Machine learning analysis of pretreatment CT radiomics features predicts risk of medication-related osteonecrosis of the jaw (MRONJ) in patients prior to bone resorption inhibitor therapy.
Key Details
- 1Retrospective study at Hiroshima University analyzed pretreatment CT scans of 94 patients.
- 2Radiomics features from jawbone CTs were used with machine learning models (RF, SVM, MLP).
- 3Models combining cancellous and cortical bone features significantly improved prediction—AUCs rose to as high as 0.931.
- 4The best model identified 88.6% of future MRONJ cases and 88.6% of controls.
- 5MRONJ affects up to 15% of patients on bone resorption inhibitors and is difficult to treat once developed.
- 6Study was limited by its retrospective nature and lack of comprehensive dental data.
Why It Matters
If validated, radiomics-based AI could enable early identification of high-risk patients, supporting tailored preventive strategies before starting bone resorption inhibitor treatment and potentially reducing severe, life-altering MRONJ complications.
Source
EurekAlert
Related News
•EurekAlert
AI Framework Accelerates Aortic Aneurysm Risk Prediction from Imaging
Researchers developed BioPINN-LM, combining physics-informed neural networks and multimodal large language models to deliver fast, interpretable risk assessments for ascending thoracic aortic aneurysms.
•EurekAlert
Study Finds Patient Voices Missing in Generative AI Design for Oncology
A Flinders University-led review found patients and carers are rarely involved in shaping generative AI tools used in oncology.
•EurekAlert
Scripps Researchers Develop AI Foundation Model for ECG-Based Heart Disease Prediction
A new AI foundation model, ECG-CLIP, improves detection and prediction of multiple heart diseases using large-scale ECG and clinician note data.