: 261
There is an unmet need for quick, physically small, and cost-effective office-based techniques that can measure bone properties without the use of ionizing radiation.
The present study reports the application of a neural network classifier to the processing of previously collected data on very-low-power radiofrequency propagation through the wrist to detect osteoporotic/osteopenic conditions. Our approach categorizes the data obtained for two dichotomic groups. Group 1 included 27 osteoporotic/osteopenic subjects with low Bone Mineral Density (BMD), characterized by a Dual X-Ray Absorptiometry (DXA) T-score below - 1, measured within one year. Group 2 included 40 healthy and mostly young subjects without major clinical risk factors such as a (family) history of bone fracture. We process the complex radiofrequency spectrum from 30 kHz to 2 GHz. Instead of averaging data for both wrists, we process them independently along with the wrist circumference and then combine the results, which greatly increases the sensitivity. Measurements along with data processing require less than 1 min.
For the two dichotomic groups identified above, the neural network classifier of the radiofrequency spectrum reports a sensitivity of 83% and a specificity of 94%.
These results are obtained without including any additional clinical risk factors. They justify that the radio transmission data are usable on their own as a predictor of bone density. This approach has the potential for screening patients at risk for fragility fractures in the office, given the ease of implementation, small device size, and low costs associated with both the technique and the equipment.
Keywords: Artificial intelligence; neural networks; osteopenia; osteoporosis; radiofrequency measurements; signal processing.
PMID: 34522471 PMCID: PMC8428761 DOI: 10.1109/JTEHM.2021.3108575