Enhancing vertebral fracture prediction using multitask deep learning computed tomography imaging of bone and muscle

Clinical Snapshot

Key Findings

• P Value: p < 0.01 for superiority over FRAX and bone-only models

• Effect Size: C-index 0.68 for multitask bone+muscle model

• Primary Outcome: Vertebral fracture prediction over 5-year follow-up

• Nnt Or Sensitivity: AUROC 0.80 in external validation for cross-sectional detection, time-specific AUROCs 0.79 (2-year), 0.71 (3-year), 0.71 (5-year)

• Confidence Interval: Not reported for primary c-index

Clinical Application

Requires deep learning infrastructure and CT image processing capabilities, but leverages existing imaging without additional patient burden Relevant for Australian radiology departments and endocrinology services. Could integrate with existing osteoporosis management pathways and PBS-subsidised bone health interventions. Aligns with RACGP guidelines for opportunistic case finding in older adults Adults aged 50-80 years undergoing routine abdominal CT scans in hospital settings

Abstract

OBJECTIVES: To develop and externally validate a computed tomography (CT)-based multitask learning model to predict fracture risk. MATERIALS AND METHODS: This study was conducted in two parts, using a multitasking learning approach. We developed a cross-sectional vertebral fracture (VF) detection model using abdominal CT scans of 2553 patients aged 50-80 years. Then, we leveraged this detection model within a multitask learning framework to develop a longitudinal VF prediction model over a 5-year follow-up period. External testing was performed on 1506 patients from two independent hospitals. The performance was compared between the single-task and multitask models, bone-only and bone+muscle images, and image-only and clinical models. RESULTS: For the cross-sectional fracture detection model, the mean age of the patients was 76.2 years, and 66.7% were female. In the classification task for detection of VF, the model using both bone and muscle showed an area under the receiver operating characteristic curve (AUROC) of 0.82 in the development set and 0.80 in the external test sets. Using multitask learning, the bone + muscle image model showed a c-index of 0.68 and had superior performance than the bone-only model in the external test set for 2-year, 3-year, and 5-year AUROCs (0.79 vs. 0.75, 0.71 vs. 0.68, and 0.71 vs. 0.68, respectively, all p < 0.01). Also, the multitask model significantly outperformed the Fracture Risk Assessment Tool (FRAX) (c-index: 0.68 vs. 0.66, p < 0.01). CONCLUSION: The CT-based multitask learning model integrating both bone and muscle data showed superior predictive performance for VFs compared with models using bone images only and traditional clinical models. KEY POINTS: Question Vertebral fracture risk remains underestimated in many individuals undergoing CT scans for other reasons, highlighting the need for improved opportunistic prediction tools. Findings A multitask deep learning model integrating both bone and muscle features from CT scans demonstrated superior performance compared to bone-only and traditional clinical models, including FRAX. Clinical relevance The proposed model enables accurate vertebral fracture risk prediction using routinely acquired CT scans, facilitating early identification and intervention without the need for additional tests.