OTDOncology Treatment Discovery3083-49962981-8079Bio-Byword Scientific Publishing Pty. Ltd.10.26689/otd.v4i1.13939ArticleAdvances in MSCT Trabecular Bone Attenuation Combined with Natural Language Processing and Large Language Models for Opportunistic Osteoporosis Screening and Fracture Risk Assessment: A Reviewhttps://artdesignp.com/journal/OTD/4/1/10.26689/otd.v4i1.13939ZhongShiyu,TaoPeng,GongHairong,DengXiangrong,ZhaoJianghai,SunFuxing,SongJinxiong,WuDan2026412026-03-18Osteoporosis and its consequent fragility fractures represent a major public health challenge in aging populations worldwide. Although dual-energy X-ray absorptiometry (DXA) remains the diagnostic gold standard, its utility for opportunistic screening is limited by equipment accessibility, low screening coverage, and inability to assess bone microarchitecture. Multislice computed tomography (MSCT), routinely performed for various clinical indications, offers a quantitative measure, trabecular bone attenuation in Hounsfield Units (HU), that can be opportunistically leveraged for osteoporosis evaluation. Recent advances in natural language processing (NLP) and large language models (LLMs) enable automated extraction of unstructured clinical data from electronic health records and integration of multimodal information. This review systematically summarizes the evidence base for MSCT-derived HU values in osteoporosis diagnosis, explores the application of NLP for extracting key variables from radiology reports and clinical notes, and discusses the potential of LLMs for multimodal data fusion and predictive modeling. We propose a novel framework combining HU measurements, NLP-extracted clinical features, and LLM-driven analysis to construct a Nomogram model for opportunistic osteoporosis screening and fracture risk prediction. This approach may expand the screened population beyond postmenopausal women to include men and individuals with chronic diseases, ultimately enabling opportunistic, individualized fracture risk assessment integrated into routine clinical workflows.

Gregson CL, Armstrong DJ, Bowden J, et al., 2022, UK Clinical Guideline for the Prevention and Treatment of Osteoporosis. Archives of Osteoporosis, 17(1): 58.

Kanis JA, Cooper C, Rizzoli R, et al., 2020, Correction to: European Guidance for the Diagnosis and Management of Osteoporosis in Postmenopausal Women. Osteoporosis International, 31(4): 801.

Willers C, Norton N, Harvey NC, et al., 2022, Osteoporosis in Europe: A Compendium of Country-Specific Reports. Archives of Osteoporosis, 17(1): 23.

Pickhardt PJ, Pooler BD, Lauder T, et al., 2013, Opportunistic Screening for Osteoporosis Using Abdominal Computed Tomography Scans Obtained for Other Indications. Annals of Internal Medicine, 158(8): 588–595.

Zou D, Li W, Deng C, et al., 2018, The Use of CT Hounsfield Unit Values to Identify the Undiagnosed Spinal Osteoporosis in Patients with Lumbar Degenerative Diseases. European Spine Journal, 28(8): 1758–1766.

Hiyama A, Sakai D, Katoh H, et al., 2024, Hounsfield Unit Values as an Adjunct Diagnostic Tool: Investigating Its Relationship with Bone Mineral Density and Vertebral Bone Quality in Lumbar Degenerative Disease Patients. World Neurosurgery, 183: e722–e729.

Burke CJ, Didolkar MM, Barnhart HX, et al., 2016, The Use of Routine Non Density Calibrated Clinical Computed Tomography Data as a Potentially Useful Screening Tool for Identifying Patients with Osteoporosis. Clinical Cases in Mineral and Bone Metabolism, 13(2): 135–140.

Wang Y, Wang L, Rastegar-Mojarad M, et al., 2017, Clinical Information Extraction Applications: A Literature Review. Journal of Biomedical Informatics, 77: 34–49.

Moor M, Banerjee O, Abad ZSH, et al., 2023, Foundation Models for Generalist Medical Artificial Intelligence. Nature, 616(7956): 259–265.

Lin X, Shen R, Zheng X, et al., 2024, Utilizing Radiomics Techniques to Isolate a Single Vertebral Body from Chest CT for Opportunistic Osteoporosis Screening. BMC Musculoskeletal Disorders, 25(1): 785.

Praveen AD, Sollmann N, Baum T, et al., 2024, CT Image-Based Biomarkers for Opportunistic Screening of Osteoporotic Fractures: A Systematic Review and Meta-Analysis. Osteoporosis International, 35(6): 971–996.

Nam KH, Seo I, Kim DH, et al., 2019, Machine Learning Model to Predict Osteoporotic Spine with Hounsfield Units on Lumbar Computed Tomography. Journal of Korean Neurosurgical Society, 62(4): 442–449.

Lambin P, Rios-Velazquez E, Leijenaar R, et al., 2012, Radiomics: Extracting More Information from Medical Images Using Advanced Feature Analysis. European Journal of Cancer, 48(4): 441–446.

Ford E, Carroll JA, Smith HE, et al., 2016, Extracting Information from the Text of Electronic Medical Records to Improve Case Detection: A Systematic Review. Journal of the American Medical Informatics Association, 23(5): 1007–1015.

Fodeh S, Wang R, Murphy TE, et al., 2024, BoneScore: A Natural Language Processing Algorithm to Extract Bone Mineral Density Data from DXA Scans. Health Informatics Journal, 30(4): 14604582241295930.

Shah NH, Entwistle D, Pfeffer MA, 2023, Creation and Adoption of Large Language Models in Medicine. JAMA, 330(9): 866–869.

Huang SC, Pareek A, Seyyedi S, et al., 2020, Fusion of Medical Imaging and Electronic Health Records Using Deep Learning: A Systematic Review and Implementation Guidelines. NPJ Digital Medicine, 3: 136.

Lessmann N, van Ginneken B, de Jong PA, et al., 2019, Iterative Fully Convolutional Neural Networks for Automatic Vertebra Segmentation and Identification. Medical Image Analysis, 53: 142–155.

Lee SB, Hong Y, Cho YJ, et al., 2024, Enhancing Radiomics Reproducibility: Deep Learning-Based Harmonization of Abdominal Computed Tomography (CT) Images. Bioengineering, 11(12): 1212.